Adaptive Unknown Fault Detection and Few-Shot Continual Learning for Condition Monitoring in Ultrasonic Metal Welding

2026-04-15

AI Summary

This study addresses the challenge of detecting previously unseen faults—such as tool wear and contamination—in ultrasonic metal welding, which conventional supervised methods struggle to handle due to their reliance on known fault classes during training. The authors propose an adaptive condition monitoring approach that integrates unknown fault detection with few-shot continual learning. By leveraging hidden-layer representations from a multilayer perceptron and statistical thresholds, the method identifies anomalies; cosine similarity and clustering are employed to minimize labeling requirements. New fault classes are incrementally learned by fine-tuning only the final network layer, preserving performance on known classes. Evaluated on a real-world multi-sensor dataset, the approach achieves 96% accuracy in unknown fault detection and attains 98% overall classification accuracy after incremental learning with just five labeled samples per new class, substantially reducing annotation and retraining costs.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Ultrasonic metal welding (UMW) is widely used in industrial applications but is sensitive to tool wear, surface contamination, and material variability, which can lead to unexpected process faults and unsatisfactory weld quality. Conventional monitoring systems typically rely on supervised learning models that assume all fault types are known in advance, limiting their ability to handle previously unseen process faults. To address this challenge, this paper proposes an adaptive condition monitoring approach that enables unknown fault detection and few-shot continual learning for UMW. Unknown faults are detected by analyzing hidden-layer representations of a multilayer perceptron and leveraging a statistical thresholding strategy. Once detected, the samples from unknown fault types are incorporated into the existing model through a continual learning procedure that selectively updates only the final layers of the network, which enables the model to recognize new fault types while preserving knowledge of existing classes. To accelerate the labeling process, cosine similarity transformation combined with a clustering algorithm groups similar unknown samples, thereby reducing manual labeling effort. Experimental results using a multi-sensor UMW dataset demonstrate that the proposed method achieves 96% accuracy in detecting unseen fault conditions while maintaining reliable classification of known classes. After incorporating a new fault type using only five labeled samples, the updated model achieves 98% testing classification accuracy. These results demonstrate that the proposed approach enables adaptive monitoring with minimal retraining cost and time. The proposed approach provides a scalable solution for continual learning in condition monitoring where new process conditions may constantly emerge over time and is extensible to other manufacturing processes.

Problem

• unknown fault detection
• few-shot continual learning
• condition monitoring
• ultrasonic metal welding
• process faults

Innovation

• unknown fault detection
• few-shot continual learning
• adaptive condition monitoring
• cosine similarity clustering
• ultrasonic metal welding