Remaining Useful

Remaining Useful Life (RUL) prediction aims to accurately estimate the time until a system or component fails, enabling proactive maintenance and preventing costly downtime. Current research heavily emphasizes data-driven approaches, employing deep learning architectures like transformers, graph neural networks, and recurrent neural networks (RNNs, such as LSTMs) often enhanced with attention mechanisms to effectively process complex, high-dimensional sensor data and capture temporal dependencies. These advancements are significantly impacting various industries, improving reliability and efficiency in applications ranging from aircraft engines and batteries to hard disk drives and optical fiber amplifiers. Furthermore, research is actively exploring methods to improve model generalization across varying operating conditions and incorporate physics-informed models to enhance prediction accuracy.

Papers

November 1, 2024

A Multi-Granularity Supervised Contrastive Framework for Remaining Useful Life Prediction of Aero-engines
Zixuan He, Ziqian Kong, Zhengyu Chen, Yuling Zhan, Zijun Que, Zhengguo Xu
Long Short Term Memory Feature Space Multi Granularity Contrastive Method Useful Life Remaining Useful Turbofan Engine Remaining Useful Life Prediction

October 4, 2024

Remaining Useful Life Prediction: A Study on Multidimensional Industrial Signal Processing and Efficient Transfer Learning Based on Large Language Models
Yan Chen, Cheng Liu
Large Language Model Study Feature Useful Life Efficient Transfer Learning Industrial Machine Learning Remaining Useful Multivariate Signal Remaining Useful Life Prediction Regression Framework

September 29, 2024

A Survey on Graph Neural Networks for Remaining Useful Life Prediction: Methodologies, Evaluation and Future Trends
Yucheng Wang, Min Wu, Xiaoli Li, Lihua Xie, Zhenghua Chen
Graph Neural Network Global Evaluation NCD Method Prognostic Prediction Useful Life Future Trend Remaining Useful Remaining Useful Life Prediction

September 22, 2024

Sparse Low-Ranked Self-Attention Transformer for Remaining Useful Lifetime Prediction of Optical Fiber Amplifiers
Dominic Schneider, Lutz Rapp
Self Attention Optical Communication Life Prediction Remaining Useful

June 21, 2024

Physics Informed Machine Learning (PIML) methods for estimating the remaining useful lifetime (RUL) of aircraft engines
Sriram Nagaraj, Truman Hickok
Machine Learning Physic Informed Machine Learning Remaining Useful Turbofan Engine Remaining Useful Life Prediction

January 29, 2024

Supervised Contrastive Learning based Dual-Mixer Model for Remaining Useful Life Prediction
En Fu, Yanyan Hu, Kaixiang Peng, Yuxin Chu
Temporal Feature Supervised Contrastive Learning Useful Life Simple Alternating Mixer Remaining Useful Remaining Useful Life Prediction Spatio Temporal Feature Extraction

January 9, 2024

A Change Point Detection Integrated Remaining Useful Life Estimation Model under Variable Operating Conditions
Anushiya Arunan, Yan Qin, Xiaoli Li, Chau Yuen
Long Short Term Memory Change Point Detection Adverse Condition Useful Life Composite Variable Construction Remaining Useful

October 29, 2023

Remaining useful life prediction of Lithium-ion batteries using spatio-temporal multimodal attention networks
Sungho Suh, Dhruv Aditya Mittal, Hymalai Bello, Bo Zhou, Mayank Shekhar Jha, Paul Lukowicz
Long Short Term Memory Lithium Ion Battery Useful Life Remaining Useful Battery Data

September 6, 2023

TFBEST: Dual-Aspect Transformer with Learnable Positional Encoding for Failure Prediction
Rohan Mohapatra, Saptarshi Sengupta
Transformer Based Self Attention Positional Encoding Failure Prediction Remaining Useful Data Loss Disk Failure

August 7, 2023

Two-stage Early Prediction Framework of Remaining Useful Life for Lithium-ion Batteries
Dhruv Mittal, Hymalai Bello, Bo Zhou, Mayank Shekhar Jha, Sungho Suh, Paul Lukowicz
Lithium Ion Battery Useful Life Battery System Remaining Useful Battery Management

June 21, 2023

Automated Machine Learning for Remaining Useful Life Predictions
Marc-André Zöller, Fabian Mauthe, Peter Zeiler, Marius Lindauer, Marco F. Huber
Machine Learning Online autoML Prognostic Prediction Useful Life Remaining Useful Remaining Useful Life Prediction

February 3, 2023

Domain Adaptation via Alignment of Operation Profile for Remaining Useful Lifetime Prediction
Ismail Nejjar, Fabian Geissmann, Mengjie Zhao, Cees Taal, Olga Fink
Domain Adaptation Domain Shift Alignment Problem Prognostic Model Domain Shift Problem Life Prediction Remaining Useful Operational Technology

December 30, 2022

Conformal Prediction Intervals for Remaining Useful Lifetime Estimation
Alireza Javanmardi, Eyke Hüllermeier
Conformal Prediction Conformal Prediction Interval Remaining Useful

December 12, 2022

Multi-Dimensional Self Attention based Approach for Remaining Useful Life Estimation
Zhi Lai, Mengjuan Liu, Yunzhu Pan, Dajiang Chen
Constructive Approach Useful Life Machine Condition Monitoring Dimensional Attention Remaining Useful

April 11, 2022

SAL-CNN: Estimate the Remaining Useful Life of Bearings Using Time-frequency Information
Bingguo Liu, Zhuo Gao, Binghui Lu, Hangcheng Dong, Zeru An
CNN Network Convolutional Block Attention Useful Life Short Time Fourier Transform Short Term Memory Remaining Useful Journal Bearing Time Frequency Information

February 21, 2022

Remaining Useful Life Prediction Using Temporal Deep Degradation Network for Complex Machinery with Attention-based Feature Extraction
Yuwen Qin, Ningbo Cai, Chen Gao, Yadong Zhang, Yonghong Cheng, Xin Chen
Useful Life Remaining Useful Degradation Feature

Remaining Useful

Papers

A Multi-Granularity Supervised Contrastive Framework for Remaining Useful Life Prediction of Aero-engines

Remaining Useful Life Prediction: A Study on Multidimensional Industrial Signal Processing and Efficient Transfer Learning Based on Large Language Models

A Survey on Graph Neural Networks for Remaining Useful Life Prediction: Methodologies, Evaluation and Future Trends

Sparse Low-Ranked Self-Attention Transformer for Remaining Useful Lifetime Prediction of Optical Fiber Amplifiers

Physics Informed Machine Learning (PIML) methods for estimating the remaining useful lifetime (RUL) of aircraft engines

Supervised Contrastive Learning based Dual-Mixer Model for Remaining Useful Life Prediction

A Change Point Detection Integrated Remaining Useful Life Estimation Model under Variable Operating Conditions

Remaining useful life prediction of Lithium-ion batteries using spatio-temporal multimodal attention networks

TFBEST: Dual-Aspect Transformer with Learnable Positional Encoding for Failure Prediction

Two-stage Early Prediction Framework of Remaining Useful Life for Lithium-ion Batteries

Automated Machine Learning for Remaining Useful Life Predictions

Domain Adaptation via Alignment of Operation Profile for Remaining Useful Lifetime Prediction

Conformal Prediction Intervals for Remaining Useful Lifetime Estimation

Multi-Dimensional Self Attention based Approach for Remaining Useful Life Estimation

SAL-CNN: Estimate the Remaining Useful Life of Bearings Using Time-frequency Information

Remaining Useful Life Prediction Using Temporal Deep Degradation Network for Complex Machinery with Attention-based Feature Extraction