中文摘要：

针对液压挖掘机动臂关节的非线性建模问题，提出一种基于神经网络的线性变参数（LPV）模型的辨识方法．在各个工作点处根据其关节速度的一阶暇性加延迟模型，获得其关节角度模型；结合调度变量特性，采用神经网络辨识出LPV模型的参数，设计出挖掘机动臂在全局工作范围的LPV模型．通过仿真实验，验证了该方法的有效性和模型的准确性．

英文摘要：

A linear parameter varying model is proposed based on neural network identification for building the hydraulic excavator boom model. The model of the joint angle is obtained based on the first-order plus dead time model of the joint velocity at each working-point. Depending on scheduling variable characteristics, the LPV model parameters are identified by using neural network, and the global LPV model of the excavator boom in the workspace is designed. The simulations and experiments indicate the accuracy of the model and the validity of the method.