Pub Date : 2001-12-01DOI: 10.1109/ISIC.2001.971516
R.R. Leal Ascencio, F. Reynaga, E. Herrera, A. Gschaedler
The ability of artificial neural networks (ANN) to learn from experience rather than from mechanistic descriptions is making them the preferred choice to model processes with intricate variable interrelations. We apply ANN as a data fusion method to provide estimations of biomass in a batch fermentation process. The readings of biomass must be periodic, of the desired frequency and reliable to a 5% error. A desired feature is that the measurement method be robust to sensor perturbations and failures. The robustness of the presented estimator system has been tested with simulated noisy inputs and with sensor failures and a mean average error of near 5% has been obtained. A new technique is presented as a data fusion method. The technique is tested on real process data. Simulated tests are applied to evaluate performance and robustness. We suggest that an artificial neural network may be used to obtain an insight on the relative influence of each of the variables used at every stage of the process.
{"title":"Artificial neural networks as a biomass virtual sensor for a batch process","authors":"R.R. Leal Ascencio, F. Reynaga, E. Herrera, A. Gschaedler","doi":"10.1109/ISIC.2001.971516","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971516","url":null,"abstract":"The ability of artificial neural networks (ANN) to learn from experience rather than from mechanistic descriptions is making them the preferred choice to model processes with intricate variable interrelations. We apply ANN as a data fusion method to provide estimations of biomass in a batch fermentation process. The readings of biomass must be periodic, of the desired frequency and reliable to a 5% error. A desired feature is that the measurement method be robust to sensor perturbations and failures. The robustness of the presented estimator system has been tested with simulated noisy inputs and with sensor failures and a mean average error of near 5% has been obtained. A new technique is presented as a data fusion method. The technique is tested on real process data. Simulated tests are applied to evaluate performance and robustness. We suggest that an artificial neural network may be used to obtain an insight on the relative influence of each of the variables used at every stage of the process.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129381524","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.2001.971490
C. García-Beltrán, S. Gentil
As safety is becoming an essential concern in industrial automation, an emerging area in automatic control is fault tolerant control. Within the various techniques, reconfiguration employs the redundancy in the plant and its control to make intelligent software that monitors the behavior of the whole. This paper analyses the reconfiguration problem from the point of view of large-scale processes under the responsibility of human operators. As analytical models cannot be envisaged for representing a process with hundred variables and several unpredictable operating modes, reconfiguration is proposed to rely on a simple qualitative model. This model represents the cause-effect relations between variables under the form of a directed graph. The graph is backward searched off line to find the action means on a variable. Then the most relevant remedial actions are selected online after a fault is detected. An example of a nuclear process is used to illustrate the method.
{"title":"Causal reasoning for human supervised process reconfiguration","authors":"C. García-Beltrán, S. Gentil","doi":"10.1109/ISIC.2001.971490","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971490","url":null,"abstract":"As safety is becoming an essential concern in industrial automation, an emerging area in automatic control is fault tolerant control. Within the various techniques, reconfiguration employs the redundancy in the plant and its control to make intelligent software that monitors the behavior of the whole. This paper analyses the reconfiguration problem from the point of view of large-scale processes under the responsibility of human operators. As analytical models cannot be envisaged for representing a process with hundred variables and several unpredictable operating modes, reconfiguration is proposed to rely on a simple qualitative model. This model represents the cause-effect relations between variables under the form of a directed graph. The graph is backward searched off line to find the action means on a variable. Then the most relevant remedial actions are selected online after a fault is detected. An example of a nuclear process is used to illustrate the method.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"8 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":"115455504","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.2001.971520
L. Aguirre-Salas, O. Begovich, A. Ramírez-Treviño
This paper studies the optimal sensor choice for observability problem in discrete event systems (DES) modeled by interpreted free-choice Petri nets (IFCN). Taking advantage of the fact that, event-detectability is a necessary and sufficient condition for observability in live, cyclic and bounded IFCN, a structural characterization of event-detectability and a simple polynomial algorithm to choose a minimal cost sensor configuration for observability in this claw of nets are provided. This algorithm is successfully applied to an illustrative example.
{"title":"Optimal sensor choice for observability in free-choice Petri nets","authors":"L. Aguirre-Salas, O. Begovich, A. Ramírez-Treviño","doi":"10.1109/ISIC.2001.971520","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971520","url":null,"abstract":"This paper studies the optimal sensor choice for observability problem in discrete event systems (DES) modeled by interpreted free-choice Petri nets (IFCN). Taking advantage of the fact that, event-detectability is a necessary and sufficient condition for observability in live, cyclic and bounded IFCN, a structural characterization of event-detectability and a simple polynomial algorithm to choose a minimal cost sensor configuration for observability in this claw of nets are provided. This algorithm is successfully applied to an illustrative example.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"91 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":"126156753","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.2001.971522
Z.G. Li, Y. C. Soh, C. Wen
Considers the global asymptotic stability of a class of fuzzy systems. Sufficient conditions for the stability of fuzzy systems are derived. They only require the Lyapunov function to be non-increasing along a subsequence of the time points. A method is presented to identify the non-increasing subsequence of the time points.
{"title":"Asymptotic stability of fuzzy systems","authors":"Z.G. Li, Y. C. Soh, C. Wen","doi":"10.1109/ISIC.2001.971522","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971522","url":null,"abstract":"Considers the global asymptotic stability of a class of fuzzy systems. Sufficient conditions for the stability of fuzzy systems are derived. They only require the Lyapunov function to be non-increasing along a subsequence of the time points. A method is presented to identify the non-increasing subsequence of the time points.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"4 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":"114428264","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.2001.971538
A. Abreu, L. Correia
A three layer behavior-based architecture using fuzzy logic is presented. A distinguishing feature is the similarity among its layers, facilitating architecture understanding and improving robot control designability. Other distinctive features are the simplicity in the way behaviors are modulated; how robustness is achieved, and how behaviors are fused. As a consequence, the whole architecture presents some interesting properties from a design perspective. Some experiments over a Khepera mobile robot are presented, attesting the interest in using such architecture in long runs.
{"title":"A fuzzy behavior-based architecture for decision control in autonomous vehicles","authors":"A. Abreu, L. Correia","doi":"10.1109/ISIC.2001.971538","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971538","url":null,"abstract":"A three layer behavior-based architecture using fuzzy logic is presented. A distinguishing feature is the similarity among its layers, facilitating architecture understanding and improving robot control designability. Other distinctive features are the simplicity in the way behaviors are modulated; how robustness is achieved, and how behaviors are fused. As a consequence, the whole architecture presents some interesting properties from a design perspective. Some experiments over a Khepera mobile robot are presented, attesting the interest in using such architecture in long runs.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"4 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":"128490383","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.2001.971503
W. Gueaieb, F. Karray, S. Al-Sharhan
We examine the complex problem of simultaneous position and internal force control in multiple cooperative manipulator systems. This is done in the presence of unwanted parametric and modeling uncertainties as well as external disturbances. A decentralized adaptive fuzzy controller scheme is proposed here. The controller makes use of a multi-input multi-output fuzzy logic engine and a systematic online adaptation mechanism. Unlike conventional adaptive controllers, the proposed algorithm does not require a precise mathematical model of the system dynamics nor does it require a linear parameterization of the system uncertain physical parameters. The performance of the controller proposed is then compared to that of a well known conventional adaptive controller.
{"title":"An adaptive fuzzy control approach for cooperative manipulators","authors":"W. Gueaieb, F. Karray, S. Al-Sharhan","doi":"10.1109/ISIC.2001.971503","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971503","url":null,"abstract":"We examine the complex problem of simultaneous position and internal force control in multiple cooperative manipulator systems. This is done in the presence of unwanted parametric and modeling uncertainties as well as external disturbances. A decentralized adaptive fuzzy controller scheme is proposed here. The controller makes use of a multi-input multi-output fuzzy logic engine and a systematic online adaptation mechanism. Unlike conventional adaptive controllers, the proposed algorithm does not require a precise mathematical model of the system dynamics nor does it require a linear parameterization of the system uncertain physical parameters. The performance of the controller proposed is then compared to that of a well known conventional adaptive controller.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"83 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":"126289482","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.2001.971495
I. Baruch, R. Garrido, J. Flores, J.C. Martinez
A recurrent trainable neural network (RTNN) together with a backpropagation trough-time learning algorithm are applied for a real-time identification and adaptive control of a DC-motor drive. The paper proposes to use three RTNNs separately for the parts of the systems identification, the state feedback control and the feedforward control. The applied RTNN model has a minimum number of parameters due to its Jordan canonical structure, which permits to use the generated vector of states directly for a DC-motor feedback control. The experimental results, confirm the applicability of the described identification and control methodology in practice and also confirm the good quality of the RTNN.
{"title":"An adaptive neural control of a DC motor","authors":"I. Baruch, R. Garrido, J. Flores, J.C. Martinez","doi":"10.1109/ISIC.2001.971495","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971495","url":null,"abstract":"A recurrent trainable neural network (RTNN) together with a backpropagation trough-time learning algorithm are applied for a real-time identification and adaptive control of a DC-motor drive. The paper proposes to use three RTNNs separately for the parts of the systems identification, the state feedback control and the feedforward control. The applied RTNN model has a minimum number of parameters due to its Jordan canonical structure, which permits to use the generated vector of states directly for a DC-motor feedback control. The experimental results, confirm the applicability of the described identification and control methodology in practice and also confirm the good quality of the RTNN.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"39 6 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":"131355144","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.2001.971515
V. Alcaraz-González, J. Harmand, Alain Rapaport, J. Steyer, V. González-Álvarez, C. Pelayo-Ortiz
A robust regulation law is proposed for the stabilization of an anaerobic digester for the treatment of organic wastewater. This process exhibits a highly nonlinear dynamic behavior with poorly known parameters. In addition, it must work under an uncertain environment with the presence of unknown inputs. Supporting some structural and operational conditions, this regulation law exponentially stabilizes the regulated variable around its nominal value in the presence of uncertainty and input disturbances. Experimental results are presented using a 1 m/sup 3/ continuous fixed bed anaerobic bioreactor used for the treatment of industrial wine distillery wastewater.
{"title":"Robust interval-based SISO regulation under maximum uncertainty conditions in an anaerobic digester","authors":"V. Alcaraz-González, J. Harmand, Alain Rapaport, J. Steyer, V. González-Álvarez, C. Pelayo-Ortiz","doi":"10.1109/ISIC.2001.971515","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971515","url":null,"abstract":"A robust regulation law is proposed for the stabilization of an anaerobic digester for the treatment of organic wastewater. This process exhibits a highly nonlinear dynamic behavior with poorly known parameters. In addition, it must work under an uncertain environment with the presence of unknown inputs. Supporting some structural and operational conditions, this regulation law exponentially stabilizes the regulated variable around its nominal value in the presence of uncertainty and input disturbances. Experimental results are presented using a 1 m/sup 3/ continuous fixed bed anaerobic bioreactor used for the treatment of industrial wine distillery wastewater.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"12 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":"116834416","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.2001.971476
S. Mukhopadhyay, Bindu Jain
A number of well known methods exist for solving Markov decision problems (MDP) involving a single decision-maker with or without model uncertainty. Recently, there has been great interest in the multi-agent version of the problem where there are multiple interacting decision makers. However, most of the suggested methods for multi-agent MDPs require complete knowledge concerning the state and action of all agents. This, in turn, results in a large communication overhead when the agents are physically distributed. In this paper, we address the problem of coping with uncertainty regarding the agent states and action with different amounts of communication. In particular, assuming a known model and common reward structure, hidden Markov models and techniques for partially observed MDPs are combined to estimate the states or actions (or both) of other agents. Simulation results are presented to compare the performances that can be realized under different assumptions on agent communications.
{"title":"Multi-agent Markov decision processes with limited agent communication","authors":"S. Mukhopadhyay, Bindu Jain","doi":"10.1109/ISIC.2001.971476","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971476","url":null,"abstract":"A number of well known methods exist for solving Markov decision problems (MDP) involving a single decision-maker with or without model uncertainty. Recently, there has been great interest in the multi-agent version of the problem where there are multiple interacting decision makers. However, most of the suggested methods for multi-agent MDPs require complete knowledge concerning the state and action of all agents. This, in turn, results in a large communication overhead when the agents are physically distributed. In this paper, we address the problem of coping with uncertainty regarding the agent states and action with different amounts of communication. In particular, assuming a known model and common reward structure, hidden Markov models and techniques for partially observed MDPs are combined to estimate the states or actions (or both) of other agents. Simulation results are presented to compare the performances that can be realized under different assumptions on agent communications.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"30 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":"127100976","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.2001.971494
K. D. Maier
Controlling the model of a movement system based on the dynamics of biological hopping and running is investigated. This movement system consists merely of a massless spring attached to a point mass. It describes a fast three-dimensional legged locomotion on even grounds. Rapidly moving legged autonomous systems require different hardware layouts and control approaches in contrast to slow moving ones. The spring mass system is a model that describes this principle movement as well as the principle control task. Multilayer-perceptrons are used to implement neurocontrollers suitable for such a movement system. They are proved to be suitable for exact control of the movement with a relatively small number of neurons. This is also shown by an experiment where the environment of the spring-mass system has been changed from even to uneven ground. The neurocontroller performs well without being trained for it.
{"title":"Neural network based control of legged hopping systems","authors":"K. D. Maier","doi":"10.1109/ISIC.2001.971494","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971494","url":null,"abstract":"Controlling the model of a movement system based on the dynamics of biological hopping and running is investigated. This movement system consists merely of a massless spring attached to a point mass. It describes a fast three-dimensional legged locomotion on even grounds. Rapidly moving legged autonomous systems require different hardware layouts and control approaches in contrast to slow moving ones. The spring mass system is a model that describes this principle movement as well as the principle control task. Multilayer-perceptrons are used to implement neurocontrollers suitable for such a movement system. They are proved to be suitable for exact control of the movement with a relatively small number of neurons. This is also shown by an experiment where the environment of the spring-mass system has been changed from even to uneven ground. The neurocontroller performs well without being trained for it.","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":"130620797","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：