An improved neural network based on L-M algorithm has been applied to fault diagnosis expert system against to the slow convergence rate of conventional BP neural network.
针对传统BP神经网络训练中收敛速度较慢的缺点,提出一种基于L - M算法的神经网络应用于机械设备故障诊断的专家系统。
Based on L-M algorithm of BP artificial neural network, the fractal parametric prediction model of running in and wear was established.
基于BP人工神经网络的L M算法,建立了磨合磨损的分形参数预测模型。
The experimental results show that the absolute value of mean error of such prediction and control precision is within 5% , which gets good effect on sheet shape control. The BP network m…
仿真与实验结果表明:该模型预测和控制板形精度的平均误差绝对值均在5%之内,具有较好的效果,可应用于板形在线预测与控制。
应用推荐