Prediction of higher heating values of biomass from proximate and ultimate analyses

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%).

Prediction of higher heating values of biochar from proximate and ultimate analysis

Biomass is the organic matter produced by photosynthesis which exists on the surface of the earth. They include all waste biomass such as municipal solid waste, municipal bio solids, animal wastes, forestry and agricultural wastes and some types of industrial wastes. Fossil fuels are the main energy resources of the earth. The only natural occurring substitute for fossil fuels is biomass. The main disadvantage of this energy is that it gives only low calorific value. So, calorific value is an important factor to evaluate the fuel quality of a special biomass material in energy applications. Using the values of proximate and ultimate analysis, many predicted equations are available in several literature to predict the higher heating value (HHV)of biomass. In this context, four different biomass species such as paddy straw, paddy husk, coconut husk and coconut shell have been characterized by proximate analysis and ultimate analysis. Further, thirty-one other varieties of biomass material characterization data have also been taken from existing literature for comparison and establishment of trend in variation of behavior. After that, various empirical equations which contain linear and nonlinear terms have taken into consideration for predicting the higher heating values (HHV)of full sample set from both analysis results. Finally validate the predicted HHV with actual HHV.

Waste-to-energy as a tool of circular economy: Prediction of higher heating value of biomass by artificial neural network (ANN) and multivariate linear regression (MLR)

High heating value (HHV) of biomass is important for the design and operation of biomass based energy conversion processes. Experimental determination of this property is always time consuming and expensive. This paper compares existing empirical correlations based on proximate and ultimate analysis of biomass for the determination of the HHV. The correlations were validated from experimental data for twelve biomass that are typical to Nigeria. The correlation based on proximate analysis with the least error is HHV=(354FC+170.8VM)/1000 having a mean absolute error of prediction in the range 0.12 to 5.71 and average absolute error of 0.07 to 24%. The Average absolute error of the correlation HHV=0.3897C+0.2976 from ultimate analysis ranges from 0.09 to 28.9% and the Mean absolute error ranges from 0.015 to 4.71. The predictions from the correlations are not showing good agreement with the experimental data. Ultimately, three correlations were developed in this study. The correlation based on ultimate analysis gave mean absolute prediction error of 0.11 to 2.45 and average absolute error of 0.6 to 16%. The correlation based on a combination of ultimate and proximate analysis gave mean absolute prediction error of 0.08 to 2.05 and average absolute error of 1-12%. The developed correlations are seen to be more accurate in predicting the HHV values. Keywords: Biomass, High Heating Value, Proximate analysis, Ultimate Analysis,

For proper design and operation of biomass‐based energy systems, it is important to determine the higher heating value (HHV) of biomass. In this paper, two machine learning (ML) approaches, namely extra trees (ET) and least squares support vector machine (LSSVM), are used to predict the value of HHV associated with biofuels. The data required for HHV calculation, including proximate and ultimate analyses datasets, were collected from the literature. The performances of these two ML approaches for predicting biomass HHV were then compared with other smart models available in the literature. Even though the available empirical models can predict the biomass HHV with acceptable precision, it was found that our proposed ML techniques have a superior performance based on the error analysis; the proposed approaches also consider all key biomass characteristics in the developed models. In addition, the ET model proved to be slightly more accurate compared to the LSSVM model. Additionally, the developed proximate‐based ET model showed better performance compared to the ultimate‐based ET model. The most influential parameters in the developed ET models for the proximate and ultimate approaches were determined to be ash fraction and carbon fraction, respectively. Finally, it was concluded that the smart modelling techniques can be utilized as a robust and reliable alternative predictive methodology to replace direct laboratory measurement of the biomass HHV.

Improved prediction of higher heating value of biomass using an artificial neural network model based on proximate analysis

The higher heating value (HHV) is an important property defining the energy content of biomass fuels. A number of proximate and/or ultimate analysis based predominantly linear correlations have been proposed for predicting the HHV of biomass fuels. A scrutiny of the relationships between the constituents of the proximate and ultimate analyses and the corresponding HHVs suggests that all relationships are not linear and thus nonlinear models may be more appropriate. Accordingly, a novel artificial intelligence (AI) formalism, namely genetic programming (GP) has been employed for the first time for developing two biomass HHV prediction models, respectively using the constituents of the proximate and ultimate analyses as the model inputs. The prediction and generalization performance of these models was compared rigorously with the corresponding multilayer perceptron (MLP) neural network based as also currently available high-performing linear and nonlinear HHV models. This comparison reveals that the HHV prediction performance of the GP and MLP models is consistently better than that of their existing linear and/or nonlinear counterparts. Specifically, the GP- and MLP-based models exhibit an excellent overall prediction accuracy and generalization performance with high (>0.95) magnitudes of the coefficient of correlation and low (<4.5 %) magnitudes of mean absolute percentage error in respect of the experimental and model-predicted HHVs. It is also found that the proximate analysis-based GP model has outperformed all the existing high-performing linear biomass HHV prediction models. In the case of ultimate analysis-based HHV models, the MLP model has exhibited best prediction accuracy and generalization performance when compared with the existing linear and nonlinear models. The AI-based models introduced in this paper due to their excellent performance have the potential to replace the existing biomass HHV prediction models.

Date palm biomass can be considered as an alternative to conventional energy combined with other renewable energy sources in the oasis. Its energy recovery requires a precise knowledge of its energy rate potential represented by its calorific value. Relationships of ultimate and proximate analysis of date palm biomass with higher heating value (HHV) have been investigated through artificial neural networks (ANNs) methods, especially, Multilayer Perceptron (MLP) model. Seven set of inputs including: (a) proximate analysis i.e. volatile matter (VM), ash (A) and moisture (M) and (b) ultimate analysis i.e carbon (C), hydrogen (H), oxygen (O) were identified and used for the prediction of (HHV) by ANNs. The adopted model allowed HHV prediction of phoenicicole biomass with a determination coefficient (R2) of up to 84% and a mean absolute percentage error (MAPE) of 2,61. (MLP) gives a good HHV prediction results for date palm biomass by taking into account hybrid variables (proximate and ultimate) especially carbon and oxygen. These input parameters were omnipresent in all the identified combinations and provided the optimum finding rates in association with volatile matter.

Higher heating value (HHV) is a key characteristic for the assessment and selection of biomass feedstocks as a fuel source. The HHV is usually measured using an adiabatic oxygen bomb calorimeter; however, this method can be time consuming and expensive. In response, researchers have attempted to use artificial neural network (ANN) systems to predict HHV using proximate and ultimate analysis data, but these efforts were hampered by varying case specific approaches and methodologies. Based on the complex ANN structures, a clear state of the art ANN understanding must be required for the prediction of biomass HHV. This study provides a comprehensive ANN application for HHV prediction in terms of how the activation functions, algorithms, hidden layers, dataset, and randomisation of the dataset affects the prediction of HHV of biomass feedstocks. In this paper we present a comparative qualitative and quantitative analysis of thirteen different algorithms, four different activation functions (logsig, tansig, poslin, purelin) with a wide range of hidden layer (3–15) for ANN models, used to predict the HHV of the biomass feedstocks. ANN models trained by the combination of ultimate-proximate analyses (UAPA) datasets provided more accurate predictions than the models trained by ultimate analysis or proximate analysis datasets. Regardless of the used datasets, sigmoidal activation functions (tansig and logsig) provide better prediction results than linear activation function (poslin and purelin). Furthermore, as training activation functions, “Levenberg-Marquardt (lm)” and “Bayesian Regularization (br)” algorithms provide the best HHV prediction. The best average correlation coefficients of 30 randomised run were observed with tansig as 0.962 and 0.876 for the ANN model developed by the UAPA dataset with a relatively high confidence levels of ∼96% for training and ∼92% for testing.

Biomass is a renewable and sustainable source of energy with little greenhouse gas emissions. The higher Heating value (HHV) of biomass is a significant parameter that is used in characterising fuel quality, class and type for energy application systems. Experimental determination of HHV is expensive, takes time and not always available. This brings the need for mathematical models for HHV prediction. In this research, proximate analysis and HHV of ten common biomass samples in Nigeria were determined. The biomass considered included rice husk, rice straw, corn cob, woodchips, groundnut shell, desert date, coconut shell, palm kernel, millet straw and sugarcane bagasse. Eight linear and five non-linear correlations with good performance from the literature were employed for predicting the biomass’ HHV from proximate analysis data. The performance of the models was tested using statistical indicators. Model M1 and M7 were the best among all the tested models with average absolute error (AAE), average bias error (ABE), and root mean square error (RSME) of 3.8389%, 2.5002% and 0.8780 MJ/kg; and 3.8918%, 2.2301% and 0.8701 MJ/kg respectively. Other models also correlated relatively well with the experimental HHV with low error, though, some are good for specific biomass only. This research identifies the best models that have high accuracy and can be used for the prediction of the higher heating value of biomass samples from proximate analysis.

A comprehensive study on estimating higher heating value of biomass from proximate and ultimate analysis with machine learning approaches

Prediction of higher heating value (HHV) using proximity and ultimate analysis is an important procedure for understanding the characteristic attribute of a fuel. Researches put effort to come up with equations to explain the relationship between the HHV value and those analyses. But conducted methods usually included only simple statistical analysis, thus they were partially effective to use in a practical manner. In this paper we approach this prediction problem from the machine learning perspective, we employ four machine learning methods, i.e. linear regression, polynomial regression, decision tree regression and support vector regression to predict HHV using proximity and ultimate analysis of different type of materials. Data set used is collected from literature and is categorized, where the resulting categories are used as features to be fed to the machine learning models to create prediction models as accurate as possible. Performances of the proposed methods are evaluated with k-fold cross-validation technique and each method’s pros and cons are discussed for both prediction accuracy and computational complexity.

Recently, biomass sources are important for energy applications. There is need for analyzing of the biomass model based on different components such as carbon, ash, and moisture content since the biomass sources are important for energy applications. In this paper, an extreme learning machine (ELM) is used to estimate efficiency. ELM was implemented for single-layer feed-forward neural network (SLFN) architectures. Because biomass modeling could be a very challenging task for conventional mathematical, it is suitable to apply machine learning models which could overcome nonlinearities of the process. The main attempt in this study was to develop a machine learning model for prediction of the higher heating values of biomass based on proximate analysis. According the prediction accuracy (coefficient of determination and root mean square error) of the higher heating value of the biomass, the inputs’ influence was determined on the higher heating value. According to the obtained results, fixed carbon has less moderate coefficient, ash has less correlation coefficient, and volatile matter has the most correlation coefficient. Therefore, the volatile matter percentage weight has the highest relevance on the higher heating value of the biomass. On the contrary, the ash has the smallest relevance on the higher heating value of the biomass based on machine learning approach.

Biomass is the organic matter formed by photosynthesis that occurs on the earth’s surface. They contain all forms of waste compost, including urban solid waste, municipal bio solids, animal wastes, forestry and agricultural wastes, and some industrial wastes. Efficient use of biomass oil would aid in the resolution of issues caused by fossil fuels. However, the biggest issue about using this energy is due to the gas composition of biomass material. As a result, properties of biomass are the critical parameter for assessing the fuel content of a special biomass substance in energetic applications. Gasification is the most mature thermo-chemical conversion technique available among the various methods of transforming biomass materials to bio resources. In this context, proximate and ultimate analysis has been used to classify two groups of biomass material that carry out in this experiment. The proximate analysis results have been obtained by the TGA technique while the ultimate analysis results will obtain by the GC mechanism. Then, based on the proximate analysis data various empirical equations containing linear and nonlinear terms were evaluated in order to predict the higher heating values (HHV) of the entire sample range. Since, the biomasses used in this analysis have different properties and fuel characteristics, the estimated HHV for the wood pellet sample are between 15.33 and 19.71 MJ/kg, while the rubber seed sample is between 15.18 and 18.64 MJ/kg. According to the experimental findings, the HHV of wood pellet is at around 2.95 MJ/Nm3 while the HHV of rubber seed of about 4.99MJ/Nm3. The comparison on the theoretical analysis have been show 0.19% compared to the results on wood pellet while the rubber seed have at around 2.07% difference compare each other. The experimental results on wood pellets, the findings reveal a 15.35% difference, while rubber seed indicates a 13.81% difference. Nonetheless, the finding and analysis on the properties, the results can be considered within reasonable limits.