A Bearing Performance Degradation Modeling Method Based on EMD‐SVD and Fuzzy Neural Network

Abstract

Bearing performance degradation assessment has great significance to condition-based maintenance (CBM). A novel degradation modeling method based on EMD-SVD and fuzzy neural network (FNN) was proposed to identify and evaluate the degradation process of bearings in the whole life cycle accurately. Firstly, the vibration signals of bearings in known states were decomposed by empirical mode decomposition (EMD) to obtain the intrinsic mode functions (IMFs) containing feature information. Then, the selected key IMFs which contain the main features were decomposed by singular value decomposition (SVD). And the decomposed results were used as the training samples of FNN. At last, the output results of the tested data were normalized to the health index (HI) through learning and training of FNN, and then the performance degradation degree could be described by the distance between the test sample and the normal one. According to the case study, this modeling method could evaluate the performance degradation of bearings effectively and identify the early fault features accurately. This method also provided an important maintenance strategy for the CBM of bearings.

Research on Mechanical Fault Prediction Method Based on Multifeature Fusion of Vibration Sensing Data

“…Feature extraction can effectively reduce the uncertainty in vibration sensing data. Common feature extraction methods include information entropy [33][34][35], time domain analysis [36,37], empirical mode decomposition [38][39][40], and wavelet packet analysis [41,42]. Compared to the information entropy method and the empirical mode decomposition method, time domain analysis is less affected by the interruption of time-frequency signals, the steps of feature extraction are relatively simple, and different time domain features contain different information in the vibration signal.…”

A Hybrid Online and Offline Approach to Teaching Spoken English Based on Modern Educational Technology

“…Rough set theory is used to overcome the problem of unjustified index weights [25], decision trees are used to analyze teaching evaluation data [26], and association rule algorithms are used to examine aspects impacting teaching quality [27]. Some scholars used artificial networks to model teaching evaluation, established relevant mathematical models, quantified the indexes synthetically, constructed BP neural network models, and obtained more reasonable evaluation results [28].…”

Neural fuzzy network configurator for calculating a residual life of production equipment

“…We pay special attention to intelligent techniques fault diagnosis: self-organising neural networks [4], dynamic wavelet neural networks [5], recurrent neural network [6,7], recurrent neural networks and neural-fuzzy inference systems [8], neural-fuzzy approach [9][10][11][12][13][14], hybrid intelligent methods [1], applied to estimation the different features of process equipment: remaining useful life [3], mean-residual-life [9], onset of a failure or predicting the time of ultimate failure [15].…”