针对气辅注塑成形的注气压力精确控制要求，设计了具有５层结构的模糊神经网络控制器和控制算法，利用神经网络的学习能力实现对模糊逻辑规则的优化，改善了系统的适应性。对系统３段压力控制的仿真 分析，验证了模糊神经网络控制模型的可行性，控制效果良好。

In this study,  an effective control method and strategy based on fuzzy neural network has been developed for gas injection pressure accurate control in gas-assisted injection. A fuzzy neural network controller with five layers and its control algorithm are established.  The learning ability of neural network is used to optimize the rules of the fuzzy logic so as to improve the adaptability of system.  The simulation of the system capability and three segmental injected pressure control are carried out under the environment of MATLAB and the results show that this theoretic model is feasible, and the control system has good characteristics and control action.

欧长劲（1956－），男，浙江杭州市人，浙江工业大学副教授，研究方向：机电控制