Research on Multi-Static Active Sonar Target Recognition Based on Machine Learning

In modern sonar systems, the automatic recognition of underwater targets has always been one of the key technologies. Active sonar is easy to be found and evaded by enemy boats when it works because of the combination of transmitter and receiver. The detection capability of passive sonar for quiet submarines is very limited. The multi-static sonar adopts the allocation of transceiver and receiver, which has the characteristics of active sonar and passive sonar. Multi-static active sonar has become the focus of research in many countries due to its unique detection advantages. In recent years, artificial intelligence has been used in the field of target recognition. Compared with the traditional recognition method based on manual, the recognition method using machine learning can learn the features of different targets more comprehensively, and mine more deep-seated feature informa-tion of data, which can effectively improve the accuracy and efficiency of recognition.