A hybrid technique based on convolutional neural network and support vector regression for intelligent diagnosis of rotating machinery
Open Access
- 15 June 2017
- journal article
- research article
- Published by SAGE Publications in Advances in Mechanical Engineering
- Vol. 9 (6)
Abstract
Rolling element bearings and gears are the most common machine elements. As they are extensively used in rotating machinery, their health conditions are crucial to the safe operation. The signals measured from rotating machines are usually affected by the working conditions and background noises. Thus, identifying faults from the mixed signals is a challenging and important task. Deep learning is initially developed for image recognition. Recently, it has attracted increasing attention in machinery fault diagnosis research. However, the generalization ability of the default classifier of it is not very satisfying. Thus, combining the feature learning ability of deep learning and the existing classifiers with satisfactory generalization ability is necessary. In this article, a hybrid technique based on convolutional neural network and support vector regression is proposed. The former part is used to promote feature extraction capability, and the latter part is used for multi-class classification. The efficiency of the proposed scheme is validated using the real acoustic signals measured from locomotive bearings and vibration signals measured from the automobile transmission gearbox. Results confirm that the method proposed is able to capture fault characteristics from the raw data, and both bearing faults and gear faults can be detected successfully.Keywords
Funding Information
- Natural Science Foundation of Jiangsu Province (BK20150339)
- Innovative Research Project for Postgraduates in Colleges of Jiangsu Province (KYZZ16_0085)
- National Natural Science Foundation of China (51375322)
- National Natural Science Foundation of China (51505311)
This publication has 34 references indexed in Scilit:
- Envelope extraction based dimension reduction for independent component analysis in fault diagnosis of rolling element bearingJournal of Sound and Vibration, 2014
- A review of unsupervised feature learning and deep learning for time-series modelingPattern Recognition Letters, 2014
- Robust boosting classification models with local sets of probability distributionsKnowledge-Based Systems, 2014
- Wavelets for fault diagnosis of rotary machines: A review with applicationsSignal Processing, 2014
- An improved fault-location method for distribution system using wavelets and support vector regressionInternational Journal of Electrical Power & Energy Systems, 2014
- A Doppler Transient Model Based on the Laplace Wavelet and Spectrum Correlation Assessment for Locomotive Bearing Fault DiagnosisSensors, 2013
- A joint sparse wavelet coefficient extraction and adaptive noise reduction method in recovery of weak bearing fault features from a multi-component signal mixtureApplied Soft Computing, 2013
- Fault diagnosis of rotating machinery based on the statistical parameters of wavelet packet paving and a generic support vector regressive classifierMeasurement, 2013
- Research on bearing life prediction based on support vector machine and its applicationJournal of Physics: Conference Series, 2011
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006