Fault diagnosis approach of rolling bearing based on NA-MEMD and FRCMAC

• Main Authors: Sheng Liu, Yue Sun, Lanyong Zhang
• Format: Article
• Language: English
• Published: Wiley 2018-10-01
• Series: The Journal of Engineering
• Subjects: genetic algorithms; acoustic signal processing; cerebellar model arithmetic computers; rolling bearings; neurocontrollers; mechanical engineering computing; white noise; vibrations; machine bearings; fault diagnosis; fault diagnosis approach; noise-assisted multivariate empirical mode decomposition; fuzzy recurrent cerebellar model articulation controller neural networks; artificial experience; genetic algorithm; auxiliary white noise parameters; FRCMAC structure; fuzzy processing; input space; association degree; Gaussian function; association unit; autoregressive unit; dynamic mapping; traditional CMAC structure; GA-NA-MEMD method; intrinsic mode functions; IMFs; fault feature vectors; FRCMAC neural network; neural network structure suitable; bearing fault diagnosis; Bearing Data Center; fault diagnosis method; diagnosis time; precision; fault diagnosis results
• Online Access: https://digital-library.theiet.org/content/journals/10.1049/joe.2018.8991

This paper proposed a new method of fault diagnosis based on Noise Assisted Multivariate Empirical Mode Decomposition (NA-MEMD) and Fuzzy Recurrent Cerebellar Model Articulation Controller (FRCMAC) Neural Networks. Aiming at the problem that during the use of the NA-MEMD method, the white noise amplitude parameter needs to be selected by artificial experience, a method of using Genetic Algorithm (GA) to optimize its auxiliary white noise parameters is proposed, which facilitates the use of NA-MEMD. We proposed a novel FRCMAC structure which improved Learning efficiency and dynamic response speed than traditional CMAC structure. First, the GA-NA-MEMD method is applied to process the vibration signals of rolling bearings, and the signals are decomposed into a group of Intrinsic Mode Functions (IMFs). Then use energy moments of IMFs as fault feature vectors to train FRCMAC neural network, a neural network structure suitable for rolling bearing fault diagnosis is obtained. Finally, the data from bearing data center of Case Western Reserve University is used to prove that the fault diagnosis method proposed in this paper is superior to other methods in diagnosis time and precision, which can meet the training requirements more quickly with limited training samples and fault diagnosis results more accurate.