{"title":"Temporal Petri nets, a modeling and control tool of manufacturing lines","authors":"N. Mouss, L. Mouss","doi":"10.1109/ISIC.1999.796621","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796621","url":null,"abstract":"Two basic tools are used in our approach. Firstly, temporal Petri nets provide elegant models for timed systems. The obtained models are general, including any structure type such as synchronizations and conflicts. Secondly, timed automata constitute a formal framework for proofs with the objective of performance evaluation and the synthesis of the control laws. These topics correspond to our current research with an application in the domain of manufacturing lines without intermediate buffers.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134008155","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}
{"title":"Emotions and intelligent choice: feasibility, seriousness, and admissibility","authors":"M. Goodrich","doi":"10.1109/ISIC.1999.796632","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796632","url":null,"abstract":"Emotions and rationality have often been treated as opponents, with emotions taking on the role of villain and rationality taking on the role of heroine. Recently, however, the positive role of emotions has received considerable attention, and resulted in the elevation of emotion to rationality's equal. With emotion's change of status, artificial and computational intelligence researchers have begun to model and use emotions as a constructive portion of designing machines and describing humans. Building on the idea that emotions are generated by past actions (or, at least by the consequences produced by past actions) and are used to determine future actions, it is desirable to create a computational framework capable of representing these dynamics. Employing the hypothesis that some aspects of emotional state result from positive influences and other aspects result from negative influences, we can determine conditions when an action is a feasible possibility, a serious possibility, and an admissible choice.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"232 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133264844","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}
{"title":"Underground pipe cracks classification using image analysis and neuro-fuzzy algorithm","authors":"S. Sinha, F. Karray, P. Fieguth","doi":"10.1109/ISIC.1999.796688","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796688","url":null,"abstract":"Pipeline surface defects such as cracks cause major problems for asset managers, particularly when the pipe is buried under the ground. The manual inspection of surface defects in the underground pipes has a number of drawbacks, including subjectivity, varying standards, and high costs. Automatic inspection systems using image processing and artificial intelligence techniques can overcome many of these disadvantages and offer asset managers an opportunity to significantly improve quality and reduce costs. A recognition and classification method for pipe cracks using image analysis and a neuro-fuzzy algorithm is proposed. In the pre-processing step, the cracks in the pipe are extracted from the homogenous background. Then, based on prior knowledge of cracks, five normalised features are extracted. In the classification step, a neuro-fuzzy algorithm is proposed that employs a trapezoidal fuzzy membership function and modified error backpropagation algorithm.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124976216","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}
{"title":"Neuro-dynamic programming based on self-organized patterns","authors":"J. Si, Y.-T. Wang","doi":"10.1109/ISIC.1999.796641","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796641","url":null,"abstract":"This paper introduces a real-time learning control mechanism, as a robust and efficient scheme of neuro-dynamic programming. The objective of the learning controller is to optimize a certain performance measure by learning to create appropriate control actions through interacting with the environment. The controller is set out to learn to perform better over time starting with no prior knowledge about the system. The system under consideration does not render a complete system model describing its behaviors. Instead, real-time sampled measurements are available to the designer. The state measurements are first analyzed by similarity and organized by proximity. Control actions are then generated in relevance to the state patterns. A critic network serves the purpose of 'monitoring' the performance of the controller to achieve a given optimality. We provide detailed implementation, and performance evaluations of this learning controller in a cart-pole balancing problem.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128580764","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}
{"title":"Emotions as forms of consciousness","authors":"E. Táborský","doi":"10.1109/ISIC.1999.796630","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796630","url":null,"abstract":"In the physico-chemical, the biological, and the conceptual realms, energy processes (understood as work or heat transfers) are thermodynamically both conservative and generative. We observe a conservation of form and process and an entropic heterogeneity of form and process. The result of this hierarchical interaction is information. By information, the author understands matter or energy that is capable of work; it permits energy to do things to other things. This means that energy as information operates within relations. The continuous expansion of information is evolution, where \"the whole universe is approaching in the infinitely distant future a state having a general character different from that toward which we look back in the infinitely distant past\". It is an axiom of this paper that, as Peirce (1935-38) pointed out, \"everywhere the main fact is growth and increasing complexity\" and \"the variety of the universe is forever increasing\". How does this evolution of information process take place? The methods of explanation have ranged from the vitalistic intentions of the gods to the accidental mechanisms of mutation. Are these the only two answers?.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125757393","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}
{"title":"Control of a high-order power system by neural adaptive feedback linearization","authors":"K. Fregene, D. Kennedy","doi":"10.1109/ISIC.1999.796626","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796626","url":null,"abstract":"Discusses the design of an adaptive feedback linearizing excitation controller/power system stabilizer using neural networks, for a high order single machine/infinite bus power system model. The neural networks are used to identify a discrete-time nonlinear dynamical model of the system. Although the controller itself is not implemented using a neural network, it adaptively uses the parameter estimates given by the neural system model to determine an appropriate feedback linearizing control law at each discrete time step. This approach avoids the requirement for exact knowledge of the plant and other difficulties associated with implementing analytical input-output feedback linearizing controllers for complex power systems. Simulation results demonstrate voltage tracking, damping of power angle oscillations and the possibility of user-specified dynamics.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117100933","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}
{"title":"The use of convex programming on fuzzy model based predictive control","authors":"J. Espinosa, J. Vandewalle","doi":"10.1109/ISIC.1999.796690","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796690","url":null,"abstract":"Some key ideas about the use of fuzzy models in predictive control are presented. The discussion is extended to the use of interior point methods to solve the optimization problem in predictive control problems. The use of interior point methods opens the door to the formulation of robust optimization problems and by using this formulation a robust model predictive control strategy can be formulated. The paper shows such a formulation and explains how the Takagi-Sugeno description of a fuzzy model can be very efficient to formulate the uncertainties.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130624374","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}
{"title":"Self-organizing CMAC neural networks and adaptive dynamic control","authors":"Jianjuen J. Hu, G. Pratt","doi":"10.1109/ISIC.1999.796665","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796665","url":null,"abstract":"A self-organizing CMAC neural network mechanism and an CMAC based adaptive control scheme are presented. Two main efforts have been made in this study. One is on the self-organizing mechanism of CMAC neural network. The CMAC basis functions with a stair-waveform are introduced. A data clustering technique is used in reducing the memory size significantly and a structural adaptation technique is developed in order to accommodate new data sets. Another effort is on the unsupervised learning scheme, which is based on a Lyapunov index function. Adaptive dynamic control is implemented by means of the self-organizing CMAC neural network, and it can identify the unmodelled dynamics of a plant and ensures asymptotic system stability in a Lyapunov sense. The adaptive control system has been applied in the locomotion control of a bipedal walking robot successfully in simulation.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130912593","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}
{"title":"An effective transfer of autonomous control technology","authors":"M. Jarriel, D. Adams, M. Hissa, F. Vasques","doi":"10.1109/ISIC.1999.796676","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796676","url":null,"abstract":"Northrop Grumman Corporation, Oceanic and Naval Systems (NG-O&NS) has built unmanned undersea vehicles (UUVs) with limited levels of autonomous control for years. Facing requirements of more complex and complete levels of autonomy, we searched for existing technologies that would provide an affordable, minimal complexity, testable, reusable approach. Through discussions with the Applied Research Laboratory at Pennsylvania State University (ARL/PSU), it became apparent that existing NG-ON&S vehicle guidance and control technologies could be structured within the ARL/PSU prototype intelligent controller (PIC), which was originally developed under ONR funding. NG-O&NS forged a close relationship with ARL/PSU as we mapped our autonomous control concept to the PIC architecture and developed a prototype autonomous sortie controller (ASC). NG-O&NS successfully conducted an in-water test series demonstrating the ASC onboard the Naval Underseas Warfare Center (NUWC) 21UUV in the Spring of 1999.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130889425","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}
{"title":"Intelligent scheduling of chemical plants: a constraint programming approach","authors":"M. Stobbe, S. Engell","doi":"10.1109/ISIC.1999.796662","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796662","url":null,"abstract":"The applicability of constraint programming to the task of scheduling batch and mixed batch/continuous plants in the chemical industry is investigated. The main features of constraint programming are described, emphasizing possible advantages when applied to the scheduling task. Based on the results, an architecture for a reactive scheduling system is outlined. The underlying strategy for developing a problem specific solution approach is described and applied to a real-world problem. Emphasis is given to the advantages gained by the use of a constraint programming language.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"213 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132719006","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}