Abstract
This study presents a machine learning technique for fault diagnostics in induction motor drives. A normal model and an extensive range of faulted models for the inverter-motor combination were developed and implemented using a generic commercial simulation tool to generate voltages and current signals at a broad range of operating points selected by a Particle Swarm Optimization (PSO) based machine learning algorithm. A structured Particle Swarm (PS)-neural network system has been designed, developed and trained to detect and isolate the most common types of faults: single switch open circuit faults, post-short circuits, short circuits and the unknown faults. Extensive simulation experiments were conducted to test the system with added noise and the results show that the structured neural network system which was trained by using the proposed machine learning approach gives high accuracy in detecting whether a faulty condition has occurred, thus isolating and pin-pointing to the type of faulty conditions occurring in power electronics inverter based electrical drives. Finally, the authors show that the proposed structured PS-neural network system has the capability of real-time detection of any of the faulty conditions mentioned above within 20 milliseconds or less.
Highlights
A large number of industrial drives, including some for electric or hybrid vehicles, fault used in Electric Vehicles (EV) and hybrid electric diagnostic techniques have not been well investigated vehicles (HEV) (Chan and Chau, 2001), consist of three- yet, since EV/HEV is still in the relatively early stage phase induction motor drives and associated power in the automotive industry compared to Internal Combustion (IC) engine electronics based inverter, together with the necessary vehicles
Extensive simulation experiments were conducted to test the system with added noise and the results show that the structured neural network system which was trained by using the proposed machine learning approach gives high accuracy in detecting whether a faulty condition has occurred, isolating and pin-pointing to the type of faulty conditions occurring in power electronics inverter based electrical drives
A large number of industrial drives, including some for electric or hybrid vehicles, fault used in Electric Vehicles (EV) and hybrid electric diagnostic techniques have not been well investigated vehicles (HEV) (Chan and Chau, 2001), consist of three- yet, since EV/HEV is still in the relatively early stage phase induction motor drives and associated power in the automotive industry compared to IC engine electronics based inverter, together with the necessary vehicles
Summary
Literature (Gertler et al, 1995; Nyberg, 2002) on fault diagnostics of Internal Combustion (IC) engine vehicles. In this study the authors present the state of the art diagnostic technologies based on PSO triggered machine learning and a model that simulates a closed loop field oriented control based electric drive to generate multiple quantitative attributes of various signals including the torque and voltages and currents in all phases. Murphey et al (2006a) and Masrur et al (2007) the authors presented a model based approach for fault diagnosis in electric drives under both open-and closed-loop controls. An innovative PSO based machine learning framework was presented that involves an algorithm that automatically selects a set of representative operating points in the torque-speed domain and the training of a diagnostic neural network for the detection of single switch faults and post short circuit faults. More information regarding the authors' related work can be found in reference
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
