S Zorb精制汽油辛烷值优化模型及工业应用

石油炼制与化工 ›› 2022, Vol. 53 ›› Issue (5): 88-94.

S Zorb精制汽油辛烷值优化模型及工业应用

王杰¹,陈博¹,刘松²,赵明洋²,欧阳福生¹,高萍¹

1. 华东理工大学化工学院石油加工研究所
2. 中国石化上海高桥分公司

收稿日期:2021-11-08 修回日期:2022-01-12 出版日期:2022-05-12 发布日期:2022-04-24
通讯作者: 欧阳福生 E-mail:ouyfsh@ecust.edu.cn

DEVELOPMENT AND COMMERCIAL APPLICATION OF AN OPTIMIZATION MODEL OF OCTANE NUMBER FOR REFINED GASOLINE FROM S Zorb UNIT

Received:2021-11-08 Revised:2022-01-12 Online:2022-05-12 Published:2022-04-24

摘要/Abstract

摘要： 针对S Zorb精制汽油研究法辛烷值（RON）损失较大的问题，以某石化企业S Zorb装置近3年的运行数据为基础，采用最大互信息系数（MIC）和Pearson相关系数并结合BP神经网络，从包括原料油性质、吸附剂性质、产品性质和操作变量在内的273个变量中筛选出22个建模变量，构建了结构为21-14-1的汽油RON预测模型，并进行验证。结果表明：建立的预测模型具有较好的拟合优度和泛化能力，其对测试集的平均绝对误差（MAE）和决定系数（R²）分别为0.116 3、0.960 1。在此基础上，针对具体原料性质，采用遗传算法（GA）优化操作变量，发现该模型通过优化能有效降低汽油RON损失；工业试验验证结果表明，通过模型优化操作变量可使汽油RON损失降低25%。

关键词: 催化裂化汽油, S Zorb工艺, BP神经网络, 遗传算法, 辛烷值损失

Abstract: Aiming at the large loss problem of research octane number (RON) of refined gasoline from S Zorb unit, based on the historical data from a S Zorb unit in the past 3 years, the maximal information coefficient (MIC) and Pearson correlation coefficient were used in combination with BP neural network, 22 modeling variables were selected from 273 variables including feed oil properties, adsorbent properties, product properties and operation variables, and a RON prediction model with the structure of 21-14-1 was established and validated. The results show that the prediction model has good goodness of fit and generalization ability, and its average absolute error and determination coefficient (R²) of the model on the test set are 0.116 3 and 0.960 1, respectively. On this basis, genetic algorithm (GA) was used to optimize the best operation variables to improve the product RON. It was found that the model could effectively reduce RON loss of gasoline through optimization, and the RON loss of gasoline could be reduced by 25% through the optimization model.

Key words: catalytic cracking gasoline, S Zorb process, BP neural network, genetic algorithm, octane loss

王杰陈博刘松赵明洋欧阳福生高萍. S Zorb精制汽油辛烷值优化模型及工业应用[J]. 石油炼制与化工, 2022, 53(5): 88-94.

参考文献

[1] 赫晓龙.石油化工催化裂化工艺技术优化[J].化工管理, 2019, 0(17):185-186 [2] Souza N L A, Tkach I, Morgado E, et al.Vanadium poisoning of FCC catalysts: A quantitative analysis of impregnated and real equilibrium catalysts[J].Applied Catalysis A: General, 2018, 560(0):206-214 [3]许友好.我国催化裂化工艺技术进展[J].中国科学:化学, 2014, 44(01):13-24 [4] 杜伟, 黄星亮.催化裂化汽油脱硫技术及其进展[J].石油与天然气化工, 2002, 31(2):74-77 [5] 吴德飞, 孙丽丽，黄泽川，等.S Zorb进展与工程应用[J].炼油技术与工程, 2014, 44(10):1-4 [6] 刘传勤.S Zorb 清洁汽油生产新技术[J].齐鲁石油化工, 2012, 40(1):14-17 [7] Wawrzyniak J.Prediction of Fungal Infestation in Stored Barley Ecosystems Using Artificial Neural Networks[J].LWT- Food Science and Technology, 2021, 137(0):1-9 [8] Reshef D N, Reshef Y A, Finucane H K, et al.Detecting Novel Associations in Large Data Sets[J].Science, 2021, 334(0):1518-1524 [9] 刘宝, 倪维起.S Zorb装置汽油辛烷值损失影响因素分析[J].齐鲁石油化工, 2019, 47(2):102-104 [10]刘永才, 李佳.影响装置汽油辛烷值损失因素分析[J].石油化工设计, 2019, 36(4):12-15 [11]刘琪.装置降低汽油烯烃含量的探索[J].中外能源, 2020, 25(1):75-80 [12]Rumelhart D E, Hinton G E, Williams R J.Learning representations by back-propagating errors[J].Nature, 1986, 323(6088):533-536 [13] Nair V, Hinton G E.Rectified Linear Units Improve Restricted Boltzmann Machines Vinod Nair[C]// International Conference on International Conference on Machine Learning. Omnipress, 2010 [14] Wang J R, Li S M, An Z H, et al.Batch-normalized deep neural networks for achieving fast intelligent fault diagnosis of machines[J].Neurocomputing, 2019, 329(0):53-65 [15] Ding Caichang, Chen Lin, Zhong Baorong.Exploration of Intelligent Computing Based on Improved Hybrid Genetic Algorithm[J].Cluster Computing-the Journal of Networks Software Tools and Applications, 2019, 22(0):S9037-S9045 [16] 董妍汝.基于选择算子的遗传算法改进[J].办公自动化, 2015, 0(16):59-61 [17] 王硕, 孙洋洋.PyQt5 快速开发与实践[M]. 北京：电子工业出版社, 2017: 1-4 [18]肖旻, 陈行.基于语言编程特点及应用之探讨[J].电脑知识与技术, 2014, 10(34):8177-8178 [19] 李艳民.基于Qt跨平台的人机交互界面的研究和应用[D]. 重庆大学, 2007 [20] 周牧.基于PyQt5的量子系统建模中间件的设计[D]. 武汉轻工大学, 2020