Pub Date : 2001-09-05DOI: 10.1109/ISIC.2001.971526
Y. Sun, M. Er
A hybrid fuzzy controller suitable for controlling both linear and nonlinear systems is proposed. The proposed controller, comprising a linear proportional integral derivative (PID) controller and a linear fuzzy logic controller, employs genetic algorithms to facilitate optimal tuning of the controller gains. A two-input dynamic linear fuzzy logic controller with linearly defined fuzzy space is developed to replace the conventional PI controller in the PID connective structure. Closed-form analysis shows that the proposed fuzzy logic controller is capable of generating nonlinear output by using varying gains and dynamic fuzzy rule base. Simulation results for a direct-current motor and a tactical missile model demonstrate that the proposed controller outperforms other existing controllers, is robust and has great potential in many other industrial applications.
{"title":"Hybrid fuzzy control of linear and nonlinear systems","authors":"Y. Sun, M. Er","doi":"10.1109/ISIC.2001.971526","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971526","url":null,"abstract":"A hybrid fuzzy controller suitable for controlling both linear and nonlinear systems is proposed. The proposed controller, comprising a linear proportional integral derivative (PID) controller and a linear fuzzy logic controller, employs genetic algorithms to facilitate optimal tuning of the controller gains. A two-input dynamic linear fuzzy logic controller with linearly defined fuzzy space is developed to replace the conventional PI controller in the PID connective structure. Closed-form analysis shows that the proposed fuzzy logic controller is capable of generating nonlinear output by using varying gains and dynamic fuzzy rule base. Simulation results for a direct-current motor and a tactical missile model demonstrate that the proposed controller outperforms other existing controllers, is robust and has great potential in many other industrial applications.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"243 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115472325","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2001-09-05DOI: 10.1109/ISIC.2001.971529
Yi-Liang Chen, G. Provan
The ability to reconfigure a ship's engineering plant in response to changing mission or equipment conditions can dramatically increase a ship's capability and survivability. In our previous work (1999, 2000), a model-based reasoning framework for the integrated control/reconfiguration and diagnosis of discrete event systems was proposed. By applying this framework, we present an approach that integrates multiple shipboard systems and provides resourceand diagnostic-driven reconfiguration at multiple system levels, such as mission-level, process-level, and component-level. Several operation scenarios are studied to illustrate the reconfigurations of shipboard systems based on the changing objectives and diagnoses.
{"title":"Model-based control reconfiguration: a shipboard system example","authors":"Yi-Liang Chen, G. Provan","doi":"10.1109/ISIC.2001.971529","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971529","url":null,"abstract":"The ability to reconfigure a ship's engineering plant in response to changing mission or equipment conditions can dramatically increase a ship's capability and survivability. In our previous work (1999, 2000), a model-based reasoning framework for the integrated control/reconfiguration and diagnosis of discrete event systems was proposed. By applying this framework, we present an approach that integrates multiple shipboard systems and provides resourceand diagnostic-driven reconfiguration at multiple system levels, such as mission-level, process-level, and component-level. Several operation scenarios are studied to illustrate the reconfigurations of shipboard systems based on the changing objectives and diagnoses.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127551730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2001-09-05DOI: 10.1109/ISIC.2001.971530
K. Prakah-Asante, M. Rao, K. N. Morman, G. Strumolo
Occupant safety systems are incorporated in vehicles to meet the requirements of occupant protection. For optimum performance safety devices require tailored activation. This paper presents a supervisory control approach using predictive collision sensor information to augment the performance of safety systems. The supervisory approach determines the potential for a collision to occur, and assists in deployment decision-making. Decision-making is based on the obstacle range, and closing velocity information obtained from the anticipatory sensor, and a reference signal indicative of the host-vehicle deceleration. The multi-input supervisory control system consists of a fuzzy rule-based system, which determines the potential for a collision to occur, and deployment command generation for activation of respective safety devices.
{"title":"Supervisory vehicle impact anticipation and control of safety systems","authors":"K. Prakah-Asante, M. Rao, K. N. Morman, G. Strumolo","doi":"10.1109/ISIC.2001.971530","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971530","url":null,"abstract":"Occupant safety systems are incorporated in vehicles to meet the requirements of occupant protection. For optimum performance safety devices require tailored activation. This paper presents a supervisory control approach using predictive collision sensor information to augment the performance of safety systems. The supervisory approach determines the potential for a collision to occur, and assists in deployment decision-making. Decision-making is based on the obstacle range, and closing velocity information obtained from the anticipatory sensor, and a reference signal indicative of the host-vehicle deceleration. The multi-input supervisory control system consists of a fuzzy rule-based system, which determines the potential for a collision to occur, and deployment command generation for activation of respective safety devices.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127555541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2001-09-05DOI: 10.1109/ISIC.2001.971486
X.W. Yan, Z. Deng, Z. Sun
This paper presents two fuzzy reinforcement learning methods for solving complicated learning tasks of continuous domains. Takagi-Sugeno fuzzy reinforcement learning (TSFRL) is constructed by combining Takagi-Sugeno type fuzzy inference systems with Q-learning. Next, genetic Takagi-Sugeno fuzzy reinforcement learning (GTSFRL) is introduced by embedding TSFRL into genetic algorithms. Both proposed learning algorithms can also be used to design Takagi-Sugeno fuzzy logic controllers. Experiments on the double inverted pendulum system demonstrate the performance and applicability of the proposed schemes. Finally, the conclusion remark is drawn.
{"title":"Genetic Takagi-Sugeno fuzzy reinforcement learning","authors":"X.W. Yan, Z. Deng, Z. Sun","doi":"10.1109/ISIC.2001.971486","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971486","url":null,"abstract":"This paper presents two fuzzy reinforcement learning methods for solving complicated learning tasks of continuous domains. Takagi-Sugeno fuzzy reinforcement learning (TSFRL) is constructed by combining Takagi-Sugeno type fuzzy inference systems with Q-learning. Next, genetic Takagi-Sugeno fuzzy reinforcement learning (GTSFRL) is introduced by embedding TSFRL into genetic algorithms. Both proposed learning algorithms can also be used to design Takagi-Sugeno fuzzy logic controllers. Experiments on the double inverted pendulum system demonstrate the performance and applicability of the proposed schemes. Finally, the conclusion remark is drawn.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"200 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121625956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2001-09-05DOI: 10.1109/ISIC.2001.971533
E. Sánchez, J. Béteau, S. Carlos-Hernandez
The authors present the synthesis of a fuzzy supervisory control for a wastewater treatment anaerobic plant. On the basis of a previously developed integrated control, which switches two controllers, two new variables are considered (COJ/X/sub 2/ and /spl Delta/QCH/sub 4/), and a Takagi-Sugeno fuzzy supervisor is developed in order to smooth the switching. This new strategy allows the increase of methane production. Applicability of the proposed structure is illustrated via simulations.
{"title":"Fuzzy supervisory control for a wastewater anaerobic treatment plant","authors":"E. Sánchez, J. Béteau, S. Carlos-Hernandez","doi":"10.1109/ISIC.2001.971533","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971533","url":null,"abstract":"The authors present the synthesis of a fuzzy supervisory control for a wastewater treatment anaerobic plant. On the basis of a previously developed integrated control, which switches two controllers, two new variables are considered (COJ/X/sub 2/ and /spl Delta/QCH/sub 4/), and a Takagi-Sugeno fuzzy supervisor is developed in order to smooth the switching. This new strategy allows the increase of methane production. Applicability of the proposed structure is illustrated via simulations.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121865129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2001-09-05DOI: 10.1109/ISIC.2001.971528
Dimitar Filev, T. Larsson
We develop a new intelligent adaptive control algorithm that is applicable to systems with large parameters variations and multiple operating modes. It uses a set of models, called the dynamic model bank, that guides the adaptation process. The dynamic model bank summarizes the parameters of the models that successfully approximate the plant. The model bank is automatically created and updated and does not call for an initial set of models. It uses a soft switching mechanism that provides a smooth transition from an interpolative to a pure "hard" switching scheme between the models in the bank. We also demonstrate the advantage of using this approach on several examples considering the control of systems with large parameter variations.
{"title":"Intelligent adaptive control using multiple models","authors":"Dimitar Filev, T. Larsson","doi":"10.1109/ISIC.2001.971528","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971528","url":null,"abstract":"We develop a new intelligent adaptive control algorithm that is applicable to systems with large parameters variations and multiple operating modes. It uses a set of models, called the dynamic model bank, that guides the adaptation process. The dynamic model bank summarizes the parameters of the models that successfully approximate the plant. The model bank is automatically created and updated and does not call for an initial set of models. It uses a soft switching mechanism that provides a smooth transition from an interpolative to a pure \"hard\" switching scheme between the models in the bank. We also demonstrate the advantage of using this approach on several examples considering the control of systems with large parameter variations.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130543396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2001-09-05DOI: 10.1109/ISIC.2001.971536
T. Shannon, G. Lendaris
We show the applicability of the dual heuristic programming (DHP) method of approximate dynamic programming to the design of a fuzzy control system. The DHP and related techniques have been developed in the neurocontrol context but can be equally productive when used with fuzzy controllers or neuro-fuzzy hybrids. We demonstrate this technique on a speed controller for a brushless motor. In our example, we take advantage of the Takagi-Sugeno model framework to initialize the tunable parameters of our plant model with reasonable problem specific values, a practice difficult to perform when applying DHP to neurocontrol.
{"title":"Adaptive critic based design of a fuzzy motor speed controller","authors":"T. Shannon, G. Lendaris","doi":"10.1109/ISIC.2001.971536","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971536","url":null,"abstract":"We show the applicability of the dual heuristic programming (DHP) method of approximate dynamic programming to the design of a fuzzy control system. The DHP and related techniques have been developed in the neurocontrol context but can be equally productive when used with fuzzy controllers or neuro-fuzzy hybrids. We demonstrate this technique on a speed controller for a brushless motor. In our example, we take advantage of the Takagi-Sugeno model framework to initialize the tunable parameters of our plant model with reasonable problem specific values, a practice difficult to perform when applying DHP to neurocontrol.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123309008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2001-09-05DOI: 10.1109/ISIC.2001.971531
M. Karam, M. A. Zohdy, S. Farinwata
A modular recurrent dynamic neural network (RDNN) based on the Hopfield model is applied to the linear quadratic regulator (LQR) optimal control of a nonlinear slider inverted pendulum (SIP). The main advantage of using neural networks is their robustness and flexibility when dealing with uncertain and ill-conditioned problems. The combination of the RDNN with LQR control is done in two ways. In the first technique, the LQR control gains are calculated by solving the algebraic Riccati equation (ARE) using the RDNN. Robustness of the control is further improved by appropriately tuning the LQR gains. In the second technique, the RDNN is trained to learn the connections between the controller's inputs and outputs. The efficacy of the training is confirmed as the neural controller performs successfully when tested on-line. Neural control results in more robustness, especially when noise is added to the system. The overall positive results of this study show that the proposed LQR/RDNN control offers an efficient alternative to traditional LQR control when dealing with noise corrupted data, and confirm the feasibility of using neural networks in the design of robust optimal controllers.
{"title":"Robust optimal control using recurrent dynamic neural network","authors":"M. Karam, M. A. Zohdy, S. Farinwata","doi":"10.1109/ISIC.2001.971531","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971531","url":null,"abstract":"A modular recurrent dynamic neural network (RDNN) based on the Hopfield model is applied to the linear quadratic regulator (LQR) optimal control of a nonlinear slider inverted pendulum (SIP). The main advantage of using neural networks is their robustness and flexibility when dealing with uncertain and ill-conditioned problems. The combination of the RDNN with LQR control is done in two ways. In the first technique, the LQR control gains are calculated by solving the algebraic Riccati equation (ARE) using the RDNN. Robustness of the control is further improved by appropriately tuning the LQR gains. In the second technique, the RDNN is trained to learn the connections between the controller's inputs and outputs. The efficacy of the training is confirmed as the neural controller performs successfully when tested on-line. Neural control results in more robustness, especially when noise is added to the system. The overall positive results of this study show that the proposed LQR/RDNN control offers an efficient alternative to traditional LQR control when dealing with noise corrupted data, and confirm the feasibility of using neural networks in the design of robust optimal controllers.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129917128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2001-09-05DOI: 10.1109/ISIC.2001.971497
H. Valdés-González, J. Flaus
This work proposes a method to estimate states in hybrid nonlinear discrete-time systems based on an interval moving horizon state estimation method, where the states of the hybrid model are described using a representation by interval numbers. The proposed technique is applied to a generic biotechnological process model, where the specific growth rate and its substrate dependence is modeled by a hybrid law, simpler than the classic dependence of a Monod law. The results obtained through computer simulation demonstrate that this estimation hybrid can be easily implemented in industrial situations.
{"title":"State estimation in a bioprocess described by a hybrid model","authors":"H. Valdés-González, J. Flaus","doi":"10.1109/ISIC.2001.971497","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971497","url":null,"abstract":"This work proposes a method to estimate states in hybrid nonlinear discrete-time systems based on an interval moving horizon state estimation method, where the states of the hybrid model are described using a representation by interval numbers. The proposed technique is applied to a generic biotechnological process model, where the specific growth rate and its substrate dependence is modeled by a hybrid law, simpler than the classic dependence of a Monod law. The results obtained through computer simulation demonstrate that this estimation hybrid can be easily implemented in industrial situations.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129739995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2001-09-05DOI: 10.1109/ISIC.2001.971527
Hong Wang, J. Zhang
By combining the entropy with the recent developed control strategies on the shape control of the output probability density function for dynamic stochastic systems, a new control algorithm is formulated for a class of unknown dynamic stochastic systems. The obtained control input minimizes a combined performance function for the closed loop system and can thus realizes the control of the shape of the output probability density functions and, at the same time, minimizes the system entropy so as to reduce the uncertainties for the closed loop system. Since the system considered is unknown, a neural network model is used online to update the optimal control input. This leads to an adaptive control framework for the closed loop control of the system. A simulated example is included to show the effectiveness of the proposed algorithm and encouraging results were obtained.
{"title":"Combined minimum entropy and output PDFS control via neural networks","authors":"Hong Wang, J. Zhang","doi":"10.1109/ISIC.2001.971527","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971527","url":null,"abstract":"By combining the entropy with the recent developed control strategies on the shape control of the output probability density function for dynamic stochastic systems, a new control algorithm is formulated for a class of unknown dynamic stochastic systems. The obtained control input minimizes a combined performance function for the closed loop system and can thus realizes the control of the shape of the output probability density functions and, at the same time, minimizes the system entropy so as to reduce the uncertainties for the closed loop system. Since the system considered is unknown, a neural network model is used online to update the optimal control input. This leads to an adaptive control framework for the closed loop control of the system. A simulated example is included to show the effectiveness of the proposed algorithm and encouraging results were obtained.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"329 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116528259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：