Prediction of Compression Ratio of Extruded Cottonseed and Castor Bean under Mechanical Pressing Using Improved Neural Network

A prediction model of compression ratio for extruded oilseeds was developed based on improved BP neural networks. As an applied example, the predicted curves were successfully used to predict critical pressing pressures. Results indicated that the predicted values of compression ratios conformed to the measured values well for extruded cottonseed and castor been. There was a limiting compression for extruded oilseeds under given conditions. The compression ratios for extruded cottonseed had more rapid increase from 0 to 40 MPa of applied pressure, less increase from 40 to 80 MPa and insignificant increase over 80 MPa, and for extruded castor bean had more rapid increase from 0 to 60 MPa of applied pressure, less increase from 60 to 100 MPa and insignificant increase over 100 MPa. 80 and 100 MPa of applied pressure were identified as the critical pressing pressure for extruded cottonseed and castor bean respectively.