Artificial bee colony, genetic, back propagation and recurrent neural networks for developing intelligent system of turning process

摘要

Intelligent manufacturing requires significant technological interventions to interface manufacturing processes withcomputational tools in order to dynamically mold the systems. In this era of the 4th industrial revolution, Artificial neuralnetwork (ANNs) is a modern tool equipped with a better learning capability (based on the past experience or historydata) and assists in intelligent manufacturing. This research paper reports on ANNs based intelligent modelling of aturning process. The central composite design is used as a data-driven modelling tool and huge input–output is generatedto train the neural networks. ANNs are trained with the data collected from the physics-based models by usingback-propagation algorithm (BP), genetic algorithm (GA), artificial bee colony (ABC), and BP algorithm trained with selffeedbackloop. The ANNs are trained and developed as both forward and reverse mapping models. Forward modellingaims at predicting a set of machining quality characteristics (i.e. surface roughness, cylindricity error, circularity error,and material removal rate) for the known combinations of cutting parameters (i.e. cutting speed, feed rate, depth ofcut, and nose radius). Reverse modelling aims at predicting the cutting parameters for the desired machining qualitycharacteristics. The parametric study has been conducted for all the developed neural networks (BPNN, GA-NN, RNN,ABC-NN) to optimize neural network parameters. The performance of neural network models has been tested with thehelp of ten test cases. The network predicted results are found in-line with the experimental values for both forward andreverse models. The neural network models namely, RNN and ABC-NN have shown better performance in forward andreverse modelling. The forward modelling results could help any novice user for off-line monitoring, that could predictthe output without conducting the actual experiments. Reverse modelling prediction would help to dynamically adjustthe cutting parameters in CNC machine to obtain the desired machining quality characteristics.