Aiming at the problem of poor generalization ability and low recognition accuracy of single feature recognition algorithm

the time domain characteristics of typical target seismic wave signals is deeply analyzed

integrates multiple features to construct training samples

and uses BP neural network algorithm to identify targets.BP neural network is optimized by genetic algorithm aiming at shortcomings of slow convergence speed and poor generalization ability.Finally

the target recognition method based on GA-BP neural network is formed and verified by experiments.The results show that the GA-BP neural network algorithm is superior to the traditional algorithm in terms of convergence

accuracy and calculation speed.