Gearbox fault diagnosis using vibration and current information fusion

This paper proposes a novel vibration and current information fusion-based fault diagnostic method for drivetrain gearboxes. First, two multiclass support vector machines (SVMs) are designed to output the probabilities of different fault (or health condition) classes according to the input features extracted from a vibration signal and a current signal collected from the condition monitoring system, respectively. The Dempster-Shafer (D-S) theory is then applied to fuse the probabilistic outputs of two SVMs to get the final fault diagnostic result. Experiments are conducted for a gearbox with different types of fault, where a gearbox vibration signal and a generator current signal are collected to prove the effectiveness of the proposed method. Results show that the proposed method is more robust and reliable than the traditional methods of using a single sensor or a single type of sensor for gearbox fault diagnosis.

[1]  Xianfeng Fan,et al.  Fault diagnosis of machines based on D-S evidence theory. Part 1: D-S evidence theory and its improvement , 2006, Pattern Recognit. Lett..

[2]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[3]  Wei Qiao,et al.  Adaptive feature extraction and SVM classification for real-time fault diagnosis of drivetrain gearboxes , 2013, 2013 IEEE Energy Conversion Congress and Exposition.

[4]  Chih-Jen Lin,et al.  Probability Estimates for Multi-class Classification by Pairwise Coupling , 2003, J. Mach. Learn. Res..

[5]  Frank Klawonn,et al.  Computational Intelligence: A Methodological Introduction , 2015, Texts in Computer Science.

[6]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[7]  Wei Qiao,et al.  Current-based diagnosis for gear tooth breaks in wind turbine gearboxes , 2012, 2012 IEEE Energy Conversion Congress and Exposition (ECCE).

[8]  J. Ribrant,et al.  Survey of Failures in Wind Power Systems With Focus on Swedish Wind Power Plants During 1997–2005 , 2007, IEEE Transactions on Energy Conversion.

[9]  C. J. Crabtree,et al.  Side-band algorithm for automatic wind turbine gearbox fault detection and diagnosis , 2014 .

[10]  Ming Cheng,et al.  Fault diagnosis of wind turbine based on multisensors information fusion technology , 2014 .

[11]  Wenhai Li,et al.  The intelligent fault diagnosis of wind turbine gearbox based on artificial neural network , 2008, 2008 International Conference on Condition Monitoring and Diagnosis.

[12]  Wei Qiao,et al.  A Survey on Wind Turbine Condition Monitoring and Fault Diagnosis—Part I: Components and Subsystems , 2015, IEEE Transactions on Industrial Electronics.

[13]  Bo-Suk Yang,et al.  Support vector machine in machine condition monitoring and fault diagnosis , 2007 .

[14]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[15]  Ahmad Ghasemloonia,et al.  Application and comparison of an ANN-based feature selection method and the genetic algorithm in gearbox fault diagnosis , 2011, Expert Syst. Appl..

[16]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[17]  Wei Qiao,et al.  Frequency demodulation-aided condition monitoring for drivetrain gearboxes , 2013, 2013 IEEE Transportation Electrification Conference and Expo (ITEC).

[18]  Ruijin Liao,et al.  An Integrated Decision-Making Model for Condition Assessment of Power Transformers Using Fuzzy Approach and Evidential Reasoning , 2011, IEEE Transactions on Power Delivery.

[19]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.