A Novel Penetration State Recognition Method Based on LSTM With Auditory Attention During Pulsed GTAW

Abstract

Weld defect detection and control is of great significance for gas tungsten arc welding (GTAW) process of aluminum alloy, and the recognition of penetration states based on acoustic signal has been a hot topic. However, previous studies have ignored that acoustic features have distinct effects on the penetration state. In this paper, inspired by the attention mechanism in the vision, a novel auditory attention model combining the attention mechanism with long short-term memory (LSTM) network for penetration state recognition has been proposed. First, the 15-dimensional informative features including 9-dimensional time-domain and 6-dimensional wavelet features related to the penetration state are extracted. Second, the auditory attention mechanism is explored and the attention-based LSTM including attention mechanism before LSTM(AT-LSTM) and attention after LSTM(LSTM-AT) are established, which are experimentally verified to show greater performance than other traditional methods with an average accuracy of 93.56% and 95.32%, respectively. Furthermore, the attention vectors are visualized to figure out the mechanism of auditory attention when different penetration occurs.