Experimental Investigation for the Multi-objective Optimization of Machining Parameters on AISI D2 Steel Using Particle Swarm Optimization Coupled with Artificial Neural Network

Abstract

High Carbon High Chromium (or AISI D2) Steels, owing to the fine surface finish they produce upon grinding, find lot of applications in die casting. Machining parameters affect the surface finish significantly during the grinding operation. In this context, this work puts an effort to arrive at the optimum machining parameters relating to fine surface finish with minimum cutting force. The material removal caused by the abrasive grinding wheel makes the process a very complex and nonlinear machining operation. In many situations, traditional optimization techniques fail to provide realistic optimum conditions because of the associated complexity. In order to overcome this issue, particle swarm optimization (PSO) coupled with artificial neural network (ANN) is applied in this research work for parameter optimization with the objective of achieving minimum surface roughness and cutting force. The machining parameters selected for the investigation were table speed, cross feed and depth of cut and the responses were surface roughness and cutting force. ANNs, inspired from biological neural networks, are well capable of providing patterns, which are too complex in behavior. The ANN model developed was used as the fitness function for PSO to complete the optimization. Optimization was also carried out using conventional response surface methodology-genetic algorithm (RSM-GA) approach in which regression equation developed with RSM was considered as the fitness function for GA. Confirmatory experiments were conducted and the comparison showed that PSO coupled with ANN is a reliable tool for complex optimization problems.

Milling of Graphene Reinforced Ti6Al4V Nanocomposites: An Artificial Intelligence Based Industry 4.0 Approach

“…Therefore, several researchers used traditional methods for optimizing the cutting conditions such as Taguchi method [ 29 ] and Response surface methodology (RSM) [ 30 , 31 ]. However, Taguchi and RSM methods obtain optimal solutions dependent on the randomly chosen initial solutions, and the optimization falls into the local solution [ 32 , 33 ]. On the other hand, metaheuristic algorithms are being proposed by researchers to guarantee a globally optimal solution for machining characteristics.…”

“…Choudhary et al [ 35 ] used hybrid particle swarm optimization and genetic algorithm for optimizing submerged arc welding process parameters. According to [ 32 ] GA method has some limitations, including higher computation time, too many control parameters, and deliberate convergence. To overcome these limitations, a multi-objective particle swarm optimization (MPSO) is adapted as an effective tool to optimize cutting parameters.…”

“…To overcome these limitations, a multi-objective particle swarm optimization (MPSO) is adapted as an effective tool to optimize cutting parameters. MPSO is faster compared to the GA method, and can simultaneously apply both global and local search, whereas GA is mainly more effective for global search, as mentioned by [ 32 , 34 , 36 , 37 , 38 ]. The effectiveness of the optimization methods depends on the prediction model as a fitness function.…”

“…Therefore, there is an increasing interest in the development of models for machining processes to guarantee and obtain reliable results. Artificial intelligence techniques are effective tools to develop models for complex nonlinear systems [ 32 , 39 ]. Bustillo et al [ 40 ] developed prediction models for flatness deviation of the milled surface during face milling of AISI 1045 steel using the machine learning method.…”

“…Conde et al [ 39 ] developed prediction models using an artificial neural network and used these models as a fitness function for simulated annealing for optimizing the wire electrical discharge machining. Gopan et al [ 32 ] combined an artificial neural network with the particle swarm optimization (PSO) method for optimizing the cutting parameters to minimize the surface roughness and cutting forces during the grinding process and found accurate results during validation. Abbas et al [ 47 ] optimized the cutting condition during the face milling of high-strength steel grade-H for minimizing surface roughness and machining time using an artificial neural network with the Edgeworth-Pareto method.…”