Modified Three-Layered Artificial Neural Network-Based Improved Control of Multilevel Inverters for Active Filtering

Multilevel Inverters (MLI) gains importance in Distribution systems, Electrical Drive systems, HVDC systems and many more applications. As Multilevel Inverters comprises of number of power switches the fault diagnosis of MLI becomes tedious. This paper is an attempt to develop and analyze the fault diagnosis method that utilizes Artificial Neural Network to get it trained with the fault situations. A performance analysis of Genetic Algorithm (GA) and the Modified Genetic Algorithm (MGA), which optimizes the Artificial Neural Network (ANN) that trains itself on the fault detection, and reconfiguration of the Cascaded Multilevel Inverters (CMLI) is attempted. The Total Harmonic Distortion (THD) occurring due to switch failures or driver failures occurring in the CMLI is considered for this comparative analysis. Elapsed time of recovery, Mean Square Error (MSE) and the computational budgets of ANN are the performance parameters considered in this comparative analysis. Optimization is involved in the process of updating the weight and the bias values in the ANN network. Matlab based simulation is carried out and the results are obtained and tabulated for the performance evaluation. It was observed that Modified Genetic Algorithm performed better than the Genetic Algorithm while optimizing the ANN training.

Download Full-text

Real time selective harmonic minimization for multilevel inverters using genetic algorithm and artificial neural network angle generation

Proceedings of The 7th International Power Electronics and Motion Control Conference ◽

10.1109/ipemc.2012.6258973 ◽

2012 ◽

Cited By ~ 7

Author(s):

Faete J. T. Filho ◽

Leon M. Tolbert ◽

Burak Ozpineci

Keyword(s):

Neural Network ◽

Genetic Algorithm ◽

Artificial Neural Network ◽

Real Time ◽

Multilevel Inverters ◽

Artificial Neural

Download Full-text

Fault Diagnosis and Reconfiguration of Multilevel Inverter Switch Failure-A Performance Perspective

International Journal of Electrical and Computer Engineering (IJECE) ◽

10.11591/ijece.v6i6.pp2610-2620 ◽

2016 ◽

Vol 6 (6) ◽

pp. 2610

Author(s):

T.G. Manjunath ◽

Ashok Kusagur

Keyword(s):

Neural Network ◽

Genetic Algorithm ◽

Artificial Neural Network ◽

Comparative Analysis ◽

Fault Diagnosis ◽

Distribution Systems ◽

Multilevel Inverters ◽

Modified Genetic Algorithm ◽

Artificial Neural ◽

A Performance

Multilevel Inverters (MLI) gains importance in Distribution systems, Electrical Drive systems, HVDC systems and many more applications. As Multilevel Inverters comprises of number of power switches the fault diagnosis of MLI becomes tedious. This paper is an attempt to develop and analyze the fault diagnosis method that utilizes Artificial Neural Network to get it trained with the fault situations. A performance analysis of Genetic Algorithm (GA) and the Modified Genetic Algorithm (MGA), which optimizes the Artificial Neural Network (ANN) that trains itself on the fault detection, and reconfiguration of the Cascaded Multilevel Inverters (CMLI) is attempted. The Total Harmonic Distortion (THD) occurring due to switch failures or driver failures occurring in the CMLI is considered for this comparative analysis. Elapsed time of recovery, Mean Square Error (MSE) and the computational budgets of ANN are the performance parameters considered in this comparative analysis. Optimization is involved in the process of updating the weight and the bias values in the ANN network. Matlab based simulation is carried out and the results are obtained and tabulated for the performance evaluation. It was observed that Modified Genetic Algorithm performed better than the Genetic Algorithm while optimizing the ANN training.

Download Full-text

Enhance the accuracy of control algorithm for multilevel inverter based on artificial neural network

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v20.i3.pp1148-1158 ◽

2020 ◽

Vol 20 (3) ◽

pp. 1148

Author(s):

Mohammed Rasheed ◽

Moataz M. A. Alakkad ◽

Rosli Omar ◽

Marizan Sulaiman ◽

Wahidah Abd Halim

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Real Time ◽

Optimization Technique ◽

Harmonic Distortion ◽

Multilevel Inverter ◽

Multilevel Inverters ◽

Harmonic Elimination ◽

Selective Harmonic Elimination ◽

Artificial Neural

In converters or multilevel inverters it is very important to ensure that the output of the multilevel inverters waveforms in term of the voltage or current of the waveforms is smooth and without distortion. The artificial neural network (ANN) technique to obtaining proper switching angles sequences for a uniform step asymmetrical modified multilevel inverter by eliminating specified higher-order harmonics while maintaining the required fundamental voltage and current waveform. However, through this paper a modified CHB-MLI are proposed using artificial intelligence optimization technique based on modulation Selective Harmonic Elimination (SHE-PWM). A most powerful modulation technique that used to minimize a harmonic contants during the outout waveform of multilevel inverter is a SHE-PWM method. The proposed a five-level Modified Cascaded H-Bridge Multilevel Inverter (M-CHBMI) with ANN controller to improve the output voltage and current performance and achieve a lower Total Harmonic Distortion (THD). The main aims of this paper cover design, modeling, prediction for real-time generation of optimal switching angles in a single-phase topology of modified five level CHB-MLI. due to the heavy cost of computation to solving transcendental nonlinear equations with specified number, a real-time application of Selective Harmonic Elimination-Pulse Width Modulation (SHE-PWM) technique is limited. SHE equations known as a transcendental nonlinear equation that contain trigonometric functions. The prototype of a 5-level inverter in Digital Signal Processing (DSP) TMS320F2812 reveals that the proposed method is highly efficient for harmonic reduction in modified multilevel inverter.

Download Full-text