A Novel Approach for Surface Integrity Monitoring in High-Energy Nanosecond-Pulse Laser Shock Peening: Acoustic Emission and Hybrid-Attention CNN

The high energy, transient, and nanosecond pulse of laser shock peening (LSP) renders real-time monitoring of material surface integrity challenging. Along these lines, this article proposes a novel method for real-time evaluation of the surface quality in the LSP process based on the multiple acoustic emission (AE) technique and hybrid attention-based convolutional neural networks (HACNN). First, a new quality index, surface hardness integrity (SHI) is constructed to fully characterize both the hardening rate and the impact depth of the material surface, while a good linear relationship is demonstrated between SHI and AE. Then, a feature extraction method, called wavelet packet energy cepstrum (WPEC), is proposed that requires minor signal processing expertise while being able to adaptively match the modal distribution of the broadband AE signals. Next, WPEC is fed into HACNN, where HA consists of channel attention and multiscale spatial attention (MSA). MSA combines the information flow at the global time, local time, and local frequency. Moreover, numerous comparisons were conducted with several traditional cepstrum and advanced attention mechanisms. The effectiveness of the proposed method is carefully verified by the LSP experiments for 7075 Al alloy achieving the highest average accuracy of 99.33% for the identification of four types of SHI. In addition, the sensitivity of HA in high-frequency event onset and offset is demonstrated by visualizing the gradient weights.

Automated summary

This article proposes a novel method for real-time evaluation of surface quality in laser shock peening (LSP) based on multiple acoustic emission (AE) technique and hybrid attention-based convolutional neural networks (HACNN). A new quality index called surface hardness integrity (SHI) is constructed, and a linear relationship between SHI and AE is demonstrated. A feature extraction method called wavelet packet energy cepstrum (WPEC) is proposed and combined with HACNN. The method achieves a high average accuracy of 99.33% for identifying four types of SHI and demonstrates sensitivity in high-frequency event onset and offset through visualization of gradient weights.