Applications of machine learning in thermochemical conversion of biomass-A review. (15th January 2023)

• Record Type: Journal Article
• Authors: khan, Muzammil; Raza Naqvi, Salman; Ullah, Zahid; Ali Ammar Taqvi, Syed; Nouman Aslam Khan, Muhammad; Farooq, Wasif; Taqi Mehran, Muhammad; Juchelková, Dagmar; Štěpanec, Libor
• Is Part Of: Fuel. Volume 332(2023)Part 1
• Publication Date: 2023-01-15
• Subjects: Artificial intelligence -- Machine learning -- Optimization -- Biomass -- Sustainability -- Climate change; ML Machine learning -- PLS Partial least square -- DT Decision tree -- PCA Principal component analysis -- ANFL Adaptive neuro-fuzzy logic -- GBM Gradient boosting machine -- MLR Multi linear regression -- ANN Artificial neural network -- RF Random forest -- LM-BP Levenberg-marquardt backpropagation algorithm -- NARX Nonlinear autoregressive network exogenous -- NARXNN Non-linear autoregressive with exogenous neural networks -- GPR Gaussian process regression -- SVM Support vector machine -- KNN K-nearest neighbor's algorithm -- PR Polynomial regression -- MVNL Multi variant non-linear -- GP Gaussian process -- LR Linear regression -- FL Fuzzy logic -- LS Least square -- Tansig Tangent-sigmoid -- Logsig Logarithmic sigmoid function -- PCDDS/PCDFS Polychlorinated dibenzo-p-dioxins and furans -- HHV Higher heating value -- EF Enhancement factor -- SY Solid yield -- RSM Response surface methodology -- KRR Kernel ridge regression -- GTB Gradient tree boosting -- MLP Multilayer perceptron -- MARS Multivariate adaptive regression splines -- ENS1 Ensembles of decision tree (bagging) -- ENS2 Ensembles of decision tree (boosting) -- FFMLP Feed forward multi-layer perceptron -- FFNN Feed forward neural network -- CFBP Cascade forward back propagation -- FFBP Feed-forward backpropagation -- EBP Error back propagation -- GDX Gradient descent with momentum-based adaptive learning rate back propagation algorithm -- CRNN Chemical reaction neural networks; Fuel -- Periodicals; Coal -- Periodicals; Coal; Fuel; Periodicals; 662.6
• DOI: 10.1016/j.fuel.2022.126055
• Languages: English
• ISSNs: 0016-2361

Abstract

Graphical abstract: Highlights: Machine learning models can accurately model thermal conversion methods. Classification, regression, and optimization are involved in thermal conversion. Artificial neural networks have been the most commonly employed algorithm. Optimization methods were used for ANN network selection and hyper-parameters. Hybrid and novel ML algorithms (deep learning) with large databases are expected. Abstract: Thermochemical conversion of biomass has been considered a promising technique to produce alternative renewable fuel sources for future energy supply. However, these processes are often complex, labor-intensive, and time-consuming. Significant efforts have been made in developing strategies for modeling thermochemical conversion processes to maximize their performance and productivity. Among these strategies, machine learning (ML) has attracted substantial interest in recent years in thermochemical conversion process optimization, yield prediction, real-time monitoring, and process control. This study presents a comprehensive review of the research and development in state-of-the-art ML applications in pyrolysis, torrefaction, hydrothermal treatment, gasification, and combustion. Artificial neural networks have been widely employed due to their ability to learn extremely non-linear input–output correlations. Furthermore, the hybrid ML models outperformed the traditional ML models in modeling and optimization tasks. The comparison between various ML methods for different applications, and insights about where the current research is heading, is highlighted. Finally, based on the critical analysis, existing research knowledge gaps are identified, and future recommendations are presented.