A Feature Inherited Hierarchical Convolutional Neural Network (FI-HCNN) for Motor Fault Severity Estimation Using Stator
- PDF / 2,578,854 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 62 Downloads / 195 Views
Online ISSN 2198-0810 Print ISSN 2288-6206
REGULAR PAPER
A Feature Inherited Hierarchical Convolutional Neural Network (FI‑HCNN) for Motor Fault Severity Estimation Using Stator Current Signals Chan Hee Park1 · Hyunjae Kim2 · Junmin Lee1 · Giljun Ahn1 · Myeongbaek Youn1 · Byeng D. Youn1,2,3 Received: 6 February 2020 / Revised: 18 August 2020 / Accepted: 13 September 2020 © The Author(s) 2020
Abstract Motors, which are one of the most widely used machines in the manufacturing field, take charge of a key role in precision machining. Therefore, it is important to accurately estimate the health state of the motor that affects the quality of the product. The research outlined in this paper aims to improve motor fault severity estimation by suggesting a novel deep learning method, specifically, feature inherited hierarchical convolutional neural network (FI-HCNN). FI-HCNN consists of a fault diagnosis part and a severity estimation part, arranged hierarchically. The main novelty of the proposed FI-HCNN is the special inherited structure between the hierarchy; the severity estimation part utilizes the latent features to exploit the fault-related representations in the fault diagnosis task. FI-HCNN can improve the accuracy of the fault severity estimation because the level-specific abstraction is supported by the latent features. Also, FI-HCNN has ease in practical application because it is developed based on stator current signals which are usually acquired for a control purpose. Experimental studies of mechanical motor faults, including eccentricity, broken rotor bars, and unbalanced conditions, are used to corroborate the high performance of FI-HCNN, as compared to both conventional methods and other hierarchical deep learning methods. Keywords Severity estimation · Fault diagnosis · Motor current signature analysis · Hierarchical network · Induction motor · Convolutional neural network
1 Introduction Motors are widely used in manufacturing applications that require a rotating force due to their low cost and high reliability. In spite of their high reliability, motors are subjected to mechanical and electrical faults because of their exposure to unexpected stresses, such as in-use damage and environmental conditions. The degradation of motors can lead to deterioration in product quality, therefore it is crucial to diagnose the motor state and evaluate the fault severity [1]. To cope with these problems, motor current signature analysis (MCSA) has been studied for fault diagnosis (FD) * Byeng D. Youn [email protected] 1
Department of Mechanical and Aerospace Engineering, Seoul National University, Seoul 08826, Republic of Korea
2
OnePredict Inc., Seoul 08826, Republic of Korea
3
Institute of Advanced Machines and Design, Seoul National University, Seoul 08826, Republic of Korea
and severity estimation (SE), due to its ease of implementation [2]. In particular, SE is crucial to enable proper maintenance decisions before a failure of the system. For condition-based maintenance, SE can be easily extended
Data Loading...
