论文部分内容阅读
针对大规模复杂工业过程,提出一种基于多块核主元分析(MBKPCA)和符号有向图(SDG)的故障诊断方法.首先,提出基于SDG和优先级的分块策略,以强连接元SCC为最高优先级、多入/出度节点群为次高优先级、节点链为最低优先级对过程进行分块;在此基础上,采用MBKPCA进行过程监控,对于检测到的故障,先确定故障发生在哪一个数据块,再触发SDG在故障块内完成故障定位.所提出方法克服了多块KPCA故障隔离不完全和SDG推理过程中组合爆炸的缺点,可以提高复杂工业过程故障诊断的准确度和速度.基于Tennessee Eastman过程的仿真研究表明了所提出故障诊断方法的有效性.
Aiming at large-scale complex industrial processes, a fault diagnosis method based on multi-kernel KPCA and SDG is proposed.Firstly, a blocking strategy based on SDG and priority is proposed, SCC is the highest priority, multiple in / out node group is the next highest priority, and the node chain is the lowest priority to process the process. On this basis, MBKPCA is used to monitor the process. For the detected faults, The fault occurred in which a data block, and then trigger the SDG to complete fault location within the fault block.The proposed method overcomes the shortcomings of multiple KPCA fault isolation incomplete and SDG inference process combinatorial explosion, can improve the accuracy of complex industrial process fault diagnosis Degree and speed.The simulation study based on Tennessee Eastman process shows the effectiveness of the proposed fault diagnosis method.