A novel hybridization of artificial neural network and moth-flame optimization (ANN–MFO) for multi-objective optimization in magnetic abrasive finishing of aluminium 6060

Abstract

In industries, the impact of magnetic abrasive finishing (MAF) is well recognized in achieving accurate surfaces, minimizing imperfections and providing high-quality surface finish especially in micro-and nano-range. In the same context, this paper presents a hybrid optimization method for multi-objective optimization that combines back-propagation artificial neural network (ANN) with a newly developed nature-inspired optimization algorithm, i.e. moth-flame optimization (MFO) algorithm, which is used to predict optimal process parameters of magnetic abrasive finishing process. The back-propagation ANN is gradient-based local search algorithm, while MFO is a rapid and global search algorithm for controlling the generation of candidate solutions. Initially, the MFO algorithm is integrated for training the neural network with unknown set of weights and biases and in the process overcomes the shortcomings of traditional training algorithms having slow convergence and local optima stagnation. Further, the MFO algorithm is also employed to predict the number of neurons in hidden layers. Finally, the proposed hybrid ANN-MFO methodology establishes a multi-objective optimization model in terms of important process parameters for optimizing the MAF process conditions. The optimization of different MAF process parameters is performed using MFO algorithm by incorporating the adaptive search procedure, which further enhances the exploration behaviour. Surface roughness, temperature of workpiece during the finishing operation and hardness of finished surface are investigated as the output response in the finishing of aluminium 6060. The design variables considered are working gap, abrasive weight, voltage and rotational speed. The results predicted by the proposed hybrid ANN-MFO algorithm provide effective and accurate process parameters to enhance surface finish and part quality that will be beneficial for real manufacturing environment.

An Improved Moth-Flame Optimization Algorithm with Adaptation Mechanism to Solve Numerical and Mechanical Engineering Problems

“…Khalilpourazari et al [ 95 ] proposed WCMFO to encounter MFO’s entrapping at local optima and low convergence rate, while taking advantage of the water cycle algorithm (WCA). A combination of MFO and artificial neural network (ANN-MFO) was proposed by Singh et al [ 112 ] to solve multi-objective problems in magnetic abrasive finishing of aluminum. Chen et al [ 96 ] introduced SMFO to improve the exploration capability of MFO by integrating it with the sine cosine strategy.…”

Modeling and Optimization of COD Removal from Cold Meat Industry Wastewater by Electrocoagulation Using Computational Techniques

“…For metaheuristic optimization, the ANN model was employed as the fitness function and was used to measure the performance of individuals in the population [22]. MFO was used as a metaheuristic algorithm to improve the performance of the ANN [17].…”

“…ANN can be optimized using metaheuristic techniques such as moth-flame optimization (MFO) [14]. ANN and MFO have been used for multi-objective optimization in detecting brain tumors in hyperspectral images [15], determination of optimal machining parameters in manufacturing processes [16], and for multi-objective optimization in magnetic abrasive finishing of aluminum 6060 [17]. Other researchers have analyzed the procedure used to remove endosulfan from aqueous systems.…”

Multi-objective optimization of magnetic abrasive finishing by desirability function with genetic algorithm

“…Their new methodology had successfully optimized the MAF process. they key findings were voltage, and the working gap should be kept at a minimum to achieve a better surface finish and hardness (Singh et al, 2019). Ahmad et al optimized five responses of the MAF utilizing the ANN-GA for multi-objective optimization.…”