Research on Genetic Neural Network Algorithm and Its Application

Abstract

The traditional BP neural network has a slow convergence speed and requires a long training time; it is easy to fall into a local optimum; the network is always of high redundancy; the learning and memory of the network are unstable. This paper uses a genetic algorithm to modify weights and thresholds of the neural network in order to obtain the global optimal value. The simulation results show that this method has the characteristics of strong detection ability of pollution concentration and high detection efficiency, which can help improve the accuracy and speed of detection of SO2 pollution concentration in urban air.