Bearing operation states will directly determine the performance of the equipment; thus, monitoring operation status and degradation indicators is the key to ensuring continuous and healthy operation of the equipment. However, most of the research uses single-source information data, which makes it difficult to model when dealing with multi-source information, complex data distribution, and noise. In this paper, a bearing performance degradation assessment method based on multi-source information is proposed to comprehensively utilize the data signals of different structures, spaces, types, and sources. First, the adversarial fusion convolutional autoencoder is constructed for obtaining the degradation index of the bearing, while the adversarial learning strategy is applied to achieve the effect of enhancing the robustness and sensitivity of the degradation indicators extracted by the network. Then the degradation index is input into the support vector data description to determine the fault anomalies of the degradation index adaptively and the fuzzy c-means algorithms to obtain the final rolling bearing performance degradation evaluation results. Through the verification results of two experiment datasets, it is found that the proposed model can achieve accurate evaluation and quantitative analysis of the performance degradation process of bearings. As a result, the entire network ensures the reconstruction accuracy of normal samples while simultaneously stretching the reconstruction error of abnormal samples to achieve accurate monitoring of degradation onset.
{"title":"Bearing performance degradation assessment using adversarial fusion convolutional autoencoder based on multi-source information","authors":"Enxiu Wang, Haoxuan Zhou, Guangrui Wen, Ziling Huang, Zimin Liu, Xuefeng Chen","doi":"10.1177/01423312231190237","DOIUrl":"https://doi.org/10.1177/01423312231190237","url":null,"abstract":"Bearing operation states will directly determine the performance of the equipment; thus, monitoring operation status and degradation indicators is the key to ensuring continuous and healthy operation of the equipment. However, most of the research uses single-source information data, which makes it difficult to model when dealing with multi-source information, complex data distribution, and noise. In this paper, a bearing performance degradation assessment method based on multi-source information is proposed to comprehensively utilize the data signals of different structures, spaces, types, and sources. First, the adversarial fusion convolutional autoencoder is constructed for obtaining the degradation index of the bearing, while the adversarial learning strategy is applied to achieve the effect of enhancing the robustness and sensitivity of the degradation indicators extracted by the network. Then the degradation index is input into the support vector data description to determine the fault anomalies of the degradation index adaptively and the fuzzy c-means algorithms to obtain the final rolling bearing performance degradation evaluation results. Through the verification results of two experiment datasets, it is found that the proposed model can achieve accurate evaluation and quantitative analysis of the performance degradation process of bearings. As a result, the entire network ensures the reconstruction accuracy of normal samples while simultaneously stretching the reconstruction error of abnormal samples to achieve accurate monitoring of degradation onset.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136013406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-12DOI: 10.1177/01423312231196639
Jianwei Ren, Ping Li, Zhibao Song
In this paper, a novel reinforcement learning (RL)-based event-triggered (ET) output feedback control algorithm is proposed for a class of uncertain strict-feedback nonlinear discrete-time systems. In contrast to traditional RL-based control methods, we proposed an ET output feedback controller based on the backstepping technique, where the transmission cost can be efficiently conserved. Then, in light of the radial basis function (RBF) neural network (NN), various critic NNs are constructed to approximate the critic functions in each step. Furthermore, with the backing of the proposed ET mechanism, a sampled output feedback controller is addressed to guarantee that the tracking errors and all signals of the closed-loop system are semi-global uniformly ultimately bounded (SGUUB). Finally, a simulation example is presented to demonstrate the effectiveness of the control strategy.
{"title":"Reinforcement learning event-triggered output feedback control for uncertain nonlinear discrete systems","authors":"Jianwei Ren, Ping Li, Zhibao Song","doi":"10.1177/01423312231196639","DOIUrl":"https://doi.org/10.1177/01423312231196639","url":null,"abstract":"In this paper, a novel reinforcement learning (RL)-based event-triggered (ET) output feedback control algorithm is proposed for a class of uncertain strict-feedback nonlinear discrete-time systems. In contrast to traditional RL-based control methods, we proposed an ET output feedback controller based on the backstepping technique, where the transmission cost can be efficiently conserved. Then, in light of the radial basis function (RBF) neural network (NN), various critic NNs are constructed to approximate the critic functions in each step. Furthermore, with the backing of the proposed ET mechanism, a sampled output feedback controller is addressed to guarantee that the tracking errors and all signals of the closed-loop system are semi-global uniformly ultimately bounded (SGUUB). Finally, a simulation example is presented to demonstrate the effectiveness of the control strategy.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135970079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-10DOI: 10.1177/01423312231193188
Taiqi Wang, Chang Wang, Shengyu Yan, Yongtao Liu
In this paper, a fixed-time sliding mode control scheme is developed to fulfill the trajectory tracking task of a marine surface vehicle with unknown dynamics. To restrain the adverse effects of the unknown dynamics including the parameter inaccuracy and exogenous disturbances, a fixed-time disturbance observer is designed to estimate the lumped uncertainties using the bi-limit homogeneous theory without requiring any knowledge of the model uncertainties. Then, a nominal tracking controller is proposed to stabilize the error dynamic model in the sense of fixed-time Lyapunov stability, based on which a novel integral-type sliding mode manifold with bi-limit homogeneity is constructed to drive tracking error convergence in fixed time. To enhance the robustness of the vessel control system, a disturbance observer–based fixed-time integral sliding mode tracking controller is finally proposed, and the chattering phenomenon is effectively alleviated by direct estimation compensations. The analysis of Lyapunov stability indicates that the closed-loop system is fixed-time stable. Numerical simulations on a model vessel are carried out to validate theoretical results of the proposed control scheme.
{"title":"Disturbance observer–based fixed-time sliding mode trajectory tracking control for marine surface vehicles with uncertain dynamics","authors":"Taiqi Wang, Chang Wang, Shengyu Yan, Yongtao Liu","doi":"10.1177/01423312231193188","DOIUrl":"https://doi.org/10.1177/01423312231193188","url":null,"abstract":"In this paper, a fixed-time sliding mode control scheme is developed to fulfill the trajectory tracking task of a marine surface vehicle with unknown dynamics. To restrain the adverse effects of the unknown dynamics including the parameter inaccuracy and exogenous disturbances, a fixed-time disturbance observer is designed to estimate the lumped uncertainties using the bi-limit homogeneous theory without requiring any knowledge of the model uncertainties. Then, a nominal tracking controller is proposed to stabilize the error dynamic model in the sense of fixed-time Lyapunov stability, based on which a novel integral-type sliding mode manifold with bi-limit homogeneity is constructed to drive tracking error convergence in fixed time. To enhance the robustness of the vessel control system, a disturbance observer–based fixed-time integral sliding mode tracking controller is finally proposed, and the chattering phenomenon is effectively alleviated by direct estimation compensations. The analysis of Lyapunov stability indicates that the closed-loop system is fixed-time stable. Numerical simulations on a model vessel are carried out to validate theoretical results of the proposed control scheme.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"70 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136352747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-04DOI: 10.1177/01423312231188168
Zhang Chunfu, Renming Yang
Using the Hamiltonian function method with different powers, this paper studies the observer-based finite-time robust control problem of general nonlinear uncertain systems with time delay and presents some new results on this issue. First, by applying Hamiltonian realization method, the paper develops an equivalent Hamiltonian form of original system and designs its observer system. Then, based on the observer system, we study finite-time control problem and present several finite-time stabilization and finite-time robust stabilization results by using the augmented technology and the Lyapunov method. Finally, a real unmanned vehicle is used to verify the performance of the observer-based finite-time robust stabilization controller. Different from the existing literature on Hamiltonian method, the Hamiltonian function in the paper has different powers, which implies that the results developed in the paper have a wider range of application.
{"title":"Observer-based finite-time robust control of nonlinear time-delay uncertain systems with different power Hamiltonian function","authors":"Zhang Chunfu, Renming Yang","doi":"10.1177/01423312231188168","DOIUrl":"https://doi.org/10.1177/01423312231188168","url":null,"abstract":"Using the Hamiltonian function method with different powers, this paper studies the observer-based finite-time robust control problem of general nonlinear uncertain systems with time delay and presents some new results on this issue. First, by applying Hamiltonian realization method, the paper develops an equivalent Hamiltonian form of original system and designs its observer system. Then, based on the observer system, we study finite-time control problem and present several finite-time stabilization and finite-time robust stabilization results by using the augmented technology and the Lyapunov method. Finally, a real unmanned vehicle is used to verify the performance of the observer-based finite-time robust stabilization controller. Different from the existing literature on Hamiltonian method, the Hamiltonian function in the paper has different powers, which implies that the results developed in the paper have a wider range of application.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"195 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135590517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-30DOI: 10.1177/01423312231201675
Rijhi Dey, Rudra Sankar Dhar, Ujjwal Mondal
Efficient control of cardiac pacing is a very important aspect as it provides lifesaving regulated cardiac rhythm in this dynamic hostile environment. The foremost control objective is set to design a highly reliable and advanced control strategy to ensure the utmost accuracy in the control effort. A modified artificial neural network (ANN)–based modelling and pace tracking using finite dimension repetitive controller (FDRC) design based on internal model principle (IMP) has been presented here. This controller will not only provide accurate tracking but also minimize the control action time due to less amount of data handling through the deployment of discrete wavelet transform (DWT) in the loop of repetitive controller (RC). Finally, a case study has been propounded considering ANN model using available data sets and software to validate the control strategy and justify the control objective for optimizing the pace tracking in a pacemaker. Result of the experiment showed good accuracy as well as very low error in terms of mean-squared error (MSE), integral absolute error (IAE), integral time absolute error (ITAE) and integral time square error (ITSE). Along with that, it is observed that DWT not only benefits the handling of very less memory but also acts as an additional filter while reconstructing the signal, which serves as an added advantage of this model.
{"title":"Artificial neural network–based modelling of pacemaker and its pace tracking using discrete wavelet transform–based finite dimension repetitive controller","authors":"Rijhi Dey, Rudra Sankar Dhar, Ujjwal Mondal","doi":"10.1177/01423312231201675","DOIUrl":"https://doi.org/10.1177/01423312231201675","url":null,"abstract":"Efficient control of cardiac pacing is a very important aspect as it provides lifesaving regulated cardiac rhythm in this dynamic hostile environment. The foremost control objective is set to design a highly reliable and advanced control strategy to ensure the utmost accuracy in the control effort. A modified artificial neural network (ANN)–based modelling and pace tracking using finite dimension repetitive controller (FDRC) design based on internal model principle (IMP) has been presented here. This controller will not only provide accurate tracking but also minimize the control action time due to less amount of data handling through the deployment of discrete wavelet transform (DWT) in the loop of repetitive controller (RC). Finally, a case study has been propounded considering ANN model using available data sets and software to validate the control strategy and justify the control objective for optimizing the pace tracking in a pacemaker. Result of the experiment showed good accuracy as well as very low error in terms of mean-squared error (MSE), integral absolute error (IAE), integral time absolute error (ITAE) and integral time square error (ITSE). Along with that, it is observed that DWT not only benefits the handling of very less memory but also acts as an additional filter while reconstructing the signal, which serves as an added advantage of this model.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136280507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To solve the problems of serious buffeting in traditional sliding mode control and difficulty in obtaining the derivative information of the system sliding mode surface, a distributed drive electric vehicles active front steering (AFS) control method based on adaptive super-twisting sliding mode control (ASTSMC) is proposed. Taking the yaw rate deviation as the state quantity, the stable and convergent sliding mode surface is designed to obtain the equivalent control input of the front wheel angle. The sliding mode function information is substituted into the parameters of the super-twisting algorithm; the discontinuous term is kept in the integrand function to keep the control signal continuous and weaken the system chattering; the adaptive control law is added to design the AFS controller. The co-simulation results of Matlab/Simulink and Carsim show that ASTSMC can reduce the yaw rate by 40.59% compared with no control under step steering condition. Compared with the sliding mode controller, ASTSMC has optimized the sideslip angle by 5.41% under the double line shifting condition.
{"title":"AFS control system research of distributed drive electric vehicles by adaptive super-twisting sliding mode control","authors":"Qiping Chen, Zuqi Xiong, Yiming Hu, Liang Huang, Qin Liu, Daoliang You","doi":"10.1177/01423312231196400","DOIUrl":"https://doi.org/10.1177/01423312231196400","url":null,"abstract":"To solve the problems of serious buffeting in traditional sliding mode control and difficulty in obtaining the derivative information of the system sliding mode surface, a distributed drive electric vehicles active front steering (AFS) control method based on adaptive super-twisting sliding mode control (ASTSMC) is proposed. Taking the yaw rate deviation as the state quantity, the stable and convergent sliding mode surface is designed to obtain the equivalent control input of the front wheel angle. The sliding mode function information is substituted into the parameters of the super-twisting algorithm; the discontinuous term is kept in the integrand function to keep the control signal continuous and weaken the system chattering; the adaptive control law is added to design the AFS controller. The co-simulation results of Matlab/Simulink and Carsim show that ASTSMC can reduce the yaw rate by 40.59% compared with no control under step steering condition. Compared with the sliding mode controller, ASTSMC has optimized the sideslip angle by 5.41% under the double line shifting condition.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136308713","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-20DOI: 10.1177/01423312231188628
Shichong Wu, Lingli Xie, Jun Xian
The emerging trans-media vehicle is significant due to its amphibious ability. A finite-time output feedback trans-media tracking control scheme is proposed for a slender body trans-media vehicle with unknown time-varying hydrodynamics and external disturbances. First, a novel neural network extended state observer is developed to observe the vehicle’s velocities and handle the time-varying hydrodynamics and total disturbances simultaneously. Then, combined with the proposed observer, the finite-time command filtered backstepping technique is carefully constructed to yield the finite-time output feedback tracking control. The strength of the proposed approach to the existing methods is that it ensures the trans-media tracking errors converge to the small region of origin within a finite time, even in the absence of velocity measurements. The simulations are given to illustrate the superiority of the proposed scheme.
{"title":"Finite-time output feedback trans-media tracking control of a slender body trans-media vehicle via neural network extended state observer","authors":"Shichong Wu, Lingli Xie, Jun Xian","doi":"10.1177/01423312231188628","DOIUrl":"https://doi.org/10.1177/01423312231188628","url":null,"abstract":"The emerging trans-media vehicle is significant due to its amphibious ability. A finite-time output feedback trans-media tracking control scheme is proposed for a slender body trans-media vehicle with unknown time-varying hydrodynamics and external disturbances. First, a novel neural network extended state observer is developed to observe the vehicle’s velocities and handle the time-varying hydrodynamics and total disturbances simultaneously. Then, combined with the proposed observer, the finite-time command filtered backstepping technique is carefully constructed to yield the finite-time output feedback tracking control. The strength of the proposed approach to the existing methods is that it ensures the trans-media tracking errors converge to the small region of origin within a finite time, even in the absence of velocity measurements. The simulations are given to illustrate the superiority of the proposed scheme.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136308055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-20DOI: 10.1177/01423312231194125
Meizhi Liu, Xiangyu Kong, Jiayu Luo, Zhiyan Yang, Lei Yang
Kernel independent component analysis (KICA), as a nonlinear extension monitoring method of independent component analysis (ICA), has attracted significant attention. To accomplish different monitoring tasks for nonlinear systems with non-Gaussian data distribution, many modified algorithms based on KICA have also been designed. However, most of the existing methods suffer from defects; for example, the computation time increases with the number of training samples and the models are insensitive to minor faults. Nevertheless, there is currently limited research on addressing these defects, which greatly limits their application in industrial processes. To fill these gaps, a novel reduced kernel independent component analysis (NRKICA) method is proposed to reduce the computation complexity and improve the ability of minor fault detection at the same time. In this approach, an important factor is defined to measure the ability of the samples to represent the properties of the system. In addition, then the top-n important observations are selected to build a data dictionary. To improve the sensitivity to minor faults, the [Formula: see text] and [Formula: see text] statistics are redesigned by introducing information from past observations. Besides, the kernel parameter is optimized by the tabu search algorithm. The proposed method is applied to fault detection with a numerical example and the Tennessee Eastman process (TEP), and the experimental results verify the effectiveness and sensitivity of the proposed method.
{"title":"Novel reduced kernel independent component analysis for process monitoring","authors":"Meizhi Liu, Xiangyu Kong, Jiayu Luo, Zhiyan Yang, Lei Yang","doi":"10.1177/01423312231194125","DOIUrl":"https://doi.org/10.1177/01423312231194125","url":null,"abstract":"Kernel independent component analysis (KICA), as a nonlinear extension monitoring method of independent component analysis (ICA), has attracted significant attention. To accomplish different monitoring tasks for nonlinear systems with non-Gaussian data distribution, many modified algorithms based on KICA have also been designed. However, most of the existing methods suffer from defects; for example, the computation time increases with the number of training samples and the models are insensitive to minor faults. Nevertheless, there is currently limited research on addressing these defects, which greatly limits their application in industrial processes. To fill these gaps, a novel reduced kernel independent component analysis (NRKICA) method is proposed to reduce the computation complexity and improve the ability of minor fault detection at the same time. In this approach, an important factor is defined to measure the ability of the samples to represent the properties of the system. In addition, then the top-n important observations are selected to build a data dictionary. To improve the sensitivity to minor faults, the [Formula: see text] and [Formula: see text] statistics are redesigned by introducing information from past observations. Besides, the kernel parameter is optimized by the tabu search algorithm. The proposed method is applied to fault detection with a numerical example and the Tennessee Eastman process (TEP), and the experimental results verify the effectiveness and sensitivity of the proposed method.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136308231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-19DOI: 10.1177/01423312231191569
Ying Han, Xinping Song, Jinmei Shi, Kun Li
Motor rolling bearings are the important supporting components of motors. It can ensure the stable operation of motor equipment in the power grid, and bearing life prediction of it is a key issue. To solve the problem of low accuracy of remaining useful life (RUL) prediction for motor rolling bearings, a neural network model based on Weibull proportional hazards model (WPHM) and stochastic configuration networks (SCNs) is proposed. To better extract and analyze features of the bearing vibration signal in both time and frequency domains, kernel principal component analysis (KPCA) is used to reduce the dimensionality of the data. Then, a WPHM model using the top three contributing feature parameters is built, which sets the start time based on the failure rate curve and reliability function. Finally, the validity of the model is verified with the rolling bearing full life cycle dataset from the IEEE PHM 2012 Data Challenge, and a comparison with other machine learning models shows that the accuracy of the proposed model in RUL prediction is higher.
{"title":"KPCA-WPHM-SCNs-based remaining useful life prediction method for motor rolling bearings","authors":"Ying Han, Xinping Song, Jinmei Shi, Kun Li","doi":"10.1177/01423312231191569","DOIUrl":"https://doi.org/10.1177/01423312231191569","url":null,"abstract":"Motor rolling bearings are the important supporting components of motors. It can ensure the stable operation of motor equipment in the power grid, and bearing life prediction of it is a key issue. To solve the problem of low accuracy of remaining useful life (RUL) prediction for motor rolling bearings, a neural network model based on Weibull proportional hazards model (WPHM) and stochastic configuration networks (SCNs) is proposed. To better extract and analyze features of the bearing vibration signal in both time and frequency domains, kernel principal component analysis (KPCA) is used to reduce the dimensionality of the data. Then, a WPHM model using the top three contributing feature parameters is built, which sets the start time based on the failure rate curve and reliability function. Finally, the validity of the model is verified with the rolling bearing full life cycle dataset from the IEEE PHM 2012 Data Challenge, and a comparison with other machine learning models shows that the accuracy of the proposed model in RUL prediction is higher.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135014570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-19DOI: 10.1177/01423312231196945
Meizhen Lei, Xianqing Wu, Yijiang Zhao, Fang Li
In this paper, a disturbance-observer–based control approach is developed for overhead crane systems. Different from existing control strategies, the issues consisting of the output feedback, input saturation, double-pendulum dynamics, and uncertain disturbances are taken into consideration here. In particular, a disturbance observer is designed first, which can exactly estimate uncertain disturbances. Next, to enhance the performance of the controller, a virtual position signal is constructed and a corresponding Lyapunov function is introduced. Then, based on the provided Lyapunov function and the designed disturbance observer, a composite control approach is developed for overhead crane systems with double-pendulum dynamics and the convergence of the system states is proved via rigorous theoretical analysis. Finally, the effectiveness and robustness of the proposed control approach are verified by simulation tests.
{"title":"Output feedback control for overhead cranes subject to double-pendulum swing effects and uncertain disturbances","authors":"Meizhen Lei, Xianqing Wu, Yijiang Zhao, Fang Li","doi":"10.1177/01423312231196945","DOIUrl":"https://doi.org/10.1177/01423312231196945","url":null,"abstract":"In this paper, a disturbance-observer–based control approach is developed for overhead crane systems. Different from existing control strategies, the issues consisting of the output feedback, input saturation, double-pendulum dynamics, and uncertain disturbances are taken into consideration here. In particular, a disturbance observer is designed first, which can exactly estimate uncertain disturbances. Next, to enhance the performance of the controller, a virtual position signal is constructed and a corresponding Lyapunov function is introduced. Then, based on the provided Lyapunov function and the designed disturbance observer, a composite control approach is developed for overhead crane systems with double-pendulum dynamics and the convergence of the system states is proved via rigorous theoretical analysis. Finally, the effectiveness and robustness of the proposed control approach are verified by simulation tests.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135014899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：