轴对称件拉深成形智能化控制过程中参数实时识别的GA-ENN建模

材料性能参数和摩擦系数的实时识别是实现拉深过程智能化控制的关键。建立了遗传算法与神经网络相结合的识别模型（GA-ENN），利用遗传算法进行网络权系的训练和优化。给出了网络输入层，输出层和稳层的确定方法以及GA-ENN模型的学习算法。验证结果表明，与BP网络模型比较，GA-ENN模型的学习效率和学习精度均有明显的提高，是一种有效的识别模型，为实现拉深成形过程的智能化控制奠定了基础。

GA-ENN Modeling of Parameter Identification in the Intelligent Control Process for Axisymmetric Workpiece Deep Drawing

The real-time identification of material properties and friction coefficient is as the key to intelligent control of deep drawing process. Identification using analytic model is only of online but not real-time. BP neural network model can realize real-time identification but its convergent speed is slow and it is liable to fall into local optimal solution. Thus a GE-ENN(genetic algorithm-evolution neural network) model is established to optimize network weight. The determination of input layer , output layer and hidden layer is given, and the training algorithm of GE-ENN model is proposed. Experiments indicate that, compared with BP network model, the training efficiency and precision of GA-ENN model are obviously improved, and the model is effective. It lays the basis of real-time properties identification in intelligent control of deep drawing process.