电熔镁炉熔炼过程异常工况识别及自愈控制方法

Abnormal Condition Identification and Self-Healing Control Scheme for the Electro-Fused Magnesia Smelting Process

本文提出了基于多源信息融合的电熔镁炉异常工况识别及自愈控制方法.通过分析与三种异常相关的专家知识及操作经验,本文提取了与异常工况相关的多源信息.通过融合多源信息,建立了用于异常工况识别的贝叶斯网络模型.根据异常工况的识别结果,利用剩余生命时间与控制变量调整量间的关系获得自愈控制措施.仿真结果表明提出的方法能够实现异常工况识别,并且能够区分严重程度,制定相应的自愈控制方案,获得比现有方法更好的性能.

In this paper,the abnormal condition identification and self-healing scheme is proposed based on the multisource information fusion.By analyzing the expert knowledge and the experience of operators related with the abnormities,the related multi-source characteristics are extracted.The Bayesian networks are established to identify the abnormities by fusing the multi-source information.Based on the identification results,the self-healing control scheme can be obtained by the relationship between the remaining lifetime and the adjustment of control variables.The simulation results show that the proposed method is effective to identify the abnormal conditions and distinguish the abnormal degree.The corresponding self-healing control scheme can be made to remove the abnormal conditions.The proposed method owns the better performance than the existing research results.