Deep Learning for Fault Diagnosis based on short-time Fourier transform
- 1 October 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 288-293
Abstract
The rapid advancements of the Internet of Things (IoT) enables maintenance strategies to be applied everyday to all sectors, IoT based health management plays an important role For producing quickly, with high quality while decreasing the risk of production break due to a machine stop, it is necessary to maintain the equipment in a good operational condition. This requirement can be satisfied by the implementation of maintenance strategies for faults detection . In this paper, a novel method called deep learning based on Short-Time Fourier Transform (STFT) is developed for fault diagnosis. An experimental analysis is carried out using a dataset under different operating conditions of speed and loading to substantiate the utility of the proposed strategy. Also a multi-fault deep learning classifier based on STFT is constructed for different faults in this paper. Hence, the purpose is to design an automatic detection system for mechanical components defects based on supervised classification. The diagnosis accuracy assessment is carried out by conducting various experiments on acceleration signals collected from a rotating machinery under different operating conditions.Keywords
This publication has 21 references indexed in Scilit:
- A sparse auto-encoder-based deep neural network approach for induction motor faults classificationMeasurement, 2016
- Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive dataMechanical Systems and Signal Processing, 2016
- Deep Convolutional Neural Network Based Regression Approach for Estimation of Remaining Useful Life2016
- Multi-fault diagnosis for rotating machinery based on orthogonal supervised linear local tangent space alignment and least square support vector machineNeurocomputing, 2015
- The Vibration Monitoring Methods and Signal Processing Techniques for Structural Health Monitoring: A ReviewArchives of Computational Methods in Engineering, 2015
- Deep learning in neural networks: An overviewNeural Networks, 2015
- Support vector machine based optimization of multi-fault classification of gears with evolutionary algorithms from time–frequency vibration dataMeasurement, 2014
- Feature extraction and fault severity classification in ball bearingsJournal of Vibration and Control, 2014
- Development of EBP-Artificial neural network expert system for rolling element bearing fault diagnosisJournal of Vibration and Control, 2010
- Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliographyMechanical Systems and Signal Processing, 2004