Modeling the effects of biodiesel chemical composition on iodine value using novel machine learning algorithm. (15th May 2022)

• Record Type: Journal Article
• Authors: Huang, Yundi; Li, Fashe; Bao, Guirong; Xiao, Qingtai; Wang, Hua
• Is Part Of: Fuel. Volume 316(2022)
• Publication Date: 2022-05-15
• Subjects: ANFIS Adaptive neuro fuzzy inference system -- COP Pearson's correlation coefficient -- CME Canola methyl ester -- COSME Camellia oleosa seed methyl ester -- CSME Cottonseed methyl ester -- DT Decision tree -- FAME Fatty acid methyl ester -- GA Genetic algorithm -- GC-MS Gas chromatography mass spectrometry -- HME Hogwash oil methyl ester -- IV Iodine value -- JME Jatropha methyl ester -- LSSVM Least squares support vector machine -- MAE Mean absolute error -- MAPE Mean absolute percentage error -- ML Machine learning -- MLPNN Multi-layer perceptron neural network -- MME Maize methyl ester -- MSE Mean squared error -- OME Olive methyl ester -- OOB Out-of-bag -- OSME Oryza sativa methyl ester -- PCA Principal component analysis -- PCC Pearson's correlation coefficients -- PME Palm methyl ester -- PNME Peanut methyl ester -- PSO Particle swarm optimization -- RBFNN Radial basis function neural network -- RF Random forest -- RL ReliefF -- RME Rapeseed methyl ester -- RMSE Root mean squared error -- RSME Rubber seed methyl ester -- SBME Soya bean methyl ester -- SSME Sunflower seed methyl ester -- SVM Support vector machine -- WOA Whale optimization algorithm; Biodiesel property -- Chemical composition -- Meta-heuristic optimization algorithm -- Feature selection -- Least squares support vector machine -- Modeling; Fuel -- Periodicals; Coal -- Periodicals; Coal; Fuel; Periodicals; 662.6
• DOI: 10.1016/j.fuel.2022.123348
• Languages: English
• ISSNs: 0016-2361

Abstract

Highlights: The feature selection methods were used to identify the important fatty acid methyl ester combination. LSSVM model is most appropriate as the predictive model compared to the ANFIS, MLPNN, and DT models. RF-WOA-LSSVM model was developed for predicting the IV of biodiesel as a function of fatty acid methyl ester profiles. William's plot is used to detect outliers. Abstract: Biodiesel is a promising renewable energy the use of which facilitates the goals of carbon neutrality and timely carbon peak. The iodine value (IV), one of the major properties of biodiesel, denotes the degree of unsaturation and correlates with the chemical composition of biodiesel. In this work, a novel approach based on random forest (RF) and least squares support vector machine (LSSVM) algorithms optimized by whale optimization algorithm (WOA) is proposed for estimating the IV of biodiesel as a function of fatty acid methyl ester profiles. In doing so, the compositions and IVs of 52 biodiesel/binary biodiesel blends were determined by gas chromatography mass spectrometry and EN14111 standard. Then, LSSVM algorithm was assessed as the most appropriate predictive method compared to the adaptive neuro fuzzy inference system, multi-layer perceptron neural network, and decision tree algorithms. Continuously, four feature selection approaches (Pearson's correlation coefficient, principal component analysis, ReliefF algorithm, and RF) were utilized to choose the most influencing fatty acid methyl ester combination as input. The RF-LSSVM model was found to be superior to other Ⅰ hybrid models. Then, WOA was incorporated into the modeling process and the RF-WOA-LSSVM model achieved a high performance with a root mean square error and correlation coefficient of 1.1893 and 0.9977, respectively. The accuracy and error of the RF-WOA-LSSVM model have been validated. Comparison with previous biodiesel IV machine learning models and application of other new experimental datasets from the literature prove the feasibility of the proposed hybrid RF-WOA-LSSVM model for estimating the IV of different biodiesels types.