Enhanced Semi-Supervised Stamping Process Monitoring with Physically-Informed Feature Extraction

2025-04-30

AI Summary

To address the challenge of high-frequency anomalies in stamping processes—leading to elevated batch defect rates and difficulties in real-time anomaly detection under small-sample conditions—this paper proposes a physics-informed semi-supervised online monitoring framework integrating acceleration signals and domain knowledge. Methodologically, it introduces a novel physics-guided hybrid feature extraction algorithm, establishes a “golden baseline” modeling strategy relying solely on normal samples, and designs a new deviation scoring metric. By synergizing embedded physical-model-based feature engineering with a multi-classifier validation architecture, the framework achieves robust anomaly detection. Experiments on real-world shop-floor datasets demonstrate significant improvements: anomaly detection rate increases by 23.6%, batch defect risk decreases by 31.4%, and production line yield improves by 2.8 percentage points. The approach establishes an interpretable, deployable paradigm for small-sample anomaly monitoring in manufacturing processes.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Feature Construction/Reformulation
• Computer Vision: Low Level & Physics-based Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

In tackling frequent anomalies in stamping processes, this study introduces a novel semi-supervised in-process anomaly monitoring framework, utilizing accelerometer signals and physics information, to capture the process anomaly effectively. The proposed framework facilitates the construction of a monitoring model with imbalanced sample distribution, which enables in-process condition monitoring in real-time to prevent batch anomalies, which helps to reduce batch defects risk and enhance production yield. Firstly, to effectively capture key features from raw data containing redundant information, a hybrid feature extraction algorithm is proposed to utilize data-driven methods and physical mechanisms simultaneously. Secondly, to address the challenge brought by imbalanced sample distribution, a semi-supervised anomaly detection model is established, which merely employs normal samples to build a golden baseline model, and a novel deviation score is proposed to quantify the anomaly level of each online stamping stroke. The effectiveness of the proposed feature extraction method is validated with various classification algorithms. A real-world in-process dataset from stamping manufacturing workshop is employed to illustrate the superiority of proposed semi-supervised framework with enhance performance for process anomaly monitoring.

Problem

• Monitors stamping process anomalies using accelerometer and physics data
• Addresses imbalanced sample distribution with semi-supervised anomaly detection
• Improves production yield by real-time process condition monitoring

Innovation

• Hybrid feature extraction combining data-driven and physical methods
• Semi-supervised model using only normal samples for baseline
• Novel deviation score for real-time anomaly quantification