FPGA Implementation of AI-Based Inverter IGBT Open Circuit Fault Diagnosis of Induction Motor Drives

Abstract

In modern industrial manufacturing processes, induction motors are broadly utilized as industrial drives. Online condition monitoring and diagnosis of faults that occur inside and/or outside of the Induction Motor Drive (IMD) system make the motor highly reliable, helping to avoid unscheduled downtimes, which cause more revenue loss and disruption of production. This can be achieved only when the irregularities produced because of the faults are sensed at the moment they occur and diagnosed quickly so that suitable actions to protect the equipment can be taken. This requires intelligent control with a high-performance scheme. Hence, a Field Programmable Gate Array (FPGA) based on neuro-genetic implementation with a Back Propagation Neural network (BPN) is suggested in this article to diagnose the fault more efficiently and almost instantly. It is reported that the classification of the neural network will provide the output within 2 µs although the clone procedure with microcontroller requires 7 ms. This intelligent control with a high-performance technique is applied to the IMD fed by a Voltage Source Inverter (VSI) to diagnose the fault. The proposed approach was simulated and experimentally validated.

Health Status Detection for Motor Drive Systems Based on Generalized-Layer-Added Principal Component Analysis

“…References [4][5][6][7][8][9][10] primarily employ signal methods, obtaining diagnostic results by processing current signals. The advantage of current-based methods is their fast detection speed, but their detection accuracy is low.…”

“…This method cannot achieve real-time diagnosis. The methods proposed in articles [7][8][9] are incapable of identifying the load status of the motor. Reference [10] proposes a fault diagnosis method that analyzes the current-vector trajectory.…”

FPGA-based fault analysis for 7-level switched ladder multi-level inverter using decision tree algorithm

“…The very high speed integrated circuit hardware description language (VHDL) code is developed for the digital pulse-width modulator (DPWM) generation and its control of the DC-DC voltage regulator and implemented in the FPGA for real-time validation [23] The FPGA-based control for the PV-fed DC-DC-AC converter gives accuracy and low total harmonic distortion (THD)% in the implementation of 81-level MLI [24]. The FPGAbased neuro-genetic algorithm for backward propagation of neural networks can be used for fault detection in induction motor drives [25]. This paper deals with the analysis of the fault that occurs in the switches of the switched ladder type MLI circuit using the decision tree algorithm implemented in the FPGA device.…”

A Thermal Management Strategy for Inverter System Based on Predictive Control

“…Gridconnected inverters play an important role in electricity generation using various energy sources, so they have been widely used in the field of power generation [1][2][3][4][5][6], and their reliability is very important for stably and reliably merging the generated electricity in to the large power grid [7][8][9][10][11]. IGBT module is one of the most widely used power switching device in various power converters, and its reliability determines the reliability of grid-connected inverters [12][13][14][15][16]. According to existing research findings, temperature fluctuation during operation is the primary reason for gradual failure of IGBT module, and causes for such temperature fluctuation include the fundamental frequency junction temperature fluctuation caused by sinusoidal changes of network side current, and the low frequency junction temperature fluctuation caused by power fluctuation of system [17][18][19][20][21][22][23].…”