Specific Energy Consumption Prediction Method Based on Machine Tool Power Measurement

Accurate prediction on energy consumption in machining is helpful to evaluate process energy characteristics and choose process methods for energy saving. Specific energy consumption expresses the required energy consumption when cutting unit volume material. The Back Propagation (BP) neural network prediction method for specific energy consumption in machining is set up in the paper. The prediction method bases on machine tool power signal measurement by power analyzer and shunt sensors. In the developed BP neural network, the input layer neurons include spindle speed, feed rate, depth of cut and material removal rate; and the output layer neurons includes specific energy consumption in machining. The power signal measurement system is built up in the computer numerical control (CNC) milling machine tool, and the prediction method for specific energy consumption is tested with cutting data. The prediction results show that the introduced method is effective to predict specific energy consumption in machining. Copyright © 2014 IFSA Publishing, S. L.