Prediction Of Higher Heating Value Research Articles

PSO/GA/ANN modeling and prediction for the higher heating values (HHVS) of solid fuels: The machine learning approach

The quick evaluation for the higher heating value (HHV) is crucial for thermochemical conversion of solid fuels. In this work, machine learning method based on artificial neural networks (ANN) was used to predict the HHV of solid fuel. 205 groups of different kinds of solid fuels collected from publications were used. The proximate analysis, ultimate analysis and the combination of two were used as input parameters. The influence of activation function, neuron number and hidden layer number on the prediction performance was studied. Results show that single hidden layer with logsig function using 8 neurons was an optimized condition for HHV prediction. The combination of two composition analyses could achieve much higher accuracy, with the average relative error of 2.57%. Impact analysis indicated that the non-combustible components, namely ash content and oxygen content showed the largest influencing weight for HHV prediction, accounting for 21.73% and 22.91% respectively. Particle swarm optimization (PSO) and genetic algorithm (GA) were further used to optimize the artificial neural network model. Results show that PSO and GA both improved the prediction performance of ANN model by optimizing the initial weight and threshold values. The average relative errors for PSOANN and GA-ANN decreased to 1.15 % and 1.72 % respectively.

Hydrothermal bio-oil yield and higher heating value of high moisture and lipid biomass: Machine learning modeling and feature response behavior analysis

The yield and higher heating value (HHV) of bio-oil products are significant performance parameters for the hydrothermal conversion of high-water and high-lipid biomass. Machine learning (ML) modeling prediction is a fast and convenient means of obtaining performance parameters. An informative dataset with 243 samples was prepared, and two highly adapted ML algorithms were used: Random Forest (RF) and Extreme Gradient Boosting Tree (XGBoost). It is interesting to note that the developed ML models demonstrated great prediction ability; for example, the regression coefficient (R2) of the XGBoost model for yield and HHV prediction was as high as 0.942 and 0.940, respectively. Furthermore, partial dependence plots (PDP) and SHapley Additive exPlanations (SHAP) interpretability methodologies were adopted to address the main contributions of the feature identification and response behavior analysis of the features. The results demonstrated that the biomass composition had the greatest effect on bio-oil yield, with fat contributing up to 40 %. In contrast, the elemental composition had the most significant effect on the HHV of bio-oil. Notably, hydrogen content affected the HHV of up to 4.5 units. The interaction response behavior showed that the interaction of the process parameters with feedstock properties was most common and significant. The information obtained from the response mechanism can be used to enhance the subsequent hydrothermal fuel preparation process for bio-oils.

Critical insights into ensemble learning with decision trees for the prediction of biochar yield and higher heating value from pyrolysis of biomass

Pyrolysis is an efficient thermochemical conversion process, but accurate prediction of yield and properties of biochar presents a significant challenge. Three prominent ensemble learning methods, viz. Random Forest (RF), eXtreme Gradient Boosting (XGB), and Adaptive Boosting (AdaBoost) were utilized to develop models to predict yield and higher heating value (HHV) of biochar. Dataset comprising 423 observations from 44 different biomasses was curated from peer-reviewed journals for predicting biochar yield. RF regressor achieved a test R2 of 0.86 for biochar yield, while XGB regressor achieved a test R2 of 0.87 for biochar HHV prediction. The SHapley Additive exPlanations (SHAP) analysis was conducted to assess influence of each feature on the model’s output. Pyrolysis temperature and ash content of biomass were identified as the most influential features for the prediction of both yield and HHV of biochar. The partial dependence plots (PDPs) revealed nonlinear relationships, interpreting how the model formulates its predictions.

Establishing a generalized model for accurate prediction of higher heating values of substances with large ash fractions

The higher heating value (HHV) of biomass is a crucial property for design calculations and numerical simulations in bioenergy utilization. However, existing models for HHV prediction faced challenges in terms of predictive accuracy and generalization capability across various solid waste types, especially for those with high ash content. This work proposed a novel HHV prediction model based on its reduction degree (DR) and ash content (Cash). First, ultimate analysis of biomass was applied to establish the calculation method of DR; then, the correlation between DR, Cash, and HHV was analyzed using the Pearson Correlation Coefficient; subsequently, the HHV = f (DR, Cash) model was developed using regression analysis. Furthermore, the accuracy was compared to previous literature in terms of correlation coefficient (R2), root mean square error (RMSE), and mean absolute error (MAE). Results revealed that this model provided attractive accuracy with R2 = 0.854, RMSE = 0.900, and MAE = 0.773 within a wide range of ash content from 0 to 83.32 wt%. Even higher accuracy was achieved with this model in predicting the HHV of coal, biochar, and bio-oil, with R2 of 0.961, 0.989, and 0.939, respectively. Conclusively, this work proposed the use of DR for HHV estimation, which was not only a simple and accurate approach but also widely applicable to various fuels.

Comparative studies of machine learning models for predicting higher heating values of biomass

This study addresses the challenge of efficiently determining the higher heating value (HHV) of biomass, a crucial parameter in large-scale biomass-based energy systems. The conventional method of measuring HHV using an oxygen bomb calorimeter is time-consuming, expensive, and less accessible to researchers, particularly in developing nations. To overcome these limitations, we employed four machine learning (ML) models, namely Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost). These models were developed by using proximate and ultimate analysis parameters as input features. Up to 200 datasets were compiled from literature and used for the ML models. Our results demonstrate the effectiveness of all ML models in accurately predicting the HHV of biomass materials. Notably, the XGBoost model exhibited superior performance with the highest R-squared (R2) values for both training (0.9683) and test datasets (0.7309), along with the lowest root mean squared error (RSME) of 0.3558. Key influential input features identified for HHV prediction include carbon (C), volatile matter (Vm), ash, and hydrogen (H). Consequently, this research provides a reliable alternative for predicting HHV without the need for costly and time-intensive experimental measurements, facilitating broader accessibility in biomass energy research.

Regression based prediction of higher heating value for refuse-derived fuel using convolutional neural networks predicted elemental data and spectrographic measurements

Regression based prediction of higher heating value for refuse-derived fuel using convolutional neural networks predicted elemental data and spectrographic measurements

Generalizability of empirical correlations for predicting higher heating values of biomass

ABSTRACT Designing efficient biomass energy systems requires a thorough understanding of the physicochemical, thermodynamic, and physical properties of biomass. One crucial parameter in assessing biomass energy potential is the higher heating value (HHV), which quantifies its energy content. Conventionally, HHV is determined through bomb calorimetry, but this method is limited by factors such as time, accessibility, and cost. To overcome these limitations, researchers have proposed a diverse range of empirical correlations and machine-learning approaches to predict the HHV of biomass based on proximate and ultimate analysis results. The novelty of this research is to explore the universal applicability of the developed empirical correlations for predicting the Higher Heating Value (HHV) of biomass. To identify the best empirical correlations, nearly 400 different biomass feedstocks were comprehensively tested with 45 different empirical correlations developed to use ultimate analysis (21 different empirical correlations), proximate analysis (16 different empirical correlations) and combined ultimate-proximate analysis (8 different empirical correlations) data of these biomass feedstocks. A quantitative and statistical analysis was conducted to assess the performance of these empirical correlations and their applicability to diverse biomass types. The results demonstrated that the empirical correlations utilizing ultimate analysis data provided more accurate predictions of HHV compared to those based on proximate analysis or combined data. Two specific empirical correlations including coefficients for each element (C, H, N) and their interactions (C*H) demonstrate the best HHV prediction with the lowest MAE (~0.49), RMSE (~0.64), and MAPE (~2.70%). Furthermore, some other empirical correlations with carbon content being the major determinant also provide good HHV prediction from a statistical point of view; MAE (~0.5–0.8), RMSE (~0.6–0.9), and MAPE (~2.8–3.8%).

Comparative study of different training algorithms in backpropagation neural networks for generalized biomass higher heating value prediction

When selecting biomass feedstock for sustainable heat and electricity generation, higher heating value (HHV) is an important consideration. Meanwhile, the laboratory procedures of using an adiabatic oxygen bomb calorimeter to determine the HHV are strenuous, costly, and time-consuming. As a result, researchers have turned to artificial intelligence techniques such as artificial neural networks (ANN) to predict HHV using data from proximate analysis. Notwithstanding, this approach has been hampered by different case-specific techniques and methodologies given the heterogeneous nature of biomass materials and intricate ANN structures. This study, therefore, examined and compared the efficacy of six training algorithms comprising thirteen distinct training functions of feedforward backpropagation neural networks to predict the HHV of a variety of biomass materials as a function of the proximate analysis. In creating the networks, the neurons of the hidden layer were iterated from 1 to 20 leading to 260 investigated scenarios. Compared to other training algorithms, the Bayesian Regularization and Levenberg-Marquardt with 15 and 12 hidden neurons respectively, demonstrated superior prediction performances based on the Nash-Sutcliff's efficiencies of 0.9044 and 0.8877, and mean squared errors of 0.002271 and 0.00267. It is envisaged that this study will create an insightful paradigm for a rapid selection of best-performing ANN algorithms for biomass HHV prediction.

Performance Analysis of Intelligent Computational Algorithms for Biomass Higher Heating Value Prediction

Higher heating value (HHV) is an essential parameter to consider when evaluating and choosing biomass substrates for combustion and power generation. Traditionally, HHV is determined in the laboratory using an adiabatic oxygen bomb calorimeter. Meanwhile, this approach is laborious and cost-intensive. Hence, it is essential to explore other viable options. In this study, two distinct artificial intelligence-based techniques, namely, a support vector machine (SVM) and an artificial neural network (ANN) were employed to develop proximate analysis-based biomass HHV prediction models. The input variables comprising ash, volatile matter, and fixed carbon were paired to form four separate inputs to the prediction models. The overall findings showed that both the ANN and the SVM tools can guarantee accurate prediction in all the input combinations. The optimal prediction performances were observed when fixed carbon and volatile matter were paired as the input combination. This combination showed that the ANN outperformed the SVM, having presented the least root mean squared error of 0.0008 and the highest correlation coefficient of 0.9274. This study, therefore, concluded that the ANN is more preferred compared to SVM for biomass HHV prediction based on the proximate analysis.

Biomass higher heating value prediction machine learning insights into ultimate, proximate, and structural analysis datasets

ABSTRACT In this study machine learning (ML) models have been employed to predict the higher heating value (HHV) of biomass by utilizing input variables derived from ultimate, proximate, and structural analyses. In total, 180 models were developed, with 124 utilizing ultimate analysis data, 28 based on proximate analysis, and 28 relying on structural analysis. Various ML techniques, including polynomial models (SOP), support vector machines (SVM), random forest regression (RFR), and artificial neural networks (ANN), were employed for analysis. The study found that ANN models, when “fed” with FC and VM data, provided considerable accuracy in prediction results, with the best results obtained with 2-12-1 architecture (R2 = 0.96). In addition, a separate model configuration that processed inputs on biomass constituents such as cellulose, lignin, and hemicellulose showed remarkable agreement with empirical data. Additional findings revealed that the models created using SOP (R2 = 0.95), SVM (R2 = 0.95), and RFR (R2 = 0.90) demonstrated minimal discrepancies when predicting HHV. This study provides significant insights into the investigation of biomass analysis techniques employing ML tools, paving the way for future research aimed at constructing a robust tool for HHV prediction. Subsequent models may explore integrating inputs from diverse analysis methods and leveraging advanced machine learning techniques to enhance accuracy further.

Machine learning prediction of higher heating value of biochar based on biomass characteristics and pyrolysis conditions

The higher heating value of biochar is an important parameter for the utilization of biomass energy. In this work, extreme gradient boosting regression and artificial neural network were used to predict it based on the characteristics of biomass and pyrolysis conditions. Besides, empirical correlations were developed for comparison. Results showed that the extreme gradient boosting regression models showed better performance (R2 = 0.83–0.94). The shapley additive explanations and partial dependence plot indicated that lignin content and higher heating value of raw material were highly positively correlated with higher heating value of biochar, and found the better conditions such as pyrolysis temperature (>550 °C), lignin content (>40 wt%) for high-higher heating value biochar preparation. What’s more, a program that predicted higher heating value of biochar was developed through PySimpleGUI library. It offered a new optimization idea for the directional preparation process of biochar.

Higher heating value prediction of high ash gasification-residues: Comparison of white, grey, and black box models

The measurement of the higher heating value (HHV) in high-ash solid waste poses persistent challenges due to the inherent limitations of using an oxygen bomb calorimeter. HHV predictive models based on the components analysis were proved to be useful methods. To improve the accuracy and applicability of HHV models, this work selected 100 actual measured data of high ash gasification residues, and compared three types of predictive models from white, grey, and black box by the following procedures: Modeling, External-validation, and Extending study. In the Modeling and External-validation processes, eight models from linear regression, grey model, and machine learning models, were proposed with R2 > 0.95 and MAPE<8.42 %. Compared to existing research, the models proposed in this study provide appealing accuracies. In the Extending study for applicability evaluation, the UA-based models UOGM (1, 5) (R2 = 0.86 and MAPE = 12.96 %) and RL-Ult (R2 = 0.89 and MAPE = 11.52 %) outperformed the other six models by using the eight-expanding data of different solid wastes that collected from the literature. Based on these results, the above two models were applied to predict the HHV of remaining 53 gasifier residues, showing reliable predicting results. This work shows that the developed models have high accuracy for the HHV prediction of high-ash solid wastes.

Prediction of higher heating value of hydrochars using Bayesian optimization tuned Gaussian process regression based on biomass characteristics and process conditions

Hydrochars are valuable resources obtained from hydrothermal carbonization (HTC) of biomass. To optimize the reaction conditions of HTC, extensive experimentation is required, which is both costly and time consuming. In order to reduce the time and cost, this study develops new predictive models for higher heating values (HHV) of hydrochar based on Gaussian Process Regression (GPR), Ensemble, and Decision Tree (DT) algorithms using Bayesian Optimization (BO). This approach reduces prediction errors by combining GPR, Ensemble, and DT with BO. This is the first study on the application of BO for the hyperparameter selection as the basic learner. BO-GPR converged during training with the lowest Mean Absolute Error (0.1783) compared to BO-Ensemble (0.5128) and BO-DT (0.7430). The efficiencies of the algorithms were measured by the Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and coefficient of determination (R2). During the testing, BO-GPR generated MAE, RMSE and R2 of 0.4435, 0.5961 and 0.9705, respectively, and performed better than BO-Ensemble and BO-DT. The Nemenyi test showed that BO-GPR, BO-Ensemble, and BO-DT were statistically different in terms of their prediction ability. BO-GPR outperformed the other two methods.

Performance of visible and Near-infrared spectroscopy to predict the energetic properties of wood

Wood can be used for fuel by direct burning, or as a raw material for other fuels; however, it is necessary to evaluate the energy properties to ensure the optimal use of this material. The most relevant characteristics to be analyzed are the higher heating value, volatile material content, fixed carbon content, and ash content. Along with the traditional methods, there are also non-destructive evaluations that are optimized for speed and reliability. Among these methods, visible spectroscopy and near-infrared spectroscopy have been proven to be robust for the prediction of several wood properties. The aim of this study was to evaluate the potential of visible spectroscopy and near-infrared spectroscopy for species discrimination and prediction of higher heating value, volatile material content, fixed carbon content, and ash content for Eucalyptus saligna, Eucalyptus dunnii, and Eucalyptus benthamii woods. For this purpose, multivariate principal component analysis and partial least squares regression were applied to the collected spectra. The principal component analysis satisfactorily discriminated the three species, explaining 99% of the variance of the visible spectroscopy spectra and 73% of that of the near-infrared spectra. The estimation of energetic properties through partial least squares regression was satisfactory for both visible spectroscopy and near-infrared spectroscopies, which presented calibration R² values close to 1 and low errors for all properties studied.

Prediction of Higher Heating Values in Bio-Oil from Solvothermal Biomass Conversion and Bio-Oil Upgrading Given Discontinuous Experimental Conditions.

Both the conversion of lignocellulosic biomass to bio-oil (BO) and the upgrading of BO have been the targets of many studies. Due to the large diversity and discontinuity seen in terms of reaction conditions, catalysts, solvents, and feedstock properties that have been used, a comparison across different publications is difficult. In this study, machine learning modeling is used for the prediction of final higher heating value (HHV) and ΔHHV for the conversion of lignocellulosic feedstocks to BO, and BO upgrading. The models achieved coefficient of determination (R2) scores ranging from 0.77 to 0.86, and the SHapley Additive exPlanations (SHAP) values were used to obtain model explainability, revealing that only a few experimental parameters are largely responsible for the outcome of the experiments. In particular, process temperature and reaction time were overwhelmingly responsible for the majority of the predictions, for both final HHV and ΔHHV. Elemental composition of the starting feedstock or BO dictated the upper possible HHV value obtained after the experiment, which is in line with what is known from previous methodologies for calculating HHV for fuels. Solvent used, initial moisture concentration in BO, and catalyst active phase showed low predicting power, within the context of the data set used. The results of this study highlight experimental conditions and variables that could be candidates for the creation of minimum reporting guidelines for future studies in such a way that machine learning can be fully harnessed.

Applying feature selection and machine learning techniques to estimate the biomass higher heating value

The biomass higher heating value (HHV) is an important thermal property that determines the amount of recoverable energy from agriculture byproducts. Precise laboratory measurement or accurate prediction of the HHV is essential for designing biomass conversion equipment. The current study combines feature selection scenarios and machine learning tools to establish a general model for estimating biomass HHV. Multiple linear regression and Pearson’s correlation coefficients justified that volatile matter, nitrogen, and oxygen content of biomass samples have a slight effect on the HHV and it is better to ignore them during the HHV modeling. Then, the prediction performance of random forest, multilayer and cascade feedforward neural networks, group method of data handling, and least-squares support vector regressor are compared to determine the intelligent estimator with the highest accuracy toward biomass HHV prediction. The ranking test shows that the multilayer perceptron neural network better predicts the HHV of 532 biomass samples than the other intelligent models. This model presents the outstanding absolute average relative error of 2.75% and 3.12% and regression coefficients of 0.9500 and 0.9418 in the learning and testing stages. The model performance is also superior to a recurrent neural network which was recently developed in the literature using the same databank.

A blended ensemble model for biomass HHV prediction from ultimate analysis

This work proposes a new blended stacked ensemble machine-learning model (BEM) to predict biomass’s higher heating value (HHV) from the ultimate analysis. Gorilla troop optimization (GTO) is utilized to estimate the hyperparameter values of BEM, leading to GBEM. In GBEM, support vector regression (SUVR), Gaussian process regression (GAPR), and Decision Tree (DETR) are used as the base learner, whereas adaptive linear neural network (ADALINE) is used as a meta-learner, respectively. Furthermore, Linear Regression (LIR), generalized additive model (GEAM), and bagging of regression trees (BAGG) are also designed for comparison purposes. Results reveal that GBEM predicts the HHV with a lower AARD% (2.959%) value than other designed ML predictive models. In addition to this, a predictive equation that gives the relationship between HHV and the ultimate analysis parameters C, H, O, N, and S is also derived using GTO.

Retraction Note: Machine learning prediction of higher heating value of biomass

Retraction Note: Machine learning prediction of higher heating value of biomass

Prediction of HHV of fuel by Machine learning Algorithm: Interpretability analysis using Shapley Additive Explanations (SHAP)

This study presents a novel approach using machine learning techniques to estimate waste materials' higher heating value (HHV), which plays a crucial role in waste-to-energy generation efficiency. The study utilizes a dataset comprising ultimate and proximate analysis of 16 different waste types. It employs six machine learning models: Extra Trees, Random Forest, Support Vector, Decision Tree, Extreme Gradient Boosting, and Multivariate Linear Regressors. The investigation explores the relationships between the features and outcomes through Spearman correlation, feature importance analysis, SHAP dependence, and decision plots, providing the interpretability of the model's predictions. The models are fine-tuned with hyperparameters for six feature sets, enabling researchers to anticipate HHV based on their specific input. The results demonstrate high accuracy in predicting HHV, with R2 ranging from 0.83 to 0.98, RMSE from 2.25 to 0.79, and MAPE from 6.01 to 0.92%. The study further reveals that higher carbon and hydrogen content increases HHV, while higher oxygen and ash content results in decreased HHV. Notably, Carbon, Ash content and Hydrogen content are the significant features with mean absolute SHAP values of2.17, 0.65, and 0.37, respectively. The proposed alternative prediction method has practical implications for waste-to-energy generation research and practice, facilitating informed decision-making in this field.

Prediction of higher heating value of coal based on gradient boosting regression tree model

Higher heating value, also known as the coal calorific value, is an important indicator of coal quality. Nevertheless, traditional experimental determination of higher heating value is expensive, tedious, and time-consuming. Some regression models have been commonly used to solve this problem. However, the prediction accuracy still needs to be improved. Accordingly, based on the correlation between proximate analysis of coal and higher heating value, a gradient boosting regression tree model was established in this study to predict the higher heating value as a means to a less intensive procedure to estimate coal heating values. This approach used data from the U.S. Geological Survey Coal Quality database and Kentucky Coal Database to evaluate coal quality. The hyperparameters of the regression tree model were tuned by cross-validation. A comparative study was conducted between the model established in this paper and the existing methods. Experimental results indicate that the coefficient of determination of the gradient boosting regression tree model of two databases achieves 0.9862 and 0.9541, respectively. Thus, the prediction capability of the gradient boosting regression tree model outperforms the existing methods.