Fault Diagnosis Approach Based On Hieracrhical Fuzzy SDG Model And Its Applicaiton

In modern industrial process, along with the increasing degree ofautomation and control systems in manufacturing scale increasing, theincreasing complexity, resulting in increased maintenance cost, loss and accidentconsequence serious problems such as seriously, so the fault detection anddiagnosis technology is paid attention to by the people day by day, become animportant research topic of manufacturing. Whether can fast accuratepositioning fault source is the guarantee of large complex system could the keyto stable operation.In this dissertation, based on the qualitative signed directed graph model, anew model combined with the hierarchical and quantitative knowledge isproposed. The new model can reduce the search space when searching for thecompatibility paths, and it is much faster. Meanwhile the diagnosis results aredescribed by the probability information, which distinguishes the possibility ofthe potential failure sources. Firstly, fault diagnosis method based on SDGmodel has the presence of low efficiency, and it is difficult to distinguish thepotential failure sources in the same fault model, then it can occur "combinatorial explosion".To solve the problems of SDG fault diagnosis method,an improved hierarchical directed graph model is proposed. Meanwhile, basedon the new model, a fault diagnosis method is proposed, too. This method hasthe completeness of SDG model. Using the layered strategy and qualitativerelationship between nodes, it can find backward the compatibility paths todetermine the fault candidate nodes. Finally, this method is applied to the faultdiagnosis of deaerator system in the power plant. The results showed that themethod effectively reduced the search space of active nodes and improved thespeed and accuracy of fault diagnosis.Secondly, for the complexity structure of traditional signed directed graphof complex thermal system, it is easy to produce combinatorial explosion insearch paths, meanwhile, it is difficult to distinguish multiple fault sources.Therefore,a new hierarchical graph model based on the quantitative knowledgewhich is named hierarchical probability signed directed graph is proposed, andon the basis of this mode, a fault diagnosis method is proposed, too. On the onehand, the hierarchical method simplifies the search paths, and it uses acombination of qualitative and quantitative methods to describe causalrelationships between failures; on the other hand, the hierarchical directed graphin the mew model can reduce the search spaces, then using compatibility ofbranches and Bayesian inference to diagnosis the system, it can get theprobability of failure and the possibility of fault sources. Finally, take the highpressure heater system in the thermal system for example, its model is established successfully. The experiment show that this method improves theresolution of the fault source and reduces the search spaces avoiding the"combinatorial explosion" occurred.The model and the proposed method is applied to a coal-fired thermalsystem fault diagnosis, which overcome the complexity structure of the thermalsystem and causation, slow speed of diagnosis and difficulty to distinguish thepossibility of the potential failure sources. The hierarchical method shortens thetime of fault diagnosis, meanwhile, it reduces the loss of property caused bythermal system downtime. The quantitative information describes the possibilityof each failure source. It reduces the fault repair time, improves the utilization ofhuman and material resources and increases the safety of the thermal system.