# A stacked deep convolutional neural network to predict the remaining useful life of a turbofan engine

arXiv: https://arxiv.org/abs/2111.12689 · HTML: https://mlsanity.com/paper/2111.12689/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 14 references that are in the map.
- First posted on arXiv 24 Nov 2021.

## Builds on (most cited first, 1 of 1)

- [Tune: A Research Platform for Distributed Model Selection and Training](https://mlsanity.com/paper/1807.05118/) (2018)

## Built on by (most cited first, 7 of 7)

- [On the Soundness of XAI in Prognostics and Health Management (PHM)](https://mlsanity.com/paper/2303.05517/) (2023)
- [Shapley-based Explainable AI for Clustering Applications in Fault Diagnosis and Prognosis](https://mlsanity.com/paper/2303.14581/) (2023)
- [Masked Self-Supervision for Remaining Useful Lifetime Prediction in Machine Tools](https://mlsanity.com/paper/2207.01219/) (2022)
- [Fault Prognosis of Turbofan Engines: Eventual Failure Prediction and Remaining Useful Life Estimation](https://mlsanity.com/paper/2303.12982/) (2023)
- [D3A-TS: Denoising-Driven Data Augmentation in Time Series](https://mlsanity.com/paper/2312.05550/) (2023)
- [Machine Learning Approaches for Diagnostics and Prognostics of Industrial Systems Using Open Source Data from PHM Data Challenges: A Review](https://mlsanity.com/paper/2312.16810/) (2023)
- [Scientific Machine Learning for Engine Health Management and Remaining Useful Life Prediction](https://mlsanity.com/paper/2605.30593/) (2026)

## Abstract (arXiv)

This paper presents the data-driven techniques and methodologies used to predict the remaining useful life (RUL) of a fleet of aircraft engines that can suffer failures of diverse nature. The solution presented is based on two Deep Convolutional Neural Networks (DCNN) stacked in two levels. The first DCNN is used to extract a low-dimensional feature vector using the normalized raw data as input. The second DCNN ingests a list of vectors taken from the former DCNN and estimates the RUL. Model selection was carried out by means of Bayesian optimization using a repeated random subsampling validation approach. The proposed methodology was ranked in the third place of the 2021 PHM Conference Data Challenge.