论文部分内容阅读
由于径向基函数(RBF)神经网络有易学,动态仿真性强,较强的输入输出映射功能和全局最优逼近的结构特点,因此将之用于预测麦杆增强复合板材力学性能。高斯函数表示形式简单,径向对称,光滑性好和解析性好,所以模型采用高斯函数作为隐含层基函数,k均值聚类法确定径向基函数的参数,运用最小二乘法确定权值。结合影响复合板材力学性能因素的特点和变化规律,以成型温度、成型压力、纤维含量、保温时间、拉伸强度、冲击韧性等为对象建立预测复合板材力学性能的模型,用它来优化模压成型的工艺参数,找出最佳工艺参数的范围。结果表明,径向基函数神经网络具有较好的学习和泛化能力,在预测力学性能中效果较好。
Radial Basis Function (RBF) neural network is used to predict the mechanical properties of wheat straw reinforced composite sheet because of its easy to learn, strong dynamic simulation, strong input and output mapping and global optimum approximation. Gaussian function is simple, radial symmetry, smoothness and good analytical performance, so the model uses Gaussian function as the hidden layer basis function, k-means clustering method to determine the parameters of the radial basis function, using the least squares method to determine the weight . Combined with the characteristics and variation rules that affect the mechanical properties of the composite sheet, a model for predicting the mechanical properties of the composite sheet is established based on the forming temperature, forming pressure, fiber content, holding time, tensile strength, impact toughness and so on. Process parameters, find the best range of process parameters. The results show that radial basis function neural network has better learning and generalization ability, and is better in predicting mechanical properties.