论文部分内容阅读
符号有向图(SDG)是揭示流程系统深层知识的定性模型,用于描述流程系统的状态变量及其变量间的故障信息传递关系.当系统的状态变量过多,运用SDG故障诊断算法生成的故障规则过于庞大,推理困难.粒矩阵的知识约简算法能有效约简冗余属性.因此,将粒矩阵的知识约简算法引入SDG故障诊断,以电站除氧器系统为例,使用粒矩阵的知识约简算法约简主要故障的故障规则,简化规则中的冗余节点,提高故障诊断效率,最后验证了约简后的故障诊断规则的正确和有效.
The symbolic directed graph (SDG) is a qualitative model that reveals the deep knowledge of the process system and describes the relationship between the state variables of the process system and the fault information transfer between the variables. When the state variables of the system are excessive, SDG is generated by using the SDG fault diagnosis algorithm The fault rules are too large and the reasoning is difficult.Knowledge reduction algorithm of granular matrix can effectively reduce the redundant attributes.Therefore, the knowledge reduction algorithm of granular matrix is introduced into the fault diagnosis of SDG. Taking the power plant deaerator system as an example, The knowledge reduction algorithm reduces the fault rules of the main faults, simplifies the redundant nodes in the rules and improves the fault diagnosis efficiency. Finally, the fault diagnosis rules after reduction are verified to be correct and effective.