Big Data Analytics Based Optimisation for Enriched Process Planning: A Methodology

To improve flexibility and accurateness of the optimisation in machining, this paper presents a big data analytics based optimisation method for enriched process planning in the concept of which cutting condition and cutting tool are optimised together and simultaneously. Within the context, the machining factors (workpiece, machining requirement, machine tool, machining process and machining result etc.) are concerned and represented by data attributes. In case that, the new machining resource, new materials and new machining tools etc., can be represented by a group of parameters, so that each machining cases can be treated by data regardless of the relevant experiments, which can enhance practicality and flexibility of potential application in real industry. Also a hybrid method combining neural networks (NN), analytic hierarchy process (AHP), and evolution based algorithm (EBA) or swarm intelligence based algorithm (SIBA) is proposed. NN based model is trained by the big data to improve the accurateness of each single objective, AHP is employed for multi-objective, and EBA or SBA is used to execute the optimising calculation.