基于GA—BP模糊神经网络轧机张力控制

Tension Control Based on GA-BP Fuzzy Neural Network for the Rolling Mill

模糊神经网络能够以任意精度逼近任意复杂的非线性关系,具有高度的自适应和自组织性,在解决高度非线性和严重不确定系统的控制方面具有巨大的潜力,然而基于BP训练算法易陷入局部极小点的缺点,提出了控制器以三角型隶属度函数的BP神经网络结构,利用改进的遗传算法(GA)对结构和参数进行同步优化,改进适应度函数指导搜索过程,保证稳定情况下大大加快了收敛的速度。最后采用Matlab7.0的Simulink工具以轧机张力为对象进行仿真试验,结果证明了其有效性。

The fuzzy neural networks can approximate any non-linear function with any given precision, It has a high self-adaptability and self-organization, which endows neural networks with large potential to solve the control of the system with high nonlinearity and serious uncertainty. Meanwhile. the currently used training algorithm for the neural networks such as BP is often inclined to local minimum, so an fuzzy - neural network controller has been presented with its parameters and the structure tuned simultaneously by GA. The structure of the controller is based on the BP networks with triangle membership functions. Dynamic crossover, mutation probabilistic rates as well as modified fitness function have been used for faster convergence, The performance of the controller is evaluated by system simulation conducted with Madab 7.0 on the rolling tension model and satisfied results are obtained.