Applied Sciences

Research

21 pages, 8764 KiB

Open AccessCommunication

Novel Fault Diagnosis of Bearings and Gearboxes Based on Simultaneous Processing of Spectral Kurtoses

by Len Gelman and Gabrijel Persin

Appl. Sci. 2022, 12(19), 9970; https://doi.org/10.3390/app12199970 - 04 Oct 2022

Cited by 5 | Viewed by 1142

Diagnosis of bearings and gears, traditionally uses the envelope (i.e., demodulation) approach. The spectral kurtosis (SK) is a technique used to identify frequency bands for demodulation. These frequency bands are related to the structural resonances, excited by a series of fault-induced impulses. The [...] Read more.

Diagnosis of bearings and gears, traditionally uses the envelope (i.e., demodulation) approach. The spectral kurtosis (SK) is a technique used to identify frequency bands for demodulation. These frequency bands are related to the structural resonances, excited by a series of fault-induced impulses. The novel approach for bearing/gear local fault diagnosis is proposed, based on division of bearing/gear vibration signals into specially defined short duration segments and simultaneous processing of SKs of all these segments for damage diagnosis. The SK-filtered vibrations are used for diagnostic feature extraction further subjected to the decision-making process, based on k-means and k-nearest neighbors. The important feature of the proposed approach is robustness to random slippage in bearings. The experimental validation of a bearing inner race local defects (1.2% relative damage size), and simulated gear vibration (15% relative pitting size), shows a very good diagnostic performance on bearing vibrations and gear vibrations to diagnose local faults. Novel diagnostic effectiveness comparison between the proposed technology and wavelet-based technology is performed for diagnosis of local bearing damage. Full article

(This article belongs to the Special Issue Health Monitoring of Mechanical Systems)

► Show Figures

Figure 1

20 pages, 6444 KiB

Open AccessArticle

Data Completion, Model Correction and Enrichment Based on Sparse Identification and Data Assimilation

by Daniele Di Lorenzo, Victor Champaney, Claudia Germoso, Elias Cueto and Francisco Chinesta

Appl. Sci. 2022, 12(15), 7458; https://doi.org/10.3390/app12157458 - 25 Jul 2022

Cited by 4 | Viewed by 1191

Abstract

Many models assumed to be able to predict the response of structural systems fail to efficiently accomplish that purpose because of two main reasons. First, some structures in operation undergo localized damage that degrades their mechanical performances. To reflect this local loss of [...] Read more.

Many models assumed to be able to predict the response of structural systems fail to efficiently accomplish that purpose because of two main reasons. First, some structures in operation undergo localized damage that degrades their mechanical performances. To reflect this local loss of performance, the stiffness matrix associated with the structure should be locally corrected. Second, the nominal model is sometimes too coarse grained for reflecting all structural details, and consequently, the predictions are expected to deviate from the measurements. In that case, there is no small region of the model that needs to be repaired, but the entire domain needs to be repaired; therefore, the entire structure-stiffness matrix should be corrected. In the present work, we propose a methodology for locally correcting or globally enriching the models from collected data, which is, upon its turn, completed beyond the sensor’s location. The proposed techniques consist in the first case of an L1-minimization procedure that, with the support of data, aims at the same time period to detect the damaged zone in the structure and to predict the correct solution. For the global enrichment, instead, the methodology consists of an L2-minimization procedure with the support of measurements. The results obtained showed, for the local problem, a correction up to 90% with respect to the initially incorrectly predicted displacement of the structure, and for the global one, a correction up to 60% was observed (this results concern the problems considered in the present study, but they depend on different factors, such as the number of data used, the geometry or the intensity of the damage). The benefits and potential of such techniques are illustrated on four different problems, showing the large generality and adaptability of the methodology. Full article

(This article belongs to the Special Issue Health Monitoring of Mechanical Systems)

► Show Figures

Figure 1

18 pages, 3858 KiB

Open AccessArticle

Smart Manufacturing in Rolling Process Based on Thermal Safety Monitoring by Fiber Optics Sensors Equipping Mill Bearings

by Eugenio Brusa, Cristiana Delprete and Lorenzo Giorio

Appl. Sci. 2022, 12(9), 4186; https://doi.org/10.3390/app12094186 - 21 Apr 2022

Cited by 4 | Viewed by 2222

Abstract

The steel rolling process is critical for safety and maintenance because of loading and thermal operating conditions. Machinery condition monitoring (MCM) increases the system’s safety, preventing the risk of fire, failure, and rupture. Equipping the mill bearings with sensors allows monitoring of the [...] Read more.

The steel rolling process is critical for safety and maintenance because of loading and thermal operating conditions. Machinery condition monitoring (MCM) increases the system’s safety, preventing the risk of fire, failure, and rupture. Equipping the mill bearings with sensors allows monitoring of the system in service and controls the heating of mill components. Fiber optic sensors detect loading condition, vibration, and irregular heating. In several systems, access to machinery is rather limited. Therefore, this paper preliminarily investigates how fiber optics can be effectively embedded within the mill cage to set up a smart manufacturing system. The fiber Bragg gratings (FBG) technology allows embedding sensors inside the pins of backup bearings and performing some prognosis and diagnosis activities. The study starts from the rolling mill layout and defines its accessibility, considering some real industrial cases. Testing of an FBG sensor prototype checks thermal monitoring capability inside a closed cavity, obtained on the surface of either the fixed pin of the backup bearing or the stator surrounding the outer ring. Results encourage the development of the whole prototype of the MCM system to be tested on a real mill cage in full operation. Full article

(This article belongs to the Special Issue Health Monitoring of Mechanical Systems)

► Show Figures

Figure 1

20 pages, 9085 KiB

Open AccessArticle

On Training Data Selection in Condition Monitoring Applications—Case Azimuth Thrusters

by Riku-Pekka Nikula, Mika Ruusunen and Stephan André Böhme

Appl. Sci. 2022, 12(8), 4024; https://doi.org/10.3390/app12084024 - 15 Apr 2022

Viewed by 2002

Abstract

Machine learning techniques are commonly used in the vibration-based condition monitoring of rotating machines. However, few research studies have focused on model training from a practical viewpoint, namely, how to select representative training samples and operating areas for monitoring applications. We focus on [...] Read more.

Machine learning techniques are commonly used in the vibration-based condition monitoring of rotating machines. However, few research studies have focused on model training from a practical viewpoint, namely, how to select representative training samples and operating areas for monitoring applications. We focus on these aspects by studying training sets with varying sizes and distributions, including their effects on the models to be identified. The analysis is based on acceleration and shaft speed data available from an azimuth thruster of a catamaran crane vessel. The considered machine learning algorithm was previously introduced in another study suggesting it could detect defects on the thruster driveline components. In this work, practical guidance is provided to facilitate its implementation, and furthermore, an adaptive method for training subset selection is proposed. Results show that the proposed method enabled the identification of usable training subsets in general, while the success of the previous approach was case-dependent. In addition, the use of Kolmogorov–Smirnov or Anderson–Darling tests for normal distribution, as a part of the method, enabled selections that covered the operating area broadly, while other tests were unfavorable in this regard. Overall, the study demonstrates that reconfigurable and automated model implementations could be achievable with minor effort. Full article

(This article belongs to the Special Issue Health Monitoring of Mechanical Systems)

► Show Figures

Figure 1

22 pages, 4738 KiB

Open AccessArticle

Efficacy Study of Fault Trending Algorithm to Prevent Fault Occurrence on Automatic Trampoline Webbing Machine

by Shi Feng and John P. T. Mo

Appl. Sci. 2022, 12(3), 1708; https://doi.org/10.3390/app12031708 - 07 Feb 2022

Cited by 1 | Viewed by 1264

Abstract

Nowadays, fault diagnostics is widely applied under Industry 4.0 to reduce machine maintenance costs, improve productivity, and increase machine availability. However, fault diagnostics are mostly post-mortem. When the fault is identified, it is already too late because damages have been done to the [...] Read more.

Nowadays, fault diagnostics is widely applied under Industry 4.0 to reduce machine maintenance costs, improve productivity, and increase machine availability. However, fault diagnostics are mostly post-mortem. When the fault is identified, it is already too late because damages have been done to the product and machine. This paper compares the efficacy of several signal data processing techniques for detecting faults that are about to occur. Our aim is to find an efficient way to predict the fault before it occurs. A continuous wavelet transform synchrosqueezed scalogram was found to be most suitable for this purpose, but it is difficult to apply. A novel procedure is proposed to count the number of pulses in the synchrosqueezed scalogram. A new method for detecting the trend from the pulse counts is then developed to predict the fault before it happens. The procedure and method are illustrated with experimental data collected while running an automated double-thread trampoline webbing machine. Full article

(This article belongs to the Special Issue Health Monitoring of Mechanical Systems)

► Show Figures

Figure 1

20 pages, 7239 KiB

Open AccessArticle

Multi-Criteria Spare Parts Classification Using the Deep Convolutional Neural Network Method

by Ke Yang, Yongjian Wang, Shidong Fan and Ali Mosleh

Appl. Sci. 2021, 11(15), 7088; https://doi.org/10.3390/app11157088 - 31 Jul 2021

Cited by 7 | Viewed by 2797

Abstract

Spare parts management is a critical issue in the industrial field, alongside planning maintenance and logistics activities. For accurate classification in particular, the decision-makers can determine the optimal inventory management strategy. However, problems such as criteria selection, rules explanatory, and learning ability arise [...] Read more.

Spare parts management is a critical issue in the industrial field, alongside planning maintenance and logistics activities. For accurate classification in particular, the decision-makers can determine the optimal inventory management strategy. However, problems such as criteria selection, rules explanatory, and learning ability arise when managing thousands of spare parts for modern industry. This paper presents a deep convolutional neural network based on graph (G-DCNN) which will realize multi-criteria classification through image identification based on an explainable hierarchical structure. In the first phase, a hierarchical classification structure is established according to the causal relationship of multiple criteria; in the second phase, nodes are colored according to their criteria level status so that the traditional numerical information can be visible through graph style; in the third phase, the colored structures are transferred into images and processed by structure-modified convolutional neural network, to complete the classification. Finally, the proposed method is applied in a real-world case study to validate its effectiveness, feasibility, and generality. This classification study supplies a good decision support to improve the monitor-focus on critical component and control inventory which will benefit the collaborative maintenance. Full article

(This article belongs to the Special Issue Health Monitoring of Mechanical Systems)

► Show Figures

Figure 1

13 pages, 29558 KiB

Open AccessFeature PaperArticle

Order-Based Identification of Bearing Defects under Variable Speed Condition

by Mohamed Habib Farhat, Xavier Chiementin, Fakher Chaari, Fabrice Bolaers and Mohamed Haddar

Appl. Sci. 2021, 11(9), 3962; https://doi.org/10.3390/app11093962 - 27 Apr 2021

Cited by 3 | Viewed by 1685

Abstract

Condition monitoring of rotating machinery plays an important role in reducing catastrophic failures and production losses in the 4.0 Industry. Vibration analysis has proven to be effective in diagnosing rotating machine failures. However, identifying bearing defects based on vibration analysis remains a difficult [...] Read more.

Condition monitoring of rotating machinery plays an important role in reducing catastrophic failures and production losses in the 4.0 Industry. Vibration analysis has proven to be effective in diagnosing rotating machine failures. However, identifying bearing defects based on vibration analysis remains a difficult task, especially in non-stationary operation conditions. This work aims to automate the process of identifying bearing defects under variable operating speeds. Based on an order analysis technique, three frequency domain features: Spectrum peak Ratio Outer (SPRO), Spectrum peak Ratio Inner (SPRI), and Spectrum peak Ratio Rolling element (SPRR) are updated to perform with non-stationary signals. The updated features are extracted from vibration data of a real ball bearing system. They are retained to build a predictive multi-kernel support vector machine (MSVM) classification model. Therefore, the effectiveness of the proposed features is evaluated based on the performance of the constructed classifier. The updated features deployed have proven their effectiveness in identifying bearing: outer race, inner race, ball, and combined defects under variable speed conditions. Full article

(This article belongs to the Special Issue Health Monitoring of Mechanical Systems)

► Show Figures

Figure 1

21 pages, 24345 KiB

Open AccessArticle

Tool Health Monitoring Using Airborne Acoustic Emission and Convolutional Neural Networks: A Deep Learning Approach

by Muhammad Arslan, Khurram Kamal, Muhammad Fahad Sheikh, Mahmood Anwar Khan, Tahir Abdul Hussain Ratlamwala, Ghulam Hussain and Mohammed Alkahtani

Appl. Sci. 2021, 11(6), 2734; https://doi.org/10.3390/app11062734 - 18 Mar 2021

Cited by 4 | Viewed by 1986

Abstract

Tool health monitoring (THM) is in great focus nowadays from the perspective of predictive maintenance. It prevents the increased downtime due to breakdown maintenance, resulting in reduced production cost. The paper provides a novel approach to monitoring the tool health of a computer [...] Read more.

Tool health monitoring (THM) is in great focus nowadays from the perspective of predictive maintenance. It prevents the increased downtime due to breakdown maintenance, resulting in reduced production cost. The paper provides a novel approach to monitoring the tool health of a computer numeric control (CNC) machine for a turning process using airborne acoustic emission (AE) and convolutional neural networks (CNN). Three different work-pieces of aluminum, mild steel, and Teflon are used in experimentation to classify the health of carbide and high-speed steel (HSS) tools into three categories of new, average (used), and worn-out tool. Acoustic signals from the machining process are used to produce time–frequency spectrograms and then fed to a tri-layered CNN architecture that has been carefully crafted for high accuracies and faster trainings. Different sizes and numbers of convolutional filters, in different combinations, are used for multiple trainings to compare the classification accuracy. A CNN architecture with four filters, each of size 5 × 5, gives best results for all cases with a classification average accuracy of 99.2%. The proposed approach provides promising results for tool health monitoring of a turning process using airborne acoustic emission. Full article

(This article belongs to the Special Issue Health Monitoring of Mechanical Systems)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Health Monitoring of Mechanical Systems

Share This Special Issue

Special Issue Editors

Special Issue Information

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI