Modeling for a small-hole drilling process of engineering plastic PEEK by Taguchi-based neural network method

Engineering plastics have specific properties in strength, hardness, impact resistance, and aging persistence, often used for structural plates electronic components. However, the holes made by drilling process always shrink after cutting heat dispersion due to their high thermal expansion coefficient. Drilling parameters must be discussed thoughtfully especially small-hole fabrication acquire a stable hole quality. This study developed parameter models Taguchi-based neural network method save experimental resources on of engineering plastic, polyetheretherketone (PEEK). A three-level full-factorial orthogonal array experiment, L27, was first conducted minimizing thrust force, shrinkage diameter, roundness error. In terms modeling, four variables were designated input layer neurons included three (spindle speed, depth peck-drilling, feed rate) force detected, that output two characteristics diameter roundness. The trained stepped-learning procedure expand network’s field information stage stage. After stages training, can provide precise simulations training sets. For non-trained cases, prediction accuracy hole’s below 1 μm 1-mm-diameter hole.