Performance evaluation of Modified Genetic Algorithm over Genetic Algorithm implementation on fault diagnosis of Cascaded Multilevel Inverter

Abstract

Fault diagnosis on Multilevel Inverter (MLI) has been a subject of research for about a decade. This paper is an attempt to deliver a performance analysis of Genetic Algorithm (GA) and the Modified Genetic Algorithm (MGA) working to optimize Artificial Neural Network (ANN) that trains itself on the fault detection and reconfiguration of the Cascaded Multilevel Inverters (CMLI). The open circuit (OC) faults occurring in the CMLI is considered for this comparative analysis of the performance. The parameters that are taken for the performance evaluation are elapsed time of recovery, Mean Square Error (MSE) and the computational budgets of ANN. Matlab/Simulink is used to develop the CMLI and M-files are used to develop the ANN and optimization algorithms like GA and MGA. The results are obtained and tabulated and performance evaluation carried out.

Analysis of Different Meta Heuristics Method in Intelligent Fault Detection of Multilevel Inverter with Photovoltaic Power Generation Source

“…Two off springs are generated using the following formulae, Where, a is the random weighting factor. In order to maintain genetic diversity between the off springs the mutation operation is carried out [3]. For the calculation of the mutation the maximum and the minimum weight values are taken from the a values and it is mentioned in the below equations as 'maxweight' and 'minweight'.…”

“…The The usage of multilevel inverter is expanding day by day as the HVDC and the Industrial Drives need performance enhancement in the quality of power that has to be delivered to the industry and the transmission systems.Cascaded H bridge being the advanced multilevel inverter topology,many literatures are using the Cascaded topology. Optimized Artificial Neural Network based implementation for fault detection of multilevel inverter is carried out in [1][2][3].Investigation of different fault mode behavior is carried out for different types of faults [4]. The park's transform vector pattern is used for the fault diagnosis in the voltage source inverter fed AC drives [5] [6].…”

“…The training of the RBF based ANN is carried out by optimizing the training parameters comprising both weight and the bias values in the neural network learning process. This paper which is the improvement of the previous works [1][2][3] is organized as follows, the Section -II would have the description about the training of the ANN with the radial basis function, Section -III discusses about the optimization algorithm used in the ANN parameter estimation, Section-IVexamines the results and discussion with inference of the different meta heuristic methods, and it is followed by the conclusion and references.…”

“…levywhere l is a constant (1< l £ 3) and G is the gamma function which is defined by the integral value , 1217 as the velocity update function of GA the following process would be calculated.The parent selection for the population generation is carried using the Roulette Selection method as defined below[3],Where is the set of all fitness values, is the ith fitness value. Let S1 be some random value and S2 and are variables.…”

Robust Fault Detection of Multilevel Inverter using Optimized Radial Basis Function based Artificial Neural Network in Renewable Energy Power Generation Application

“…Considering the Total Harmonic Distortion for the fault detection implementation has been successfully analyzed in our previous papers [1][2][3]. With the frequent use of multilevel inverters in the HVDC systems and electrical drives systems the fault detection of the multilevel inverters would be of utmost importance since there are multiple switches that have to be monitored for faults.…”