论文部分内容阅读
针对高炉关键异常炉况悬料难以预测的问题,基于D-S证据理论,提出一种综合模糊专家推理和后验概率最小二乘支持向量机的悬料预测方法.首先,结合高炉生产过程和悬料现象,分析悬料形成的内在机理;其次,通过模糊专家推理提取基于专家规则的主观证据,再通过建立后验概率最小二乘支持向量机模型提取基于数据内在客观规律的客观证据;最后,基于D-S证据理论完成主客观证据融合,实现悬料预测.该方法充分利用专家经验和最小二乘支持向量机的自学习能力,能够提高预测精度.仿真结果表明本文提出的方法有效、准确.
Aiming at the unpredictable problem of hanging material in the key abnormal furnace condition of blast furnace, based on the DS evidence theory, a method of predicting the suspended material is proposed based on fuzzy expert reasoning and posterior probability least squares support vector machine.Firstly, based on blast furnace production process and hanging material Secondly, the subjective evidences based on expert rules are extracted by fuzzy expert reasoning, and objective evidence based on inherent laws of data is extracted through the establishment of posteriori probabilistic least squares support vector machine model. Finally, DS evidence theory to complete the subjective and objective evidence fusion to realize the suspension forecasting.This method can make full use of the expert experience and the least squares support vector machine self learning ability to improve the prediction accuracy.The simulation results show that the proposed method is effective and accurate.