Data-driven analysis in magnetic field-assisted electrical discharge machining of high-volume SiCp/Al

This paper presents a framework of data-driven intelligence system which can be applied on magnetic field-assisted electrical discharge machining (MF-EDM) process for SiC particulate reinforced Al-based metal matrix composites (SiCp/Al) with different high-volume fractions. The implemented consists data modelling, predicating, optimization and monitoring modules. A multi-objective moths search (MOMS) algorithm backpropagation neural network (BPNN) model multi-hierarchy non-dominated strategy is proposed tuning optimal processing performance. Data are collected from fraction volumes SiCp/Al by MF-EDM, peak current, magnetic, pulse width interval time as input, material removal rate, electrode wear surface roughness output. BPNN shows the best accuracy compared to K-nearest neighbors, least square support vector machine Kriging model. To demonstrate effectiveness MOMS algorithm, set results selected paradigm, dominates 95.83% original experiments. verification experiment also done an optimized parameter 65% 0.2T magnetic. Both result three-dimensional topography comparison show that similar input designs.