Predicting Temperature in Orthopaedic Drilling using Back Propagation Neural Network

Present work deals with the prediction of temperature in orthopaedic drilling using back propagation neural network. Drilling of bone is common to prepare an implant site during orthopaedic surgery. The increase in temperature during such a procedure increases the chances of thermal invasion of bone which can cause thermal osteonecrosis. Drilling operations have been performed in polymethylmethacrylate (PMMA) (as a substitute for bone) work-piece by high-speed steel (HSS) drill bits over a wide range of cutting conditions. Drill diameter, feed rate and spindle speed are used as input for the back propagation neural network whereas temperature is taken as output. The performance of the trained neural network has been tested with the experimental results. Good agreement is observed between the predictive model values and experimental values.