| Title | Multiple Open-Switch Fault Diagnosis Using ANNs for Three-Phase PWM Converters |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Kim, Won-Jae, Kim, Sang-Hoon |
| Conference Name | 2021 24th International Conference on Electrical Machines and Systems (ICEMS) |
| Date Published | oct |
| Keywords | adaptive linear neuron, artificial neural network, Artificial neural networks, Cyber-physical systems, Diagnosis, fault diagnosis, human factors, Metrics, multiple fault diagnosis, Neurons, open-fault, pubcrawl, Pulse width modulation, Pulse width modulation converters, Resiliency, Stators, three-phase PWM converter, total harmonic distortion |
| Abstract | In this paper, a multiple switches open-fault diagnostic method using ANNs (Artificial Neural Networks) for three-phase PWM (Pulse Width Modulation) converters is proposed. When an open-fault occurs on switches in the converter, the stator currents can include dc and harmonic components. Since these abnormal currents cannot be easily cut off by protection circuits, secondary faults can occur in peripherals. Therefore, a method of diagnosing the open-fault is required. For open-faults for single switch and double switches, there are 21 types of fault modes depending on faulty switches. In this paper, these fault modes are localized by using the dc component and THD (Total Harmonics Distortion) in fault currents. For obtaining the dc component and THD in the currents, an ADALINE (Adaptive Linear Neuron) is used. For localizing fault modes, two ANNs are used in series; the 21 fault modes are categorized into six sectors by the first ANN of using the dc components, and then the second ANN localizes fault modes by using both the dc and THDs of the d-q axes current in each sector. Simulations and experiments confirm the validity of the proposed method. |
| DOI | 10.23919/ICEMS52562.2021.9634387 |
| Citation Key | kim_multiple_2021 |
Multiple Open-Switch Fault Diagnosis Using ANNs for Three-Phase PWM Converters