This paper proposes a novel approach based on artificial intelligence technologies (multi-objective Self-Exploration process based Intelligent Control System-mSEICS) for intelligent control systems. Not only can this ...
详细信息
This paper proposes a novel approach based on artificial intelligence technologies (multi-objective Self-Exploration process based Intelligent Control System-mSEICS) for intelligent control systems. Not only can this system adapt to various environments, but it can also continually improve its performance. The mSEICS consists of four basic functions, controller, receptor, m-adaptor and advancer. A five-layer fuzzy neural network is applied to implement the controller. The receptor is used to evaluate the performance of system. The m-adaptor (multi-objective based adaptor) that comprises two elements, action explorer and rule generator, can generate a variety of new action sets in order to adapt to various environments. The Pareto optimality based multi-objective genetic algorithm is proposed to implement the action explorer to discover multiple action sets, and the rule generator is employed to transform the action set to fuzzy rules. In addition, the advancer consisting of action discoverer and rule generator is constructed to produce the novel action set to enhance the system efficiency. The parallel-simulated annealing approach is presented to realize the action discoverer. An application of the robotic path planning is applied to demonstrate the proposed model. The simulation results show that the mobile robot can reach the target successfully in various environments, and the proposed model is more efficient than the similar model. (C) 2003 Elsevier B.V. All rights reserved.
This paper presents an efficient BIST scheme with low power consumption for sequential circuits. The BIST structure is obtained by using a ghost-FSM. A multi-objective genetic algorithm (MOGA) is employed to optimize ...
详细信息
ISBN:
(纸本)0769519512
This paper presents an efficient BIST scheme with low power consumption for sequential circuits. The BIST structure is obtained by using a ghost-FSM. A multi-objective genetic algorithm (MOGA) is employed to optimize the twin criteria of BIST quality and power consumption of the resultant circuit simultaneously. The scheme ensures enhancement of fault coverage along with minimization of power overhead of the BISTed circuits. Experimental results on MCNC benchmarks confirm the effectiveness of the proposed scheme to produce circuits with improved fault efficiency along with lower power consumption.
This paper presents the use of neural networks and a geneticalgorithm in time-optimal control of a closed-loop 3-dof robotic system. Extended Kohonen networks which contain an additional lattice of output neurons are...
详细信息
This paper presents the use of neural networks and a geneticalgorithm in time-optimal control of a closed-loop 3-dof robotic system. Extended Kohonen networks which contain an additional lattice of output neurons are used in conjunction with PID controllers in position control to minimize command tracking errors. The extended Kohonen networks are trained using reinforcement learning where the overall learning algorithm is derived from a self-organizing feature-mapping algorithm and a delta learning rule. The results indicate that the extended Kohonen network controller is more efficient than other techniques reported in early literature when the robot is operated under normal conditions. Subsequently, a multi-objective genetic algorithm (MOGA) is used to solve an optimization problem related to time-optimal control. This problem involves the selection of actuator torque limits and an end-effector path subject to time-optimality and tracking error constraints. Two chromosome coding schemes are explored in the investigation: Gray and integer-based coding schemes. The results suggest that the integer-based chromosome is more suitable at representing the decision variables. As a result of using both neural networks and a geneticalgorithm in this application, an idea of a hybridization between a neural network and a geneticalgorithm at the task level for use in a control system is also effectively demonstrated.
We are interested in a job-shop scheduling problem corresponding to an industrial problem. Gantt diagram's optimization can be considered as an NP-difficult problem. Determining an optimal solution is almost impos...
详细信息
We are interested in a job-shop scheduling problem corresponding to an industrial problem. Gantt diagram's optimization can be considered as an NP-difficult problem. Determining an optimal solution is almost impossible, but trying to improve the current solution is a way of leading to a better allocation. The goal is to reduce the delay in an existing solution and to obtain better scheduling at the end of the planning. We propose an original solution based on geneticalgorithms which allows to determine a set of good heuristics for a given benchmark. From these results, we propose a dynamic model based on the contract-net protocol. This model describes a way to obtain new schedulings with agent negotiations. We implement the agent paradigm on parallel machines. After a description of the problem and the genetic method we used, we present the benchmark calculations that have been performed on an SGI Origin 2000. The interpretation of these is a way to refine heuristics given by our evolution process and a way to constrain our agents based on the contract-net protocol. This dynamic model using agents is a way to simulate the behavior of entities that are going to collaborate to improve the Gantt diagram. (C) 2000 Elsevier Science B.V. All rights reserved.
With the aim of developing a flexible optimization method for managing conflict resolution, this paper concerns itself with site location problems under multi-objectives. As known from the term NIMBY (Not In My Back Y...
详细信息
With the aim of developing a flexible optimization method for managing conflict resolution, this paper concerns itself with site location problems under multi-objectives. As known from the term NIMBY (Not In My Back Yard), disposal site location problems of hazardous waste is an eligible case study associated with environmental and economic concerns. After describing the problem generally as a multi-objective mixed-integer program, we have proposed an intelligence supported approach that extends the hybrid geneticalgorithm developed by the author to derive the best-compromise solution, For this purpose, we have developed a novel modeling method of value function using neural networks, and incorporated it into the approach. As a result, we can provide a practical and effective method in which the hybrid strategy maintains its advantages of relying on good matches between the solution methods and the problem properties such as a geneticalgorithm for unconstrained discrete optimization and a mathematical program for constrained continuous ones. Finally, by taking an example formulated as a multi-objective mixed-integer linear program, we have examined the effectiveness of the proposed approach numerically.
暂无评论