Next Issue
Volume 8, December
Previous Issue
Volume 8, August
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.4
3.4
Journals
Inventions
Volume 8
Issue 5
share announcement

Inventions, Volume 8, Issue 5 (October 2023) – 26 articles

Cover Story (view full-size image): The quest for ensuring the safety of electric vehicles looms large, and addressing the critical concern of potential hydrogen fuel leaks induced by Proton-Exchange Membrane Fuel Cell (PEMFC) gasket material degradation is a major task. This study pioneers an innovative approach by employing advanced Finite Element Analysis (FEA) techniques to rigorously evaluate the suitability of gasket materials for PEMFC applications, focusing on two pivotal scenarios: aging and tensile stress. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
15 pages, 3257 KiB  
Article
A Modified Phase-Transition Model for Multi-Oscillations of Spark-Generated Bubbles
by Rui Han, Jiayi Chen and Taikun Guo
Inventions 2023, 8(5), 131; https://doi.org/10.3390/inventions8050131 - 23 Oct 2023
Viewed by 1369
Abstract
The main composition within a spark-generated bubble primarily consists of vapor, accompanied by a minor presence of noncondensable gases. The phase transition exerts a substantial influence on bubble dynamics throughout various stages, a facet that has been frequently overlooked in prior research. In [...] Read more.
The main composition within a spark-generated bubble primarily consists of vapor, accompanied by a minor presence of noncondensable gases. The phase transition exerts a substantial influence on bubble dynamics throughout various stages, a facet that has been frequently overlooked in prior research. In this study, we introduce a modified theoretical model aimed at accurately predicting the multiple oscillations of spark-generated bubbles. Leveraging the Plesset equation, which integrates second-order corrections for compressibility and non-equilibrium evaporation, we further incorporate the thermal boundary layer approximation for bubbles, as proposed by Zhong et al. We employ an adjusted phase transition duration tailored to the unique characteristics of spark-generated bubbles. Furthermore, we meticulously ascertain initial conditions through repeated gas content measurements within the bubble. Our proposed theoretical model undergoes rigorous validation through quantitative comparisons with experimental data, yielding commendable agreement in modeling the dynamic behavior of bubbles across multiple cycles. Remarkably, we uncover that the condensation rate significantly governs the behavior of spark bubbles during their initial two cycles. Finally, we investigate the dependence of spark-generated bubble dynamics on the phase transition and the presence of air. Air content exhibits a minimal impact on bubble motion prior to the initial bubble collapse, but plays a role in the bubble’s rebound thereafter. Full article
(This article belongs to the Special Issue Innovative Research and Applications in Hydrodynamics and Flow Control)
►▼ Show Figures

Figure 1

19 pages, 3699 KiB  
Article
Optimal Dispatch Strategy for a Distribution Network Containing High-Density Photovoltaic Power Generation and Energy Storage under Multiple Scenarios
by Langbo Hou, Heng Chen, Jinjun Wang, Shichao Qiao, Gang Xu, Honggang Chen and Tao Liu
Inventions 2023, 8(5), 130; https://doi.org/10.3390/inventions8050130 - 19 Oct 2023
Viewed by 1357
Abstract
To better consume high-density photovoltaics, in this article, the application of energy storage devices in the distribution network not only realizes the peak shaving and valley filling of the electricity load but also relieves the pressure on the grid voltage generated by the [...] Read more.
To better consume high-density photovoltaics, in this article, the application of energy storage devices in the distribution network not only realizes the peak shaving and valley filling of the electricity load but also relieves the pressure on the grid voltage generated by the distributed photovoltaic access. At the same time, photovoltaic power generation and energy storage cooperate and have an impact on the tidal distribution of the distribution network. Since photovoltaic output has uncertainty, the maximum photovoltaic output in each scenario is determined by the clustering algorithm, while the storage scheduling strategy is reasonably selected so the distribution network operates efficiently and stably. The tidal optimization of the distribution network is carried out with the objectives of minimizing network losses and voltage deviations, two objectives that are assigned comprehensive weights, and the optimization model is constructed by using a particle swarm algorithm to derive the optimal dispatching strategy of the distribution network with the cooperation of photovoltaic and energy storage. Finally, a model with 30 buses is simulated and the system is optimally dispatched under multiple scenarios to demonstrate the necessity of conducting coordinated optimal dispatch of photovoltaics and energy storage. Full article
(This article belongs to the Special Issue Recent Advances and Challenges in Emerging Power Systems)
►▼ Show Figures

Figure 1

29 pages, 5796 KiB  
Article
Harnessing Deep Convolutional Neural Networks Detecting Synthetic Cannabinoids: A Hybrid Learning Strategy for Handling Class Imbalances in Limited Datasets
by Catalina Mercedes Burlacu, Adrian Constantin Burlacu, Mirela Praisler and Cristina Paraschiv
Inventions 2023, 8(5), 129; https://doi.org/10.3390/inventions8050129 - 16 Oct 2023
Cited by 1 | Viewed by 2130
Abstract
The aim of this research was to develop and deploy efficient deep convolutional neural network (DCNN) frameworks for detecting and discriminating between various categories of designer drugs. These are of particular relevance in forensic contexts, aiding efforts to prevent and counter drug use [...] Read more.
The aim of this research was to develop and deploy efficient deep convolutional neural network (DCNN) frameworks for detecting and discriminating between various categories of designer drugs. These are of particular relevance in forensic contexts, aiding efforts to prevent and counter drug use and trafficking and supporting associated legal investigations. Our multinomial classification architectures, based on Attenuated Total Reflectance Fourier-Transform Infrared (ATR-FTIR) spectra, are primarily tailored to accurately identify synthetic cannabinoids. Within the scope of our dataset, they also adeptly detect other forensically significant drugs and misused prescription medications. The artificial intelligence (AI) models we developed use two platforms: our custom-designed, pre-trained Convolutional Autoencoder (CAE) and a structure derived from the Vision Transformer Trained on ImageNet Competition Data (ViT-B/32) model. In order to compare and refine our models, various loss functions (cross-entropy and focal loss) and optimization algorithms (Adaptive Moment Estimation, Stochastic Gradient Descent, Sign Stochastic Gradient Descent, and Root Mean Square Propagation) were tested and evaluated at differing learning rates. This study shows that innovative transfer learning methods, which integrate both unsupervised and supervised techniques with spectroscopic data pre-processing (ATR correction, normalization, smoothing) and present significant benefits. Their effectiveness in training AI systems on limited, imbalanced datasets is particularly notable. The strategic deployment of CAEs, complemented by data augmentation and synthetic sample generation using the Synthetic Minority Oversampling Technique (SMOTE) and class weights, effectively address the challenges posed by such datasets. The robustness and adaptability of our DCNN models are discussed, emphasizing their reliability and portability for real-world applications. Beyond their primary forensic utility, these systems demonstrate versatility, making them suitable for broader computer vision tasks, notably image classification and object detection. Full article
(This article belongs to the Special Issue Perspectives and Challenges in Doctoral Research—Selected Papers from the 11th Edition of the Scientific Conference of the Doctoral Schools of “Dunărea de Jos” University of Galati (SCDS-UDJG))
►▼ Show Figures

Figure 1

23 pages, 8844 KiB  
Review
Mixer Design and Flow Rate as Critical Variables in Flow Chemistry Affecting the Outcome of a Chemical Reaction: A Review
by Ilya V. Myachin and Leonid O. Kononov
Inventions 2023, 8(5), 128; https://doi.org/10.3390/inventions8050128 - 16 Oct 2023
Cited by 3 | Viewed by 2215
Abstract
Flow chemistry offers several advantages for performing chemical reactions and has become an important area of research. It may seem that sufficient knowledge has already been acquired on this topic to understand how to choose the design of microreactor/micromixer and flow rate in [...] Read more.
Flow chemistry offers several advantages for performing chemical reactions and has become an important area of research. It may seem that sufficient knowledge has already been acquired on this topic to understand how to choose the design of microreactor/micromixer and flow rate in order to achieve the desired outcome of a reaction. However, some experimental data are difficult to explain based on commonly accepted concepts of chemical reactivity and performance of microfluidic systems. In this mini review, we attempt to identify such data and offer a rational explanation of unusual results based on the supramer approach. We demonstrate that variation in flow regime (determined by mixer design and flow rate) can either improve or worsen the reactivity and lead to completely different products, including stereoisomers. It is not necessary to mix the reagents with maximum efficiency. The real challenge is to mix reagents the right way since at a too high or too low flow rate (in the particular mixer), the molecules of reagents are incorrectly presented on the surface of supramers, leading to altered stereoselectivity, or form tight supramers, in which most of the molecules are located inside the supramer core and are inaccessible for attack, leading to low yields. Full article
(This article belongs to the Special Issue Innovative Research and Applications in Hydrodynamics and Flow Control)
►▼ Show Figures

Graphical abstract

23 pages, 4036 KiB  
Article
Sustainable Power Generation Expansion in Island Systems with Extensive RES and Energy Storage
by Emmanuel Karapidakis, Christos Kalogerakis and Evangelos Pompodakis
Inventions 2023, 8(5), 127; https://doi.org/10.3390/inventions8050127 - 11 Oct 2023
Cited by 2 | Viewed by 1378
Abstract
Insular networks constitute ideal fields for investment in renewables and storage due to their excellent wind and solar potential, as well the high generation cost of thermal generators in such networks. Nevertheless, in order to ensure the stability of insular networks, network operators [...] Read more.
Insular networks constitute ideal fields for investment in renewables and storage due to their excellent wind and solar potential, as well the high generation cost of thermal generators in such networks. Nevertheless, in order to ensure the stability of insular networks, network operators impose strict restrictions on the expansion of renewables. Storage systems render ideal solutions for overcoming the aforementioned restrictions, unlocking additional renewable capacity. Among storage technologies, hybrid battery-hydrogen demonstrates beneficial characteristics thanks to the complementary features that battery and hydrogen exhibit regarding efficiency, self-discharge, cost, etc. This paper investigates the economic feasibility of a private investment in renewables and hybrid hydrogen-battery storage, realized on the interconnected island of Crete, Greece. Specifically, an optimization formulation is proposed to optimize the capacity of renewables and hybrid battery-hydrogen storage in order to maximize the profit of investment, while simultaneously reaching a minimum renewable penetration of 80%, in accordance with Greek decarbonization goals. The numerical results presented in this study demonstrate that hybrid hydrogen-battery storage can significantly reduce electricity production costs in Crete, potentially reaching as low as 64 EUR/MWh. From an investor’s perspective, even with moderate compensation tariffs, the energy transition remains profitable due to Crete’s abundant wind and solar resources. For instance, with a 40% subsidy and an 80 EUR/MWh compensation tariff, the net present value can reach EUR 400 million. Furthermore, the projected cost reductions for electrolyzers and fuel cells by 2030 are expected to enhance the profitability of hybrid renewable-battery-hydrogen projects. In summary, this research underscores the sustainable and economically favorable prospects of hybrid hydrogen-battery storage systems in facilitating Crete’s energy transition, with promising implications for investors and the wider renewable energy sector. Full article
(This article belongs to the Special Issue The Development and Optimization of Innovative Systems, Processes, and Materials for the Production, Conversion, and Storage of Energy (Volume 2))
►▼ Show Figures

Figure 1

20 pages, 5632 KiB  
Article
Predicting Energy Generation in Large Wind Farms: A Data-Driven Study with Open Data and Machine Learning
by Matheus Paula, Wallace Casaca, Marilaine Colnago, José R. da Silva, Kleber Oliveira, Mauricio A. Dias and Rogério Negri
Inventions 2023, 8(5), 126; https://doi.org/10.3390/inventions8050126 - 11 Oct 2023
Viewed by 2203
Abstract
Wind energy has become a trend in Brazil, particularly in the northeastern region of the country. Despite its advantages, wind power generation has been hindered by the high volatility of exogenous factors, such as weather, temperature, and air humidity, making long-term forecasting a [...] Read more.
Wind energy has become a trend in Brazil, particularly in the northeastern region of the country. Despite its advantages, wind power generation has been hindered by the high volatility of exogenous factors, such as weather, temperature, and air humidity, making long-term forecasting a highly challenging task. Another issue is the need for reliable solutions, especially for large-scale wind farms, as this involves integrating specific optimization tools and restricted-access datasets collected locally at the power plants. Therefore, in this paper, the problem of forecasting the energy generated at the Praia Formosa wind farm, an eco-friendly park located in the state of Ceará, Brazil, which produces around 7% of the state’s electricity, was addressed. To proceed with our data-driven analysis, publicly available data were collected from multiple Brazilian official sources, combining them into a unified database to perform exploratory data analysis and predictive modeling. Specifically, three machine-learning-based approaches were applied: Extreme Gradient Boosting, Random Forest, and Long Short-Term Memory Network, as well as feature-engineering strategies to enhance the precision of the machine intelligence models, including creating artificial features and tuning the hyperparameters. Our findings revealed that all implemented models successfully captured the energy-generation trends, patterns, and seasonality from the complex wind data. However, it was found that the LSTM-based model consistently outperformed the others, achieving a promising global MAPE of 4.55%, highlighting its accuracy in long-term wind energy forecasting. Temperature, relative humidity, and wind speed were identified as the key factors influencing electricity production, with peak generation typically occurring from August to November. Full article
(This article belongs to the Special Issue Distribution Renewable Energy Integration and Grid Modernization)
►▼ Show Figures

Figure 1

19 pages, 6629 KiB  
Article
Experimental Validation of the Numerical Model for Oil–Gas Separation
by Sorin Gabriel Tomescu, Ion Mălăel, Rareș Conțiu and Sebastian Voicu
Inventions 2023, 8(5), 125; https://doi.org/10.3390/inventions8050125 - 10 Oct 2023
Cited by 1 | Viewed by 1569
Abstract
The oil and gas sector is important to the global economy because it covers the exploration, production, processing, transportation, and distribution of oil and natural gas resources. Despite constant innovation and development of technologies to improve efficiency, reduce environmental impact, and optimize operations [...] Read more.
The oil and gas sector is important to the global economy because it covers the exploration, production, processing, transportation, and distribution of oil and natural gas resources. Despite constant innovation and development of technologies to improve efficiency, reduce environmental impact, and optimize operations in the gas and oil industry over the last few decades, there is still room to increase the efficiency of the industry’s equipment in order to reduce its carbon footprint. The separation of gas from oil is a critical stage in the technological production chain, and it is carried out using high-performance multi-phase separators to limit greenhouse gas emissions and have a low impact on the environment. In this study, an improved gas–oil separator configuration was established utilizing CFD techniques. Two separator geometry characteristics were studied. Both cases have the same number of subdomains, two porous media, and four fluid zones, but with a difference in the pitch of the cyclone from the inlet subdomain. The streamlines in a cross-plan of the separator and the distribution of the oil volume fraction from the intake to the outlet were two of the numerical results that were shown as numeric outcomes. The validation of these results was performed using an experimental testing campaign that had the purpose of determining the amount of lubricating oil that is discharged together with the compressed gas at the separator outlet. Full article
(This article belongs to the Special Issue Recent Advances in Fluid Mechanics and Transport Phenomena)
►▼ Show Figures

Figure 1

14 pages, 4196 KiB  
Article
Obtaining Vortex Formation in Blood Flow by Particle Tracking: Echo-PV Methods and Computer Simulation
by Ilya Starodumov, Sergey Sokolov, Ksenia Makhaeva, Pavel Mikushin, Olga Dinislamova and Felix Blyakhman
Inventions 2023, 8(5), 124; https://doi.org/10.3390/inventions8050124 - 09 Oct 2023
Viewed by 1238
Abstract
Micrometer-sized particles are widely introduced as fluid flow markers in experimental studies of convective flows. The tracks of such particles demonstrate a high contrast in the optical range and well illustrate the direction of fluid flow at local vortices. This study addresses the [...] Read more.
Micrometer-sized particles are widely introduced as fluid flow markers in experimental studies of convective flows. The tracks of such particles demonstrate a high contrast in the optical range and well illustrate the direction of fluid flow at local vortices. This study addresses the theoretical justification on the use of large particles for obtaining vortex phenomena and its characterization in stenotic arteries by the Echo Particle Velocimetry method. Calcite particles with an average diameter of 0.15 mm were chosen as a marker of streamlines using a medical ultrasound device. The Euler–Euler model of particle motion was applied to simulate the mechanical behavior of calcite particles and 20 µm aluminum particles. The accuracy of flow measurement at vortex regions was evaluated by computational fluid dynamics methods. The simulation results of vortex zone formation obtained by Azuma and Fukushima (1976) for aluminum particles with the use of the optical velocimetry method and calcite particles were compared. An error in determining the size of the vortex zone behind of stenosis does not exceed 5%. We concluded that the application of large-size particles for the needs of in vitro studies of local hemodynamics is possible. Full article
(This article belongs to the Special Issue Innovative Research and Applications in Hydrodynamics and Flow Control)
►▼ Show Figures

Figure 1

16 pages, 1877 KiB  
Article
Fault Location Method for Overhead Power Line Based on a Multi-Hypothetical Sequential Analysis Using the Armitage Algorithm
by Aleksandr Kulikov, Pavel Ilyushin, Anton Loskutov and Sergey Filippov
Inventions 2023, 8(5), 123; https://doi.org/10.3390/inventions8050123 - 27 Sep 2023
Viewed by 1364
Abstract
The use of modern methods for determining the fault location (FL) on overhead power lines (OHPLs), which have high accuracy and speed, contributes to the reliable operation of power systems. Various physical principles are used in FL devices for OHPLs, as well as [...] Read more.
The use of modern methods for determining the fault location (FL) on overhead power lines (OHPLs), which have high accuracy and speed, contributes to the reliable operation of power systems. Various physical principles are used in FL devices for OHPLs, as well as various algorithms for calculating the distance to the FL. Some algorithms for FL on OHPLs use emergency mode parameters (EMP); other algorithms use measurement results based on wave methods. Many random factors that determine the magnitude of the error in calculating the distance to the FL affect the operation of FL devices by EMP. Methods based on deterministic procedures used in well-known FL devices for OHPLs do not take into account the influence of random factors, which significantly increases the time to search for the fault. The authors have developed a method of FL on OHPLs based on a multi-hypothetical sequential analysis using the Armitage algorithm. The task of recognizing a faulted section of an OHPL is formulated as a statistical problem. To do this, the inspection area of the OHPL is divided into many sections, followed by the implementation of the procedure for FL. The developed method makes it possible to adapt the distortions of currents and voltages on the emergency mode oscillograms to the conditions for estimating their parameters. The results of the calculations proved that the implementation of the developed method has practically no effect on the speed of the FL algorithm for the OHPL by EMP. This ensures the uniqueness of determining the faulted section of the OHPL under the influence of random factors, which leads to a significant reduction in the inspection area of the OHPL. The application of the developed method in FL devices for OHPLs will ensure the required reliability of power supply to consumers and reduce losses from power outages by minimizing the time to search for a fault. Full article
(This article belongs to the Special Issue Recent Advances and Challenges in Emerging Power Systems)
►▼ Show Figures

Figure 1

24 pages, 15079 KiB  
Article
Sensing Spontaneous Combustion in Agricultural Storage Using IoT and ML
by Umar Farooq Shafi, Imran Sarwar Bajwa, Waheed Anwar, Hina Sattar, Shabana Ramzan and Aqsa Mahmood
Inventions 2023, 8(5), 122; https://doi.org/10.3390/inventions8050122 - 26 Sep 2023
Cited by 2 | Viewed by 1540
Abstract
The combustion of agricultural storage represents a big hazard to the safety and quality preservation of crops during lengthy storage times. Cotton storage is considered more prone to combustion for many reasons, i.e., heat by microbial growth, exothermic and endothermic reactions in storage [...] Read more.
The combustion of agricultural storage represents a big hazard to the safety and quality preservation of crops during lengthy storage times. Cotton storage is considered more prone to combustion for many reasons, i.e., heat by microbial growth, exothermic and endothermic reactions in storage areas, and extreme weather conditions in storage areas. Combustion not only increases the chances of a big fire outbreak in the long run, but it may also affect cotton’s quality factors like its color, staple length, seed quality, etc. The cotton’s quality attributes may divert from their normal range in the presence of combustion. It is difficult to detect, monitor, and control combustion. The Internet of Things (IoT) offers efficient and reliable solutions for numerous research problems in agriculture, healthcare, business analytics, and industrial manufacturing. In the agricultural domain, the IoT provides various applications for crop monitoring, warehouse protection, the prevention of crop diseases, and crop yield maximization. We also used the IoT for the smart and real-time sensing of spontaneous combustion inside storage areas in order to maintain cotton quality during lengthy storage. In the current research, we investigate spontaneous combustion inside storage and identify the primary reasons for it. Then, we proposed an efficient IoT and machine learning (ML)-based solution for the early sensing of combustion in storage in order to maintain cotton quality during long storage times. The proposed system provides real-time sensing of combustion-causing factors with the help of the IoT-based circuit and prediction of combustion using an efficient artificial neural network (ANN) model. The proposed smart sensing of combustion is verified by a different set of experiments. The proposed ANN model showed a 99.8% accuracy rate with 95–98% correctness and 97–99% completeness. The proposed solution is very efficient in detecting combustion and enables storage owners to become aware of combustion hazards in a timely manner; hence, they can improve the storage conditions for the preservation of cotton quality in the long run. The whole article consists of five sections. Full article
(This article belongs to the Special Issue Inventions and Innovation in Smart Sensing Technologies for Agriculture)
►▼ Show Figures

Figure 1

22 pages, 6664 KiB  
Article
Liquid Natural Gas Cold Energy Recovery for Integration of Sustainable District Cooling Systems: A Thermal Performance Analysis
by Yang Luo, Xuesong Lu, Yi Chen, John Andresen and Mercedes Maroto-Valer
Inventions 2023, 8(5), 121; https://doi.org/10.3390/inventions8050121 - 25 Sep 2023
Viewed by 1517
Abstract
This paper investigates the heat transfer properties of liquefied natural gas (LNG) in a corrugated plate heat exchanger and explores its application in cold energy recovery for enhanced energy efficiency. The study aims to integrate this technology into a 500 MW gas-fired power [...] Read more.
This paper investigates the heat transfer properties of liquefied natural gas (LNG) in a corrugated plate heat exchanger and explores its application in cold energy recovery for enhanced energy efficiency. The study aims to integrate this technology into a 500 MW gas-fired power plant and a district cooling system to contribute to sustainable city development. Using computational fluid dynamics simulations and experimental validation, the heat transfer behaviour of LNG in the corrugated plate heat exchanger is examined, emphasising the significance of the gas film on the channel wall for efficient heat transfer between LNG and water/ethylene glycol. The study analyses heat exchange characteristics below and above the critical point of LNG. Below the critical point, the LNG behaves as an incompressible fluid, whereas above the critical point, the compressible supercritical state enables a substantial energy recovery and temperature rise at the outlet, highlighting the potential for cold energy recovery. The results demonstrate the effectiveness of cold energy recovery above the critical point, leading to significant energy savings and improved efficiency compared to conventional systems. Optimal operational parameters, such as the number of channels and flow rate ratios, are identified for successful cold energy recovery. This research provides valuable insights for sustainable city planning and the transition towards low-carbon energy systems, contributing to the overall goal of creating environmentally friendly and resilient urban environments. Full article
(This article belongs to the Special Issue The Development and Optimization of Innovative Systems, Processes, and Materials for the Production, Conversion, and Storage of Energy (Volume 2))
►▼ Show Figures

Figure 1

23 pages, 8270 KiB  
Article
A Dynamic Control Model of the Blades Position for the Vertical-Axis Wind Generator by a Program Method
by Ivaylo Stoyanov, Teodor Iliev, Alina Fazylova and Gulsara Yestemessova
Inventions 2023, 8(5), 120; https://doi.org/10.3390/inventions8050120 - 25 Sep 2023
Cited by 1 | Viewed by 1259
Abstract
This article discusses the construction of a dynamic model for controlling the position of the blades of a vertical-axis wind generator using an automatic approach; a method is presented that relates the rotation of the motor to the position of the blades, which [...] Read more.
This article discusses the construction of a dynamic model for controlling the position of the blades of a vertical-axis wind generator using an automatic approach; a method is presented that relates the rotation of the motor to the position of the blades, which allows the optimization of the operation of the control system. In the research process, an automatic approach is used, which makes it possible to carry out numerical calculations that predict the behavior of the system at various values of motor rotation. The model allows us to analyze the dependence of the position of the blades on the rotation of the motor and determine the optimal parameters of the mathematical control model. The main goal of our study is to develop a mathematical model of the mechanism for further adjustment of the wind turbine blade position control system depending on the wind speed. Full article
(This article belongs to the Special Issue Automatic Control and System Theory and Advanced Applications)
►▼ Show Figures

Figure 1

18 pages, 4578 KiB  
Article
Developments in the Use of Hinfinity Control and μ-Analysis for Reducing Vibration in Intelligent Structures
by Amalia Moutsopoulou, Georgios E. Stavroulakis, Markos Petousis, Anastasios Pouliezos and Nectarios Vidakis
Inventions 2023, 8(5), 119; https://doi.org/10.3390/inventions8050119 - 25 Sep 2023
Viewed by 1052
Abstract
During the past few years, there has been a notable surge of interest in the field of smart structures. An intelligent structure is one that automatically responds to mechanical disturbances by minimizing oscillations after intelligently detecting them. In this study, a smart design [...] Read more.
During the past few years, there has been a notable surge of interest in the field of smart structures. An intelligent structure is one that automatically responds to mechanical disturbances by minimizing oscillations after intelligently detecting them. In this study, a smart design that contains integrated actuators and sensors that can dampen oscillations is shown. A finite element analysis is used in conjunction with the application of dynamic loads such as wind force. The dynamic-loading-induced vibration of the intelligent piezoelectric structure is aimed to be mitigated using a μ-controller. The controller’s robustness against uncertainties in the parameters to address vibration-related concerns is showcased. This article offers a thorough depiction of the benefits stemming from μ-analysis and active vibration control in the behavior of intelligent structures. The gradual surmounting of these challenges is attributed to the increasing affordability and enhanced capability of electronic components used for control implementation. The advancement of μ-analysis and robust control for vibration reduction in intelligent structures is amply demonstrated in this study. Full article
(This article belongs to the Section Inventions and Innovation in Electrical Engineering/Energy/Communications)
►▼ Show Figures

Figure 1

24 pages, 4044 KiB  
Article
Effect of Support Stiffness Nonlinearity on the Low-Frequency Vibro-Acoustic Characteristics for a Mechanical Equipment—Floating Raft—Underwater Cylindrical Shell Coupled System
by Likang Wang and Rui Huo
Inventions 2023, 8(5), 118; https://doi.org/10.3390/inventions8050118 - 21 Sep 2023
Viewed by 1122
Abstract
The low-frequency vibro-acoustic characteristics of a mechanical equipment—floating raft—cylindrical shell—underwater acoustic field coupled system with nonlinear supports are studied in this paper. Firstly, the state space equations were established by a modal superposition theory for the coupled system, and a modal parameter identification [...] Read more.
The low-frequency vibro-acoustic characteristics of a mechanical equipment—floating raft—cylindrical shell—underwater acoustic field coupled system with nonlinear supports are studied in this paper. Firstly, the state space equations were established by a modal superposition theory for the coupled system, and a modal parameter identification method was deduced and verified for the cylindrical shell—underwater acoustic field coupled subsystem. On this basis, the formulas were derived for transmitted power flow in the coupled system, and the nonlinear stiffness constitutive relation of the vibration isolation supports was expressed by softening and hardening characteristics. Finally, dynamic simulations were carried out by the Runge—Kutta method to analyze the effect of nonlinear stiffness characteristic parameters on the low-frequency vibration modes and vibro-acoustic transfer characteristics in the coupled system. The research shows that a superharmonic phenomenon is common in the steady vibration mode of the coupled system with a nonlinear softening (or hardening) stiffness characteristic under harmonic excitation. The stronger the softening (or hardening) stiffness characteristic is, the more complex the vibration form is, and the smaller (or larger) the low-frequency vibro-acoustic transfer level in resonance regions is. Full article
(This article belongs to the Special Issue Innovative Research and Applications in Hydrodynamics and Flow Control)
►▼ Show Figures

Figure 1

17 pages, 3366 KiB  
Article
Optimal Siting and Sizing of Electric Vehicle Energy Supplement Infrastructure in Highway Networks
by Ding Jin, Huayu Zhang, Bing Han, Gang Liu, Fei Xue and Shaofeng Lu
Inventions 2023, 8(5), 117; https://doi.org/10.3390/inventions8050117 - 15 Sep 2023
Viewed by 1486
Abstract
The electric vehicle (EV) market is expanding rapidly to achieve the future goal of eco-friendly transportation. The scientific planning of energy supplement infrastructures (ESIs), with appropriate locations and capacity, is imperative to develop the EV industry. In this research, a mixed integer linear [...] Read more.
The electric vehicle (EV) market is expanding rapidly to achieve the future goal of eco-friendly transportation. The scientific planning of energy supplement infrastructures (ESIs), with appropriate locations and capacity, is imperative to develop the EV industry. In this research, a mixed integer linear programming (MILP) model is proposed to optimize the location and capacity of ESIs, including vehicle charging stations (VCSs), battery swapping stations (BSSs), and battery charging stations (BCSs), in highway networks. The objective of this model is to minimize the total cost with the average waiting time for EVs being constrained. In this model, battery swapping and transportation behaviors are optimized such that the EV average waiting time can be reduced, and the average queue and service process waiting time is estimated by the M/M/1 model. Real-world data, i.e., from the London M25 highway network system, are used as a case study to test the effectiveness of the proposed method. The results show that considering battery transportation behaviors is more cost efficient, and the results are sensitive to the EV average waiting time tolerance, battery cost, and charging demand. Full article
(This article belongs to the Special Issue Connected Vehicles and Charging Infrastructure: Innovations and Security)
►▼ Show Figures

Figure 1

29 pages, 22889 KiB  
Article
FEA Assessment of Contact Pressure and Von Mises Stress in Gasket Material Suitability for PEMFCs in Electric Vehicles
by Soo-Hyun Park, Akeem Bayo Kareem, Woo Jeong Joo and Jang-Wook Hur
Inventions 2023, 8(5), 116; https://doi.org/10.3390/inventions8050116 - 14 Sep 2023
Viewed by 1603
Abstract
Ensuring the safety of electric vehicles is paramount, and one critical concern is the potential for hazardous hydrogen fuel leaks caused by the degradation of Proton-Exchange Membrane Fuel Cell (PEMFC) gasket materials. This study employs advanced techniques to address this issue. We leverage [...] Read more.
Ensuring the safety of electric vehicles is paramount, and one critical concern is the potential for hazardous hydrogen fuel leaks caused by the degradation of Proton-Exchange Membrane Fuel Cell (PEMFC) gasket materials. This study employs advanced techniques to address this issue. We leverage Finite Element Analysis (FEA) to rigorously assess the suitability of gasket materials for PEMFC applications, focusing on two crucial conditions: ageing and tensile stress. To achieve this, we introduce a comprehensive “dual degradation framework” that considers the effects of contact pressure and von Mises stress. These factors are instrumental in evaluating the performance and durability of Liquid Silicon Rubber (LSR) and Ethylene Propylene Diene Monomer (EPDM) materials. Our findings reveal the Yeoh model as the most accurate and efficient choice for ageing simulations, boasting a minimal Mean Absolute Percentage Error (MAPE) and computational time of just 0.27 s. In contrast, the Ogden model, while accurate, requires more computational resources. In assessing overall model performance using MAE, Root Mean Square Error (RMSE), and R-squared metrics, both LSR and EPDM materials proved promising, with LSR exhibiting superior performance in most areas. Furthermore, our study incorporates uniaxial tensile testing, which yields RMSE and MAE values of 0.30% and 0.40%, respectively. These results provide valuable insights into material behaviour under tensile stress. Our research underscores the pivotal role of FEA in identifying optimal gasket materials for PEMFC applications. Notably, LSR is a superior choice, demonstrating enhanced FEA modelling performance under ageing and tensile conditions. These findings promise to significantly contribute to developing safer and more reliable electric vehicles by advancing gasket material design. Full article
(This article belongs to the Special Issue Connected Vehicles and Charging Infrastructure: Innovations and Security)
►▼ Show Figures

Figure 1

18 pages, 1413 KiB  
Article
Modelling the Application of Telemedicine in Emergency Care
by Gyoergy (George) L. Ferenczi and Áron Perényi
Inventions 2023, 8(5), 115; https://doi.org/10.3390/inventions8050115 - 14 Sep 2023
Viewed by 1747
Abstract
Emergency services are under pressure worldwide. Ambulance services in Victoria in Australia are particularly overloaded and the quality of service is suffering in comparison to other health services in Australia. An abundance of articles addresses this issue both in academic and industry outlets, [...] Read more.
Emergency services are under pressure worldwide. Ambulance services in Victoria in Australia are particularly overloaded and the quality of service is suffering in comparison to other health services in Australia. An abundance of articles addresses this issue both in academic and industry outlets, and the proposed solutions usually advise upgrades and better use of available resources. We believe that telemedicine could be part of the solution. Patients can be quickly assessed and monitored by advanced medical sensors, connected by straightforward means including a direct video link, to the hospital. Pre-assessment of conditions can be sent ahead to the emergency department, where specialists and physicians can select priorities and prepare for urgent interventions. An increasing number of patients with mental health, drug or alcohol-related issues can be transported elsewhere, thus reducing the load of emergency departments. We have methodically analysed Victorian ambulance statistics and we have identified appropriate telemedical technologies to be used in appropriate settings. We applied telemedical technology models in our work, to demonstrate the potential improvements in outcomes, including patient lives saved. Full article
(This article belongs to the Section Inventions and Innovation in Design, Modeling and Computing Methods)
►▼ Show Figures

Figure 1

20 pages, 6692 KiB  
Article
A Rank Analysis and Ensemble Machine Learning Model for Load Forecasting in the Nodes of the Central Mongolian Power System
by Tuvshin Osgonbaatar, Pavel Matrenin, Murodbek Safaraliev, Inga Zicmane, Anastasia Rusina and Sergey Kokin
Inventions 2023, 8(5), 114; https://doi.org/10.3390/inventions8050114 - 05 Sep 2023
Cited by 3 | Viewed by 1568
Abstract
Forecasting electricity consumption is currently one of the most important scientific and practical tasks in the field of electric power industry. The early retrieval of data on expected load profiles makes it possible to choose the optimal operating mode of the system. The [...] Read more.
Forecasting electricity consumption is currently one of the most important scientific and practical tasks in the field of electric power industry. The early retrieval of data on expected load profiles makes it possible to choose the optimal operating mode of the system. The resultant forecast accuracy significantly affects the performance of the entire electrical complex and the operating conditions of the electricity market. This can be achieved through using a model of total electricity consumption designed with an acceptable margin of error. This paper proposes a new method for predicting power consumption in all nodes of the power system through the determination of rank coefficients calculated directly for the corresponding voltage level, including node substations, power supply zones, and other parts of the power system. The forecast of the daily load schedule and the construction of a power consumption model was based on the example of nodes in the central power system in Mongolia. An ensemble of decision trees was applied to construct a daily load schedule and rank coefficients were used to simulate consumption in the nodes. Initial data were obtained from daily load schedules, meteorological factors, and calendar features of the central power system, which accounts for the majority of energy consumption and generation in Mongolia. The study period was 2019–2021. The daily load schedules of the power system were constructed using machine learning with a probability of 1.25%. The proposed rank analysis for power system zones increases the forecasting accuracy for each zone and can improve the quality of management and create more favorable conditions for the development of distributed generation. Full article
(This article belongs to the Special Issue Recent Advances and Challenges in Emerging Power Systems)
►▼ Show Figures

Figure 1

23 pages, 1865 KiB  
Article
Contribution to the Development of a Smart Ultrasound Scanner: Design and Analysis of the High-Voltage Power Supply of the Transmitter
by Nicolas Daniel Mbele Ndzana, Claude Bernard Lekini Nkodo, Aristide Tolok Nelem, Mathieu Jean Pierre Pesdjock, Yannick Antoine Abanda, Achille Melingui, Odile Fernande Zeh and Pierre Ele
Inventions 2023, 8(5), 113; https://doi.org/10.3390/inventions8050113 - 03 Sep 2023
Viewed by 1210
Abstract
A smart ultrasound scanner plays an important role in the transition to point-of-care imaging. DC–DC bipolar converters are essential in the generation of the ultrasound burst signal as they power the piezoelectric transducer. The conventional bipolar converter has minimal output gain and high-voltage [...] Read more.
A smart ultrasound scanner plays an important role in the transition to point-of-care imaging. DC–DC bipolar converters are essential in the generation of the ultrasound burst signal as they power the piezoelectric transducer. The conventional bipolar converter has minimal output gain and high-voltage stress, and the longer duty cycle on the semiconductors produces high conduction losses and reduces the efficiency of the system. The transmitter supply voltage is minimal, necessitating the use of high-gain bipolar converters. This proposed study is concerned with the development of an improved high-output voltage gain symmetric bipolar DC–DC converter topology which may be suitable for applications such as powering a smart ultrasound scanner transmitter. The proposed converter combines the conventional single-ended primary inductor converter (SEPIC) with a voltage multiplier cell (VMC) to improve voltage gain, transistor duty cycle, efficiency, and reliability. The present study describes the working principle of the proposed converter. The analysis of the voltage gain is carried out in continuous current mode (CCM) and discontinuous current mode (DCM), taking into account the nonidealities of the device. The simulation of the proposed system is carried out in the numerical environment Matlab/Simulink in order to verify its characteristics. A prototype model is realized and the experimental study presented validates the theoretical arguments and simulations. Due to the advantages of continuous input current, self-balancing bipolar outputs, and small component size, the proposed converter is a suitable choice for smart ultrasound transmitters. Full article
(This article belongs to the Special Issue The Development and Optimization of Innovative Systems, Processes, and Materials for the Production, Conversion, and Storage of Energy (Volume 2))
►▼ Show Figures

Figure 1

14 pages, 408 KiB  
Article
Improving Multiclass Classification of Fake News Using BERT-Based Models and ChatGPT-Augmented Data
by Elena Shushkevich, Mikhail Alexandrov and John Cardiff
Inventions 2023, 8(5), 112; https://doi.org/10.3390/inventions8050112 - 01 Sep 2023
Cited by 3 | Viewed by 2052
Abstract
Given the widespread accessibility of content creation and sharing, false information proliferation is a growing concern. Researchers typically tackle fake news detection (FND) in specific topics using binary classification. Our study addresses a more practical FND scenario, analyzing a corpus with unknown topics [...] Read more.
Given the widespread accessibility of content creation and sharing, false information proliferation is a growing concern. Researchers typically tackle fake news detection (FND) in specific topics using binary classification. Our study addresses a more practical FND scenario, analyzing a corpus with unknown topics through multiclass classification, encompassing true, false, partially false, and other categories. Our contribution involves: (1) exploring three BERT-based models—SBERT, RoBERTa, and mBERT; (2) enhancing results via ChatGPT-generated artificial data for class balance; and (3) improving outcomes using a two-step binary classification procedure. Our focus is on the CheckThat! Lab dataset from CLEF-2022. Our experimental results demonstrate a superior performance compared to existing achievements but FND’s practical use needs improvement within the current state-of-the-art. Full article
(This article belongs to the Special Issue From Sensing Technology towards Digital Twin in Applications)
►▼ Show Figures

Figure 1

20 pages, 6047 KiB  
Article
Quantification of Statins in Pharmaceutical Products Using Screen-Printed Sensors Based of Multi-Walled Carbon Nanotubes and Gold Nanoparticles
by Ramona Oana Roșca, Alexandra Virginia Bounegru and Constantin Apetrei
Inventions 2023, 8(5), 111; https://doi.org/10.3390/inventions8050111 - 30 Aug 2023
Viewed by 2574
Abstract
This study describes the use of electrochemical sensors to detect and quantify several statins (rosuvastatin and simvastatin) in pharmaceutical products. Two types of commercially screen-printed sensors were used and compared: one based on carbon (SPCE) and the other modified with gold nanoparticles and [...] Read more.
This study describes the use of electrochemical sensors to detect and quantify several statins (rosuvastatin and simvastatin) in pharmaceutical products. Two types of commercially screen-printed sensors were used and compared: one based on carbon (SPCE) and the other modified with gold nanoparticles and multi-walled carbon nanotubes (SPE/GNP-MWCNT). Cyclic voltammetry was employed for determination. The AuNP-MWCNTs/SPCE sensor outperformed the SPCE sensor, displaying excellent electrochemical properties. It demonstrated high sensitivity with low limits of detection (LOD) and quantification (LOQ) values: 0.15 µM and 5.03 µM, respectively, for rosuvastatin and 0.30 µM and 1.01 µM, respectively, for simvastatin. The sensor had a wide linear range of 20–275 µM for rosuvastatin and 50–350 µM for simvastatin. Using the AuNP-MWCNTs/SPCE sensor, rosuvastatin and simvastatin were successfully quantified in pharmaceutical products. The results were validated towards producer-reported values (standardized drugs) and a conventional analysis method (FTIR). The sensor exhibited excellent stability, reproducibility, and analytical recovery ranging from 99.3% to 106.6% with a low relative standard deviation (RSD) of less than 1%. In conclusion, the AuNP-MWCNTs/SPCE sensor proved to be a reliable and sensitive tool for detecting and quantifying statins in pharmaceutical products. Its superior electrochemical properties, low LOD and LOQ values, wide linear range, and high analytical recovery make it a promising choice for pharmaceutical quality control. Full article
(This article belongs to the Special Issue Perspectives and Challenges in Doctoral Research—Selected Papers from the 11th Edition of the Scientific Conference of the Doctoral Schools of “Dunărea de Jos” University of Galati (SCDS-UDJG))
►▼ Show Figures

Figure 1

15 pages, 6204 KiB  
Article
Design and Construction of a Device to Evaluate the Performance of Variable Orifice Flow Meters (VOFM)
by William Prado Martínez, Juan Felipe Arroyave Londoño and Jefferson Vásquez Gómez
Inventions 2023, 8(5), 110; https://doi.org/10.3390/inventions8050110 - 30 Aug 2023
Cited by 1 | Viewed by 1233
Abstract
This work presents a low-cost device for evaluating Variable Orifice Flow Meters (VOFM) used in medical mechanical ventilation applications. Specifically, the equipment was used to assess the impact of length and thickness on pressure drop for different flows in a rectangular geometry VOFM. [...] Read more.
This work presents a low-cost device for evaluating Variable Orifice Flow Meters (VOFM) used in medical mechanical ventilation applications. Specifically, the equipment was used to assess the impact of length and thickness on pressure drop for different flows in a rectangular geometry VOFM. A total of six VOFMs, with three different lengths and two different thicknesses, were evaluated. All VOFMs were stimulated with an airflow ranging from 0 L.min−1 to 90 L.min−1, with increments of approximately 2 L.min−1. The experiments conducted with the device showed a strong relationship between pressure drop ∆P and flow rate Q in the evaluated VOFMs, with two different zones: one exhibiting non-linear behavior and another showing linear behavior. The results suggest that increased length and decreased thickness lead to higher sensitivity. However, it is essential to reduce the cross-sectional area to mitigate nonlinear effects of the sensor. Full article
(This article belongs to the Special Issue Recent Advances in Fluid Mechanics and Transport Phenomena)
►▼ Show Figures

Figure 1

14 pages, 42777 KiB  
Article
The Effects of Anodization Conditions on TiO2 Nanotubes Features Obtained Using Aqueous Electrolytes with Xanthan Gum
by Robinson Aguirre Ocampo and Félix Echeverría Echeverría
Inventions 2023, 8(5), 109; https://doi.org/10.3390/inventions8050109 - 29 Aug 2023
Viewed by 930
Abstract
Titanium surfaces were anodized to create nanotube structures utilizing an aqueous electrolyte made of xanthan gum (XG) and sodium fluoride. The purpose of employing this type of anodizing solution was to investigate the impact of XG addition on the morphology and organization of [...] Read more.
Titanium surfaces were anodized to create nanotube structures utilizing an aqueous electrolyte made of xanthan gum (XG) and sodium fluoride. The purpose of employing this type of anodizing solution was to investigate the impact of XG addition on the morphology and organization of nanotubes. As far as we know, this is the first time that TiO2 nanotubes, made using aqueous electrolytes with XG as an additive, have been reported. The organization of the nanotubes was measured using the regularity ratio (RR) from the fast Fourier transformation (FFT) pictures. Contrary to the nanotubes formed in aqueous solutions without XG, the addition of XG to the aqueous electrolyte improved the nanotube organization, with no effect on packability. Based on the findings of this experimental work, organized and homogeneous nanotubular structures might be produced utilizing an inexpensive and non-toxic aqueous electrolyte. Full article
(This article belongs to the Special Issue The Development and Optimization of Innovative Systems, Processes, and Materials for the Production, Conversion, and Storage of Energy (Volume 2))
►▼ Show Figures

Figure 1

21 pages, 1635 KiB  
Article
Estimation of the Achievable Performance of Mobile Ad Hoc Networks with Optimal Link State Routing
by Gennady Kazakov
Inventions 2023, 8(5), 108; https://doi.org/10.3390/inventions8050108 - 29 Aug 2023
Cited by 3 | Viewed by 1010
Abstract
The paper explores the challenges of constructing self-organizing wireless mobile ad hoc networks (MANETs) utilizing Optimal Link State Routing (OLSR) with MPR (MultiPoint Relay) optimization and quality control through the RSVP (Resource Reservation Protocol). Analytical expressions are presented for calculating the achievable network [...] Read more.
The paper explores the challenges of constructing self-organizing wireless mobile ad hoc networks (MANETs) utilizing Optimal Link State Routing (OLSR) with MPR (MultiPoint Relay) optimization and quality control through the RSVP (Resource Reservation Protocol). Analytical expressions are presented for calculating the achievable network characteristics, including route acquisition time, network efficiency (routing overhead), packet transmission delay (end-to-end delay), and signal propagation losses between nodes assuming no packet collisions within the network nodes. The possibility of network scalability is analyzed depending on the scenarios of operation and the number of network nodes. Recommendations for the construction and scalability of self-organizing wireless networks are formulated based on the conducted evaluations and calculations. Full article
(This article belongs to the Special Issue Recent Advances and New Trends in Signal Processing)
►▼ Show Figures

Figure 1

24 pages, 4856 KiB  
Article
Modeling and Simulation of Photovoltaic Modules Using Bio-Inspired Algorithms
by Lucas Lima Provensi, Renata Mariane de Souza, Gabriel Henrique Grala, Rosângela Bergamasco, Rafael Krummenauer and Cid Marcos Gonçalves Andrade
Inventions 2023, 8(5), 107; https://doi.org/10.3390/inventions8050107 - 25 Aug 2023
Cited by 2 | Viewed by 1022
Abstract
This research aims to employ and qualify the bio-inspired algorithms: Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Differential Evolution Algorithm (DE) in the extraction of the parameters of the circuit equivalent to a photovoltaic module in the models of a diode and [...] Read more.
This research aims to employ and qualify the bio-inspired algorithms: Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Differential Evolution Algorithm (DE) in the extraction of the parameters of the circuit equivalent to a photovoltaic module in the models of a diode and five parameters (1D5P) and two diodes and seven parameters (2D7P) in order to simulate the I-V characteristics curves for any irradiation and temperature scenarios. The peculiarity of this study stands in the exclusive use of information present in the module’s datasheet to carry out the full extraction and simulation process without depending on external sources of data or experimental data. To validate the methods, a comparison was made between the data obtained by the simulations with data from the module manufacturer in different scenarios of irradiation and temperature. The algorithm bound to the model with the highest accuracy was DE 1D5P, with a maximum relative error of 0.4% in conditions close to the reference and 3.61% for scenarios far from the reference. On the other hand, the algorithm that obtained the worst result in extracting parameters was the GA in the 2D7P model, which presented a maximum relative error of 9.59% in conditions far from the reference. Full article
(This article belongs to the Section Inventions and Innovation in Energy and Thermal/Fluidic Science)
►▼ Show Figures

Figure 1

20 pages, 5216 KiB  
Article
Short-Term Solar Insolation Forecasting in Isolated Hybrid Power Systems Using Neural Networks
by Pavel Matrenin, Vadim Manusov, Muso Nazarov, Murodbek Safaraliev, Sergey Kokin, Inga Zicmane and Svetlana Beryozkina
Inventions 2023, 8(5), 106; https://doi.org/10.3390/inventions8050106 - 23 Aug 2023
Cited by 2 | Viewed by 1197
Abstract
Solar energy is an unlimited and sustainable energy source that holds great importance during the global shift towards environmentally friendly energy production. However, integrating solar power into electrical grids is challenging due to significant fluctuations in its generation. This research aims to develop [...] Read more.
Solar energy is an unlimited and sustainable energy source that holds great importance during the global shift towards environmentally friendly energy production. However, integrating solar power into electrical grids is challenging due to significant fluctuations in its generation. This research aims to develop a model for predicting solar radiation levels using a hybrid power system in the Gorno-Badakhshan Autonomous Oblast of Tajikistan. This study determined the optimal hyperparameters of a multilayer perceptron neural network to enhance the accuracy of solar radiation forecasting. These hyperparameters included the number of neurons, learning algorithm, learning rate, and activation functions. Since there are numerous combinations of hyperparameters, the neural network training process needed to be repeated multiple times. Therefore, a control algorithm of the learning process was proposed to identify stagnation or the emergence of erroneous correlations during model training. The results reveal that different seasons require different hyperparameter values, emphasizing the need for the meticulous tuning of machine learning models and the creation of multiple models for varying conditions. The absolute percentage error of the achieved mean for one-hour-ahead forecasting ranges from 0.6% to 1.7%, indicating a high accuracy compared to the current state-of-the-art practices in this field. The error for one-day-ahead forecasting is between 2.6% and 7.2%. Full article
(This article belongs to the Special Issue The Development and Optimization of Innovative Systems, Processes, and Materials for the Production, Conversion, and Storage of Energy (Volume 2))
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-26
Previous Issue
Next Issue
Back to TopTop