Natural gas dehydration is an important link of its storage and transportation process.Natural gas dehydration equipment is usually in an environment of high temperature,high pressure,and corrosive substances.Once a safety accident occurs,it often causes serious consequences.Therefore,it is of great significance to ensure the safe and reliable operation of natural gas dehydration devices.Aiming at the problems of anomaly identification and fault location of natural gas dehydration equipment,this paper studies the fault diagnosis method of natural gas dehydration equipment based on Principal Component Analysis(PCA)and Sign Directed Graph(SDG).PCA can capture the main information of all parameters to more accurately describe the state of the system,realize the anomaly state recognition of the dehydration device,and detect anomaly parameters.According to anomaly parameters,the SDG model of the dehydration device is used to locate the source of the fault.The main research work of this paper is as follows:(1)According to the process of triethylene glycol dehydration process,the typical process anomalies and equipment anomalies of the dehydration device are analyzed.A mapping relationship between typical anomalies and monitoring parameters is established to provide support for subsequent SDG fault source location.(2)Aiming at the problem that the single parameter threshold method is difficult to comprehensively monitor the status information of the system,the anomaly identification method of the dehydration device combining PCA principal element and PCA principal element statistics is studied.On the basis of identifying the anomaly state,the PCA cumulative residual contribution map is used to identify the anomaly parameter.The experiment proves that the paper method can effectively identify the anomaly state and anomaly parameters of the dehydration device.(3)the SDG model has the advantages of reasoning about the fault source and the anomaly propagation network,so this paper studies the method of identifying the fault source of the dehydration device based on the SDG.Based on the mapping relationship between the anomalies and the monitoring parameters,the SDG model of the dehydration device is established.The actual application proves that the SDG fault source location model combined with PCA can better locate the fault source and effectively improve the fault location ability of the dehydration device. |