Artificial Neural Network Based Rotor Reactance Control Essay

Abstract Problem statement The Rotor reactance control by inclusion of external capacitance in the rotor coil circumference has been in recent research for improving the performances of Wound Rotor Induction Motor (WRIM). The rotor capacitive reactance is adjusted such that for every desired load torque the efficiency of the WRIM is maximized. The rotor external capacitance can be controlled utilise dynamic capacitor in which the duty ratio is varied for emulating the capacitance care for. This study presents a novel technique for tracking maximum efficiency point in the entire operating range of WRIM using Artificial Neural Network (ANN). The data for ANN training were obtained on a three phase WRIM with dynamic capacitor control and rotor short circuit at different speed and load torque values. Approach A novel nueral network model based on back-propagation algorithm has been developed and accomplished for determining the maximum efficiency of the motor with no prior knowledge of the machine parameters. The input proteans to the ANN are stator current (Is), Speed (N) and Torque(Tm) and the output variable is duty ratio (D). Results The target is set with a goal of 0.00001. The accuracy of the ANN model is measured using Mean Square Error (MSE) and R2 parameters. The result of R2 value of the proposed ANN model is 0.99980. Conclusion The optimal duty ratio and corresponding optimal rotor capacitance for improving the performances of the motor are predicted for low, medium and full scores by using proposed ANN model. Key wordsArtificial Neural Network (ANN), Wound Rotor Induction Motor (WRIM), Torque(Tm), Digital Signal Processor (DSP), rotor reactance control, corresponding optimal rotor INTRODUCTIONIt is known from the literatu... ...11. Neural network based new energy conservation scheme for three phase generalization motor operating under varying load torques. IEEE Int. Conf. PACC11, pp 1-6.R. A. Jayabarathi and N. Devarajan, 2007. ANN Based DSPI C Controller for Reactive Power Compensation. American Journal of Applied Sciences, 4 508-515. inside 10.3844/ajassp.2007.508.515.T. Benslimane, B. Chetate and R. Beguenane, 2006. alternative Of Input Data Type Of Artificial Neural Network To Detect Faults In Alternative Current Systems. American Journal of Applied Sciences, 3 1979-1983. DOI 10.3844/ajassp.2006.1979.1983.M. M. Krishan, L. Barazane and A. Khwaldeh, 2010. Using an Adaptative Fuzzy-Logic System to Optimize the Performances and the Reduction of Chattering Phenomenon in the Control of Induction Motor. American Journal of Applied Sciences, 7 110-119. DOI 10.3844/ajassp.2010.110.119.