Pub Date : 2023-09-19DOI: 10.1177/01423312231196642
Yushi Yang, Meng Li, Yong Chen
This paper investigates the problem of tracking target control of a nonlinear system in the context of cyber-physical systems for connected autonomous vehicles with external unknown disturbances. A new robust tracking strategy via backstepping sliding-mode control is proposed. First, a connected nonlinear vehicle dynamical model with disturbances is constructed. Then, a disturbance observer is presented to approximate the unknown disturbances when the derivative of the disturbance is bounded. This paper has proved that the error of the observation can converge to zero in finite time. Third, a tracking control method is designed which combines the backstepping method with the sliding-mode method. According to the method, the estimated values of interference are used as a priori knowledge. Furthermore, the stability of the designed control strategy is demonstrated through using the Lyapunov theory. Finally, simulation experiments are presented to demonstrate the feasibility of the proposed approaches.
{"title":"Robust tracking strategy for nonlinear connected vehicle cyber-physical systems","authors":"Yushi Yang, Meng Li, Yong Chen","doi":"10.1177/01423312231196642","DOIUrl":"https://doi.org/10.1177/01423312231196642","url":null,"abstract":"This paper investigates the problem of tracking target control of a nonlinear system in the context of cyber-physical systems for connected autonomous vehicles with external unknown disturbances. A new robust tracking strategy via backstepping sliding-mode control is proposed. First, a connected nonlinear vehicle dynamical model with disturbances is constructed. Then, a disturbance observer is presented to approximate the unknown disturbances when the derivative of the disturbance is bounded. This paper has proved that the error of the observation can converge to zero in finite time. Third, a tracking control method is designed which combines the backstepping method with the sliding-mode method. According to the method, the estimated values of interference are used as a priori knowledge. Furthermore, the stability of the designed control strategy is demonstrated through using the Lyapunov theory. Finally, simulation experiments are presented to demonstrate the feasibility of the proposed approaches.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"29 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":"135063054","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: 10.1177/01423312231175996
Suraj Damodaran, TK Sunil Kumar, AP Sudheer
A new method for the rational approximation of stable/unstable single-input, single-output (SISO)/multiple-input, multiple-output (MIMO) fractional-order systems is proposed. The objective of the proposed algorithm is to obtain an integer-order approximant of an SISO/MIMO fractional-order system. The developed method utilizes the concept of matching of an appropriate number of approximate generalized time moments and approximate generalized Markov parameters of squared magnitude function of fractional-order system to those of approximant. The proposed method preserves the stability/instability property and minimum phase/non-minimum phase characteristics of fractional-order system in the approximant. The method also incorporates a provision for matching the steady-state response of the approximant to that of fractional-order system. Numerical examples consider three cases of approximation, while fractional-order system has the characteristics of (a) stable non-minimum phase SISO, (b) stable non-minimum phase MIMO, and (c) unstable SISO which are presented to validate the efficiency of the proposed method.
{"title":"Generalized method for rational approximation of SISO/MIMO fractional-order systems using squared magnitude function","authors":"Suraj Damodaran, TK Sunil Kumar, AP Sudheer","doi":"10.1177/01423312231175996","DOIUrl":"https://doi.org/10.1177/01423312231175996","url":null,"abstract":"A new method for the rational approximation of stable/unstable single-input, single-output (SISO)/multiple-input, multiple-output (MIMO) fractional-order systems is proposed. The objective of the proposed algorithm is to obtain an integer-order approximant of an SISO/MIMO fractional-order system. The developed method utilizes the concept of matching of an appropriate number of approximate generalized time moments and approximate generalized Markov parameters of squared magnitude function of fractional-order system to those of approximant. The proposed method preserves the stability/instability property and minimum phase/non-minimum phase characteristics of fractional-order system in the approximant. The method also incorporates a provision for matching the steady-state response of the approximant to that of fractional-order system. Numerical examples consider three cases of approximation, while fractional-order system has the characteristics of (a) stable non-minimum phase SISO, (b) stable non-minimum phase MIMO, and (c) unstable SISO which are presented to validate the efficiency of the proposed method.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"172 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":"135014199","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: 10.1177/01423312231195932
Dinh Cong Huong
This paper addresses the problem of event-triggered robust state and fault simultaneous estimation for nonlinear time-delay systems subject to actuator and sensor unknown disturbances. Based on a fault decomposition technique and some basic mathematical transformations, we obtain an augmented system where the state vector consists of the variable of the original system and the fault. Then a novel event-triggered state observer for the augmented system is proposed to robustly estimate the variable of the original system and the fault. We next established a sufficient condition for the existence of such an observer. We translated it into a linear matrix inequality (LMI), which can be effectively solved using the MATLAB LMI Control Toolbox. Finally, an illustrative example is applied to test the proposed method.
{"title":"Event-triggered state and fault simultaneous estimation for nonlinear systems with time delays","authors":"Dinh Cong Huong","doi":"10.1177/01423312231195932","DOIUrl":"https://doi.org/10.1177/01423312231195932","url":null,"abstract":"This paper addresses the problem of event-triggered robust state and fault simultaneous estimation for nonlinear time-delay systems subject to actuator and sensor unknown disturbances. Based on a fault decomposition technique and some basic mathematical transformations, we obtain an augmented system where the state vector consists of the variable of the original system and the fault. Then a novel event-triggered state observer for the augmented system is proposed to robustly estimate the variable of the original system and the fault. We next established a sufficient condition for the existence of such an observer. We translated it into a linear matrix inequality (LMI), which can be effectively solved using the MATLAB LMI Control Toolbox. Finally, an illustrative example is applied to test the proposed method.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"30 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":"135014463","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: 10.1177/01423312231188871
Junbo Tong, Shuhan Du, Wenhui Fan, Yueting Chai
Robust model predictive control (RMPC) is an effective technology for controlling uncertain systems while robustly handling constraints, and its closed-loop performance heavily relies on the selection of objective functions. However, the objective functions are typically chosen to be close to the real control objectives, despite an objective function that leads to less conservative constraints often provides better closed-loop performance. In this paper, we propose an automatic tuning framework for RMPC in iterative tasks. In particular, we parameterize RMPC and develop a Bayesian optimization (BO) method to tune it by solving a black-box optimization problem. We then introduce an efficient transfer learning framework within BO, which speeds up the searching process and enhances the controller performance. The effectiveness of the proposed tuning framework is illustrated on numerical examples.
{"title":"Automatic tuning of robust model predictive control in iterative tasks using efficient Bayesian optimization","authors":"Junbo Tong, Shuhan Du, Wenhui Fan, Yueting Chai","doi":"10.1177/01423312231188871","DOIUrl":"https://doi.org/10.1177/01423312231188871","url":null,"abstract":"Robust model predictive control (RMPC) is an effective technology for controlling uncertain systems while robustly handling constraints, and its closed-loop performance heavily relies on the selection of objective functions. However, the objective functions are typically chosen to be close to the real control objectives, despite an objective function that leads to less conservative constraints often provides better closed-loop performance. In this paper, we propose an automatic tuning framework for RMPC in iterative tasks. In particular, we parameterize RMPC and develop a Bayesian optimization (BO) method to tune it by solving a black-box optimization problem. We then introduce an efficient transfer learning framework within BO, which speeds up the searching process and enhances the controller performance. The effectiveness of the proposed tuning framework is illustrated on numerical examples.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"46 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":"135015044","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}
Most nonlinear dynamic systems are characterized by uncertainties in models and parameters. Deterministic models cannot account for these uncertainties; therefore, model-based control using such models cannot provide the required performance. It is crucial to establish a practical concept of model-free control as a powerful alternative to model-based control. This paper develops a model-free adaptive backstepping control (MFABC) based on type 2 fuzzy Petri nets for a class of uncertain nonlinear systems. To provide valuable robustness to the MFABC structure, we have exploited the universal approximation property of type 2 fuzzy Petri nets to approximate the different nonlinear functions of the uncertain nonlinear system. The parameter adaptive laws are designed by the Lyapunov function; the stability and error convergence can be guaranteed. The simulation tests show that the proposed MFABC can provide good performance and high accuracy compared with the backstepping control. Moreover, the stability of this control scheme is affirmed.
{"title":"Model-free adaptive backstepping control for a class of uncertain nonlinear systems","authors":"Mohamed Segheri, Fares Boudjemaa, Abdelkrim Nemra, Youssouf Bibi","doi":"10.1177/01423312231189380","DOIUrl":"https://doi.org/10.1177/01423312231189380","url":null,"abstract":"Most nonlinear dynamic systems are characterized by uncertainties in models and parameters. Deterministic models cannot account for these uncertainties; therefore, model-based control using such models cannot provide the required performance. It is crucial to establish a practical concept of model-free control as a powerful alternative to model-based control. This paper develops a model-free adaptive backstepping control (MFABC) based on type 2 fuzzy Petri nets for a class of uncertain nonlinear systems. To provide valuable robustness to the MFABC structure, we have exploited the universal approximation property of type 2 fuzzy Petri nets to approximate the different nonlinear functions of the uncertain nonlinear system. The parameter adaptive laws are designed by the Lyapunov function; the stability and error convergence can be guaranteed. The simulation tests show that the proposed MFABC can provide good performance and high accuracy compared with the backstepping control. Moreover, the stability of this control scheme is affirmed.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135395640","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 : 2023-09-11DOI: 10.1177/01423312231195365
Ming Yin, Jiayi Tian, Dan Zhu, Yibo Wang, Jijiao Jiang
Process monitoring technology can help make the right decisions in manufacturing, but the complexity and scale of modern process industry processes render process monitoring difficult. Existing data-driven process monitoring methods utilize abundant monitoring data that are accumulated in industrial processes, but nonlinearity, high coupling, noise effects, and other problems continuously appear in process industry monitoring data. This study proposes a process monitoring method based on variational autoencoder and long short-term memory techniques. The method reconstructs the monitoring data by learning their distribution and time series characteristics under the controlled state, and then it monitors the state of the manufacturing process in real time by calculating the statistics. Evaluation is conducted using the Tennessee Eastman process case verification and experimental comparison method. Then, the proposed method is compared with the centralized process via principal component analysis and kernel principal component analysis. The results show that the proposed method can more significantly improve the effect of fault detection in distributed system process monitoring compared with the traditional method, and it has a better process monitoring effect.
{"title":"A data-driven distributed process monitoring method for industry manufacturing systems","authors":"Ming Yin, Jiayi Tian, Dan Zhu, Yibo Wang, Jijiao Jiang","doi":"10.1177/01423312231195365","DOIUrl":"https://doi.org/10.1177/01423312231195365","url":null,"abstract":"Process monitoring technology can help make the right decisions in manufacturing, but the complexity and scale of modern process industry processes render process monitoring difficult. Existing data-driven process monitoring methods utilize abundant monitoring data that are accumulated in industrial processes, but nonlinearity, high coupling, noise effects, and other problems continuously appear in process industry monitoring data. This study proposes a process monitoring method based on variational autoencoder and long short-term memory techniques. The method reconstructs the monitoring data by learning their distribution and time series characteristics under the controlled state, and then it monitors the state of the manufacturing process in real time by calculating the statistics. Evaluation is conducted using the Tennessee Eastman process case verification and experimental comparison method. Then, the proposed method is compared with the centralized process via principal component analysis and kernel principal component analysis. The results show that the proposed method can more significantly improve the effect of fault detection in distributed system process monitoring compared with the traditional method, and it has a better process monitoring effect.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135981064","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 : 2023-09-08DOI: 10.1177/01423312231194603
Jingrui Chu, Shi-kui Wang, Runlin Gan, Wenhang Wang, Baoren Li, Gang Yang
The gas flow temperature signal simulation system (ATSSS) plays a crucial role in the hardware-in-the-loop simulation of hypersonic aircraft. The accuracy of gas flow temperature measurements is of paramount importance for the ATSSS. This system comprises a high-temperature plasma heater, a gas flow mixing chamber, and thermocouples. The ATSSS exhibits specific characteristics such as high temperatures, rapid temperature changes, and fast flow rates. However, due to the large measurement time constant of high-temperature thermocouples, significant dynamic errors are introduced into the measurement results. To address this issue and enhance the dynamic measurement accuracy of gas flow temperature, this study establishes a thermocouple heat transfer model for the ATSSS. It also analyzes the mechanism behind the generation of dynamic errors in the ATSSS and proposes a three-thermocouple coupled temperature measurement dynamic compensation method (TTCTMDC). This method compensates for errors caused by thermal convection, thermal radiation, and thermal conduction under high-temperature conditions. Simulation results demonstrate that the proposed method can reduce errors by 50% to 80%. In addition, an experimental platform for the ATSSS is constructed, and the TTCTMDC method is employed to compensate for measurement errors. The results indicate that the dynamic measurement error can be reduced to 1/4 to 1/2 of the original value using the TTCTMDC method. This research lays a foundation for the successful development of the ATSSS and provides a novel approach to dynamically measuring high-temperature gas flow, thereby advancing scientific research in the field of measurement.
{"title":"Dynamic compensation by coupled triple-thermocouples for temperature measurement error of high-temperature gas flow","authors":"Jingrui Chu, Shi-kui Wang, Runlin Gan, Wenhang Wang, Baoren Li, Gang Yang","doi":"10.1177/01423312231194603","DOIUrl":"https://doi.org/10.1177/01423312231194603","url":null,"abstract":"The gas flow temperature signal simulation system (ATSSS) plays a crucial role in the hardware-in-the-loop simulation of hypersonic aircraft. The accuracy of gas flow temperature measurements is of paramount importance for the ATSSS. This system comprises a high-temperature plasma heater, a gas flow mixing chamber, and thermocouples. The ATSSS exhibits specific characteristics such as high temperatures, rapid temperature changes, and fast flow rates. However, due to the large measurement time constant of high-temperature thermocouples, significant dynamic errors are introduced into the measurement results. To address this issue and enhance the dynamic measurement accuracy of gas flow temperature, this study establishes a thermocouple heat transfer model for the ATSSS. It also analyzes the mechanism behind the generation of dynamic errors in the ATSSS and proposes a three-thermocouple coupled temperature measurement dynamic compensation method (TTCTMDC). This method compensates for errors caused by thermal convection, thermal radiation, and thermal conduction under high-temperature conditions. Simulation results demonstrate that the proposed method can reduce errors by 50% to 80%. In addition, an experimental platform for the ATSSS is constructed, and the TTCTMDC method is employed to compensate for measurement errors. The results indicate that the dynamic measurement error can be reduced to 1/4 to 1/2 of the original value using the TTCTMDC method. This research lays a foundation for the successful development of the ATSSS and provides a novel approach to dynamically measuring high-temperature gas flow, thereby advancing scientific research in the field of measurement.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2023-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45599831","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 : 2023-09-08DOI: 10.1177/01423312231190965
Lian Lian, Zhong-da Tian
The problem of unknown input observer design for discrete-time nonlinear generalized Markov jump systems is studied. First, like a normal system, the whole nonlinear system is transformed into a local linear system, and then a large number of linear system theories can be applied to solve related problems. Second, in the observer design of general discrete-time Markov jump systems, only the unknown input in the state equation is usually considered. In this paper, the unknown input is considered in both the state equation and the output equation. The state estimation error system is derived by defining the error. The non-uniform Lyapunov functional is selected to stabilize the estimation error system using the Lyapunov theory. The sufficient conditions for the stability of the system are obtained and transformed into the feasibility problem of linear matrix inequality. The problem of unknown input observer design for discrete-time nonlinear generalized Markov jump systems is solved using MATLAB software. Finally, a numerical example of two rules and two modes is used to verify the effectiveness and feasibility of the proposed unknown input observer.
{"title":"Design of unknown input observer for discrete-time Markov jump systems with unknown input in both state equation and output equation","authors":"Lian Lian, Zhong-da Tian","doi":"10.1177/01423312231190965","DOIUrl":"https://doi.org/10.1177/01423312231190965","url":null,"abstract":"The problem of unknown input observer design for discrete-time nonlinear generalized Markov jump systems is studied. First, like a normal system, the whole nonlinear system is transformed into a local linear system, and then a large number of linear system theories can be applied to solve related problems. Second, in the observer design of general discrete-time Markov jump systems, only the unknown input in the state equation is usually considered. In this paper, the unknown input is considered in both the state equation and the output equation. The state estimation error system is derived by defining the error. The non-uniform Lyapunov functional is selected to stabilize the estimation error system using the Lyapunov theory. The sufficient conditions for the stability of the system are obtained and transformed into the feasibility problem of linear matrix inequality. The problem of unknown input observer design for discrete-time nonlinear generalized Markov jump systems is solved using MATLAB software. Finally, a numerical example of two rules and two modes is used to verify the effectiveness and feasibility of the proposed unknown input observer.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":" ","pages":""},"PeriodicalIF":1.8,"publicationDate":"2023-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48874829","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 : 2023-09-08DOI: 10.1177/01423312231190193
Nacim Meslem
In this work, a new approach to design set-valued state estimator for linear discrete-time systems subject to additive and bounded process and measurement uncertainties is proposed. First, the system state equation is rewritten to obtain a stable numerical scheme on which an explicit reachability method is developed, based on zonotopic set computation and a re-initialization procedure. Then, to enhance the accuracy of the computed reachable set, a set-filtering technique is designed based on the system output equation and its intrinsic invariant relationships. The implementation of this filtering method is based on interval analysis coupled to contractor algorithms. The convergence property of the proposed set-valued state estimator is shown under the classical detectability assumption of linear systems. Some simulation results are presented to show the merit of the proposed new set-membership state estimation approach.
{"title":"Tight set-valued state estimation by combining reachability analysis and set-filtering approaches","authors":"Nacim Meslem","doi":"10.1177/01423312231190193","DOIUrl":"https://doi.org/10.1177/01423312231190193","url":null,"abstract":"In this work, a new approach to design set-valued state estimator for linear discrete-time systems subject to additive and bounded process and measurement uncertainties is proposed. First, the system state equation is rewritten to obtain a stable numerical scheme on which an explicit reachability method is developed, based on zonotopic set computation and a re-initialization procedure. Then, to enhance the accuracy of the computed reachable set, a set-filtering technique is designed based on the system output equation and its intrinsic invariant relationships. The implementation of this filtering method is based on interval analysis coupled to contractor algorithms. The convergence property of the proposed set-valued state estimator is shown under the classical detectability assumption of linear systems. Some simulation results are presented to show the merit of the proposed new set-membership state estimation approach.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136362168","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 : 2023-09-08DOI: 10.1177/01423312231197363
Xing Luo, Qi Lei, Huirui Wang
Soft sensors have become reliable tools for estimating difficult-to-measure target variables in modern industrial processes. In order to make full use of labeled and unlabeled samples, an active semi-supervised soft sensor modeling method is proposed, which combines active learning and semi-supervised learning to maximize model performance and minimize the laboratory analysis cost of expanding the labeled sample data set. First, manifold regularization is introduced into the deep extreme learning machine (DELM) algorithm to form a semi-supervised DELM that improves the performance of a model trained with unlabeled samples. Then, considering non-Gaussian processes and the error information between the predicted and true values, an active sample selection strategy based on error Gaussian mixture model is developed. Using this strategy, the most uncertain and representative unlabeled samples are selected for labeling, and thereby expanding the labeled sample data set. Finally, the effectiveness of the proposed method is verified using industrial debutanizer process data.
{"title":"Gaussian mixture model sample selection strategy–based active semi-supervised soft sensor for industrial processes","authors":"Xing Luo, Qi Lei, Huirui Wang","doi":"10.1177/01423312231197363","DOIUrl":"https://doi.org/10.1177/01423312231197363","url":null,"abstract":"Soft sensors have become reliable tools for estimating difficult-to-measure target variables in modern industrial processes. In order to make full use of labeled and unlabeled samples, an active semi-supervised soft sensor modeling method is proposed, which combines active learning and semi-supervised learning to maximize model performance and minimize the laboratory analysis cost of expanding the labeled sample data set. First, manifold regularization is introduced into the deep extreme learning machine (DELM) algorithm to form a semi-supervised DELM that improves the performance of a model trained with unlabeled samples. Then, considering non-Gaussian processes and the error information between the predicted and true values, an active sample selection strategy based on error Gaussian mixture model is developed. Using this strategy, the most uncertain and representative unlabeled samples are selected for labeling, and thereby expanding the labeled sample data set. Finally, the effectiveness of the proposed method is verified using industrial debutanizer process data.","PeriodicalId":49426,"journal":{"name":"Transactions of the Institute of Measurement and Control","volume":"2018 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136362140","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：