Discriminant Feature Distribution Analysis-Based Hybrid Feature Selection for Online Bearing Fault Diagnosis in Induction Motors

Abstract

Optimal feature distribution and feature selection are of paramount importance for reliable fault diagnosis in induction motors. This paper proposes a hybrid feature selection model with a novel discriminant feature distribution analysis-based feature evaluation method. The hybrid feature selection employs a genetic algorithm- (GA-) based filter analysis to select optimal features and ak-NN average classification accuracy-based wrapper analysis approach that selects the most optimal features. The proposed feature selection model is applied through an offline process, where a high-dimensional hybrid feature vector is extracted from acquired acoustic emission (AE) signals, which represents a discriminative fault signature. The feature selection determines the optimal features for different types and sizes of single and combined bearing faults under different speed conditions. The effectiveness of the proposed feature selection scheme is verified through an online process that diagnoses faults in an unknown AE fault signal by extracting only the selected features and using thek-NN classification algorithm to classify the fault condition manifested in the unknown signal. The classification performance of the proposed approach is compared with those of existing state-of-the-art average distance-based approaches. Our experimental results indicate that the proposed approach outperforms the existing methods with regard to classification accuracy.

Recognition of rotor damages in a DC motor using acoustic signals

“…For this reason, the step of classification could be selected in various ways. Most of the obtained feature vectors were separable linearly, therefore many classification methods could be used to solve problems such as: fuzzy logic [46], clustering method [47], nearest mean, k-nearest neighbour classifier [36,48,49], neural network [50][51][52][53][54][55], naive Bayes classifier [56], classifier based on word coding [36], linear discriminant analysis (LDA) [57,58], support vector machine [59,60], rules based on the theory of rough sets [61], Gaussian mixture models (GMM) [62,63]. The authors decided to analyse LDA, nearest neighbour (NN) classifier, and the nearest mean (NM) classi- Fig.…”

“…The authors used Manhattan distance for these two classifiers (NN, NM). More about the nearest neighbour classifier is available in the literature [36,48].…”

A Pipelined FFT Processor Using an Optimal Hybrid Rotation Scheme for Complex Multiplication: Design, FPGA Implementation and Analysis

“…State-of-the-art methods for the intelligent maintenance of rotary machines rely on the timely and accurate analysis of condition monitoring signals, such as acoustic emissions (AE) [1][2][3][4] and vibration acceleration signals [5,6]. AE signals are sampled at very high frequencies, typically 1 MHz, to capture ultrasonic sounds released during the initiation and propagation of cracks in machine components.…”

“…Ever since its introduction, the computational advantages of the FFT have made it an essential algorithm with widespread applications in science and engineering, such as communication, signal processing, image processing, bio-robotics, and intelligent maintenance [1,2,4,[7][8][9][10]. The high-speed requirements of smart maintenance systems, such as fault diagnosis in rotary machines using the spectral analysis of AE signals, necessitate a high-performance FFT processor.…”

Research on Big Data Attribute Selection Method in Submarine Optical Fiber Network Fault Diagnosis Database

“…According to the real-time performance of submarine optical fiber network fault diagnosis [3][4][5], a big data attribute selection method based on rough set of submarine optical fiber network fault diagnosis database is proposed [6].. The current candidate reduction is chosen to be the big data reduction in the submarine optical fiber network fault diagnosis database, so as to complete its attribute selection [7]. This method has become the focus of discussion of relevant experts and scholars, and its research has gradually entered the scope of experts and scholars.…”