基于动态云贝叶斯网络的气化炉风险预测

Risk Prediction of Gasifier System Based on Dynamic Cloud Bayesian Network

针对目前气化炉系统存在的风险等级分析不足问题,提出一种云模型和动态贝叶斯网络(DBN,Dynamic Bayesian Network)相结合的评估方法。以气化炉系统为评估目标,利用云模型将连续型数据离散化,将评价体系中的各个风险因素设为动态贝叶斯网络中的节点,构建动态贝叶斯网络。利用熵权法计算各风险指标权重,并采用最大似然估计的方法处理云模型得到的隶属度,将以隶属度–概率转换方法得到的概率作为证据输入动态贝叶斯网络中,最后利用动态贝叶斯网络的正、反向推理特点,结合重要度综合分析,完成针对气化炉系统的风险预测评估。研究表明,维修效率、设备完整度、气化炉压力及氧煤比是系统运行中需要重点关注的薄弱环节。

Aiming at the problem of insufficient risk level analysis in the current gasifier system,an evaluation method combining cloud model and Dynamic Bayesian Network(DBN)is proposed.Taking the gasifier system as the evaluation target,the cloud model is used to discretize continuous data,and the risk factors in the evaluation system are set as nodes in the dynamic Bayesian network to construct a dynamic Bayesian network.The entropy method is used to calculate the weight of each risk index,and the maximum likelihood estimation method is used to process the membership degree obtained by the cloud model,and the probability obtained by the membership degree-probability conversion method is input into the dynamic Bayesian network as evidence.Finally,using the characteristics of forward and reverse reasoning of dynamic Bayesian network and combining with the comprehensive analysis of importance,the risk prediction and assessment for the gasifier system is completed.The research shows that maintenance efficiency,equipment integrity,gasifier pressure and oxygen coal ratio are the weak links that need to be paid attention to in the operation of the system.