In this paper, a data-based fault tolerant control(FTC) scheme is investigated for unknown continuous-time(CT)affine nonlinear systems with actuator faults. First, a neural network(NN) identifier based on particle swa...In this paper, a data-based fault tolerant control(FTC) scheme is investigated for unknown continuous-time(CT)affine nonlinear systems with actuator faults. First, a neural network(NN) identifier based on particle swarm optimization(PSO) is constructed to model the unknown system dynamics. By utilizing the estimated system states, the particle swarm optimized critic neural network(PSOCNN) is employed to solve the Hamilton-Jacobi-Bellman equation(HJBE) more efficiently.Then, a data-based FTC scheme, which consists of the NN identifier and the fault compensator, is proposed to achieve actuator fault tolerance. The stability of the closed-loop system under actuator faults is guaranteed by the Lyapunov stability theorem. Finally, simulations are provided to demonstrate the effectiveness of the developed method.展开更多
In this paper, the data-based control problem is investigated for a class of networked nonlinear systems with measurement noise as well as packet dropouts in the feedback and forward channels. The measurement noise an...In this paper, the data-based control problem is investigated for a class of networked nonlinear systems with measurement noise as well as packet dropouts in the feedback and forward channels. The measurement noise and the number of consecutive packet dropouts in both channels are assumed to be random but bounded. A data-based networked predictive control method is proposed, in which a sequence of control increment predictions are calculated in the controller based on the measured output error, and based on the control increment predictions received by the actuator, a proper control action is obtained and applied to the plant according to the real-time number of consecutive packet dropouts at each sampling instant. Then the stability analysis is performed for the networked closedloop system. Finally, the effectiveness of the proposed method is illustrated by a numerical example.展开更多
Support vector machines and a Kalman-like observer are used for fault detection and isolation in a variable speed horizontalaxis wind turbine composed of three blades and a full converter. The support vector approach ...Support vector machines and a Kalman-like observer are used for fault detection and isolation in a variable speed horizontalaxis wind turbine composed of three blades and a full converter. The support vector approach is data-based and is therefore robust to process knowledge. It is based on structural risk minimization which enhances generalization even with small training data set and it allows for process nonlinearity by using flexible kernels. In this work, a radial basis function is used as the kernel. Different parts of the process are investigated including actuators and sensors faults. With duplicated sensors, sensor faults in blade pitch positions,generator and rotor speeds can be detected. Faults of type stuck measurements can be detected in 2 sampling periods. The detection time of offset/scaled measurements depends on the severity of the fault and on the process dynamics when the fault occurs. The converter torque actuator fault can be detected within 2 sampling periods. Faults in the actuators of the pitch systems represents a higher difficulty for fault detection which is due to the fact that such faults only affect the transitory state(which is very fast) but not the final stationary state. Therefore, two methods are considered and compared for fault detection and isolation of this fault: support vector machines and a Kalman-like observer. Advantages and disadvantages of each method are discussed. On one hand, support vector machines training of transitory states would require a big amount of data in different situations, but the fault detection and isolation results are robust to variations in the input/operating point. On the other hand, the observer is model-based, and therefore does not require training, and it allows identification of the fault level, which is interesting for fault reconfiguration. But the observability of the system is ensured under specific conditions, related to the dynamics of the inputs and outputs. The whole fault detection and isolation scheme is evaluated using a wind t展开更多
In the globalized market environment, increasingly significant economic and environmental factors withincomplex industrial plants impose importance on the optimization of global production indices; such opti-mization ...In the globalized market environment, increasingly significant economic and environmental factors withincomplex industrial plants impose importance on the optimization of global production indices; such opti-mization includes improvements in production efficiency, product quality, and yield, along with reductionsof energy and resource usage. This paper briefly overviews recent progress in data-driven hybrid intelli-gence optimization methods and technologies in improving the performance of global production indicesin mineral processing. First, we provide the problem description. Next, we summarize recent progress indata-based optimization for mineral processing plants. This optimization consists of four layers： optimiza-tion of the target values for monthly global production indices, optimization of the target values for dailyglobal production indices, optimization of the target values for operational indices, and automation systemsfor unit processes. We briefly overview recent progress in each of the different layers. Finally, we point outopportunities for future works in data-based optimization for mineral processing plants.展开更多
An electro-hydraulic control system is designed and implemented for a robotic excavator known as the Lancaster University Computerised and Intelligent Excavator （LUCIE）. The excavator is being developed to autonomou...An electro-hydraulic control system is designed and implemented for a robotic excavator known as the Lancaster University Computerised and Intelligent Excavator （LUCIE）. The excavator is being developed to autonomously dig trenches without human intervention. Since the behavior of the excavator arm is dominated by the nonlinear dynamics of the hydraulic actuators and by the large and unpredictable external disturbances when digging, it is difficult to provide adequate accurate, quick and smooth movement under traditional control methodology, e.g., PI/PID, which is comparable with that of an average human operator. The data-based dynamic models are developed utilizing the simplified refined instrumental variable （SRIV） identification algorithm to precisely describe the nonlinear dynamical behaviour of the electro-hydraulic actuation system. Based on data-based model and proportional-integral-plus （PIP） methodology, which is a non-minimal state space method of control system design based on the true digital control （TDC） system design philosophy, a novel control system is introduced to drive the excavator arm accurately, quickly and smoothly along the desired path. The performance of simulation and field tests which drive the bucket along straight lines both demonstrate the feasibility and validity of the proposed control scheme.展开更多
Vibration monitoring by virtual sensing methods has been well developed for linear timeinvariant structures with limited sensors.However,few methods are proposed for Time-Varying(TV)structures which are inevitable in ...Vibration monitoring by virtual sensing methods has been well developed for linear timeinvariant structures with limited sensors.However,few methods are proposed for Time-Varying(TV)structures which are inevitable in aerospace engineering.The core of vibration monitoring for TV structures is to describe the TV structural dynamic characteristics with accuracy and efficiency.This paper propose a new method using the Long Short-Term Memory(LSTM)networks for Continuously Variable Configuration Structures(CVCSs),which is an important subclass of TV structures.The configuration parameters are used to represent the time-varying dynamic characteristics by the‘‘freezing"method.The relationship between TV dynamic characteristics and vibration responses is established by LSTM,and can be generalized to estimate the responses with unknown TV processes benefiting from the time translation invariance of LSTM.A numerical example and a liquid-filled pipe experiment are used to test the performance of the proposed method.The results demonstrate that the proposed method can accurately estimate the unmeasured responses for CVCSs to reveal the actual characteristics in time-domain and modal-domain.Besides,the average one-step estimation time of responses is less than the sampling interval.Thus,the proposed method is promising to on-line estimate the important responses of TV structures.展开更多
It is crucial to investigate the characteristics of fire danger in the areas around Beijing to increase the accuracy of fire danger monitoring,forecasting,and management.Using meteorological data from 17 national mete...It is crucial to investigate the characteristics of fire danger in the areas around Beijing to increase the accuracy of fire danger monitoring,forecasting,and management.Using meteorological data from 17 national meteorological stations in the areas around Beijing from 1981−2021,this study calculated the fire weather index(FWI)and analyzed its spatiotemporal characteristics.It was found that the high and low fire danger periods were in April−May and July−August,with spatial patterns of“decrease in the northwest−increase in the southeast”and a significant increase throughout the areas around Beijing,respectively.Next,the contributions of different meteorological factors were quantified by the multiple regression method.We found that during the high fire danger period,the northern and southern parts were affected by precipitation and minimum relative humidity,respectively.However,most areas were influenced by wind speed during the low fire danger period.Finally,comparing with the FWI characteristics under different SSP scenarios,we found that the FWI decreased during high fire danger period and increased during low fire danger period under different SSP scenarios(i.e.,SSP245,SSP585)for periods of 2021−2050,2071−2100,2021−2100,except for SSP245 in 2071−2100 with an increasing trend both in high and low fire danger periods.This study implies that there is a higher probability of FWI in the low fire danger period,threatening the ecological environment and human health.Therefore,it is necessary to enhance research on fire danger during the low fire danger period to improve the ability to predict summer fire danger.展开更多
This paper proposes linear and nonlinear filters for a non-Gaussian dynamic system with an unknown nominal covariance of the output noise.The challenge of designing a suitable filter in the presence of an unknown cova...This paper proposes linear and nonlinear filters for a non-Gaussian dynamic system with an unknown nominal covariance of the output noise.The challenge of designing a suitable filter in the presence of an unknown covariance matrix is addressed by focusing on the output data set of the system.Considering that data generated from a Gaussian distribution exhibit ellipsoidal scattering,we first propose the weighted sum of norms(SON)clustering method that prioritizes nearby points,reduces distant point influence,and lowers computational cost.Then,by introducing the weighted maximum likelihood,we propose a semi-definite program(SDP)to detect outliers and reduce their impacts on each cluster.Detecting these weights paves the way to obtain an appropriate covariance of the output noise.Next,two filtering approaches are presented:a cluster-based robust linear filter using the maximum a posterior(MAP)estimation and a clusterbased robust nonlinear filter assuming that output noise distribution stems from some Gaussian noise resources according to the ellipsoidal clusters.At last,simulation results demonstrate the effectiveness of our proposed filtering approaches.展开更多
Proton exchange membrane fuel cell (PEMFC) is considered essential for climate change mitigation, and a fast and accurate model is necessary for its control and operation in practical applications. In this study, vari...Proton exchange membrane fuel cell (PEMFC) is considered essential for climate change mitigation, and a fast and accurate model is necessary for its control and operation in practical applications. In this study, various machine learning methods are used to develop data-based models for PEMFC performance attributes and internal states. Techniques such as Artificial Neural Network (ANN) and Support Vector Machine Regressor (SVR) are used to predict the cell voltage, membrane resistance, and membrane hydration level for various operating conditions. Varying input features such as cell current, temperature, reactant pressures, and humidity are introduced to evaluate the accuracy of the model, especially under extreme conditions. Two different sets of data are considered in this study, which are acquired from, a physics-based semiempirical model and a 1-D reduced-dimension Computational Fluid Dynamics model, respectively. The aspect of data preprocessing and hyperparameter tuning procedures are investigated that are extensively used to calibrate the artificial neural network layers and support vector regressor to predict the fuel cell attributes. ANN clearly shows an advantage in comparison with SVR, especially on a multivariable output regression. However, the SVR is advantageous to model simple regressions as it greatly reduces the level of computation without sacrificing accuracy. Data-based models for PEMFC are successfully developed on both the data sets by adapting advanced modeling techniques and calibration procedures such as ANN incorporating the dropout technique, resulting in an R2 ≥ 0.99 for all the predicted variables, demonstrating the ability to build accurate data-based models solely on data from validated physics-based models, reducing the dependency on extensive experimentation.展开更多
In this paper,a data-based scheme is proposed to solve the optimal tracking problem of autonomous nonlinear switching systems.The system state is forced to track the reference signal by minimizing the performance func...In this paper,a data-based scheme is proposed to solve the optimal tracking problem of autonomous nonlinear switching systems.The system state is forced to track the reference signal by minimizing the performance function.First,the problem is transformed to solve the corresponding Bellman optimality equation in terms of the Q-function(also named as action value function).Then,an iterative algorithm based on adaptive dynamic programming(ADP)is developed to find the optimal solution which is totally based on sampled data.The linear-in-parameter(LIP)neural network is taken as the value function approximator.Considering the presence of approximation error at each iteration step,the generated approximated value function sequence is proved to be boundedness around the exact optimal solution under some verifiable assumptions.Moreover,the effect that the learning process will be terminated after a finite number of iterations is investigated in this paper.A sufficient condition for asymptotically stability of the tracking error is derived.Finally,the effectiveness of the algorithm is demonstrated with three simulation examples.展开更多
基金supported in part by the National Natural ScienceFoundation of China(61533017,61973330,61773075,61603387)the Early Career Development Award of SKLMCCS(20180201)the State Key Laboratory of Synthetical Automation for Process Industries(2019-KF-23-03)。
文摘In this paper, a data-based fault tolerant control(FTC) scheme is investigated for unknown continuous-time(CT)affine nonlinear systems with actuator faults. First, a neural network(NN) identifier based on particle swarm optimization(PSO) is constructed to model the unknown system dynamics. By utilizing the estimated system states, the particle swarm optimized critic neural network(PSOCNN) is employed to solve the Hamilton-Jacobi-Bellman equation(HJBE) more efficiently.Then, a data-based FTC scheme, which consists of the NN identifier and the fault compensator, is proposed to achieve actuator fault tolerance. The stability of the closed-loop system under actuator faults is guaranteed by the Lyapunov stability theorem. Finally, simulations are provided to demonstrate the effectiveness of the developed method.
基金supported in part by the National Natural Science Foundation of China under Grant Nos.61673023,61203230,61273104,61333003,61210012,and 61490701the Beijing Municipal Natural Science Foundation under Grant No.4152014+3 种基金the Great Wall Scholar Candidate Training Program of North China University of Technology(NCUT)the Excellent Youth Scholar Nurturing Program of NCUTthe Outstanding Young Scientist Award Foundation of Shandong Province of China under Grant No.BS2013DX015the Research Fund for the Taishan Scholar Project of Shandong Province of China
文摘In this paper, the data-based control problem is investigated for a class of networked nonlinear systems with measurement noise as well as packet dropouts in the feedback and forward channels. The measurement noise and the number of consecutive packet dropouts in both channels are assumed to be random but bounded. A data-based networked predictive control method is proposed, in which a sequence of control increment predictions are calculated in the controller based on the measured output error, and based on the control increment predictions received by the actuator, a proper control action is obtained and applied to the plant according to the real-time number of consecutive packet dropouts at each sampling instant. Then the stability analysis is performed for the networked closedloop system. Finally, the effectiveness of the proposed method is illustrated by a numerical example.
文摘Support vector machines and a Kalman-like observer are used for fault detection and isolation in a variable speed horizontalaxis wind turbine composed of three blades and a full converter. The support vector approach is data-based and is therefore robust to process knowledge. It is based on structural risk minimization which enhances generalization even with small training data set and it allows for process nonlinearity by using flexible kernels. In this work, a radial basis function is used as the kernel. Different parts of the process are investigated including actuators and sensors faults. With duplicated sensors, sensor faults in blade pitch positions,generator and rotor speeds can be detected. Faults of type stuck measurements can be detected in 2 sampling periods. The detection time of offset/scaled measurements depends on the severity of the fault and on the process dynamics when the fault occurs. The converter torque actuator fault can be detected within 2 sampling periods. Faults in the actuators of the pitch systems represents a higher difficulty for fault detection which is due to the fact that such faults only affect the transitory state(which is very fast) but not the final stationary state. Therefore, two methods are considered and compared for fault detection and isolation of this fault: support vector machines and a Kalman-like observer. Advantages and disadvantages of each method are discussed. On one hand, support vector machines training of transitory states would require a big amount of data in different situations, but the fault detection and isolation results are robust to variations in the input/operating point. On the other hand, the observer is model-based, and therefore does not require training, and it allows identification of the fault level, which is interesting for fault reconfiguration. But the observability of the system is ensured under specific conditions, related to the dynamics of the inputs and outputs. The whole fault detection and isolation scheme is evaluated using a wind t
文摘In the globalized market environment, increasingly significant economic and environmental factors withincomplex industrial plants impose importance on the optimization of global production indices; such opti-mization includes improvements in production efficiency, product quality, and yield, along with reductionsof energy and resource usage. This paper briefly overviews recent progress in data-driven hybrid intelli-gence optimization methods and technologies in improving the performance of global production indicesin mineral processing. First, we provide the problem description. Next, we summarize recent progress indata-based optimization for mineral processing plants. This optimization consists of four layers： optimiza-tion of the target values for monthly global production indices, optimization of the target values for dailyglobal production indices, optimization of the target values for operational indices, and automation systemsfor unit processes. We briefly overview recent progress in each of the different layers. Finally, we point outopportunities for future works in data-based optimization for mineral processing plants.
基金supported by the Lancaster University (UK)SooChow University, China+2 种基金the UK Engineering and Physical Sciences Research CouncilUniversities’ Natural Science Research Council of Jiangsu Universities, China(Grant No. 08KJB510021)Scientific Research Foundation for the Returned Overseas Chinese Scholars, Ministry of Education of China
文摘An electro-hydraulic control system is designed and implemented for a robotic excavator known as the Lancaster University Computerised and Intelligent Excavator （LUCIE）. The excavator is being developed to autonomously dig trenches without human intervention. Since the behavior of the excavator arm is dominated by the nonlinear dynamics of the hydraulic actuators and by the large and unpredictable external disturbances when digging, it is difficult to provide adequate accurate, quick and smooth movement under traditional control methodology, e.g., PI/PID, which is comparable with that of an average human operator. The data-based dynamic models are developed utilizing the simplified refined instrumental variable （SRIV） identification algorithm to precisely describe the nonlinear dynamical behaviour of the electro-hydraulic actuation system. Based on data-based model and proportional-integral-plus （PIP） methodology, which is a non-minimal state space method of control system design based on the true digital control （TDC） system design philosophy, a novel control system is introduced to drive the excavator arm accurately, quickly and smoothly along the desired path. The performance of simulation and field tests which drive the bucket along straight lines both demonstrate the feasibility and validity of the proposed control scheme.
文摘Vibration monitoring by virtual sensing methods has been well developed for linear timeinvariant structures with limited sensors.However,few methods are proposed for Time-Varying(TV)structures which are inevitable in aerospace engineering.The core of vibration monitoring for TV structures is to describe the TV structural dynamic characteristics with accuracy and efficiency.This paper propose a new method using the Long Short-Term Memory(LSTM)networks for Continuously Variable Configuration Structures(CVCSs),which is an important subclass of TV structures.The configuration parameters are used to represent the time-varying dynamic characteristics by the‘‘freezing"method.The relationship between TV dynamic characteristics and vibration responses is established by LSTM,and can be generalized to estimate the responses with unknown TV processes benefiting from the time translation invariance of LSTM.A numerical example and a liquid-filled pipe experiment are used to test the performance of the proposed method.The results demonstrate that the proposed method can accurately estimate the unmeasured responses for CVCSs to reveal the actual characteristics in time-domain and modal-domain.Besides,the average one-step estimation time of responses is less than the sampling interval.Thus,the proposed method is promising to on-line estimate the important responses of TV structures.
基金funded by the National Natural Science Foundation of China(Grant Nos.42305055,42171030 and 41901017)the Science and Technology Project of Beijing Meteorological Service(No.BMBKJ202302001)+1 种基金the Key Project of Beijing Academy of Emergency Management Science and Technology(No.Y2023046)Open Foundation of Key Laboratory of Land Surface Pattern and Simulation,Chinese Academy of Sciences.
文摘It is crucial to investigate the characteristics of fire danger in the areas around Beijing to increase the accuracy of fire danger monitoring,forecasting,and management.Using meteorological data from 17 national meteorological stations in the areas around Beijing from 1981−2021,this study calculated the fire weather index(FWI)and analyzed its spatiotemporal characteristics.It was found that the high and low fire danger periods were in April−May and July−August,with spatial patterns of“decrease in the northwest−increase in the southeast”and a significant increase throughout the areas around Beijing,respectively.Next,the contributions of different meteorological factors were quantified by the multiple regression method.We found that during the high fire danger period,the northern and southern parts were affected by precipitation and minimum relative humidity,respectively.However,most areas were influenced by wind speed during the low fire danger period.Finally,comparing with the FWI characteristics under different SSP scenarios,we found that the FWI decreased during high fire danger period and increased during low fire danger period under different SSP scenarios(i.e.,SSP245,SSP585)for periods of 2021−2050,2071−2100,2021−2100,except for SSP245 in 2071−2100 with an increasing trend both in high and low fire danger periods.This study implies that there is a higher probability of FWI in the low fire danger period,threatening the ecological environment and human health.Therefore,it is necessary to enhance research on fire danger during the low fire danger period to improve the ability to predict summer fire danger.
文摘This paper proposes linear and nonlinear filters for a non-Gaussian dynamic system with an unknown nominal covariance of the output noise.The challenge of designing a suitable filter in the presence of an unknown covariance matrix is addressed by focusing on the output data set of the system.Considering that data generated from a Gaussian distribution exhibit ellipsoidal scattering,we first propose the weighted sum of norms(SON)clustering method that prioritizes nearby points,reduces distant point influence,and lowers computational cost.Then,by introducing the weighted maximum likelihood,we propose a semi-definite program(SDP)to detect outliers and reduce their impacts on each cluster.Detecting these weights paves the way to obtain an appropriate covariance of the output noise.Next,two filtering approaches are presented:a cluster-based robust linear filter using the maximum a posterior(MAP)estimation and a clusterbased robust nonlinear filter assuming that output noise distribution stems from some Gaussian noise resources according to the ellipsoidal clusters.At last,simulation results demonstrate the effectiveness of our proposed filtering approaches.
基金Supported by National Natural Science Foundation of China （61304079, 61125306, 61034002）, the Open Research Project from SKLMCCS （20120106）, the Fundamental Research Funds for the Central Universities （FRF-TP-13-018A）, and the China Postdoctoral Science. Foundation （201_3M_ 5305_27）_ _ _
文摘为有致动器浸透和未知动力学的分离时间的系统的一个班的一个新奇最佳的追踪控制方法在这份报纸被建议。计划基于反复的适应动态编程(自动数据处理) 算法。以便实现控制计划，一个 data-based 标识符首先为未知系统动力学被构造。由介绍 M 网络，稳定的控制的明确的公式被完成。以便消除致动器浸透的效果， nonquadratic 表演功能被介绍，然后一个反复的自动数据处理算法被建立与集中分析完成最佳的追踪控制解决方案。为实现最佳的控制方法，神经网络被用来建立 data-based 标识符，计算性能索引功能，近似最佳的控制政策并且分别地解决稳定的控制。模拟例子被提供验证介绍最佳的追踪的控制计划的有效性。
基金support from Canadian Urban Transit Research and Innovation Consortium(CUTRIC)via Project Number 160028Natural Sciences and Engineering Research Council of Canada(NSERC)via a Discovery Grant。
文摘Proton exchange membrane fuel cell (PEMFC) is considered essential for climate change mitigation, and a fast and accurate model is necessary for its control and operation in practical applications. In this study, various machine learning methods are used to develop data-based models for PEMFC performance attributes and internal states. Techniques such as Artificial Neural Network (ANN) and Support Vector Machine Regressor (SVR) are used to predict the cell voltage, membrane resistance, and membrane hydration level for various operating conditions. Varying input features such as cell current, temperature, reactant pressures, and humidity are introduced to evaluate the accuracy of the model, especially under extreme conditions. Two different sets of data are considered in this study, which are acquired from, a physics-based semiempirical model and a 1-D reduced-dimension Computational Fluid Dynamics model, respectively. The aspect of data preprocessing and hyperparameter tuning procedures are investigated that are extensively used to calibrate the artificial neural network layers and support vector regressor to predict the fuel cell attributes. ANN clearly shows an advantage in comparison with SVR, especially on a multivariable output regression. However, the SVR is advantageous to model simple regressions as it greatly reduces the level of computation without sacrificing accuracy. Data-based models for PEMFC are successfully developed on both the data sets by adapting advanced modeling techniques and calibration procedures such as ANN incorporating the dropout technique, resulting in an R2 ≥ 0.99 for all the predicted variables, demonstrating the ability to build accurate data-based models solely on data from validated physics-based models, reducing the dependency on extensive experimentation.
基金supported by the National Natural Science Foundation of China(61921004,U1713209,61803085,and 62041301)。
文摘In this paper,a data-based scheme is proposed to solve the optimal tracking problem of autonomous nonlinear switching systems.The system state is forced to track the reference signal by minimizing the performance function.First,the problem is transformed to solve the corresponding Bellman optimality equation in terms of the Q-function(also named as action value function).Then,an iterative algorithm based on adaptive dynamic programming(ADP)is developed to find the optimal solution which is totally based on sampled data.The linear-in-parameter(LIP)neural network is taken as the value function approximator.Considering the presence of approximation error at each iteration step,the generated approximated value function sequence is proved to be boundedness around the exact optimal solution under some verifiable assumptions.Moreover,the effect that the learning process will be terminated after a finite number of iterations is investigated in this paper.A sufficient condition for asymptotically stability of the tracking error is derived.Finally,the effectiveness of the algorithm is demonstrated with three simulation examples.
