Optimum selection of machining conditions in abrasive flow machining using neural network

Abrasive flow machining (AFM) is a finishing process with wider bounds of application areas, which offers both automation and flexibility in final machining operations. This paper presents the use of neural network for modeling and optimal selection of input parameters of AFM process. First, a generalized back-propagation neural network with four inputs, two outputs, and one hidden layer has been used to establish the process model. A second network, which parallelizes the augmented Lagrange multiplier (ALM) algorithm, determines the corresponding optimal machining parameters by minimizing a performance index subject to appropriate operating constraints. Simulation results confirm the feasibility of this approach, and show a good agreement with experimental results for a wide range of machining conditions. To validate the optimization results of the neural network approach, optimization of the AFM process has also been carried out using genetic algorithm (GA).