This paper develops and evaluates a low-cost parallel computing platform for the implementation of parallel algorithms in Power engineering applications. The proposed approach utilises an existing local area network w...
详细信息
ISBN:
(纸本)0852967918
This paper develops and evaluates a low-cost parallel computing platform for the implementation of parallel algorithms in Power engineering applications. The proposed approach utilises an existing local area network without incurring any additional hardware costs. Application of computational intelligence techniques based on the developed computing platform to the economic dispatch problem is outlined. The performance of geneticalgorithms in parallel and cluster structures and their abilities in coping time constraint applications are also demonstrated. It is found that when the workload is large, a parallel computing structure should be exploited for cost-effectiveness purpose.
The application of neural networks (NNs) as a direct inverse controller for general nonlinear systems is considered Since little knowledge of the nonlinear plant is normally available, it is difficult to obtain an ana...
详细信息
The application of neural networks (NNs) as a direct inverse controller for general nonlinear systems is considered Since little knowledge of the nonlinear plant is normally available, it is difficult to obtain an analytical expression for the plant Jacobian. Thus, an emulator is required as a channel to compute the derivative of the system output with respect to its input for NN training. Neural network training using geneticalgorithms (GAs) offer several advantages. No understanding of the plant model is required. Also, since no derivative computations are involved, it is less likely for these algorithms to get trapped in local minima. The scheme imitates nature's cleansing phenomena of natural selection and survival of the fittest to generate individual controllers with the best fitness values. A hybrid coding method and several appropriate modifications of the classical geneticalgorithms for NN control purposes are discussed. To overcome the difficulties of saturation and fluctuation in the controller output, the output of the NN controller is obtained as the sum of several small sigmoidal functions. This effectively increases the linear range of operation of controller output without affecting the nonlinear feature of a sigmoidal function It is noted in this case that, better control is achieved. Fuzzy logic with dynamic features is used to provide an optimal direction for genetic search. It, thus, speeds up the process of convergence by bringing the chromosomes near to the problem space and bringing more exploration amongst the most desirable ones. The method is demonstrated with the control of a single-link flexible manipulator.
This paper presents an evaluation system for the dynamic control of TETRA radio systems. Detailed link-level simulation results are controlled by event driven system level simulations which allows the operation of the...
详细信息
This paper presents an evaluation system for the dynamic control of TETRA radio systems. Detailed link-level simulation results are controlled by event driven system level simulations which allows the operation of the overall system to be emulated accurately but with relatively low computational overhead. The system is particularly useful for studying the behaviour of adaptive algorithms when the system is in a transition between different states, and for predicting the Quality of Service delivered to the end user.
The broad range of issues related to the industrial exploitation of model predictive control (MPC) are discussed. By demonstration projects on mainstream process applications, developments of software tools to minimiz...
详细信息
The broad range of issues related to the industrial exploitation of model predictive control (MPC) are discussed. By demonstration projects on mainstream process applications, developments of software tools to minimize engineering costs and embedding MPC with the plant regulatory control system, such barriers can be minimized. Successful control encompasses two major issues, such as driving the line to its optimum operating point, and maintaining control through variations in characteristics. The developments done on a genetic algorithm based non-linear controller are also discussed.
This paper presents a genetic algorithm to solve the orienteering problem, which is concerned with finding a path between a given set of control points, among which a start and an end point are specified, so as to max...
详细信息
The application of neural nets (NN) as a direct inverse controller for general nonlinear systems is considered. Since little knowledge of the nonlinear plant is normally available, it is difficult to obtain an analyti...
The application of neural nets (NN) as a direct inverse controller for general nonlinear systems is considered. Since little knowledge of the nonlinear plant is normally available, it is difficult to obtain an analytical expression for its Jacobian. Thus, an emulator is required as a channel to compute the derivative of the output with respect to the input for NN training. Neural net training using geneticalgorithms (GA) offers several advantages. No understanding of the plant model is required. Since no derivative computations are involved, it is less likely for these algorithms to get trapped in local minima. The scheme generates individual controllers with the best fitness values. A hybrid coding method and several appropriate modifications of the classical geneticalgorithms for NN control purposes are discussed. To overcome the difficulties of saturation and fluctuation in the controller output, the output of the NN controller is obtained as the sum of several small sigmoidal functions. This effectively increases the linear range of operation of controller output without affecting the nonlinear feature of a sigmoidal function. It is noted in this case that, better control is achieved. Fuzzy logic with dynamic features is used to provide an optimal direction for genetic search. It, thus, speeds up the process of convergence by bringing the chromosomes near to the problem space and bringing more exploration amongst the most desirable ones. The method is demonstrated with the control of a single-link flexible manipulator.
The use of multiobjective geneticalgorithms (MOGA) as a powerful decision-making aid for the control system designer is discussed. This approach uses a rank-based fitness assignment, where the rank of a certain indiv...
详细信息
The use of multiobjective geneticalgorithms (MOGA) as a powerful decision-making aid for the control system designer is discussed. This approach uses a rank-based fitness assignment, where the rank of a certain individual at a particular generation is related to the number of inidividuals in the current popyulation by which it is dominated. Fitness is assigned by interpolating from the best individual to the worst, and then the fitness assigned to individuals with the same rank is averaged where the global population fitness is kept constant. Using this approach it is possible to search for many Pareto-optimal solutions concurrently, while concentrating on relevant regions of the Pareto set.
A technique, dynamic integrated optimization and parameter estimation (DISOPE), used for solving optimal control problems was discussed. The method was used to solve optimal control problems where there were differenc...
详细信息
A technique, dynamic integrated optimization and parameter estimation (DISOPE), used for solving optimal control problems was discussed. The method was used to solve optimal control problems where there were differences in structure and parameter values between reality and the model employed in the computations. algorithms were developed in both continuous and discrete time for a general nonlinear optimal control problem with terminal weighting, bounded controls and terminal constraints. The results show that inequality constraints on control and state variables could also be handled using the DISOPE technique.
A genetic programming paradigm using Lindenmayer system re-writing grammars is proposed as a means of specifying robot behaviors for autonomous navigation of mobile robots in uncertain environments. The concise nature...
详细信息
genetic programming has rarely been applied to manufacturing optimisation problems. In this report we investigate the potential use of genetic programming for the solution of the one-machine total tardiness problem. C...
详细信息
暂无评论