KNN-based safety evaluation model for dimethyl oxalate process

The synthesis process of dimethyl oxalate is a crucial step in the coal to ethylene glycol process, which is classified as a national key regulatory dangerous chemical process. Consequently, the safety of the synthesis process of dimethyl oxalate has garnered widespread attention. At present, there are several issues in the safety evaluation of this process, such as underutilization of process parameters, limited intelligent evaluation, and information technology. Therefore, it is of significant practical importance to deeply integrate computer science and safety science in order to enhance and innovate the existing safety evaluation technology. The research focuses on the synthesis process of dimethyl oxalate, integrating big data from chemical production and incorporating machine learning to organically evaluate safety. This study constructs an intelligent algorithm model for the safety evaluation of the synthesis process of dimethyl oxalate. The results indicate that the K-Nearest Neighbors (KNN) based dimethyl oxalate process safety evaluation model demonstrates superior performance in terms of accuracy and speed. It satisfies the requirements of the process safety evaluation, making it the optimal choice for this purpose.