Tool wear states recognition based on genetic algorithm and back propagation neural network model

The recognition model of tool wear states based on genetic algorithm and back propagation (BP) network is proposed. There are some disadvantages in BP algorithm, such as low rate of convergence, easily falling into local minimum point and weak global search capability. In order to settle these problems, genetic algorithm is used to optimize BP neural network. At first, the genetic algorithm is used to optimize the weights and threshold values of BP neural network when its topology is determined. Then the stable weights and threshold values can be obtained after a number of generations´ crossover and mutation. Assign them to the BP neural network as the initial value and retrain the network. The global optimal solution of the network parameters can be obtained in this way, and the performance of condition recognition network can be improved. The experimental results show that the neural network optimized by genetic algorithm greatly improves the efficiency and accuracy of the tool wear states recognition system.