Semi-supervised Learning with Deep Generative Models for Asset Failure Prediction
arXiv:1709.00845
Abstract
This work presents a novel semi-supervised learning approach for data-driven modeling of asset failures when health status is only partially known in historical data. We combine a generative model parameterized by deep neural networks with non-linear embedding technique. It allows us to build prognostic models with the limited amount of health status information for the precise prediction of future asset reliability. The proposed method is evaluated on a publicly available dataset for remaining useful life (RUL) estimation, which shows significant improvement even when a fraction of the data with known health status is as sparse as 1% of the total. Our study suggests that the non-linear embedding based on a deep generative model can efficiently regularize a complex model with deep architectures while achieving high prediction accuracy that is far less sensitive to the availability of health status information.
9 pages, 6 figures, 1 table, KDD17 Workshop on Machine Learning for Prognostics and Health Management.August 13-17, 2017, Halifax, Nova Scotia - Canada
References in corpus (3)
Cited by in corpus (7)
- A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacoustic
- Feature Learning for Fault Detection in High-Dimensional Condition-Monitoring Signals
- Self-Supervised Learning for Data Scarcity in a Fatigue Damage Prognostic Problem
- Domain Adaptation for One-Class Classification: Monitoring the Health of Critical Systems Under Limited Information
- Machine Learning for Reliability Engineering and Safety Applications: Review of Current Status and Future Opportunities
- Deep learning models for predictive maintenance: a survey, comparison, challenges and prospect
- Two Birds with One Network: Unifying Failure Event Prediction and Time-to-failure Modeling