Polyetheretherketone (PEEK) is one of the semi-crystalline thermoplastic polymers with excellent machinability and chemical stability applied to precise structural plates and electronic components. This study installed multiple sensors to analyze the machining characteristics in the PEEK drilling. According to the time domain signals, the effects of spindle speed and feed rate on the machining characteristics of cutting force and vibration were investigated. In addition, an infrared thermography was installed to record the temperature variation within the drilling area. The experimental hole was 2-mm diameter with a 4.5-mm depth. Experimental results showed that the effect of the feed rate on thrust force is greater than the spindle speed; drilling by a low-level spindle speed with a low-level feed rate can obtain the smallest cutting force and acceleration amplitude in the spindle axis; the temperature within the drilling area is inverse to the feed rate and a high-level feed rate is helpful for forming regular curl chips. When adequate airflow was applied during the drilling operation, the hole’s shrinkage ratio and roundness can be decreased. The data presented in this paper provide valuable references for realizing the drilling of the thermoplastic—PEEK.

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