A least squares SVM algorithm for NIR gasoline octane number prediction

Yao, Xiaogang; Dai, Liankui

doi:10.1109/wcica.2004.1343314

Cited by 2 publications

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[4] In recent years, researchers have developed some methods using spectroscopic analysis to predict octane numbers. [5][6][7][8] However, instrument measurement is timeconsuming, labor-intensive, and expensive. Therefore, establishing a theoretical prediction model for octane number is of great significance.…”

Section: Introductionmentioning

confidence: 99%

Multi-feature optimization of QSPR model for fuel octane number

Gao,

Su,

Miao

et al. 2024

Second International Conference on Electrical, Electronics, and Information Engineering (EEIE 2023)

View full text Add to dashboard Cite

Octane number is one of the most important indicators in gasoline, and the standard method for determining octane number is time-consuming and expensive. In this study, a set of quantitative structure-property relationship (QSPR) descriptors of fuel molecules were used, and a combination method of variance filter and recursive feature elimination was applied to screen the descriptor subset that influences the prediction accuracy of octane number. The motor-octane numbers (MON) of 82 hydrocarbons were collected, and five different molecular descriptor tools: E-dragon, ChemoPy, CDK, RDKit, and PaDEL, were used to calculate five molecular descriptor libraries (MDLs). These MDLs were then integrated into a large comprehensive molecular descriptor library (CMDL), and the optimal subset was selected using the above-mentioned method. Screening models were established between these five MDLs, CMDL, and MON, and the molecular descriptor subset that contributed the most to MON prediction was found using evaluation models. The results showed that the globally optimal descriptor subset was from CMDL, while the optimal descriptor subsets in E-dragon and PaDEL of the MDLs have similar contributed to MON prediction and better than ChemoPy, CDK, RDKit.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-feature optimization of QSPR model for fuel octane number

Gao,

Su,

Miao

et al. 2024

Second International Conference on Electrical, Electronics, and Information Engineering (EEIE 2023)

View full text Add to dashboard Cite

show abstract

Research on New Nonlinear Method Applied on Coal Calorific Value Prediction

Sun

Zhu

Zhou

2013

AMM

View full text Add to dashboard Cite

Based on research of the relationship between the industrial analysis of coal composition and the calorific value, a multiple linear regression - support vector machine model for predicting calorific value of coal is put forward. The training sample set is made up of the original industrial analysis data and calorific value. Then the preliminary predicted model is established based on multiple linear regression algorithm. At the same time, error compensation is achieved by the support vector machine amend sub-model. The final predicted value is the sum of the preliminary predicted model output and the error compensation. Experimental results demonstrate that the predicted accuracy of the integrated model is more accurate than the traditional predicted models.

show abstract

A least squares SVM algorithm for NIR gasoline octane number prediction

Cited by 2 publications

References 2 publications

Multi-feature optimization of QSPR model for fuel octane number

Multi-feature optimization of QSPR model for fuel octane number

Research on New Nonlinear Method Applied on Coal Calorific Value Prediction

Contact Info

Product

Resources

About