Deep Transfer Learning Based on Sparse Autoencoder for Remaining Useful Life Prediction of Tool in Manufacturing
By Chuang Sun, Meng Ma, Zhibin Zhao, Shaohua Tian, Ruqiang Yan, Xuefeng Chen. IEEE Transactions on Industrial Informatics, 2019
434 citations recorded by the source corpus.
Deep learning with ability to feature learning and nonlinear function approximation has shown its effectiveness for machine fault prediction. While, how to transfer a deep network trained by historical failure data for prediction of a new object is rarely researched. In this paper, a deep transfer learning (DTL) network based on sparse autoencoder (SAE) is presented. In the DTL method, three transfer strategies, that is, weight transfer, transfer learning of hidden feature, and weight update, are used to transfer an SAE trained by historical failure data to a new object. By these strategies, prediction of the new object without supervised information for training is achieved. Moreover, the learned features by deep transfer network for the new object share joint and similar characteristic to that of historical failure data, which is beneficial to accurate prediction. Case study on remaining useful life (RUL) prediction of cutting tool is performed to validate effectiveness of the DTL method. An SAE network is first trained by run-to-failure data with RUL information of a cutting tool in an off-line process. The trained network is then transferred to a new tool under operation for on-line RUL prediction. The prediction result with high accuracy shows advantage of the DTL method for RUL prediction.
Subfields: Industrial and Manufacturing Engineering, Mechanical Engineering
View Paper: https://www.semanticscholar.org/paper/217c1c0c67a007ee1ccb4d602702fd1f560b20e3
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Industrial and Manufacturing Engineering
In Mechanical Engineering
Citations in the corpus
- Tackling Faults in the Industry 4.0 Era—A Survey of Machine-Learning Solutions and Key Aspects (2019, background): “, 2019 [74] RUL relevant feature transfer in DL network DTL with SAE”
- Quo vadis artificial intelligence? (2022, methodology): “With advanced techniques of acceleration taking place in both hardware architecture [45] and software algorithms, the training tasks that usually take several months can be shortened to several days or even hours [46–48].”
- Intelligent Fault Diagnosis of Rotor-Bearing System Under Varying Working Conditions With Modified Transfer Convolutional Neural Network and Thermal Images (2020, background): “Transfer learning is considered to have great potential to complete different but similar tasks from the source domain to the target domain [25], [26].”
- WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis (2019, background): “ROGNOSTIC and health management (PHM) in mechanical system has been applied widely to achieve predictive maintenance, including fault tracking, reduced downtime and asset preservation [1-3].”
- Deep-Convolution-Based LSTM Network for Remaining Useful Life Prediction (2021, background): “Accurate prediction of remaining useful life (RUL) after a fault has been detected as a key part of PHM implementation [5].”
- A Stacked GRU-RNN-Based Approach for Predicting Renewable Energy and Electricity Load for Smart Grid Operation (2021, methodology): “2) Comparisons With Shallow Models, SAE, and DBN: In this part, the proposed method is compared with least squares support vector regression (LSSVR), extreme learning machine (ELM), and wavelet neural network (WNN), and two types of state-of-the-art deep learning models (improved SAE and improved DB”
- Fault Description Based Attribute Transfer for Zero-Sample Industrial Fault Diagnosis (2021, background): “Considering many faults can be destructive and cause huge losses, few factories would be allowed to run to failure and collect samples to train a fault diagnosis system [11].”