Semi-supervised multi-source meta-domain generalization method for tool wear state prediction under varying cutting conditions

• Published in: Journal of manufacturing systems Vol. 71; pp. 323 - 341
• Main Authors: Li, Wangyang, Fu, Hongya, Zhuo, Yue, Liu, Chuyu, Jin, Hongyu
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.12.2023
• Subjects: Few-shot; Meta learning; Semi-supervised domain generalization; Tool wear state prediction; Varying cutting condition; Semi-supervised domain generalization; Tool wear state prediction; Varying cutting condition; Few-shot; Meta learning
• ISSN: 0278-6125; 1878-6642
• DOI: 10.1016/j.jmsy.2023.09.011

Accurate tool wear state prediction during machining is essential for lowering production costs and ensuring quality. Conventional deep learning-based methods perform excellently under constant cutting conditions with sufficient labeled data. During training, domain-adaptation-based transfer learning methods require exposure to partial target domain data to accurately predict under varying cutting conditions. However, the performance of these two methods drops considerably under unseen cutting conditions. Therefore, we propose a semi-supervised multi-source meta-domain generalization (SSM2DG) method for label scarcity training scenarios, which can generalize the deep models to predict tool wear state under unseen cutting conditions. SSM2DG adopts an episodic training strategy based on meta-learning to simulate cutting condition shifts. Then, one basic model based on multiple attention mechanisms is presented for enhancing temporal and cross-channel feature extraction. Next, the entropy-based semi-supervised learning method is incorporated into the episodic training procedure to enrich intra-domain representations using unlabeled data. Besides, class relationship alignment loss based on the distributional sliced-Wasserstein distance and memory centroid-based loss are designed to improve generalization ability. Finally, milling experiments under variable working conditions and multiple ablation studies verify the effectiveness and superiority of the proposed method. •A novel semi-supervised meta-domain generalization method is proposed for tool wear state prediction under unseen cutting conditions.•Episodic training strategy with entropy-based semi-supervised learning incorporated is proposed for simulating cutting condition shifts under label scarcity.•One basic model with multiple attention mechanisms establishes temporal and cross-channel feature correlations.•Class relationship loss with distributional sliced-Wasserstein distance and memory centroid- based loss are designed to enhance generalization ability.•Model performance is validated via milling experiments under variable cutting conditions.