Design And Optimization Of Wire-Electrochemical Discharge Machining (W-EDM) Process Based On Vibration System Detector On Material Variations By Particle Swarm Optimization Algorithm Method

Abstract

Vibration analysis is one way that industrial machine maintenance can be done quickly and conveniently. A pattern of sound is produced by engine vibrations in which the sounds of several engines are mixed together. Engine component damage is indicated by excessive vibration levels in the engine. The machine will sustain more significant harm if nothing is done about this high vibration. The machine has to be maintained in order for it to function at its best. In order to prolong machine life, machine maintenance systems are crucial in the industrial sector. Vibration-signal-based predictive maintenance is one often employed maintenance technique. One form of maintenance that can be performed by keeping an eye on the vibration conditions the machine is producing is called predictive maintenance. Predictive maintenance based on vibration cues is one often employed maintenance technique. One kind of maintenance that can be done is predictive maintenance, which involves keeping an eye on the vibration conditions that the machine produces. Analyzing the machine's vibration level as represented by the vibration speed's amplitude value is one technique to prevent damage to the device. By using the vibration signals that arise, this technology can predict machine damage and prevent major damage. The research combined the two outputs of vibration detection and process optimization to create a prototype Wire-Electrochemical Discharge Machining (W-EDM) machine. The goal of this study is to identify and ascertain the parameter values that yield the best possible result. Full factorial, orthogonal array, and response surface approach are the experimental designs employed, and back propagation neural network and particle swarm optimization algorithm are the optimization techniques.