Application of Artificial Neural Network Modeling for Machining Parameters Optimization in Drilling Operation

Abstract

Machining is one of the material removal processes, which is used to make a component to closer tolerance for assembly. In that, drilling is one of the traditional machining processes used for making a hole on component faces by removing a volume of metal from the job by cutting tool called drill. A drill is a rotary end-cutting tool with one or more cutting lips and usually one or more flutes for the passage of chips and the admission of cutting fluid. The general machining parameters considered in drilling operations are spindle speed and feed rate. These parameters relationship should be identified to improve hole quality and to increase productivity. For solving these difficulties, lots of mathematical and statistical modelling techniques were used in past decades. In the sense that, now a day newer methods are being identified. Of those Artificial Neural Network (ANN) is widely used in modelling machining parameters. An artificial neural network, usually called neural network, is a mathematical model or computational model that is inspired by the structure and functional aspects of biological neural networks. A neural network consists of an interconnected group of artificial neurons and it processes information using a connectionist approach to computation. To select the best machining parameters optimization techniques are used. Genetic algorithm (GA) and particle swarm optimization (PSO) are the two most used optimization techniques in research field. The roles of GA and PSO in drilling parameters optimization were discussed and a comparison is made between GA and PSO in this paper. The best optimization technique is proposed for drilling operation.