论文部分内容阅读
基于实际工业数据的分析,针对氧气顶吹转炉炼钢过程,提出一种软测量建模方法。该方法的主要思想是为了实现转炉炼钢过程中的终点预测。为了更准确地预测终点温度和终点碳含量,结合最小二乘支持向量机和改进的粒子群算法被用来建立预测模型。改进的粒子群算法被用来优化模型的参数,使得模型具有一个更好的适应性。同时,采用基于事件驱动的策略,以加强模型的普适性。实验结果表明该软测量方法是有效的,并且能成功地应用于实际工业领域。
Based on the analysis of actual industrial data, aiming at the steelmaking process of oxygen top-blown converter, a soft-sensing modeling method is proposed. The main idea of this method is to achieve the end-point prediction in BOF steelmaking process. In order to predict the endpoint temperature and end point carbon content more accurately, a least square support vector machine (SVM) and improved Particle Swarm Optimization (PS-SVM) are used to establish the prediction model. The improved Particle Swarm Optimization algorithm is used to optimize the model parameters, making the model has a better adaptability. At the same time, the use of event-driven strategy to enhance the universality of the model. Experimental results show that the soft-sensing method is effective and can be successfully applied in practical industrial fields.