基于非线性BP算法的中密度纤维板(MDF)调施胶系统辨识

Identification of dosing and aplying glue system in MDF production based on nonlinear BP algorithm

利用三层前馈神经网络作为被辨识对象的模型,对中密度纤维板(MDF)调施胶控制系统进行建模与仿真,并给出基于非线性BP算法的调施胶系统辨识计算步骤,实现了对中密度纤维板调施胶非线性动态系统的辨识。实验结果表明,文中建立的中密度纤维板调施胶系统模型是有效的,将其系统模型嵌入调施胶控制系统中可使系统响应时间变快并获得较好的控制效果。

Using the three-layer feed-forward neural network as the model of identified object to set up model and simulate, and also presenting the computing steps of identification of dosing glue system based on nonlinear BP algorithm. Nonlinear dynamical system identification of dosing glue of MDF is realized. The experimental results show that the established model is effective. The system model to control system of dosing glue can gain less response time and better controlling effect.