Adaptive digital twin for product surface quality: supervisory controller for surface roughness control

For surface quality control, a digital twin model was created and tested. A prediction model with an embedded neuro-fuzzy adaptive inference engine calculates and compares the surface roughness with the required values by utilizing real-time inputs on process parameters, tool wear, acoustic emission, and force signals. Fuzzy logic controls create control commands to modify the machining variables and achieve an appropriate surface quality. Simulation results demonstrate that the developed DT system significantly reduces errors between desired and predicted surface roughness from 11 to 0.8% and effectively controls surface quality in CNC machining online.