在电弧炉(EAF)冶炼生产过程中，出钢温度、碳含量和磷含量等终点参数直接关系到后续生产工艺，甚至影响产品质量。准确预报电弧炉的终点参数对降低冶炼成本，提高生产效益具有重要意义。考虑到电弧炉终点参数既受定量因素的影响，又受非定量因素的影响，将GM与LSSVM结合，建立了GSVM预报模型。GM反映炉体自身变化等非定量因素对系统的影响，LSSVM反映各种定量因素的影响，提高了预报精度。该方法具有模型结构简单，建模所需样本数据少，速度快等优点。实践证明，预报结果接近实际值，该方法是切实可行并有效的，可以用于电弧炉炼钢终点预报。
In the steelmaking process of electric arc furnace (EAF), the endpoint parameters, ie temperature, carbon content and phosphor content of molten steel, are very important to the product quality. An exact prediction of endpoint is propitious to improvement of the production efficiency. In this article, measurable factors and unmeasurable factors of the EAF′s endpoint parameters are used to build a GSVM (support vector machine) prediction model, which combines Grey model (GM) and LSSVM. This method makes the model has a simple structure and high precision, needs a few sample data. The effectiveness of the proposed method is illustrated by a simulation example for predicting the endpoint of EAF.
参考文献
- 下载量()
- 访问量()
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%