Abstract
In this research work, we introduce an octane loss prediction model to solve the problems of difficult product quality control and untimely process optimization response in the catalytic cracking process. A decision tree algorithm is first used to regress the raw data to generate an optimal cut-off variable and cut-off point. Then, the variables with high correlation are screened according to Pearson coefficients. A four-layer BP neural network was constructed to predict octane loss. The model was validated by a cross-validation method, with 70% of the data selected as the training set and 30% of the data selected as the test set. The experimental data show that the mean error (MAE) of the prediction results is 16.23%, the mean squared error (MSE) is 4.27%, and the root means squared error (RMSE) is 20.66%. Finally, the model was optimized by the particle swarm algorithm to obtain the final operating ranges of the main operating variables. The model has a high degree of fit for the prediction of the target values, which helps to optimize the operating conditions and improve the quality of gasoline.
REFERENCES
Amaral, L.V., Santos, N.D.S.A., Roso, V.R., de Cássia de Oliveira Sebastião, R., and Pujatti, F.J.P., Effects of gasoline composition on engine performance, exhaust gases and operational costs, Renewable Sustainable Energy Rev., 2021, vol. 135, p. 110196. https://doi.org/10.1016/j.rser.2020.110196
Ding, G., Guangdong Chem. Ind., 2021, vol. 48, no. 18, pp. 105–106.
Zhang, J., Wang, W., and Chen, G., Technical analysis and countermeasures of China VI gasoline quality upgrade, Contemp. Chem. Ind., 2021, vol. 50, no. 11, pp. 2656–2661.
Xu, Zh., Huang, X., Lin, L., Wang, Q., Liu, J., Yu, K., Chen, Ch., BP neural networks and random forest models to detect damage by Dendrolimus punctatus Walker, J. Forestry Res., 2020, vol. 31, no. 1, pp. 107–121. https://doi.org/10.1007/s11676-018-0832-1
Bifulco, I., Cirillo, S., Esposito, C., Guadagni, R., and Polese, G., An intelligent system for focused crawling from Big Data sources, Expert Syst. Appl., 2021, vol. 184, pp. 115560. https://doi.org/10.1016/j.eswa.2021.115560
Tang, X. and Liu, G., Octane number prediction of blend gasoline based on improved particle swarm optimization, Acad. J. Comput. Inf. Sci., 2021, vol. 4, no. 1, pp. 53–59. https://doi.org/10.25236/AJCIS.2021.040109
Hu, K., Luo, W., and Jia, Sh., Octane number prediction model based on BP neural network, J. Wuhan Text. Univ., 2021, vol. 34, no. 4, pp. 27–32.
Wang, N., Construction of prediction model of gasoline octane loss based on BP neural network, Intell. Comput. Appl., 2021, vol. 11, no. 2, pp. 76–79.
Huang, X., Liu, T., and Ma, G., Research on gasoline octane loss prediction model based on BP neural network, Pract. Understanding Math., 2021, vol. 51, no. 23, pp. 158–164.
Xu, M., Zheng, Ya., Zhou, R., and Zhang, R., Octane number prediction based on BP neural network and multiple linear regression, J. Nanjing Univ. Inf. Sci. Technol. (Nat. Sci. Ed.), pp. 1–17.
Singh, P. and Bose, S.S., A quantum-clustering optimization method for COVID-19 CT scan image segmentation, Expert Syst. Appl., 2021, vol. 185, p. 115637. https://doi.org/10.1016/j.eswa.2021.115637
Singh, P., FQTSFM: A fuzzy-quantum time series forecasting model, Inf. Sci., 2021, vol. 566, pp. 57–79. https://doi.org/10.1016/j.ins.2021.02.024
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare that they have no conflicts of interest.
About this article
Cite this article
Bao-wei Zhang, Li, X., Song, Jx. et al. Construction and Analysis of Octane Number Loss Prediction Model. Aut. Control Comp. Sci. 57, 296–304 (2023). https://doi.org/10.3103/S0146411623030100
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411623030100