Bearing fault diagnostic using machine learning algorithms
- PDF / 420,784 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 93 Downloads / 296 Views
REGULAR PAPER
Bearing fault diagnostic using machine learning algorithms Laith S. Sawaqed1
· Ayman M. Alrayes1
Received: 24 February 2020 / Accepted: 19 September 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract This study aims to enhance the condition monitoring of external ball bearings using the raw data provided by Paderborn University which provided sufficient data for motor current signal MCS. Three classes of bearings have been used: healthy bearings, bearings with an inner race defect, and bearings with outer race defect. Online data at different operating conditions, bearings, and faults extent of artificial and real damages have been chosen to provide the generalization and robustness of the model. After proper preprocessing to the raw data of vibration and MCS, time, frequency, and time–frequency domain features have been extracted. Then, optimal features have been selected using genetic algorithm. Artificial neural network with optimized structure using genetic algorithm has been implemented. A comparison between the performance of vibration and motor current signal has been presented. Moreover, our results are compared to previous work by using the same raw data. Results showed the potential of motor current signal in bearing fault diagnosis with high classification accuracy. Moreover, the results showed the possibility to provide a promised diagnostic model that can diagnose bearings of real faults with different fault severities using MCS. Keywords Bearing damage detection · Machine fault diagnostic · Vibration · Motor current signal · Machine learning algorithm · Neural networks · Genetic algorithm
1 Introduction There is no doubt that the proper maintenance management system contributes significantly in increasing the company profits and prevents huge losses. Condition monitoring (CM) and predictive maintenance are an essential aspects for improving a sufficient maintenance management system, for instance; a case study for a paper mill at Swedish showed that preventing unplanned stoppage for a year will increase the profits by 0.975 million USD [1]. CM is essential to avoid harmful consequences and reduce financial loss and that’s why it has been attracting the interest of researchers for the last few decades [2]. Machine failure occurs due to many reasons, such as stator faults, rotor faults, or bearing faults [3]. Statistics, in the industrial world, showed that up to two-thirds of motor fail-
B
Laith S. Sawaqed [email protected] Ayman M. Alrayes [email protected]
1
ures in the electromechanical drive systems are initiated in the bearings due to rolling bearing damages [4]. Data-driven bearing fault diagnostic passes through three main steps to give a final decision regarding the state of the bearing as per ISO 13374, which are data acquisition (DA), data manipulation (DM), and state detection (SD). In the first step, raw data are to be collected from the system. These data could be any signal that carries the signature of the fault, for instance,
Data Loading...
