# Predicting machine failures from multivariate time series: an industrial case study

arXiv: https://arxiv.org/abs/2402.17804 · HTML: https://mlsanity.com/paper/2402.17804/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 101 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Builds on (most cited first, 11 of 11)

- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data](https://mlsanity.com/paper/2201.07284/) (2022)
- [Time-Series Anomaly Detection Service at Microsoft](https://mlsanity.com/paper/1906.03821/) (2019)
- [Exploring Interpretable LSTM Neural Networks over Multi-Variable Data](https://mlsanity.com/paper/1905.12034/) (2019)
- [sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification](https://mlsanity.com/paper/2108.10566/) (2021)
- [Neural networks versus Logistic regression for 30 days all-cause readmission prediction](https://mlsanity.com/paper/1812.09549/) (2018)
- [Real-time predictive maintenance for wind turbines using Big Data frameworks](https://mlsanity.com/paper/1709.07250/) (2017)
- [Imbalance Learning for Variable Star Classification](https://mlsanity.com/paper/2002.12386/) (2020)
- [Semi-supervised Learning with Deep Generative Models for Asset Failure Prediction](https://mlsanity.com/paper/1709.00845/) (2017)
- [Deep Autoencoders for Anomaly Detection in Textured Images using CW-SSIM](https://mlsanity.com/paper/2208.14045/) (2022)

## Built on by (most cited first, 3 of 3)

- [A Joint Reconstruction-Triplet Loss Autoencoder Approach Towards Unseen Attack Detection in IoV Networks](https://mlsanity.com/paper/2505.21703/) (2025)
- [Short-Horizon Predictive Maintenance of Industrial Pumps Using Time-Series Features and Machine Learning](https://mlsanity.com/paper/2508.19974/) (2025)
- [Understanding Online Failure Prediction in Linux Through Complementary Multi-View Explainability](https://mlsanity.com/paper/2608.00651/) (2026)

## Abstract (arXiv)

Non-neural Machine Learning (ML) and Deep Learning (DL) models are often used to predict system failures in the context of industrial maintenance. However, only a few researches jointly assess the effect of varying the amount of past data used to make a prediction and the extension in the future of the forecast. This study evaluates the impact of the size of the reading window and of the prediction window on the performances of models trained to forecast failures in three data sets concerning the operation of (1) an industrial wrapping machine working in discrete sessions, (2) an industrial blood refrigerator working continuously, and (3) a nitrogen generator working continuously. The problem is formulated as a binary classification task that assigns the positive label to the prediction window based on the probability of a failure to occur in such an interval. Six algorithms (logistic regression, random forest, support vector machine, LSTM, ConvLSTM, and Transformers) are compared using multivariate telemetry time series. The results indicate that, in the considered scenarios, the dimension of the prediction windows plays a crucial role and highlight the effectiveness of DL approaches at classifying data with diverse time-dependent patterns preceding a failure and the effectiveness of ML approaches at classifying similar and repetitive patterns preceding a failure.