Real-Time Underwater Acoustic Homing Weapon Target Recognition Based on a Stacking Technique of Ensemble Learning

Abstract

Underwater acoustic homing weapons (UAHWs) are formidable underwater weapons with the capability to detect, identify, and rapidly engage targets. Swift and precise target identification is crucial for the successful engagement of targets via UAHWs. This study presents a real-time target recognition method for UAHWs based on stacking ensemble technology. UAHWs emit active broadband detection signals that manifest distinct reflection characteristics on the target. Consequently, we have extracted energy and spatial distribution features from the target’s broadband correlation detection output. To address the problem of imbalanced original sea trial data, we employed the SMOTE algorithm to generate a relatively balanced dataset. Then, we established a stacking ensemble model and performed training and testing on both the original dataset and relatively balanced dataset separately. In conclusion, we deployed the stacking ensemble model on an embedded system. The proposed method was validated using real underwater acoustic homing weapon sea trial data. The experiment utilized 5-fold cross-validation. The results indicate that the method presented in this study achieved an average accuracy of 93.3%, surpassing that of individual classifiers. The model’s single-cycle inference time was 15 ms, meeting real-time requirements.