Study On Intelligent Coking Diagnosis Method Of Ethylene Cracking Furnace Tubes

Ethylene is the most basic raw material for the petrochemical industry.Ethylene production has been regarded as one of the important indicators of the development level of a country’s petrochemical industry.However,in the process of producing ethylene by thermal cracking,carburization and coking are always inevitable in cracking furnace tubes,which greatly affects the production efficiency of ethylene enterprises.The tube metal temperature(TMT)of cracking furnace tube is one of the most important factors influencing the coking of cracking furnace tube.Therefore,the research on how to accurately measure the TMT,and then accurately diagnose and predict the coking degree of cracking furnace tube has become one of the key problems to ensure the operation safety of cracking furnace,improve the production benefit of cracking furnace,and make ethylene industry become industrial intelligent.Aiming at the shortcomings of the current widely used contact and non-contact TMT measurement technology and the method of diagnosing the degree of coking of the furnace tube by means of coking mechanism model,"black box" model,infrared thermal imaging technology and manual experience,this paper proposed a new TMT measurement method and a method of diagnosing the coking degree of the furnace tube and predicting the coking trend,and the verification experiment was carried out.The main research work of this paper is as follows:(1)Introduced the causes of coking problem of cracking furnace tube in ethylene production,and focuses on the technology of TMT measurement,diagnosis of coking degree and prediction of coking trend.(2)In view of the shortcomings of the existing infrared temperature measurement technology in temperature measurement accuracy,furnace tube temperature discrimination accuracy and technology cost,a novel cracking furnace tube temperature measurement and processing method is proposed in this paper.Based on the new generation of intelligent temperature measuring devices developed by our research team for measuring TMT,an intelligent temperature processing algorithm based on machine learning and neural network was proposed.This method not only improves the accuracy of measuring TMT and the accuracy of tube identification,but also reduces the technical cost of TMT measurement to some extent.(3)Aiming at the shortcomings of the existing diagnosis methods of coking degree of cracking furnace tube,a fusion diagnosis and prediction method based on artificial bee colony(ABC)and adaptive neural fuzzy inference system(ANFIS)is proposed,which also introduces a coking-time factor(CTF).The actual data verification shows that the method not only improves the training efficiency and diagnosis accuracy of the coking diagnosis and inference system of the cracking furnace tube,but also realizes the prediction of the development trend of the coking degree of the furnace tube.(4)Introduced how to apply the proposed method of intelligent diagnosis of coking degree to the ethylene enterprise.The application of this method depends on a set of intelligent health monitoring system for ethylene cracking furnace tubes developed by our research team,which is suitable for the ethylene enterprise system platform.The monitoring system first collects the data related to the coking of the cracking furnace tube in real time,and then realizes the diagnosis of the coking degree and the prediction of coking trend of the furnace tube through the embedded coking diagnostic method.Practical application proves that the proposed method for diagnosis of coking degree and prediction of coking trend of the tube is feasible and useful in engineering.