Optimal design of 4KW squirrel cage induction motor using Particle Swarm Optimization (PSO) and Genetic Algorithm (GA)

The optimal design of machines is essential to conserve scarce resources while ensuring standard or improved output. That is why this work seeks to determine the optimal design of a 4-kilowatt (4KW) squirrel cage induction motor through evolutionary algorithms. The paper seeks to minimize mass, cost and losses of production while improving efficiency and torque. Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) are the chosen analytical techniques to determine the optimal design model for a squirrel cage induction motor. Common design parameters were retrieved from existing motors along with relevant constraints to furnish both algorithms. MATLAB R2018a was used to set both algorithms and run analysis. It was discovered after the analysis that both evolutionary algorithms can create superior designs of squirrel cage induction motors while reducing costs, losses and mass. The findings also show that squirrel cage induction motors constructed in line with design parameters from both intelligent algorithms can improve net efficiency and torque. Based on these findings, it is recommended that artificial neural networks should be adopted in building the most efficient models for mechanical parts in industrial manufacturing processes and Computer Aided Design (CAD) should feature in electrical and electronics engineering to increase the probability of solving design problems with greater ease and accuracy.