焦炉加热智能控制系统的研究与应用

焦炉是具有大时滞、强非线性、多变量耦合、变参数的复杂对象，直行温度受多种因 素的影响，采用常规的控制方法难以将直行温度控制到要求的精度范围内．焦炉生产过程既 受连续时间信号驱动，又受离散事件信号驱动，本文将焦炉及其操作过程作为一类混杂系统 ，研究并开发了焦炉加热智能控制系统．系统采用神经网络建模、多变量模糊控制、专家控 制和预测控制等多种算法，构造了切换系统模型，在北京炼焦化学厂投入生产运行后，取得 良好控制效果．该系统对提高焦炭质量，降低能耗和延长炉体使用寿命都有重要的意义．

RESEARCH AND APPLICATION ON COKE OVEN HEATING INTELLIGENT CONTROL SYSTEM

Coke oven is a complex plant with the characteristics of large time-delay, strong non-linear, multivariable coupling and changeable parameter. The mean flue temperature is affected by many reasons and it is difficult to control the temperature to required precision by the normal control methods. The dynamic process of the coke oven is driven by both continuous state variables and discrete state variables. In this paper, the coke oven and its operation are thought as a kind of hybrid systems, the coke oven heating intelligent control system is developed. Switching system model is applied in the control system including neural network modeling, multivariable fuzzy control, expert control and predictive control. The .good performance of control can be obtained in its application in Beijing Coking and Chemical Works. This control system has a great significe to improve the quality of the coke, reduce energy consumption and prolong the service life of oven body.