Prediction model based on improved particle swarm optimization algorithm analysis and its application scenario building

Aimed at the very nonlinear and vulnerability of differing cost of building changes, another technique for differing cost of building destruction in view of Enhanced Particle Swarm Optimization (EPSO) back propagation has been proposed. By presenting transformation operation and versatile modify of dormancy weight, the issue of simple to fall into neighborhood ideal, untimely, low exactness and low later interation effectiveness of Particle Swarm Optimization are comprehended. By utilizing the Enhanced Particle Swarm Optimization to streamline Back Propagation neural network's parameters, the learning rate and optimization capacity of traditional Back Propagation are adequately moved forward. At that point the versatile molecule swarm optimization calculation taking into account cloud hypothesis was utilized to improve the weights and edges of wavelet Back propagation neural network, Instead of customary inclination drop strategy. The reproduction aftereffects of differing cost of building expectation demonstrate that the anticipate exactness of the new strategy is altogether higher than that of ordinary Back Propagation neural network and wavelet neural network technique. What's more, the technique is viable and attainable.