The application of AnfIS (Adaptive network-based Fuzzy Inference System) to the fuzzy control of structures was investigated by the authors in a earlier paper (L. Faravelli and T. Yao, 1994). Through neural network le...
详细信息
The application of AnfIS (Adaptive network-based Fuzzy Inference System) to the fuzzy control of structures was investigated by the authors in a earlier paper (L. Faravelli and T. Yao, 1994). Through neural network learning, AnfIS can be trained to replace an existing fuzzy controller. The resulting controller makes use of the more efficient Takagi-Sugeno inference scheme instead of COG (center of gravity) and is inherently computationally faster. The next logical step accomplished in this paper is to implement the trajectory adaptive networks (TAN) and stage adaptive networks (SAN) that were proposed to be used with temporal back propagation to achieve a self learning fuzzy controller. This approach should result in a fuzzy controller that is optimized to handle loads of the type used in the self learning training. Because the learning process is goal directed (i.e., a zero vector is the desired displacement behavior), some optimization is introduced.
Recent work has demonstrated the ability of neural-network-based controllers to optimize and control machines with complex, non-linear, relatively unknown control spaces. We present a brief overview of neural networks...
Recent work has demonstrated the ability of neural-network-based controllers to optimize and control machines with complex, non-linear, relatively unknown control spaces. We present a brief overview of neural networks via a taxonomy illustrating some capabilities of different kinds of neutral networks. We present some successful control examples, particularly the optimization and control of a small-angle negative ion source.
作者:
LI, WTSING HUA UNIV
NATL LAB INTELLIGENT TECHNOL & SYSTDEPT COMP SCIBEIJING 100084PEOPLES R CHINA
This paper presents a strategy for optimization of a fuzzy logic controller based on a control scheme, which consists of a fuzzy logic (FL) controller and a conventional derivative (D) controller. For this purpose, we...
详细信息
ISBN:
(纸本)0780318978
This paper presents a strategy for optimization of a fuzzy logic controller based on a control scheme, which consists of a fuzzy logic (FL) controller and a conventional derivative (D) controller. For this purpose, we first choose a set of membership functions regarding change-in-error e, which represent the feedback of velocity. Then we optimize them using neural network in self-organizing process. To demonstrate the effectiveness of the proposed method, we report a number of simulation results involving both step and tracking control of a nonlinear plant.
The Experimental Physics and Industrial control System (EPICS), has been used at a number of sites for performing data acquisition, supervisory control, closed-loop control, sequential control, and operational optimiz...
The Experimental Physics and Industrial control System (EPICS), has been used at a number of sites for performing data acquisition, supervisory control, closed-loop control, sequential control, and operational optimization. The EPICS architecture was originally developed by a group with diverse backgrounds in physics and industrial control. The current architecture represents one instance of the ''standard model''. It provides distributed processing and communication from any local area network (LAN) device to the front end controllers. This paper presents the current architecture, performance envelope, current installations, and planned extensions for requirements not met by the current architecture.
This paper presents a strategy for optimization of a fuzzy logic controller based on a control scheme, which consists of a fuzzy logic controller and a conventional derivative controller. For this purpose, we first ch...
详细信息
ISBN:
(纸本)078031896X
This paper presents a strategy for optimization of a fuzzy logic controller based on a control scheme, which consists of a fuzzy logic controller and a conventional derivative controller. For this purpose, we first choose a set of membership functions regarding change-in-error e/spl dot/, which represent the feedback of velocity. Then we optimize them using neural network in self-organizing process. To demonstrate the effectiveness of the proposed method, we report a number of simulation results involving both step and tracking control of a nonlinear plant.< >
Based on the optimization theory and LaGrange multipliers concept, a novel strategy for "fair" and "economic" resource sharing in an ATM network is proposed in the paper. The main essence of propos...
详细信息
ISBN:
(纸本)0818665955
Based on the optimization theory and LaGrange multipliers concept, a novel strategy for "fair" and "economic" resource sharing in an ATM network is proposed in the paper. The main essence of proposed strategy is to confirm the minimal cost waste, that is the minimal cell loss in the ATM network, under the various negotiated Quality of Services (QoS). By doing so, consumers (senders of services) can obtain a fair share of the resources under their QoS requirements and the provider of broadband ISDN services will possess an economic operation. The tactics are realized by using the MatLab tool in a workstation.
This paper newly proposes a unified approach for frequency assignment of any macro and micro cellular networks having irregular cell shapes and non-uniform traffic distribution. This approach copes with network evolut...
详细信息
This paper newly proposes a unified approach for frequency assignment of any macro and micro cellular networks having irregular cell shapes and non-uniform traffic distribution. This approach copes with network evolution such as growth of traffic and service area as well as initial frequency assignment. The approach is effective for spectrum conservation in flexible assignment for time-variant traffic and provides a guideline on frequency utilization in dynamic assignment. The paper presents efficient algorithms based on combinatorial optimization, whose excellent performance is demonstrated by simulation results. The algorithms provide optimum or quasi-optimum solution with the computing time of polynomial order.< >
The successful application of speech recognition systems to new domains greatly depends on the tuning of the architecture to the new task, especially if the amount of training data is small. In this paper we present 1...
详细信息
This paper deals with the on-site evaluation of PRODYN traffic control method. The idea of PRODYN was inspired by studies on the off-line computation of a short sample time optimal control of an intersection using Bac...
详细信息
ISBN:
(纸本)085296398X
This paper deals with the on-site evaluation of PRODYN traffic control method. The idea of PRODYN was inspired by studies on the off-line computation of a short sample time optimal control of an intersection using Backward Dynamic Programming. From that initial point, research has been conducted since 1978 it has consisted of: finding a suboptimal optimization method to compute the controls on-line;finding the best method for coordination of intersections controllers;developing a queue estimator;improving the traffic model used. The simulation tests realized during this research showed the interest of the method, and on site experiments were conducted in 1987 on an isolated intersection and in 1988 on a 7 intersections network. The first section of this paper presents the tested algorithm. The second section is devoted to the implementation of a PRODYN prototype on the system of the Zone Experimentale et Laboratoire de Trafic de Toulouse (ZELT). The last section presents the evaluation of the control strategy on the isolated intersection and the network.
The future points to the development of an expert system which switches on when certain levels of congestion are reached and defines remedial congestion signal control to override the timings defined by conventional s...
详细信息
ISBN:
(纸本)085296398X
The future points to the development of an expert system which switches on when certain levels of congestion are reached and defines remedial congestion signal control to override the timings defined by conventional systems. This paper begins by describing the role traffic detection systems play in enabling an expert system to define remedial control strategies for congestion management. It highlights the need for algorithms to infer the traffic conditions and route patterns in a city network and justifies the need to study the origin and destinations of all vehicles entering, leaving and travelling within a subarea of a SCOOT (Split Cycle Offset optimization Technique) system, whilst simultaneously monitoring traffic with SCOOT detectors. Finally, the design and results of a number plate survey is described.
暂无评论