Application of machine learning to process simulation of n-pentane cracking to produce ethylene and

• 作 者: Weijun Zhu Xingwang Liu Xu Hou Jiayao Hu Zhenheng Diao
• 机 构: School of Chemical Engineering, Changchun University of Technology, Changchun 130012, China“,”School
• 出 处: 中国化学工程学报（英文版）
• 发表日期: 2020年7期
• 关键词: Machine learning ANN Calculation accuracy Light olefins n-Pentane cracking

Modeling light olefin production was one of the main concs in chemical engineering field. In this paper, ma-chine leing model based on artificial neural networks (ANN) was established to describe the effects of temper-ature and catalyst on ethylene and propene formation in n-pentane cracking. The establishment procedure included data pretreatment, model design, training process and testing process, and the mean square error (MSE) and regression coefficient (R2) indexes were employed to evaluate model performance. It was found that the leing algorithm and ANN topology affected the calculation accuracy. GD24223, CGB2423, and LM24223 models were established by optimally matching the leing algorithm with ANN topology, and achieved excellent calculation accuracy. Furthermore, the stability of GD24223, CGB2423 and LM24223 models was investigated by gradually decreasing training data and simultaneously transforming data distribution. Com-pared with GD24223 and LM24223 models, CGB2423 model was more stable against the variations of training data, and the MSE values were always maintained at the magnitude of 10?3–10?4, confirming its applicability for simulating light olefin production in n-pentane cracking.