A Method for Measuring Tube Metal Temperature of Ethylene Cracking Furnace Tubes Based on Machine Learning and Neural Network

Abstract

Temperature monitoring of the tube metal temperature (TMT) of cracking furnace tubes is essential to the normal production of ethylene. However, the existing infrared temperature measurement technology has certain defects in the accuracy of temperature measurement, the accuracy of temperature discrimination of overlapping furnace tubes and the technical cost. In view of this, this paper proposes a novel measurement and processing method. In this method, our team developed a new generation of intelligent temperature measurement devices for measuring TMT, and proposed an intelligent temperature processing algorithm based on machine learning and neural network running on this intelligent temperature measurement devices. This method not only realizes the automatic measurement of TMT, reduces the workload of operators, but also improves the accuracy of measuring TMT and the accuracy of overlapping tube identification. In addition, this method also reduces the technical cost of TMT measurement to some extent. Finally, by comparing the TMT data measured by different methods, it is proved that the proposed method has better performance level than other methods.

Keywords

• Ethylene cracking furnace tubes
• machine learning
• neural network
• embedded processor