Using Deep Learning-Based Approach to Predict Remaining Useful Life of Rotating Components

By Jason Deutsch, David He. IEEE Transactions on Systems, Man & Cybernetics. Systems, 2018

417 citations recorded by the source corpus.

In the age of Internet of Things and Industrial 4.0, prognostic and health management (PHM) systems are used to collect massive real-time data from mechanical equipment. PHM big data has the characteristics of large-volume, diversity, and high-velocity. Effectively mining features from such data and accurately predicting the remaining useful life (RUL) of the rotating components with new advanced methods become issues in PHM. Traditional data driven prognostics is based on shallow learning architectures, requires establishing explicit model equations and much prior knowledge about signal processing techniques and prognostic expertise, and therefore is limited in the age of big data. This paper presents a deep learning-based approach for RUL prediction of rotating components with big data. The presented approach is tested and validated using data collected from a gear test rig and bearing run-to-failure tests and compared with existing PHM methods. The test results show the promising RUL prediction performance of the deep learning-based approach.

Subfields: Control and Systems Engineering, Mechanical Engineering, Mechanics of Materials

View Paper: https://www.semanticscholar.org/paper/811551ca0c9e74fb673ff5698a5c34380394eaa1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

1. Ruqiang Yan
2. Rui Zhao
3. Robert X. Gao
4. Cheng-Geng Huang
5. Min Wu
6. Feri Guretno
7. Hongzhong Huang
8. Shen Zhang

In Mechanical Engineering

1. Ruqiang Yan
2. Rui Zhao
3. Cheng-Geng Huang
4. Hongzhong Huang
5. Yanfeng Li
6. Min Wu
7. Feri Guretno
8. Robert X. Gao

In Mechanics of Materials

1. Cheng-Geng Huang
2. Min Wu
3. Feri Guretno
4. Hongzhong Huang
5. Robert X. Gao
6. Shen Zhang
7. Bingnan Wang
8. Ruqiang Yan

Citations in the corpus

• Machine Learning and Deep Learning Algorithms for Bearing Fault Diagnostics - A Comprehensive Review (2019, methodology): “In [142], a DBN-feed-forward neural network (FNN) is applied”
• Machine Remaining Useful Life Prediction via an Attention-Based Deep Learning Approach (2021, background): “Deutsch and He [25] presented a deep belief network feedforward neural network (DBN-FNN) for the RUL prediction [25].”
• DCNN-Based Multi-Signal Induction Motor Fault Diagnosis (2020, methodology): “In order to investigate the influence caused by measurement uncertainty, confidence interval estimation for the classification accuracy is performed using the bootstrap method [56].”
• Deep Learning Algorithms for Bearing Fault Diagnosticsx—A Comprehensive Review (2019, methodology): “In [143], a DBN-feed-forward neural network (FNN) is applied to perform automatic feature learning with DBN and RUL prediction with FNN.”
• A Bidirectional LSTM Prognostics Method Under Multiple Operational Conditions (2019, methodology): “[22] proposed a DBN-FNN-based approach for RUL prediction of rotating equipment using vibration data.”