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

Abstract

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. Keyword:Artificial [3]. CMLI gets rid of the capacitor voltage balancing method, which is a major challenge in the Flying Capacitor Multilevel Inverter as; it needs very complex voltage balancing techniques [4]. Modular topology of the CMLI facilitates the topology for the location of fault and the reconfiguration applied in a simpler manner [5]. Whereas the Diode Clamped MLI and the Flying Capacitor MLI has switches continuously connected according to the number of voltage levels it can deliver, which introduces complexity while fault location and reconfiguration. Application of CMLI ranges from STATCOM [6] to Active Power Filter, which demands fault free operation since it involves power quality solutions [7]. The fault diagnosis and the reconfiguration of the MLI by the use of Artificial Neural Network as the fault diagnosis tool was developed which exhibited 95% accuracy in diagnosis of the faults was tabulated [6]. The reconfiguration method proposed in [8] cleared both the open circuit and the closed circuit faults in six periodic cycles. In order to develop the fault diagnosis the development of a mathematical model

Extended Kalman observer based sensor fault detection

“…Fault detection concerned with extraction of relevant features that indicate the existence of a fault, whereas, fault identification refers location and categorization of a fault or a set of faults. To avoid these consequences in the control systems, it is critical to detect and identify any possible faults at the earliest stage [1]. Among all the methods for fault diagnosis, one of the particular interesting techniques is the model-based fault detection observer approach [2][3][4][5][6][7].…”

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

“…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.…”

Rolling Element Bearing Condition Monitoring using Filtered Acoustic Emission

“…Albarbar et al, shows the acoustic monitoring of engine fuel injection [10]. Fault diagnosis for the multilevel inverter switch is found in literature [11]. M.A.…”