提出了一种新型神经网络控制器 ,其控制机理与PID控制相类似 ,但解决了常规PID控制存在的快速性与超调量的矛盾。给出了该神经网络控制器的自适应学习算法 ,分析讨论了控制系统的稳定性。仿真实验表明 ,这种新型神经网络控制器构成的自适应控制系统具有较强的适应性和鲁棒性。 A new neural network controller is proposed, whose control mechanism is similar to PID control, but it solves the contradiction between the fastness and overshoot of conventional PID control. The adaptive learning algorithm of the neural network controller is given, and the stability of the control system is analyzed and discussed. Simulation results show that the adaptive control system composed of the new neural network controller has strong adaptability and robustness.