Enhancing Motor Vibration Characteristics using Particle Swarm Optimization and Artificial Neural Network

In this paper, Particle Swarm Optimization (PSO) and Artificial Neural Network (ANN) algorithms are used to improve the characteristics of vibration of an electric motor considering high efficiency and prolongation of the operating time of the motor. Applying a PSO algorithm, it can be observed that the optimal speed of the motor is 1578.74 RPM at a vibration amplitude of 0.50, which means the compromise between resource efficiency and mechanical reliability. Using a similar ANN model, the predicted motor speed was 1497.51 RPM at a vibration amplitude of 9. These models have thereby proven the appropriateness of computational intelligence techniques for reducing vibration amplitudes and thus improving performance in service, cutting down maintenance costs, and increasing service life in industrial applications. These findings emphasize that in the case of production engineering, aviation, and automotive engineering, motor vibration is of significant relevance because reduced vibration means better efficiency with less wear and tear. Finally, the study proved that PSO and ANN algorithms could be applied to other engineering optimization challenges, thus showing the versatility of computational intelligence. It can be further extended to work out finer tuning of PSO and ANN parameters for better optimization, or any other computational techniques, such as genetic algorithms or fuzzy logic, could be used to work out further advancements in motor vibration optimization. This research illustrates the potential of transforming computational intelligence methods to realize improvement in the design, implementation, and performance of motors for very different industries