BALL MILL DOUBLE-FACTORS MODELLING BASED ON RBF NETWORK

Based on using simple measuring devices(such as electronic ear,transducer)to establish relationship between mill speed and ball ore ratio,the double factors modelling of milling process has been accomplished by means of radial cardinal network.Through training of network,an accuracy of below 10^-10 has been achieved for both newral network forecasting value and erroneous square sum.The result of emulation showed that the radial cardinal network has the advantage of high accuracy,and the training of network has solved the problem of interactive influencing of multiple factors.