Decision fusion scheme for bearing defects diagnosis in induction motors
- PDF / 1,954,149 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 85 Downloads / 226 Views
ORIGINAL PAPER
Decision fusion scheme for bearing defects diagnosis in induction motors Hamed Agahi1 · Azar Mahmoodzadeh1 Received: 29 October 2019 / Accepted: 25 May 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Intelligent fault diagnostic systems are fast becoming key instruments in industrial applications. This paper presents a recognition system for diagnosing bearing defects in induction motors. The proposed scheme is comprised of five steps, namely signal segmentation, feature extraction and reduction, fault classification and the decision fusion. First, the vibration signal is segmented into successive equal-length intervals, which are considered as patterns in a recognition problem. The objective is to predict the defect mode (class) for each pattern. Then, the time- and the frequency-domain features are extracted from each interval. At the next step, a small set of distinctive and informative features is found by resorting to different feature reduction techniques to guarantee well-organized learning and immediate and accurate classification. Then, in the fourth step, various classifiers are trained to learn to distinguish between the faulty and healthy states. To make the final decision, different combinations of classifiers are considered using the voting and stacking techniques to enhance the overall performance of the recognition system. Evaluation of the proposed diagnostic scheme on the standard CWRU bearing defect database demonstrates that this system attains reasonable performance measures, validating the ideas put forward in this paper. Keywords Classification · Decision fusion · Fault diagnosis · Feature extraction · Feature reduction
1 Introduction Induction motor (IM) is perhaps the most common type of AC electric motor in industrial drives, as a result of its ruggedness and trustworthiness. IMs are economical in cost due to simple construction and absence of brushes, commutators and slip rings. Also, these motors can operate in any environmental condition including polluted and explosive situations and provide power in various industries. However, the components of IMs are subject to some defects. These faults can result in failure or even breakdown and consequently unpredicted repair services. Although some factories schedule periodic maintenance services, these programs are highly expensive and do not necessarily avoid the failures in induction motors [1, 2]. Recent studies show that bearing defect is the most frequent fault compared to other electrical and mechanical damages. Hence, diagnosing this fault, as the main focus of our paper, is of great importance in academic * Hamed Agahi [email protected] 1
Department of Electrical Engineering, Shiraz Branch, Islamic Azad University, Shiraz, Iran
and industrial studies. Prompt and accurate diagnosis of bearing defects can increase the reliability, efficiency and productivity of the motors for long periods of time and also decrease the maintenance cost. Finding such diagnosis techniques has been att
Data Loading...
