Attention-stacked Generative Adversarial Network (AS-GAN)-empowered Sensor Data Augmentation for Online Monitoring of Manufacturing System

Machine learning (ML) has been extensively adopted for the online sensing-based monitoring in advanced manufacturing systems. However, the sensor data collected under abnormal states are usually insufficient, leading to significant data imbalanced issue for supervised machine learning. A common solution for this issue is to incorporate data augmentation technique, i.e., augmenting the available abnormal states data (i.e., minority samples) via synthetic generation. To generate the high-quality minority samples effectively, it is vital to learn the underlying distribution of the abnormal states data. In recent years, the generative adversarial network (GAN)-based approaches become popular to learn data distribution as well as perform data augmentation. However, in practice, the quality of generated samples from GAN-based data augmentation may vary drastically. In addition, the sensor signals are collected sequentially by time from the manufacturing systems, which means the consideration of sequential information is also very important in data augmentation. To address these limitations, inspired by the multi-head attention mechanism, this paper proposed an attention-stacked GAN (AS-GAN) architecture for the sensor data augmentation of online monitoring in advanced manufacturing. In this proposed AS-GAN, a new attention-stacked framework is incorporated to strengthen the generator in GAN with the learning capability of considering sequential information. Furthermore, the developed attention-stacked framework also greatly helps to improve the quality of generated sensor signals. The case studies conducted in additive manufacturing also successfully validate the effectiveness of AS-GAN to augment high-quality artificial multi-channel sensor signals for online monitoring of manufacturing systems.