基于粗糙集的焦炉加热工序控制规则提取

Rough Set-based Control Rules Extraction in Coke Oven Heating Process

应用粗糙集(RS)理论对焦炉直行温度的控制规则进行了提取。首先收集人工成功控制直行温度的原始样本,添加可控与不可控参数,得到初始决策表;指出模糊控制方法因输入参数过少,从而会导致不确定性决策;然后利用RS理论对初始决策表进行约简,发现了关键影响因素及潜在规律,最终得到两组仅含有三个参数,简洁、一致、完备的控制规则,并经实际运行检验了规则的适用性。

Rough set （RS） theory is applied to the rules extraction of the coke oven longitudinal temperature （LT） control. First, original samples are collected from the successful historical recorders of manual operation in LT control. The initial decision table is built by appending controllable and uncontrollable parameters to those samples. Second, it is pointed that because of the insufficiency of input parameters in the fuzzy control method, the uncertain decisions will be occurred. Third, the main influencing factors and the underlying laws are discovered after reducing the initial decision table with RS theory. Finally, two groups of LT control rules, which merely contained three parameters, are obtained with succinctness, concordance and completeness. The practice shows that the LT control rules are applicable.