An intelligent fault diagnosis framework dealing with arbitrary length inputs under different working conditions
- 20 September 2019
- journal article
- research article
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 30 (12) , 125107
Abstract
As fault diagnosis for motor drive systems enters the era of big data, intelligent fault diagnosis methods exhibit excellent performance because of their learning capabilities. However, the existing methods are strict with the signal size, which reduces the performance of these methods for modern condition monitoring. Besides, most existing intelligent methods have a great limitation: the training data and testing data are under the same working conditions. To overcome these limitations, we propose a novel three-layer model inspired by a recurrent neural network (RNN) and transfer learning, which has the ability to process variable size sequences under different working conditions. In the first layer, the input unit is extended to ensure that there is adequate dimension to store the information of sequences. In the second layer, the main information of the whole sequence is stored, transmitted, transformed and output by gates. In the final layer, softmax is employed to classify the health conditions based on the output of the RNN with a long short-term memory cell. The classification loss based on the whole framework and the domain loss using kernel method are proposed to train the model. Furthermore, a bearing dataset is adopted to verify the effectiveness of the proposed method. The experimental results show that the proposed method can not only break the limitations of existing methods, but also achieve a superior performance compared with related methods.Keywords
Funding Information
- Fundamental Research Funds for the Central Universities (NP2018304)
- National Natural Science Foundation of China (51675262)
- Major National Science and Technology Projects (2017-IV-0008-0045)
This publication has 44 references indexed in Scilit:
- Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive dataMechanical Systems and Signal Processing, 2016
- Maxout neurons for deep convolutional and LSTM neural networks in speech recognitionSpeech Communication, 2016
- Transfer Learning in Brain-Computer InterfacesIEEE Computational Intelligence Magazine, 2016
- A theory of learning from different domainsMachine Learning, 2009
- Gear crack level identification based on weighted K nearest neighbor classification algorithmMechanical Systems and Signal Processing, 2009
- Intelligent condition monitoring of a gearbox using artificial neural networkMechanical Systems and Signal Processing, 2007
- Integrating structured biological data by Kernel Maximum Mean DiscrepancyBioinformatics, 2006
- STOCHASTIC PROGNOSTICS FOR ROLLING ELEMENT BEARINGSMechanical Systems and Signal Processing, 2000
- Long Short-Term MemoryNeural Computation, 1997
- ARTIFICIAL NEURAL NETWORK BASED FAULT DIAGNOSTICS OF ROTATING MACHINERY USING WAVELET TRANSFORMS AS A PREPROCESSORMechanical Systems and Signal Processing, 1997