Artificial Neural Network Based Rotor Reactance Control Essay

Conceptual: Problem explanation: The Rotor reactance control by incorporation of outer capacitance in the rotor circuit has been in late research for improving the exhibitions of Wound Rotor Induction Motor (WRIM). The rotor capacitive reactance is balanced with the end goal that for any ideal burden torque the effectiveness of the WRIM is augmented. The rotor outside capacitance can be controlled utilizing dynamic capacitor in which the obligation proportion is changed for copying the capacitance esteem. This examination presents a novel procedure for following most extreme proficiency point in the whole working scope of WRIM utilizing Artificial Neural Network (ANN). The information for ANN preparing were gotten on a three stage WRIM with dynamic capacitor control and rotor hamper diverse speed and burden torque esteems. Approach: A tale nueral organize model dependent on back-proliferation calculation has been created and prepared for deciding the most extreme productivity of the engine with no earlier information on the machine parameters. The info factors to the ANN are stator current (Is), Speed (N) and Torque(Tm) and the yield variable is obligation proportion (D). Results: The objective is define with an objective of 0.00001. The precision of the ANN model is estimated utilizing Mean Square Error (MSE) and R2 parameters. The consequence of R2 estimation of the proposed ANN model is 0.99980. End: The ideal obligation proportion and relating ideal rotor capacitance for improving the exhibitions of the engine are anticipated for low, medium and full loads by utilizing proposed ANN model. Key words: Artificial Neural Network (ANN), Wound Rotor Induction Motor (WRIM), Torque(Tm), Digital Signal Processor (DSP), rotor reactance control, comparing ideal rotor Presentation It is known from the literatu... ...11. Neural system based new vitality preservation plot for three stage acceptance engine working under changing burden torques. IEEE Int. Conf. PACC’11, pp: 1-6. R. A. Jayabarathi and N. Devarajan, 2007. ANN Based DSPIC Controller for Reactive Power Compensation. American Journal of Applied Sciences, 4: 508-515. DOI: 10.3844/ajassp.2007.508.515. T. Benslimane, B. Chetate and R. Beguenane, 2006. Decision 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. Utilizing 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.