Hybrid Particle Swarm Optimization And Its Application In Embedded Intelligent Control

In this paper, some hybrid intelligent computing method including Neural Network(NN), Fuzzy Logic(FL), Simulated Annealing(SA) etc, as well as its application have been researched systematically in both theory and experiment based on particle swarm optimization algorithm.The thesis researched deeply particle swarm optimization algorithm. The concept of aggregation degree of particle swarm has been proposed. The particles' diversity was improved through periodically monitoring aggregation degree of the particle swarm. On the later development of the PSO algorithm, adopting mutation strategy to the best particle's position enhances its ability of jumping out the local minima. Through further analysis to the improved algorithm, the thesis proposed an algorithm of mutation to individual best position, which can increase activity of particle in a greater degree and enhances the optimization performance. Combining SA optimization technique, the hybrid PSO algorithm embedded the improved SA was proposed. The probability-sudden-jump character of SA can avoid getting into local minima of PSO algorithm effectively. Meanwhile, applying parallel PSO and adopting improved SA optimization mechanism, the dissatisfactory time character of the SA algorithm could be made better. The computer simulating indicated the algorithm is an effective optimized method. Moreover, the research showed the solution form of random optimizing search algorithm along with the neighbourhood structure would take a great effect on the speed and precision of algorithm convergence.In the research of forwardfeed neural network(FNN) based on PSO algorithm, the FNN learning algorithm based on the improved PSO algorithm(PSOFNN) has been proposed, in which the derivative information is not requisite. PSOFNN has overcome the defection of the traditional learning algorithm easily to fall into the local minima and has a good property of initial robustness. In the research of learning algorithm on FNN's variable structure based on PSO, the PSOFNN algorithm could optimize the NN's weight and the number of the hide layer of NN automatically, which provides a new method for design of NN.According the industry washing machine fuzzy control system, the model building method of industry washing machine based on neural network has been proposed. Based on the proposed hybrid PSO algorithm in this paper, the training strategy which could rise generalization performance and decrease generalization error of NN has been proposed. The learning function based on the NN of industry washing machine and its realizing method as well as washing speed design and evenly distributing process control method have been approached. The thesis discussis the general solution of embedded intelligent control system for industry washing machine and system task model dividing along with the system flow diagram. The hardware platform based on the ARM chip and the software platform based on theμC/OS-Ⅱreal time operation system have been established while the realize mechanism of NN intelligent control has been studied in embedded soft-hardware platform. At last, the realization of friendly GUI for embedded system has been discussed.