Self-Supervised Learning for Data Scarcity in a Fatigue Damage Prognostic Problem

Abstract

With the increasing availability of data for Prognostics and Health Management (PHM), Deep Learning (DL) techniques are now the subject of considerable attention for this application, often achieving more accurate Remaining Useful Life (RUL) predictions. However, one of the major challenges for DL techniques resides in the difficulty of obtaining large amounts of labelled data on industrial systems. To overcome this lack of labelled data, an emerging learning technique is considered in our work: Self-Supervised Learning, a sub-category of unsupervised learning approaches. This paper aims to investigate whether pre-training DL models in a self-supervised way on unlabelled sensors data can be useful for RUL estimation with only Few-Shots Learning, i.e. with scarce labelled data. In this research, a fatigue damage prognostics problem is addressed, through the estimation of the RUL of aluminum alloy panels (typical of aerospace structures) subject to fatigue cracks from strain gauge data. Synthetic datasets composed of strain data are used allowing to extensively investigate the influence of the dataset size on the predictive performance. Results show that the self-supervised pre-trained models are able to significantly outperform the non-pre-trained models in downstream RUL prediction task, and with less computational expense, showing promising results in prognostic tasks when only limited labelled data is available.

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions
• Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
• Self-supervised Learning: Generative or Contrastive
• Self-supervised learning methods and applications in medical imaging analysis: A survey
• Gated Recurrent Unit (GRU) for Emotion Classification from Noisy Speech
• Semi-supervised Learning with Deep Generative Models for Asset Failure Prediction
• Less is More: Surgical Phase Recognition with Less Annotations through Self-Supervised Pre-training of CNN-LSTM Networks
• Tensorized Embedding Layers for Efficient Model Compression
• Improving Maritime Traffic Emission Estimations on Missing Data with CRBMs

Cited by in corpus (1)

• Self-Supervised Learning for Text Recognition: A Critical Survey