# Semi-supervised Learning with Deep Generative Models for Asset Failure Prediction

arXiv: https://arxiv.org/abs/1709.00845 · HTML: https://mlsanity.com/paper/1709.00845/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Sep 2017.

## Built on by (most cited first, 5 of 5)

- [A Review of Machine Learning Methods Applied to Structural Dynamics and Vibroacoustic](https://mlsanity.com/paper/2204.06362/) (2022)
- [Improving Semi-Supervised Learning for Remaining Useful Lifetime Estimation Through Self-Supervision](https://mlsanity.com/paper/2108.08721/) (2021)
- [Self-Supervised Learning for Data Scarcity in a Fatigue Damage Prognostic Problem](https://mlsanity.com/paper/2301.08441/) (2023)
- [Predicting machine failures from multivariate time series: an industrial case study](https://mlsanity.com/paper/2402.17804/) (2024)
- [Bayesian Deep Learning for Remaining Useful Life Estimation via Stein Variational Gradient Descent](https://mlsanity.com/paper/2402.01098/) (2024)

## Abstract (arXiv)

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.