Prediction of Gasoline Octane Loss Based on t-SNE and Random Forest

Chen Zheng (), Shan Li, Chengcheng Song and Siyu Yang
Additional contact information
Chen Zheng: Nanjing University of Aeronautics and Astronautics
Shan Li: Nanjing University of Aeronautics and Astronautics
Chengcheng Song: Nanjing University of Aeronautics and Astronautics
Siyu Yang: Nanjing University of Aeronautics and Astronautics

A chapter in AI and Analytics for Smart Cities and Service Systems, 2021, pp 43-54 from Springer

Abstract: Abstract Octane loss is an important index to measure economic benefit in the process of gasoline refining. Therefore, it is of great significance to construct the prediction model of octane loss in industrial production. In view of the characteristics of numerous variables and complex relationship of variables in gasoline refining data, t-SNE and K-Means algorithms are used in this paper to do data reduction and clustering analysis, and then collinear matrix method is used to gradually select the input variables for model construction, and finally random forest regression algorithm is introduced to build the prediction model of octane loss. The experimental results show that compared with the traditional prediction model, the prediction accuracy of the random forest is significantly improved, and the weight value of each variable of the model can be obtained by means of information gain, which provides a reference for the control variable level in the workshop production process.

Keywords: Octane loss; t-SNE; K-Means; Random forest (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnopch:978-3-030-90275-9_4

Ordering information: This item can be ordered from
http://www.springer.com/9783030902759

DOI: 10.1007/978-3-030-90275-9_4

Access Statistics for this chapter

More chapters in Lecture Notes in Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().