{"title":"Deterministic Learning and Pattern-Based NN Control","authors":"Cong Wang, Tengfei Liu, Chenghong Wang","doi":"10.1109/ISIC.2007.4450875","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450875","url":null,"abstract":"A deterministic learning theory was recently presented for identification, control and recognition of nonlinear dynamical systems. In this paper, we propose a pattern-based neural network (NN) control approach based on the deterministic learning theory. Firstly in the training phase, the definitions of dynamical patterns normally occurred in closed-loop control are given. The closed-loop system dynamics corresponding to the dynamical patterns are identified via deterministic learning. The representation, similarity definition and rapid recognition of dynamical patterns in closed-loop are also presented. A set of pattern-based NN controllers are constructed using the knowledge obtained from deterministic learning. In the test phase, secondly, a pattern classification system is introduced which can rapidly recognize the dynamical patterns in closed-loop. If the dynamical pattern for a test control task is recognized as very similar to a previous training pattern, then the NN controller corresponding to the training pattern is selected and activated, which can achieve exponential stability and guaranteed performance of the closed-loop control system without readaptation and high control gains. The proposed pattern-based NN control approach may provide insight into human's ability to learn and control and possibly lead to smarter robots.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128799248","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":"Discrete-time JLQG with dependently controlled jump probabilities","authors":"Yan-Kai Xu, X. Chen","doi":"10.1109/ISIC.2007.4450926","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450926","url":null,"abstract":"Jump linear quadratic Gaussian (JLQG) model is well studied due to its wide applications. The existing studies on JLQG model with controlled jump probabilities usually impose an assumption that jump probabilities are independent and separately controlled. However, in some practical systems, their jump probabilities may not be independent of each other. In this paper, we study JLQG model with dependently controlled jump probabilities and formulate it as a two-level control problem. We propose an approach to calculate its performance gradient with respect to jump probabilities and develop a gradient-based optimization algorithm. We present an application of manufacturing system to illustrate the main results of this paper.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126503070","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":"Near Optimal Neural Network-based Output Feedback Control of Affine Nonlinear Discrete-Time Systems","authors":"Qinmin Yang, S. Jagannathan","doi":"10.1109/ISIC.2007.4450950","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450950","url":null,"abstract":"In this paper, a novel online reinforcement learning neural network (NN)-based optimal output feedback controller, referred to as adaptive critic controller, is proposed for affine nonlinear discrete-time systems, to deliver a desired tracking performance. The adaptive critic design consist of three entities, an observer to estimate the system states, an action network that produces optimal control input and a critic that evaluates the performance of the action network. The critic is termed adaptive as it adapts itself to output the optimal cost-to-go function which is based on the standard Bellman equation. By using the Lyapunov approach, the uniformly ultimate boundedness (UUB) of the estimation and tracking errors and weight estimates is demonstrated. The effectiveness of the controller is evaluated for the task of nanomanipulation in a simulation environment.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116542798","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":"A Fuzzy PID Thermal Control System for Die Casting Processes","authors":"Tiebao Yang, Xiang Chen, Henry Hu","doi":"10.1109/ISIC.2007.4450917","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450917","url":null,"abstract":"In high-pressure die casting processes, proper control of die temperature is essential for producing superior quality components and yielding high production rates. However, die temperature distribution depends on various die design and process variables for which accurate models are normally very difficult to obtain. In this paper, a new intelligent control scheme is proposed for die thermal management. In this scheme, extra cooling water lines controlled by a pump and solenoid valves are attached to each established cooling channel. A fuzzy PID controller is designed to minimize the temperature differences between channels. Some implementation issues such as latency have been discussed. The experimental results obtained from a laboratory die casting process simulator indicate that the developed control system is capable of adjusting the desired supply of cooling water into multiple cooling lines so that the local temperature distribution of the die insert may become more homogeneous.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131488111","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":"Image Based Visual Servoing Using Takagi-Sugeno Fuzzy Neural Network Controller","authors":"Miao Hao, Zeng-qi Sun, Masakazu Fujii","doi":"10.1109/ISIC.2007.4450860","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450860","url":null,"abstract":"In this paper, a Takagi-Sugeno fuzzy neural network controller (TS-FNNC) based image based visual servoing (IBVS) method is proposed. Firstly, the eigenspace based image compression method is explored which is chosen as the global feature transformation method. After that, the inner structure, performance and training method of T-S neural network controller are discussed respectively. Besides, the whole architecture of the TS-FNNC is investigated. No artificial mark is needed in the visual servoing process. No priori knowledge of the robot kinetics and dynamics or camera calibration is needed. The method is implemented and validated on a Motoman UP6 based eye-in-hand platform and the experimental results are also reported in the end.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116524030","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":"A Discrete Time Optimal Control Solution for Hard Disk Drives Servo Design","authors":"Shaohua Hu, Zhiqiang Gao","doi":"10.1109/ISIC.2007.4450900","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450900","url":null,"abstract":"This paper concerns with the challenge in high performance motion control systems, typified by the computer hard disk drive positioning control problem. Not only such systems seek very high accuracy, there is also an insatiable appetite for speed. To make the problem more challenging, the design has to address the actuator saturation issue. This is, in essence, a time optimal control problem and a novel solution, a discrete time optimal control law, is proposed in this paper. It is shown that such solution is: (1) a single controller that unifies the separate track-seeking and track-following control functions in existing methods; (2) robust against unknown resonant modes; and (3) easy to implement and tune. The new control law is compared with existing methods and the results are quite promising in simulation studies of two different hard disk drives.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130383391","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":"A Modified Approach to Observer-based Fault Detection","authors":"F. Chowdhury, Wen Chen","doi":"10.1109/ISIC.2007.4450943","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450943","url":null,"abstract":"This paper presents a practical and useful modification to the observer-based fault detection technique so that the fault indicator is independent of the observer gain. To this end, the notion of \"Total Measurable Fault Information Residual\" (ToMFIR) is utilized. It is shown that the conventional fault indicator used in observer-based approaches (the observer output residual), being a function of the observer gain, is not totally reliable for the detection of small faults. We present a simple modification that results in a fault indicator which approaches the ToMFIR in the limit, if the fault function approaches a constant. A DC motor example is simulated in Matlab environment to illustrate the effectiveness of the modified observer residual as a fault indicator.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115543398","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":"Multiple Hierarchical Reasoning in Uncertain Situations for Complex Device Fault Diagnosis","authors":"Yushu Lai, Xunbo Li, Yan Xiong","doi":"10.1109/ISIC.2007.4450942","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450942","url":null,"abstract":"An efficient diagnostic method is proposed for complex device fault diagnosis. In rule-based reasoning, an efficient retrieving strategy is crucial. The generic retrieving method is based on a diagnostic tree built according to the hierarchical decomposition of devices, but it is difficult to achieve such diagnostic tree for some complex devices. So a multiple hierarchical diagnosis method based on fault categories is proposed. And then, the retrieving priorities of rules in a certain diagnostic level are determined based on a fuzzy multi-attribute group decision-making method, which can more effectively work out the priority factors. Based on this diagnostic method, a fault diagnosis system for intelligent instruments was developed based on SQL2005 database. And comparison between two systems is presented to validate the diagnostic method.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114827194","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":"Broadcasting Performance Comparison Among IVC MAC Protocol Candidates","authors":"Xianbo Chen, H. Refai, Xiaomin Ma","doi":"10.1109/ISIC.2007.4450854","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450854","url":null,"abstract":"Inter-vehicle communication (IVC) is essential for any intelligent transportation system implementation. In North America, dedicated short range communication (DSRC) protocol based on carrier sense multiple access with collision avoidance (CSMA/CA) was proposed. At the same time, in Europe, IVC implementation is based on R-ALOHA medium access protocol. In this paper we conduct a performance comparison between CSMA/CA and R-ALOHA protocols in a mobile environment while vehicles broadcast their messages. Computer simulation is used to obtain performance parameters such as delay, throughput, and packet delivery ratio. The results reveal that while the delay performance of both protocols is acceptable, the system throughput of CSMA/CA performs worse when being compared to R-ALOHA. Packet delivery ratio characteristics are also shown through simulation.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115009041","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":"Hybrid H∞ state feedback control for discrete-time switched linear systems","authors":"Hai Lin, P. Antsaklis","doi":"10.1109/ISIC.2007.4450870","DOIUrl":"https://doi.org/10.1109/ISIC.2007.4450870","url":null,"abstract":"In this paper, the co-design of continuous-variable controllers and discrete-event switching logics, both in state feedback form, for discrete-time switched linear control systems is investigated. Sufficient synthesis conditions for this co-design problem are proposed here in the form of bilinear matrix inequalities, which is based on the argument of multiple Lyapunov functions. The closed-loop switched system forms a special class of piecewise linear hybrid systems, and is shown to be exponentially stable with a finite l2 induced gain.","PeriodicalId":184867,"journal":{"name":"2007 IEEE 22nd International Symposium on Intelligent Control","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122772282","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}