Self-supervised representation learning anomaly detection methodology based on boosting algorithms enhanced by data augmentation using StyleGAN for manufacturing imbalanced data

• DOI: 10.1016/j.compind.2023.104024
• Publication Date: 2023-10-09T09:03:55Z
• Authors: Yoonseok Kim; Taeheon Lee; Youngjoo Hyun; Eric Coatanea; Siren Mika; Jeonghoon Mo; YoungJun Yoo
• Keywords: ta213; 213 Electronic, automation and communications engineering, electronics; Time-series data; Anomaly detection; 02 engineering and technology; 213; 620; Boosting algorithm; and Infrastructure; 0202 electrical engineering, electronic engineering, information engineering; Innovation; Generative adversarial network; SDG 9 - Industry

This study proposes a methodology for detecting anomalies in the manufacturing industry using a self-supervised representation learning approach based on deep generative models. The challenge arises from the limited availability of data on defective products compared with normal data, leading to degradation in the performance of deep learning models owing to data imbalances. To address this limitation, we propose a process that leverages the Gramian angular field to transform time-series data into images, applies StyleGAN for image augmentation of anomalous data, and utilizes a boosting algorithm for classifier selection in supervised learning. Additionally, we compared the accuracy of the classifier before and after data augmentation. In experimental cases involving CNC milling machine data and wire arc additive manufacturing data, the proposed approach outperformed the approach before augmentation, resulting in improved precision, recall, and F1-score for anomaly detection. Furthermore, Bayesian optimization of the hyperparameters of the boosting algorithm further enhanced the performance metrics. The proposed process effectively addresses the data imbalance problem, and demonstrates its applicability to various manufacturing industries.