Applied Sciences

17 pages, 4923 KiB

Open AccessArticle

A Method for Safety Evaluation of Train Braking System Considering Multiple Types of Preventive Maintenance Cycles

by Lilei Zhang, Linhan Guo, Ruiyang Li and Yu Wang

Appl. Sci. 2022, 12(9), 4799; https://doi.org/10.3390/app12094799 - 09 May 2022

Cited by 1 | Viewed by 1910

The train braking system with redundant components has an essential effect on driver safety. In this paper, we consider the failure of K-out-of-N brake motors during operation and the redundant recovery by preventive maintenance. Two Continuous Time Markov Chains (CTMC) are used to [...] Read more.

The train braking system with redundant components has an essential effect on driver safety. In this paper, we consider the failure of K-out-of-N brake motors during operation and the redundant recovery by preventive maintenance. Two Continuous Time Markov Chains (CTMC) are used to model the working process and the preventive maintenance process of the braking system corresponding to the real situation of the train. Considering the maintenance effect of intermittent daily and cyclical overhaul with nested relationships, a new operation risk assessment model of the K-out-of-N system is developed to evaluate the effectiveness of the preventive maintenance of the train. Some safety parameters are solved based on the two coupled preventive maintenance periods, which conveniently design the safety of the train braking system. Finally, a case study illustrates the effectiveness of the safety evaluation method. The results show that we can trade off the effects of the multiple PM intervals on train safety considering the redundancy structure of the braking system by the proposed model. Full article

► Show Figures

Figure 1

19 pages, 4107 KiB

Open AccessArticle

GAIA: Great-Distribution Artificial Intelligence-Based Algorithm for Advanced Large-Scale Commercial Store Management

by Cettina Giaconia and Aziz Chamas

Appl. Sci. 2022, 12(9), 4798; https://doi.org/10.3390/app12094798 - 09 May 2022

Cited by 2 | Viewed by 2513

Abstract

Today, the intelligent management of market stores in the large distribution field represents one of the most difficult tasks to address, considering the various problems to be managed. Specifically, from the classic issues of managing out-of-stock to the reconstruction of customer sentiment and [...] Read more.

Today, the intelligent management of market stores in the large distribution field represents one of the most difficult tasks to address, considering the various problems to be managed. Specifically, from the classic issues of managing out-of-stock to the reconstruction of customer sentiment and the optimal management of shelves, scientific research has placed considerable effort on producing robust and efficient solutions to the aforementioned problems. In this context, modern deep learning techniques have allowed for the development of intelligent and adaptive systems capable of automating and significantly improving the management of a large-scale distribution market. Specifically, the authors have designed and implemented an innovative full pipeline that integrates modern deep learning technologies. More in detail, an innovative pipeline embedding a visual AI-based engine for customer sentiment assessment merged with a deep framework for stock management and market store cashflow monitoring is proposed. The innovative proposed system has been tested and validated in a large-scale distribution supermarket, confirming the effectiveness of the proposed solution. Specifically, in the performed testing sessions, the designed pipeline was able to show ad hoc visual customer sentiment assessment with an accuracy of 95% as well as intelligent stock monitoring with an accuracy of 93% in cross validation. Full article

(This article belongs to the Special Issue Advanced Deep Learning Methods for Large-Scale Food Distribution)

► Show Figures

Figure 1

17 pages, 1745 KiB

Open AccessArticle

Resource Profiling and Performance Modeling for Distributed Scientific Computing Environments

by Md Azam Hossain, Soonwook Hwang and Jik-Soo Kim

Appl. Sci. 2022, 12(9), 4797; https://doi.org/10.3390/app12094797 - 09 May 2022

Viewed by 1330

Abstract

Scientific applications often require substantial amount of computing resources for running challenging jobs potentially consisting of many tasks from hundreds of thousands to even millions. As a result, many institutions collaborate to solve large-scale problems by creating virtual organizations (VOs), and integrate hundreds [...] Read more.

Scientific applications often require substantial amount of computing resources for running challenging jobs potentially consisting of many tasks from hundreds of thousands to even millions. As a result, many institutions collaborate to solve large-scale problems by creating virtual organizations (VOs), and integrate hundreds of thousands of geographically distributed heterogeneous computing resources. Over the past decade, VOs have been proven to be a powerful research testbed for accessing massive amount of computing resources shared by several organizations at almost no cost. However, VOs often suffer from providing exact dynamic resource information due to their scale and autonomous resource management policies. Furthermore, shared resources are inconsistent, making it difficult to accurately forecast resource capacity. An effective VO’s resource profiling and modeling system can address these problems by forecasting resource characteristics and availability. This paper presents effective resource profiling and performance prediction models including Adaptive Filter-based Online Linear Regression (AFOLR) and Adaptive Filter-based Moving Average (AFMV) based on the linear difference equation combining past predicted values and recent profiled information, which aim to support large-scale applications in distributed scientific computing environments. We performed quantitative analysis and conducted microbenchmark experiments on a real multinational shared computing platform. Our evaluation results demonstrate that the proposed prediction schemes outperform well-known common approaches in terms of accuracy, and actually can help users in a shared resource environment to run their large-scale applications by effectively forecasting various computing resource capacity and performance. Full article

(This article belongs to the Special Issue Applications of Parallel Computing)

► Show Figures

Figure 1

18 pages, 2453 KiB

Open AccessArticle

Evaluation of Post-Stroke Impairment in Fine Tactile Sensation by Electroencephalography (EEG)-Based Machine Learning

by Jianing Zhang, Yanhuan Huang, Fuqiang Ye, Bibo Yang, Zengyong Li and Xiaoling Hu

Appl. Sci. 2022, 12(9), 4796; https://doi.org/10.3390/app12094796 - 09 May 2022

Cited by 5 | Viewed by 2039

Abstract

Electroencephalography (EEG)-based measurements of fine tactile sensation produce large amounts of data, with high costs for manual evaluation. In this study, an EEG-based machine-learning (ML) model with support vector machine (SVM) was established to automatically evaluate post-stroke impairments in fine tactile sensation. Stroke [...] Read more.

Electroencephalography (EEG)-based measurements of fine tactile sensation produce large amounts of data, with high costs for manual evaluation. In this study, an EEG-based machine-learning (ML) model with support vector machine (SVM) was established to automatically evaluate post-stroke impairments in fine tactile sensation. Stroke survivors (n = 12, stroke group) and unimpaired participants (n = 15, control group) received stimulations with cotton, nylon, and wool fabrics to the different upper limbs of a stroke participant and the dominant side of the control. The average and maximal values of relative spectral power (RSP) of EEG in the stimulations were used as the inputs to the SVM-ML model, which was first optimized for classification accuracies for different limb sides through hyperparameter selection (γ, C) in radial basis function (RBF) kernel and cross-validation during cotton stimulation. Model generalization was investigated by comparing accuracies during stimulations with different fabrics to different limbs. The highest accuracies were achieved with (γ = 2¹, C = 2³) for the RBF kernel (76.8%) and six-fold cross-validation (75.4%), respectively, in the gamma band for cotton stimulation; these were selected as optimal parameters for the SVM-ML model. In model generalization, significant differences in the post-stroke fabric stimulation accuracies were shifted to higher (beta/gamma) bands. The EEG-based SVM-ML model generated results similar to manual evaluation of cortical responses to fabric stimulations; this may aid automatic assessments of post-stroke fine tactile sensations. Full article

(This article belongs to the Special Issue Artificial Intelligence Applied to Medical Imaging and Computational Biology)

► Show Figures

Figure 1

22 pages, 7508 KiB

Open AccessArticle

Buckwheat Disease Recognition Based on Convolution Neural Network

by Xiaojuan Liu, Shangbo Zhou, Shanxiong Chen, Zelin Yi, Hongyu Pan and Rui Yao

Appl. Sci. 2022, 12(9), 4795; https://doi.org/10.3390/app12094795 - 09 May 2022

Cited by 6 | Viewed by 1875

Abstract

Buckwheat is an important cereal crop with high nutritional and health value. Buckwheat disease greatly affects the quality and yield of buckwheat. The real-time monitoring of disease is an essential part of ensuring the development of the buckwheat industry. In this research work, [...] Read more.

Buckwheat is an important cereal crop with high nutritional and health value. Buckwheat disease greatly affects the quality and yield of buckwheat. The real-time monitoring of disease is an essential part of ensuring the development of the buckwheat industry. In this research work, we proposed an automated way to identify buckwheat diseases. It was achieved by integrating a convolutional neural network (CNN) with the image processing technology. Firstly, the proposed approach would detect the buckwheat disease area accurately. Then, to improve the accuracy of classification, a two-level inception structure was added to the traditional convolutional neural network for accurate feature extraction. It also helps to handle low-quality image problems, which includes complex imaging environment and leaf crossing in sampling buckwheat image, etc. At the same time, instead of the traditional convolution, the convolution based on cosine similarity was adopted to reduce the influence of uneven illumination during the imaging. The experiment proved that the revised convolution enabled better feature extraction within samples with uneven illumination. Finally, the experiment results showed that the accuracy, recall, and F1-measure of the disease detection reached 97.54, 96.38, and 97.82%, respectively. For identifying disease categories, the mean values of precision, recall, and F1-measure were 84.86, 85.78, and 85.4%. Our method has provided important technical support for realizing the automatic recognition of buckwheat diseases. Full article

(This article belongs to the Special Issue Applications of Computer Science in Agricultural Engineering)

► Show Figures

Figure 1

18 pages, 576 KiB

Open AccessReview

Whole-Body Cryostimulation in Fibromyalgia: A Scoping Review

by Jacopo Maria Fontana, Michele Gobbi, Paolo Piterà, Emanuele Maria Giusti and Paolo Capodaglio

Appl. Sci. 2022, 12(9), 4794; https://doi.org/10.3390/app12094794 - 09 May 2022

Cited by 4 | Viewed by 2181

Abstract

Currently, all available therapies for the control and management of fibromyalgia (FM) are mostly focused on relieving patients’ symptoms and improving their quality of life. The purpose of this review is to provide an up-to-date overview of the evidence supporting the beneficial effects [...] Read more.

Currently, all available therapies for the control and management of fibromyalgia (FM) are mostly focused on relieving patients’ symptoms and improving their quality of life. The purpose of this review is to provide an up-to-date overview of the evidence supporting the beneficial effects of whole-body cryostimulation (WBC) in patients with FM and evidence-based guidance on the possible adjuvant use of WBC in the treatment of FM. We searched the most recent literature by retrieving 10 eligible studies, 4 of which were abstracts only, from a total of 263 records. Thermal stress caused by cryostimulation induces an analgesic effect, improving pain, redox balance, and inflammatory symptoms in an exercise-mimicking fashion. In addition, it reduces the feeling of fatigue, improves mood, and reduces mental health deterioration with positive consequences on depressive states and improved sleep quality. Although the studies included in this review are not of sufficient quality and quantity to draw definitive conclusions about the effectiveness of WBC in FM, initial evidence indicates WBC as a promising add-on option in the multidisciplinary treatment of FM, due to its rapid action and high patients’ compliance. The application of WBC protocols has the potential to expand therapeutic options for the treatment of FM and related disorders; however, larger, high-quality primary studies are still needed. Full article

(This article belongs to the Special Issue Role of Physiotherapy and Physical Agent Modalities for Musculoskeletal Disorders: Present and Future)

► Show Figures

Figure 1

15 pages, 3076 KiB

Open AccessArticle

Research on Influence of Switching Angle on the Vibration of Switched Reluctance Motor

by Xiao Ling, Chenhao Zhou, Lianqiao Yang and Jianhua Zhang

Appl. Sci. 2022, 12(9), 4793; https://doi.org/10.3390/app12094793 - 09 May 2022

Cited by 1 | Viewed by 1467

Abstract

Switched Reluctance Motors (SRMs) have emerged as a viable competitor to other established electrical machines. Although SRMs have many advantages, such as a rare earth free nature, simple structure, high fault tolerance capability and low cost, vibration problems due to radial force variations [...] Read more.

Switched Reluctance Motors (SRMs) have emerged as a viable competitor to other established electrical machines. Although SRMs have many advantages, such as a rare earth free nature, simple structure, high fault tolerance capability and low cost, vibration problems due to radial force variations is still a major issue faced by SRMs. Hence, aimed at the problem of vibration suppression for SRMs, this paper proposes a method that focuses on the influence of the change of the turn-on angle and turn-off angle on the vibration of the SRM under the switching angle control (SAC) strategy. Firstly, the influence of the turn-on and turn-off angles on the harmonic components of the current is analyzed in detail. Then, the vibration caused by the frequency of the harmonic components of the current and the natural frequency of the motor is mainly studied. The results show that the harmonic order affecting vibration is related to the rotational speed, and by analyzing the value of this harmonic order, the variation law of vibration with the switching angle can be obtained. When the turn-off angle is constant, the amplitudes of the current harmonic component and vibration first decrease and then increase with the increase of the turn-on angle. Additionally, when the turn-on angle is constant, the current harmonic and vibration show the tendency of periodic oscillation with the variation of the turn-off angle, and the oscillation period is related to the harmonic order. The combination of switching angles that minimizes the certain current harmonic component also minimizes vibration. The effectiveness of the variation law was verified on a 12/8 poles and 1.5 KW SRM drive system test bench, which provide a new perspective on vibration suppression of SRMs. Full article

(This article belongs to the Special Issue Machine Learning in Vibration and Acoustics)

► Show Figures

Figure 1

26 pages, 7029 KiB

Open AccessArticle

Bending Behavior of a Frictional Single-Layered Spiral Strand Subjected to Multi-Axial Loads: Numerical and Experimental Investigation

by Biwen Zhou, Yumei Hu, Xingyuan Zheng and Hao Zhu

Appl. Sci. 2022, 12(9), 4792; https://doi.org/10.3390/app12094792 - 09 May 2022

Cited by 3 | Viewed by 1789

Abstract

Bending deformation gives rise to interwire slippage for spiral strands subjected to multi-axial loads, and further induces wear or fatigue phenomena in practice. The interwire friction would resist bending deformation and lead to uneven tension distribution of individual constituent wires but little research [...] Read more.

Bending deformation gives rise to interwire slippage for spiral strands subjected to multi-axial loads, and further induces wear or fatigue phenomena in practice. The interwire friction would resist bending deformation and lead to uneven tension distribution of individual constituent wires but little research has quantified these effects. To figure out this issue, a beam finite element (FE) is established, into which a penalty stiffness algorithm and a Coulomb friction model are incorporated. A series of free bending simulations are developed for parametric study on deflection near the terminations and tension distribution of individual wire for strands with different levels of length and friction coefficient as well as external loads. Based on the simulation results, it is found that strand length has little influence on bending deformation and tension distribution if the strand length exceeds six times the pitch length. A deflection formula extended from the classical Euler beam model well predicts the sag deflections and the relative error with respect to experimental measurements is less than 10%. Furthermore, additional axial tension induced by the friction is clearly characterized and an approximate expression is proposed to estimate tension distribution for outer layer wires. Its predictions are encouraging for longer strands. Full article

(This article belongs to the Topic Processing, Analysis, Modelling and Mechanics of Materials and Structures)

► Show Figures

Figure 1

21 pages, 7711 KiB

Open AccessArticle

PAS: Privacy-Preserving Authentication Scheme Based on SDN for VANETs

by Xinyang Deng, Tianhan Gao, Nan Guo, Jiayu Qi and Cong Zhao

Appl. Sci. 2022, 12(9), 4791; https://doi.org/10.3390/app12094791 - 09 May 2022

Cited by 6 | Viewed by 1809

Abstract

Privacy disclosure has become a key challenge in vehicular ad hoc networks (VANETs). Although IEEE, ERSI, etc. suggest that a pseudonym-based scheme is a solution, how to support pseudonym management and vehicle authentication is still an open issue. In this paper, a secure [...] Read more.

Privacy disclosure has become a key challenge in vehicular ad hoc networks (VANETs). Although IEEE, ERSI, etc. suggest that a pseudonym-based scheme is a solution, how to support pseudonym management and vehicle authentication is still an open issue. In this paper, a secure VANETs authentication scheme (PAS) is proposed, where software-defined network (SDN) is integrated as a suitable infrastructure to support anonymous authentication and pseudonym management, while removing the requirement for pseudonym certification in the dynamic VANETs environment. The security and performance analysis indicate that PAS is able protect the privacy of vehicles and has a high efficiency. Full article

► Show Figures

Figure 1

14 pages, 2027 KiB

Open AccessArticle

Forecasting the Global Battery Material Flow: Analyzing the Break-Even Points at Which Secondary Battery Raw Materials Can Substitute Primary Materials in the Battery Production

by Michael Neidhardt, Jordi Mas-Peiro, Magnus Schulz-Moenninghoff, Josep O. Pou, Rafael Gonzalez-Olmos, Arno Kwade and Benedikt Schmuelling

Appl. Sci. 2022, 12(9), 4790; https://doi.org/10.3390/app12094790 - 09 May 2022

Cited by 13 | Viewed by 3900

Abstract

Growing numbers of electric vehicles (EVs) as well as controversial discussions on cost, scarcity and the environmental and social sustainability of primary raw materials that are needed for battery production together emphasize the necessity for battery recycling in the future. Nonetheless, the market [...] Read more.

Growing numbers of electric vehicles (EVs) as well as controversial discussions on cost, scarcity and the environmental and social sustainability of primary raw materials that are needed for battery production together emphasize the necessity for battery recycling in the future. Nonetheless, the market for battery recycling is not fully understood and captured in data today. The underlying reasons are found in both market size and various parameters such as the battery-technology mix, the resulting material demand and expected battery lifetime. In consequence, the question of when secondary-material availability from battery recycling is sufficient to satisfy the global cobalt demand for EV applications has not yet been clarified. To address this question, this study estimates the global battery raw-material demand together with the expected amount of the recycled materials by 2035, taking into account a number of parameters affecting future battery material flows. While focusing on cobalt, nickel, lithium, and manganese, the results indicate that the global cobalt demand can be satisfied from secondary sources by the early 2030s in three out of four different technology forecast scenarios. Furthermore, a sensitivity analysis highlights the amount of waste occurring during battery production and battery lifetime as the main drivers for secondary-material availability by 2035. Full article

(This article belongs to the Special Issue Advances in Lithium-Ion Automobile Batteries)

► Show Figures

Figure 1

19 pages, 3636 KiB

Open AccessArticle

Slip Estimation Model for Planetary Rover Using Gaussian Process Regression

by Tianyi Zhang, Song Peng, Yang Jia, Junkai Sun, He Tian and Chuliang Yan

Appl. Sci. 2022, 12(9), 4789; https://doi.org/10.3390/app12094789 - 09 May 2022

Cited by 5 | Viewed by 1935

Abstract

Monitoring the rover slip is important; however, a certain level of estimation uncertainty is inevitable. In this paper, we establish slip estimation models for China’s Mars rover, Zhurong, using Gaussian process regression (GPR). The model was able to predict not only the average [...] Read more.

Monitoring the rover slip is important; however, a certain level of estimation uncertainty is inevitable. In this paper, we establish slip estimation models for China’s Mars rover, Zhurong, using Gaussian process regression (GPR). The model was able to predict not only the average value of the longitudinal (slip_x) and lateral slip (slip_y), but also the maximum possible value that slip_x and slip_y could reach. The training data were collected on two simulated soils, TYII-2 and JLU Mars-2, and the GA-BP algorithm was applied as a comparison. The analysis results demonstrated that the soil type and dataset source had a direct impact on the applicability of the slip model on Mars conditions. The properties of the Martian soil near the Zhurong landing site were closer to the JLU Mars-2 simulated soil. The proposed GPR model had high estimation accuracy and estimation potential in slip value, and a 95% confidence interval that the rover could reach during motion. This work was part of a research effort aimed at ensuring the safety of Zhurong. The slip value may be used in subsequent path tracking research, and the slip confidence interval will be able to help guide path planning. Full article

► Show Figures

Figure 1

23 pages, 9389 KiB

Open AccessArticle

Soil Treatment to Reduce Grounding Resistance by Applying Low-Resistivity Material (LRM) Implemented in Different Grounding Systems Configurations and in Soils with Different Resistivities

by Freddy Sinchi-Sinchi, Cristian Coronel-Naranjo, Antonio Barragán-Escandón and Flavio Quizhpi-Palomeque

Appl. Sci. 2022, 12(9), 4788; https://doi.org/10.3390/app12094788 - 09 May 2022

Cited by 1 | Viewed by 2970

Abstract

In the present study, field tests were performed using low-resistivity materials (LRMs) in different grounding system (GS) configurations to reduce the grounding resistance (GR) and assess the variation in the effectiveness of the LRMs with increases in the complexity of the GS design. [...] Read more.

In the present study, field tests were performed using low-resistivity materials (LRMs) in different grounding system (GS) configurations to reduce the grounding resistance (GR) and assess the variation in the effectiveness of the LRMs with increases in the complexity of the GS design. Different configurations were implemented in soils with different resistivity values to determine the variation in the effectiveness of each LRM design with increases in the soil resistivity. Lastly, the percentage decrease in the GR was assessed as a function of the increase in the complexity of the GS design and the variation in the soil resistivity. The results of this study provide a useful guide for engineers and researchers who study, design, and build innovative and effective GSs by applying improved compounds for safe electrical installations. Full article

(This article belongs to the Topic Power Distribution Systems)

► Show Figures

Figure 1

16 pages, 2163 KiB

Open AccessArticle

Finite Element Analysis for Pre-Clinical Testing of Custom-Made Knee Implants for Complex Reconstruction Surgery

by Georg Hettich, Josef-Benedikt Weiß, Benjamin Wünsch and Thomas M. Grupp

Appl. Sci. 2022, 12(9), 4787; https://doi.org/10.3390/app12094787 - 09 May 2022

Cited by 2 | Viewed by 2582

Abstract

In severe cases of total knee arthroplasty, where off-the-shelf implants are not suitable or available anymore (i.e., in cases with extended bone defects or periprosthetic fractures), custom-made knee implants represent one of the few remaining treatment options. Design verification and validation of such [...] Read more.

In severe cases of total knee arthroplasty, where off-the-shelf implants are not suitable or available anymore (i.e., in cases with extended bone defects or periprosthetic fractures), custom-made knee implants represent one of the few remaining treatment options. Design verification and validation of such custom-made implants is very challenging. The aim of this study is to support surgeons and engineers in their decision on whether a developed design is suitable for the specific case. A novel method for the pre-clinical testing of custom-made knee implants is suggested, which relies on the biomechanical test and finite element analysis (FEA) of a comparable reference implant. The method comprises six steps: (1) identification of the main potential failure mechanism and its corresponding FEA quantity of interest, (2) reproduction of the biomechanical test of the reference implant via FEA, (3) identification of the maximum value of the corresponding FEA quantity of interest at the required load level, (4) definition of this value as the acceptance criterion for the FEA of the custom-made implant, (5) reproduction of the biomechanical test with the custom-made implant via FEA, (6) conclusion, whether the acceptance criterion is fulfilled or not. Two exemplary cases of custom-made knee implants were evaluated with this method. The FEA acceptance criterion derived from the reference implants was fulfilled in both custom-made implants. Subsequent biomechanical tests verified the FEA results. The suggested method allows a quantitative evaluation of the biomechanical properties of a custom-made knee implant without performing a biomechanical test with it. This represents an important contribution in the pre-clinical testing of custom-made implants in order to achieve a sustainable treatment of complex revision total knee arthroplasty patients in a timely manner. Full article

(This article belongs to the Special Issue Recent Advance in Finite Elements and Biomechanics)

► Show Figures

Graphical abstract

26 pages, 3763 KiB

Open AccessArticle

Development of Charging/Discharging Scheduling Algorithm for Economical and Energy-Efficient Operation of Multi-EV Charging Station

by Hojun Jin, Sangkeum Lee, Sarvar Hussain Nengroo and Dongsoo Har

Appl. Sci. 2022, 12(9), 4786; https://doi.org/10.3390/app12094786 - 09 May 2022

Cited by 17 | Viewed by 2727

Abstract

As the number of electric vehicles (EVs) significantly increases, the excessive charging demand of parked EVs in the charging station may incur an instability problem to the electricity network during peak hours. For the charging station to take a microgrid (MG) structure, an [...] Read more.

As the number of electric vehicles (EVs) significantly increases, the excessive charging demand of parked EVs in the charging station may incur an instability problem to the electricity network during peak hours. For the charging station to take a microgrid (MG) structure, an economical and energy-efficient power management scheme is required for the power provision of EVs while considering the local load demand of the MG. For these purposes, this study presents the power management scheme of interdependent MG and EV fleets aided by a novel EV charging/discharging scheduling algorithm. In this algorithm, the maximum amount of discharging power from parked EVs is determined based on the difference between local load demand and photovoltaic (PV) power production to alleviate imbalances occurred between them. For the power management of the MG with charging/discharging scheduling of parked EVs in the PV-based charging station, multi-objective optimization is performed to minimize the operating cost and grid dependency. In addition, the proposed scheme maximizes the utilization of EV charging/discharging while satisfying the charging requirements of parked EVs. Moreover, a more economical and energy-efficient PV-based charging station is established using the future trends of local load demand and PV power production predicted by a gated recurrent unit (GRU) network. With the proposed EV charging/discharging scheduling algorithm, the operating cost of PV-based charging station is decreased by 167.71% and 28.85% compared with the EV charging scheduling algorithm and the conventional EV charging/discharging scheduling algorithm, respectively. It is obvious that the economical and energy-efficient operation of PV-based charging station can be accomplished by applying the power management scheme with the proposed EV charging/discharging scheduling strategy. Full article

(This article belongs to the Special Issue Future Intelligent Transportation System for Tomorrow and Beyond)

► Show Figures

Figure 1

18 pages, 875 KiB

Open AccessArticle

Multimodal Classification of Teaching Activities from University Lecture Recordings

by Oscar Sapena and Eva Onaindia

Appl. Sci. 2022, 12(9), 4785; https://doi.org/10.3390/app12094785 - 09 May 2022

Viewed by 1919

Abstract

The way of understanding online higher education has greatly changed due to the worldwide pandemic situation. Teaching is undertaken remotely, and the faculty incorporate lecture audio recordings as part of the teaching material. This new online teaching–learning setting has largely impacted university classes. [...] Read more.

The way of understanding online higher education has greatly changed due to the worldwide pandemic situation. Teaching is undertaken remotely, and the faculty incorporate lecture audio recordings as part of the teaching material. This new online teaching–learning setting has largely impacted university classes. While online teaching technology that enriches virtual classrooms has been abundant over the past two years, the same has not occurred in supporting students during online learning. To overcome this limitation, our aim is to work toward enabling students to easily access the piece of the lesson recording in which the teacher explains a theoretical concept, solves an exercise, or comments on organizational issues of the course. To that end, we present a multimodal classification algorithm that identifies the type of activity that is being carried out at any time of the lesson by using a transformer-based language model that exploits features from the audio file and from the automated lecture transcription. The experimental results will show that some academic activities are more easily identifiable with the audio signal while resorting to the text transcription is needed to identify others. All in all, our contribution aims to recognize the academic activities of a teacher during a lesson. Full article

(This article belongs to the Special Issue Artificial Intelligence in Online Higher Educational Data Mining)

► Show Figures

Figure 1

17 pages, 2818 KiB

Open AccessArticle

Sports Information Needs in Chinese Online Q&A Community: Topic Mining Based on BERT

by Chuanlin Ning, Jian Xu, Hao Gao, Xi Yang and Tianyi Wang

Appl. Sci. 2022, 12(9), 4784; https://doi.org/10.3390/app12094784 - 09 May 2022

Cited by 2 | Viewed by 3628

Abstract

The online Question and Answering (Q&A) community has grown globally, allowing users to ask, discuss, and answer questions based on shared interests. As a gathering place for people’s knowledge production, collaboration, and dissemination in the current Internet scene, the online Q&A community can [...] Read more.

The online Question and Answering (Q&A) community has grown globally, allowing users to ask, discuss, and answer questions based on shared interests. As a gathering place for people’s knowledge production, collaboration, and dissemination in the current Internet scene, the online Q&A community can intuitively reflect the public’s information needs and behavior. It also collects many sports-related data and becomes an effective vehicle for comprehending mass sports information needs and disseminating sports knowledge. However, sports-related studies on the online Q&A community have rarely been reported. This study took the sports information in Zhihu, the largest Q&A community in China, as the research object to explore the public needs for sports information in China. We introduced the BERT model through a self-compiled python program and collected 391,092 sports-topic answers in the online Q&A community of Zhihu. Then, we explored the topic content, evolution trend, and user attributes of these answers. We found that the overall trend of sports information needs in Zhihu can be divided into three cycles: the London 2012 Olympic period, the Rio 2016 Olympic period, and the Tokyo 2020 Olympic period in general. The diversified content of information needs included 40 second-level themes and eight first-level themes. Male and female users had similarities and differences in sports information needs. The male and female users had the same information needs for fitness-related information. However, men were more concerned with confrontational solid sports such as basketball and football; women were more likely to care about weight loss, shape effect, and self-protection while doing sports activities. In addition, compared with men, women preferred to emphasize their gender attributes when expressing their needs for sports information to obtain more practical knowledge. In conclusion, our finding reveals that the sports community formed by the current online Q&A community in China is still a male-dominated information field. Full article

(This article belongs to the Special Issue Computational Intelligence and Data Mining in Sports 2021)

► Show Figures

Figure 1

15 pages, 2618 KiB

Open AccessArticle

Development and Opportunities of Clean Energy in China

by Jin Han and Hongmei Chang

Appl. Sci. 2022, 12(9), 4783; https://doi.org/10.3390/app12094783 - 09 May 2022

Cited by 20 | Viewed by 2618

Abstract

In the context of the energy crisis and global climate deterioration, the sustainable development of clean energy will become a new direction for future energy development. Based on the development process of clean energy in China in the past ten years, this paper [...] Read more.

In the context of the energy crisis and global climate deterioration, the sustainable development of clean energy will become a new direction for future energy development. Based on the development process of clean energy in China in the past ten years, this paper expounds on China’s clean energy policy and development plan. The development of hydropower, wind power, and solar power in China in recent years is analyzed. On this basis, the Grey Forecasting Model is used to forecast the development and structure of China’s clean energy in the next 10 years, point out the direction and market opportunities of China’s clean energy development in the future, and put forward the implementation methods for the sustainable development of China’s clean energy. It provides a reference for the policy decision-making of China’s clean energy development. Full article

(This article belongs to the Collection Renewable and Sustainable Energy Systems: Recent Developments, Challenges, and Future Perspectives)

► Show Figures

Figure 1

12 pages, 8567 KiB

Open AccessArticle

A Full Ka-Band CMOS Amplifier Using Inductive Neutralization with a Flat Gain of 13 ± 0.2 dB

by Byungwook Kim and Sanggeun Jeon

Appl. Sci. 2022, 12(9), 4782; https://doi.org/10.3390/app12094782 - 09 May 2022

Cited by 1 | Viewed by 2882

Abstract

This paper presents a CMOS wideband amplifier operating in the full Ka-band, with a low gain variation. An inductive neutralization is applied to the amplifier to compensate for the gain roll-off in the high-frequency region. Neutralization inductance is carefully determined considering the tradeoff [...] Read more.

This paper presents a CMOS wideband amplifier operating in the full Ka-band, with a low gain variation. An inductive neutralization is applied to the amplifier to compensate for the gain roll-off in the high-frequency region. Neutralization inductance is carefully determined considering the tradeoff between stability and gain. To achieve a low gain variation over the full Ka-band, the amplifier employs the frequency staggering technique in which impedance matching for three gain stages is performed at different frequencies of 26, 34, and 42 GHz. The experimental results show that a peak gain of 13.2 dB is achieved at 39.2 GHz. The 3 dB bandwidth is from 23.5 to 41.7 GHz, which fully covers the Ka-band. Especially, the gain ripple of the amplifier is only 13 ± 0.2 dB over a wide bandwidth from 26.2 to 40.2 GHz. The input and output return loss values are better than −10 dB from 26.3 to 40.1 GHz and from 25.3 to 50 GHz, respectively. The DC power consumption is 18.6 mW. Full article

(This article belongs to the Special Issue Recent Research in Microwave and Millimeter-Wave Components)

► Show Figures

Figure 1

17 pages, 5369 KiB

Open AccessArticle

A Strategic Pathway from Cell to Pack-Level Battery Lifetime Model Development

by Md Sazzad Hosen, Ashkan Pirooz, Theodoros Kalogiannis, Jiacheng He, Joeri Van Mierlo and Maitane Berecibar

Appl. Sci. 2022, 12(9), 4781; https://doi.org/10.3390/app12094781 - 09 May 2022

Cited by 4 | Viewed by 2589

Abstract

The automotive energy storage market is currently dominated by the existing Li-ion technologies that are likely to continue in the future. Thus, the on-road electric (and hybrid) vehicles running on the Li-ion battery systems require critical diagnosis considering crucial battery aging. This work [...] Read more.

The automotive energy storage market is currently dominated by the existing Li-ion technologies that are likely to continue in the future. Thus, the on-road electric (and hybrid) vehicles running on the Li-ion battery systems require critical diagnosis considering crucial battery aging. This work aims to provide a guideline for pack-level lifetime model development that could facilitate battery maintenance, ensuring a safe and reliable operational lifespan. The first of the twofold approach is a cell-level empirical lifetime model that is developed from a lab-level aging dataset of commercial LTO cells. The model is validated with an exhaustive sub-urban realistic driving cycle yielding a root-mean-square error of 0.45. The model is then extended to a 144S1P modular architecture for pack-level simulation. The second step provides the pack electro-thermal simulation results that are upscaled from a cell-level and validated 1D electrical model coupled with a 3D thermal model. The combined simulation framework is online applicable and considers the relevant aspects into account in predicting the battery system’s lifetime that results in over 350,000 km of suburban driving. This robust tool is a collaborative research outcome from two Horizon2020 EU projects—GHOST and Vision xEV, showcasing outstanding cell-level battery modeling accuracies. Full article

(This article belongs to the Special Issue Advances in Lithium-Ion Automobile Batteries)

► Show Figures

Figure 1

15 pages, 5629 KiB

Open AccessArticle

On-Machine Measurements for Aircraft Gearbox Machining Process Assisted by Adaptive Neuro-Fuzzy Inference System

by Grzegorz Bomba, Artur Ornat, Piotr Gierlak and Magdalena Muszyńska

Appl. Sci. 2022, 12(9), 4780; https://doi.org/10.3390/app12094780 - 09 May 2022

Cited by 1 | Viewed by 1652

Abstract

This paper deals with the development of dimensional control technology for the production of accessory drive train (ADT) gearbox housing, according to the closed door technology approach. The work presents the methodology of the final inspection of bearing seat position deviation by replacing [...] Read more.

This paper deals with the development of dimensional control technology for the production of accessory drive train (ADT) gearbox housing, according to the closed door technology approach. The work presents the methodology of the final inspection of bearing seat position deviation by replacing the coordinate measuring machines (CMMs) with a computerized numerical control (CNC) machine and adaptive neuro-fuzzy inference system. The results of the work indicated that correct solutions were obtained. In addition, the technological process of manufacturing is fully automated and performed entirely on the production line. Full article

(This article belongs to the Topic Manufacturing Metrology)

► Show Figures

Figure 1

15 pages, 3248 KiB

Open AccessArticle

Research on a mmWave Beam-Prediction Algorithm with Situational Awareness Based on Deep Learning for Intelligent Transportation Systems

by Jia Liang, Kaiming Li, Qun Zhang and Zisen Qi

Appl. Sci. 2022, 12(9), 4779; https://doi.org/10.3390/app12094779 - 09 May 2022

Cited by 2 | Viewed by 1470

Abstract

Simply speaking, automatic driving requires the calculation of a large amount of traffic data and, finally, the obtainment of the optimal driving route and speed. However, the key technical difficulty is the obtainment of data; thus, radar has become an indispensable hardware for [...] Read more.

Simply speaking, automatic driving requires the calculation of a large amount of traffic data and, finally, the obtainment of the optimal driving route and speed. However, the key technical difficulty is the obtainment of data; thus, radar has become an indispensable hardware for automatic driving. Compared to the optical and infrared radar, millimeter-wave radar is not affected by the shape and color of the target, and it is not affected by the atmospheric turbulence, compared to ultrasonic, and so it has a stable detection performance and good environmental adaptability. It is little affected by changes in the weather, and the external environment, rain, snow, dust, and sunshine have no interference in it. The Doppler frequency shift is large, and the accuracy of the relative velocity measurement is improved. However, one challenge for vehicles in fast environments is millimeter-wave-based communication. Because of the short wavelength of the millimeter wave and the high path and penetration losses, the beamforming technology of a large-scale antenna array plays a key role in the construction and maintenance of millimeter-wave communication links. Millimeter waves have wide channel bandwidths, unique channel characteristics, and hardware limitations, and so there are many challenges in the direct use of beamforming technology in millimeter-wave communication. Traditional beam training cannot meet the requirements of low overhead and low delay. This paper, in order to obtain beam information, introduces the context-awareness module to the deep-learning net, which is derived from past observation data. This paper establishes a model that contains the receiver and the surrounding vehicles to perceive the environment. Then, a long short-term memory (LSTM) neural network is used to foresee the acquired power, which is quantized by several beam powers. According to the conclusion, the prediction accuracy is greatly increased, and the model could yield throughput with almost zero overhead and little performance loss. Full article

(This article belongs to the Special Issue Selected Papers from FCPAE2022 and 4th International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM2022))

► Show Figures

Figure 1

15 pages, 1362 KiB

Open AccessArticle

Parallel Frequent Subtrees Mining Method by an Effective Edge Division Strategy

by Jing Wang and Xiongfei Li

Appl. Sci. 2022, 12(9), 4778; https://doi.org/10.3390/app12094778 - 09 May 2022

Viewed by 1115

Abstract

Most data with a complicated structure can be represented by a tree structure. Parallel processing is essential to mining frequent subtrees from massive data in a timely manner. However, only a few algorithms could be transplanted to a parallel framework. A new parallel [...] Read more.

Most data with a complicated structure can be represented by a tree structure. Parallel processing is essential to mining frequent subtrees from massive data in a timely manner. However, only a few algorithms could be transplanted to a parallel framework. A new parallel algorithm is proposed to mine frequent subtrees by grouping strategy (GS) and edge division strategy (EDS). The main idea of GS is dividing edges according to different intervals and then dividing subtrees consisting of the edges in different intervals to their corresponding groups. Besides, the compression stage in mining is optimized by avoiding all candidate subtrees of a compression tree, which reduces the mining time on the nodes. Load balancing can improve the performance of parallel computing. An effective EDS is proposed to achieve load balancing. EDS divides the edges with different frequencies into different intervals reasonably, which directly affects the task amount in each computing node. Experiments demonstrate that the proposed algorithm can implement parallel mining, and it outperforms other compared methods on load balancing and speedup. Full article

(This article belongs to the Special Issue Data Analysis and Mining)

► Show Figures

Figure 1

23 pages, 20764 KiB

Open AccessArticle

Integrated System for Official Vehicles with Online Reservation and Moving Path Monitoring

by Kuo-Tai Hsu, Wei-Chang Lu, Hao-Yu Jheng, Yun-Ting Hung, Xin-Zhang Chen and Wen-Ping Chen

Appl. Sci. 2022, 12(9), 4777; https://doi.org/10.3390/app12094777 - 09 May 2022

Cited by 1 | Viewed by 2087

Abstract

Companies have official vehicles for the convenience and time efficiency of employees to carry out official duties. However, private uses, false reports of fuel consumption, and excessive use by users may harm the company’s finance and reputation. Moreover, it is difficult to quantify [...] Read more.

Companies have official vehicles for the convenience and time efficiency of employees to carry out official duties. However, private uses, false reports of fuel consumption, and excessive use by users may harm the company’s finance and reputation. Moreover, it is difficult to quantify and manage the use of official vehicles as they are used by different groups in the company. Locating vehicles also is a problem that is caused by inappropriate management. To solve these problems, an online monitoring and management system of official vehicles is proposed in this study. The system includes a set-top box (STB), key cabinet unit, line bot, and backstage management system in four major units with GPS and moving path tracking functions. The STB functions include GPS mobile tracking, power management, and Wi-Fi communication. The key cabinet unit manages key storage for the STB and detects the location of the set-top box. The backstage management system stores general information and GPS locations of vehicles. Line Bot allows online management, and the backstage management system provides administrators with information on official vehicle uses. The test result of the system shows successful monitoring of the vehicles on identifying moving paths, mileage, and locations with an accuracy of 5 m. The system prevents doubled reservations and informs the exact location of the vehicles. It helps the administrator of the official vehicles monitor and analyze the data of uses of the vehicles to improve the management efficiency and prevent misuse of the vehicles. The system also provides a solution for sharing economy of vehicles. Full article

(This article belongs to the Special Issue Human-Computer Interactions)

► Show Figures

Figure 1

31 pages, 5324 KiB

Open AccessArticle

Tool for Predicting College Student Career Decisions: An Enhanced Support Vector Machine Framework

by Zhuang Wang, Guoxi Liang and Huiling Chen

Appl. Sci. 2022, 12(9), 4776; https://doi.org/10.3390/app12094776 - 09 May 2022

Cited by 6 | Viewed by 2343

Abstract

The goal of this research is to offer an effective intelligent model for forecasting college students’ career decisions in order to give a useful reference for career decisions and policy formation by relevant departments. The suggested prediction model is mainly based on a [...] Read more.

The goal of this research is to offer an effective intelligent model for forecasting college students’ career decisions in order to give a useful reference for career decisions and policy formation by relevant departments. The suggested prediction model is mainly based on a support vector machine (SVM) that has been modified using an enhanced butterfly optimization approach with a communication mechanism and Gaussian bare-bones mechanism (CBBOA). To get a better set of parameters and feature subsets, first, we added a communication mechanism to BOA to improve its global search capability and balance exploration and exploitation trends. Then, Gaussian bare-bones was added to increase the population diversity of BOA and its ability to jump out of the local optimum. The optimal SVM model (CBBOA-SVM) was then developed to predict the career decisions of college students based on the obtained parameters and feature subsets that are already optimized by CBBOA. In order to verify the effectiveness of CBBOA, we compared it with some advanced algorithms on all benchmark functions of CEC2014. Simulation results demonstrated that the performance of CBBOA is indeed more comprehensive. Meanwhile, comparisons between CBBOA-SVM and other machine learning approaches for career decision prediction were carried out, and the findings demonstrate that the provided CBBOA-SVM has better classification and more stable performance. As a result, it is plausible to conclude that the CBBOA-SVM is capable of being an effective tool for predicting college student career decisions. Full article

(This article belongs to the Special Issue Soft Computing Application to Engineering Design)

► Show Figures

Figure 1

19 pages, 2582 KiB

Open AccessArticle

Calculation of a Climate Change Vulnerability Index for Nakdong Watersheds Considering Non-Point Pollution Sources

by Jungmin Kim and Heongak Kwon

Appl. Sci. 2022, 12(9), 4775; https://doi.org/10.3390/app12094775 - 09 May 2022

Cited by 2 | Viewed by 4494

Abstract

As a response to climate change, South Korea has established its third National Climate Change Adaptation Plan (2021–2025) alongside the local governments’ plans. In this study, proxy variables in 22 sub-watersheds of the Nakdong River, Korea were used to investigate climate exposure, sensitivity, [...] Read more.

As a response to climate change, South Korea has established its third National Climate Change Adaptation Plan (2021–2025) alongside the local governments’ plans. In this study, proxy variables in 22 sub-watersheds of the Nakdong River, Korea were used to investigate climate exposure, sensitivity, adaptive capacity, and non-point pollution in sub-watersheds, a climate change vulnerability index (CCVI) was established, and the vulnerability of each sub-watershed in the Nakdong River was evaluated. Climate exposure was highest in the Nakdong Estuary sub-watershed (75.5–81.7) and lowest in the Geumhogang sub-watershed (21.1–28.1). Sensitivity was highest (55.7) in the Nakdong Miryang sub-watershed and lowest (19.6) in the Habcheon dam sub-watershed. Adaptive capacity and the resulting CCVI were highest in the Geumhogang sub-watershed (96.2 and 66.2–67.9, respectively) and lowest in the Wicheon sub-watershed (2.61 and 18.5–20.4, respectively), indicating low and high vulnerabilities to climate change, respectively. The study revealed that the high CCVI sensitivity was due to adaptive capacity. These findings can help establish rational climate change response plans for regional water resource management. To assess climate change vulnerability more accurately, regional bias can be prevented by considering various human factors, including resources, budget, and facilities. Full article

(This article belongs to the Topic Complex Systems and Artificial Intelligence)

► Show Figures

Figure 1

19 pages, 6160 KiB

Open AccessArticle

Typhoon-Induced Fragility Analysis of Transmission Tower in Ningbo Area Considering the Effect of Long-Term Corrosion

by Qiang Li, Hongtao Jia, Qing Qiu, Yongzhu Lu, Jun Zhang, Jianghong Mao, Weijie Fan and Mingfeng Huang

Appl. Sci. 2022, 12(9), 4774; https://doi.org/10.3390/app12094774 - 09 May 2022

Cited by 18 | Viewed by 1895

Abstract

The purpose of this paper was to investigate the influence of long-term corrosion on the deterioration of wind resistance of a steel transmission tower during its service life. An analytical model for predicting the long-term corrosion depth of carbon steel was established, and [...] Read more.

The purpose of this paper was to investigate the influence of long-term corrosion on the deterioration of wind resistance of a steel transmission tower during its service life. An analytical model for predicting the long-term corrosion depth of carbon steel was established, and the corrosion depth of carbon steel in the Ningbo area was predicted based on the local atmospheric environment data. With the help of typhoon full-track simulation and wind field simulation technology, a joint probability distribution model of multidirectional extreme wind speeds was constructed using the t-Copula function to determine the typhoon climate of the transmission tower site. Finite element models of the ZM4 cathead transmission tower under 30/60/90 corrosion years were then established, respectively, according to the predicted corrosion depth of carbon steel in Ningbo. Three damage modes, i.e., minor damage, moderate damage and severe damage, corresponding to the transmission tower under wind loads, were defined, and pushover analyses were used to determine the limit values of each damage mode so as to obtain the typhoon-induced fragility curves of the transmission tower within 30/60/90 corrosion years. The results show that the increase in corrosion age leads to a deterioration in the nominal mechanical properties of the transmission tower components, making the damage probability to the transmission tower increase. Under the typhoon wind loads of a 50-year return period in the most unfavorable wind direction in Ningbo, the probability of moderate damage of the tower is within 10% and the probability of minor damage is controlled between 10% and 40%. Full article

(This article belongs to the Special Issue Advances in Engineering Structural Systems)

► Show Figures

Figure 1

21 pages, 822 KiB

Open AccessArticle

Smart Contract Generation Assisted by AI-Based Word Segmentation

by Yu Tong, Weiming Tan, Jingzhi Guo, Bingqing Shen, Peng Qin and Shuaihe Zhuo

Appl. Sci. 2022, 12(9), 4773; https://doi.org/10.3390/app12094773 - 09 May 2022

Cited by 4 | Viewed by 3302

Abstract

In the last decade, blockchain smart contracts emerged as an automated, decentralized, traceable, and immutable medium of value exchange. Nevertheless, existing blockchain smart contracts are not compatible with legal contracts. The automatic execution of a legal contract written in natural language is an [...] Read more.

In the last decade, blockchain smart contracts emerged as an automated, decentralized, traceable, and immutable medium of value exchange. Nevertheless, existing blockchain smart contracts are not compatible with legal contracts. The automatic execution of a legal contract written in natural language is an open research question that can extend the blockchain ecosystem and inspire next-era business paradigms. In this paper, we propose an AI-assisted Smart Contract Generation (AIASCG) framework that allows contracting parties in heterogeneous contexts and different languages to collaboratively negotiate and draft the contract clauses. AIASCG provides a universal representation of contracts through the machine natural language (MNL) as the common understanding of the contract obligations. We compare the design of AIASCG with existing smart contract generation approaches to present its novelty. The main contribution of AIASCG is to address the issue in our previous proposed smart contract generation framework. For sentences written in natural language, existing framework requires editors to manually split sentences into words with semantic meaning. We propose an AI-based automatic word segmentation technique called Separation Inference (SpIn) to fulfill automatic split of the sentence. SpIn serves as the core component in AIASCG that accurately recommends the intermediate MNL outputs from a natural language sentence, tremendously reducing the manual effort in contract generation. SpIn is evaluated from a robustness and human satisfaction point of view to demonstrate its effectiveness. In the robustness evaluation, SpIn achieves state-of-the-art F1 scores and Recall of Out-of-Vocabulary (R_OOV) words on multiple word segmentation tasks. In addition, in the human evaluation, participants believe that 88.67% of sentences can be saved 80–100% of the time through automatic word segmentation. Full article

► Show Figures

Figure 1

17 pages, 2613 KiB

Open AccessArticle

Interpreted Petri Nets Applied to Autonomous Components within Electric Power Systems

by Iwona Grobelna and Paweł Szcześniak

Appl. Sci. 2022, 12(9), 4772; https://doi.org/10.3390/app12094772 - 09 May 2022

Cited by 6 | Viewed by 1761

Abstract

In this article, interpreted Petri nets are applied to the area of power and energy systems. These kinds of nets, equipped with input and output signals for communication with the environment, have so far proved to be useful in the specification of control [...] Read more.

In this article, interpreted Petri nets are applied to the area of power and energy systems. These kinds of nets, equipped with input and output signals for communication with the environment, have so far proved to be useful in the specification of control systems and cyber–physical systems (in particular, the control part), but they have not been used in power systems themselves. Here, interpreted Petri nets are applied to the specification of autonomous parts within power and energy systems. An electric energy storage (EES) system is presented as an application system for the provision of a system service for stabilizing the power of renewable energy sources (RES) or highly variable loads. The control algorithm for the EES is formally written as an interpreted Petri net, allowing it to benefit from existing analysis and verification methods. In particular, essential properties of such specifications can be checked, including, e.g., liveness, safety, reversibility, and determinism. This enables early detection of possible structural errors. The results indicate that interpreted Petri nets can be successfully used to model and analyze autonomous control components within power energy systems. Full article

(This article belongs to the Collection Advanced Power Electronics in Power Networks)

► Show Figures

Figure 1

10 pages, 1803 KiB

Open AccessArticle

Natural Stones with a Self-Cleaning Surface via Self-Assembled Monolayers

by Zhuoqi Duan, Zaixin Xie, Bao Zhou, Xiaobo Yang, Heng-Yong Nie and Yongmao Hu

Appl. Sci. 2022, 12(9), 4771; https://doi.org/10.3390/app12094771 - 09 May 2022

Viewed by 1564

Abstract

Heritage buildings and monuments are mostly made from natural stone, which undergoes irreversible decay under outdoor conditions. The main reason for the contamination, degradation, and cracking of natural stones is water and oil permeation. Hence, modifications on stones rendering their surface self-cleaning are [...] Read more.

Heritage buildings and monuments are mostly made from natural stone, which undergoes irreversible decay under outdoor conditions. The main reason for the contamination, degradation, and cracking of natural stones is water and oil permeation. Hence, modifications on stones rendering their surface self-cleaning are effective for stone protection. Reported in this paper is the development of a bionic approach to enabling self-cleaning stone surface via growing self-assembled polydopamine (PDA) as the adhesive layer on the stone surface, followed by depositing Al₂O₃ nanoparticles derivatized by self-assembled monolayers of a fluorophosphonic acid (FPA). This approach ensured a robust surface modification that realized superhydrophobicity, as demonstrated on natural marbles, Hedishi, and Qingshi. The surface modification was thermally stable up to 400 °C. Full article

(This article belongs to the Special Issue Self-Assembled Monolayers (SAMs) and Their Applications)

► Show Figures

Figure 1

25 pages, 4680 KiB

Open AccessArticle

A Machine Learning Approach for the Non-Destructive Estimation of Leaf Area in Medicinal Orchid Dendrobium nobile L.

by Madhurima Das, Chandan Kumar Deb, Ram Pal and Sudeep Marwaha

Appl. Sci. 2022, 12(9), 4770; https://doi.org/10.3390/app12094770 - 09 May 2022

Cited by 1 | Viewed by 1969

Abstract

In this study, leaf area prediction models of Dendrobium nobile, were developed through machine learning (ML) techniques including multiple linear regression (MLR), support vector regression (SVR), gradient boosting regression (GBR), and artificial neural networks (ANNs). The best model was tested using the [...] Read more.

In this study, leaf area prediction models of Dendrobium nobile, were developed through machine learning (ML) techniques including multiple linear regression (MLR), support vector regression (SVR), gradient boosting regression (GBR), and artificial neural networks (ANNs). The best model was tested using the coefficient of determination (R²), mean absolute errors (MAEs), and root mean square errors (RMSEs) and statistically confirmed through average rank (AR). Leaf images were captured through a smartphone and ImageJ was used to calculate the length (L), width (W), and leaf area (LA). Three orders of L, W, and their combinations were taken for model building. Multicollinearity status was checked using Variance Inflation Factor (VIF) and Tolerance (T). A total of 80% of the dataset and the remaining 20% were used for training and validation, respectively. KFold (K = 10) cross-validation checked the model overfit. GBR (R², MAE and RMSE values ranged at 0.96, (0.82–0.91) and (1.10–1.11) cm²) in the testing phase was the best among the ML models. AR statistically confirms the outperformance of GBR, securing first rank and a frequency of 80% among the top ten ML models. Thus, GBR is the best model imparting its future utilization to estimate leaf area in D. nobile. Full article

(This article belongs to the Section Agricultural Science and Technology)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Appl. Sci., Volume 12, Issue 9 (May-1 2022) – 706 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI