In this survey paper, we systematically summarize existing literature on bearing fault diagnostics with machine learning (ML) and data mining techniques. While conventional ML methods, including artificial neural network (ANN), principal component analysis (PCA), support vector machines (SVM), etc., have been successfully applied to the detection and categorization of bearing faults for decades, recent developments in deep learning (DL) algorithms in the last five years have sparked renewed interest in both industry and academia for intelligent machine health monitoring. In this paper, we first provide a brief review of conventional ML methods, before taking a deep dive into the state-of-the-art DL algorithms for bearing fault applications. Specifically, the superiority of DL based methods over conventional ML methods are analyzed in terms of fault feature extraction and classification performances; many new functionalities enabled by DL techniques are also summarized. In addition, to obtain a more intuitive insight, a comparative study is conducted on the classification accuracy of different algorithms utilizing the open source Case Western Reserve University (CWRU) bearing dataset. Finally, to facilitate the transition on applying various DL algorithms to bearing fault diagnostics, detailed recommendations and suggestions are provided for specific application conditions such as the setup environment, the data size, and the number of sensors and sensor types. Future research directions to further enhance the performance of DL algorithms on health monitoring are also discussed.
Abstract-A breakdown of the electrical insulation system causes catastrophic failure of the electrical machine and brings large process downtime losses. To determine the conditions of the stator insulation system of motor drive systems, various testing and monitoring methods have been developed. This paper presents an in-depth literature review of testing and monitoring methods, categorizing them into online and offline methods, each of which is further grouped into specific areas according to their physical nature. The main focus of this paper is on testing and monitoring techniques that diagnose the condition of the turn-to-turn insulation of low-voltage machines, which is a rapidly expanding area for both research and product development efforts. In order to give a compact overview, the results are summarized in two tables. In addition to monitoring methods on turn-to-turn insulation, some of the most common methods to assess the stator's phase-to-ground and phase-to-phase insulation conditions are included in the tables as well.
The advent of the transformerless multilevel inverter topology has brought forth various pulsewidth modulation (PWM) schemes as a means to control the switching of the active devices in each of the multiple voltage levels in the inverter. An analysis of how existing multilevel carrier-based PWM affects switch utilization for the different levels of a diode-clamped inverter is conducted. Two novel carrier-based multilevel PWM schemes are presented which help to optimize or balance the switch utilization in multilevel inverters. A 10-kW prototype sixlevel diode-clamped inverter has been built and controlled with the novel PWM strategies proposed in this paper to act as a voltage-source inverter for a motor drive.Index Terms-Carrier-based pulsewidth modulation, diodeclamped inverter, multilevel converter, multilevel inverter, multilevel pulsewidth modulation.
This paper investigates the experimental implementation and detection of rotor faults in permanent magnet synchronous machines. Methods are shown how to experimentally introduce static and dynamic eccentricities and broken magnet cases. A new magnet flux estimation that does not require the measurement of the rotor position or speed is developed. The detection of these and other rotor faults by measuring only the stator currents and voltages are shown experimentally. The paper concludes by contributing a description of a condition-monitoring scheme for detection rotor faults. Index Terms-Permanent magnet synchronous machines (PMSM).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.