![[2504.20823] Hybrid quantum recurrent neural network for remaining useful life prediction](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2504.20823] Hybrid quantum recurrent neural network for remaining useful life prediction
Summary
This article presents a Hybrid Quantum Recurrent Neural Network framework for predicting the remaining useful life of jet engines, showcasing improved accuracy over traditional methods.
Why It Matters
The study addresses the critical need for accurate predictive maintenance in aerospace, leveraging quantum computing to enhance forecasting capabilities. As industries increasingly adopt AI and quantum technologies, this research highlights innovative approaches that could lead to more reliable and efficient maintenance strategies.
Key Takeaways
- Introduces a Hybrid Quantum Recurrent Neural Network for life prediction.
- Achieves up to 5% improvement in accuracy over traditional RNNs.
- Demonstrates superiority over established methods like Random Forest and CNN.
- Highlights potential of hybrid quantum-classical methods in time-series forecasting.
- Offers insights into enhancing predictive maintenance under limited data conditions.
Computer Science > Machine Learning arXiv:2504.20823 (cs) [Submitted on 29 Apr 2025 (v1), last revised 17 Feb 2026 (this version, v2)] Title:Hybrid quantum recurrent neural network for remaining useful life prediction Authors:Olga Tsurkan, Aleksandra Konstantinova, Aleksandr Sedykh, Arsenii Senokosov, Daniil Tarpanov, Matvei Anoshin, Asel Sagingalieva, Alexey Melnikov View a PDF of the paper titled Hybrid quantum recurrent neural network for remaining useful life prediction, by Olga Tsurkan and 7 other authors View PDF HTML (experimental) Abstract:Predictive maintenance in aerospace heavily relies on accurate estimation of the remaining useful life of jet engines. In this paper, we introduce a Hybrid Quantum Recurrent Neural Network framework, combining Quantum Long Short-Term Memory layers with classical dense layers for Remaining Useful Life forecasting on NASA's Commercial Modular Aero-Propulsion System Simulation dataset. Each Quantum Long Short-Term Memory gate replaces conventional linear transformations with Quantum Depth-Infused circuits, allowing the network to learn high-frequency components more effectively. Experimental results demonstrate that, despite having fewer trainable parameters, the Hybrid Quantum Recurrent Neural Network achieves up to a 5% improvement over a Recurrent Neural Network based on stacked Long Short-Term Memory layers in terms of mean root-mean-square error and mean absolute error. Moreover, a thorough comparison of our method with establi...
