The BP neural network used in the temperature characteristic of the boundaryfilm on the screw-nut pairs surface in the wear-self-compensation system was established.
本文用双隐层BP人工神经网络建立了丝杆螺母副表面边界膜温度特性的磨损自补偿数学模型。
2
The network could predict the effects of the temperature on the boundaryfilm strength. the network trained with the L-M rule were quick in convergence and small in error.
This model takes into account both the diffusion resistance of the membrane phase in non-steady state and the diffusion resistance of the external phase boundaryfilm and the membrane leakage.