论文部分内容阅读
蒸馏装置的加热炉是一个复杂的受控对象,存在着非线性、时变性、纯滞后因素和不确定随机干扰等因素;着重研究了神经网络与模糊系统融合的可行性及融合方式,提出了将模糊控制和神经网络两种技术相结合,共同控制;仿真研究结果表明,这种神经网络模糊控制在克服对象的大惯性、抗干扰性、非线性和纯滞后方面,大大改善了控制品质;最后进行了现场实验,实验表明,所应用的控制器性能令人满意,具有很好的鲁棒性,一定会具有更广阔的发展前景。
The heating furnace of the distillation unit is a complex controlled object with some factors such as non-linearity, time-varying, pure hysteresis factor and uncertain random disturbance. The feasibility and fusion of neural network and fuzzy system fusion are emphatically studied. The fuzzy control and neural network are combined and controlled together. The simulation results show that this neural network fuzzy control greatly improves the control quality in overcoming the large inertia, anti-jamming, nonlinearity and hysteresis of the object. Finally, a field experiment was carried out. Experiments show that the performance of the proposed controller is satisfactory and has good robustness. It will certainly have a broader development prospect.