Prediction of energy content of biomass based on hybrid machine learning ensemble algorithm

Dodo, Usman Alhaji; Ashigwuike, Evans Chinemezu; Emechebe, Jonas N.; Abba, S.I.

doi:10.1016/j.nexus.2022.100157

Cited by 16 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first layer of the model, fuzzification, contains the input variables and their membership functions (MFs). MF permits tuning as a measure to improve computation accuracy with a minimum error. , To simulate the data sets for optimal ANFIS model prediction and fuzzy inference system (FIS) generation, grid partitioning with an input number of membership functions (MFs = 3, 3, and 3) as well as input and output membership functions of types of “trimf” and “constant”, respectively, was selected, and the hybrid optimization method was used to train the FIS with an error tolerance of zero …”

Section: Methodsmentioning

confidence: 99%

“…69,70 To simulate the data sets for optimal ANFIS model prediction and fuzzy inference system (FIS) generation, grid partitioning with an input number of membership functions (MFs = 3, 3, and 3) as well as input and output membership functions of types of "trimf" and "constant", respectively, was selected, and the hybrid optimization method was used to train the FIS with an error tolerance of zero. 71 2.7.4. Assessment of the Developed Models.…”

Section: Adaptive Neuro-fuzzy Inference System (Anfis)mentioning

confidence: 99%

See 1 more Smart Citation

Performance Evaluation of Benzyl Alcohol Oxidation with tert-Butyl Hydroperoxide to Benzaldehyde Using the Response Surface Methodology, Artificial Neural Network, and Adaptive Neuro-Fuzzy Inference System Model

Emeji,

Kumi,

Meijboom

2024

ACS Omega

View full text Add to dashboard Cite

The adaptive neuro-fuzzy inference system (ANFIS), central composite experimental design (CCD)-response surface methodology (RSM), and artificial neural network (ANN) are used to model the oxidation of benzyl alcohol using the tert-butyl hydroperoxide (TBHP) oxidant to selectively yield benzaldehyde over a mesoporous ceria-zirconia catalyst. Characterization reveals that the produced catalyst has hysteresis loops, a sponge-like structure, and structurally induced reactivity. Three independent variables were taken into consideration while analyzing the ANN, RSM, and ANFIS models: the amount of catalyst (A), reaction temperature (B), and reaction time (C). With the application of optimum conditions, along with a constant (45 mmol) TBHP oxidant amount, (30 mmol) benzyl alcohol amount, and rigorous refluxing of 450 rpm, a maximum optimal benzaldehyde yield of 98.4% was obtained. To examine the acceptability of the models, further sensitivity studies including statistical error functions, analysis of variance (ANOVA) results, and the lack-of-fit test, among others, were employed. The obtained results show that the ANFIS model is the most suited to predicting benzaldehyde yield, followed by RSM. Green chemistry matrix calculations for the reaction reveal lower values of the E-factor (1.57), mass intensity (MI, 2.57), and mass productivity (MP, 38%), which are highly desirable for green and sustainable reactions. Therefore, utilizing a ceria-zirconia catalyst synthesized via the inverse micelle method for the oxidation of benzyl alcohol provides a green and sustainable methodology for the synthesis of benzaldehyde under mild conditions.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Adaptive Neuro-fuzzy Inference System (Anfis)mentioning

confidence: 99%

Performance Evaluation of Benzyl Alcohol Oxidation with tert-Butyl Hydroperoxide to Benzaldehyde Using the Response Surface Methodology, Artificial Neural Network, and Adaptive Neuro-Fuzzy Inference System Model

Emeji,

Kumi,

Meijboom

2024

ACS Omega

View full text Add to dashboard Cite

show abstract

“…It involves directly averaging the result of the individual model to provide the final outputs. 52 The simple averaging ensemble technique (SAE) is achieved through two steps: in the first step, each model is trained and tested separately, 53,54 and in the second step, the average of the model output was tested and compared with the observed tested values as illustrated in Fig. 5.…”

Section: Ensemble Learning Conceptmentioning

confidence: 99%

Ensemble hybrid machine learning to simulate dye/divalent salt fractionation using a loose nanofiltration membrane

Baig,

Abba,

Usman

et al. 2023

Environ. Sci.: Adv.

View full text Add to dashboard Cite

show abstract

“…In recent years, various statistical and machine learning techniques have been employed to develop predictive models for biomass HHV estimation [15], [16], [17], [18]. These models leverage the relationships between elemental composition and calorific value to establish robust prediction algorithms [19], [20], [21].…”

Section: Introductionmentioning

confidence: 99%

Predicting a Higher Heating Value for Torrefied Kesambi Leaf Biobriquettes through Ultimate Analysis

Sula Dethan

2024

ijcsrr

View full text Add to dashboard Cite

The escalating global pursuit of sustainable energy solutions has led to the emergence of biomass-derived fuels, such as biobriquettes, as feasible substitutes for traditional fossil fuels. Kesambi leaves, which are abundant in Southeast Asia and boast a high calorific value, represent a promising prospect for the production of biobriquettes. In this investigation, a conclusive analytical method is employed to construct a predictive framework for estimating the Higher Heating Value (HHV) of torrefied kesambi leaf biobriquettes. By incorporating ash content (PS), volatile matter (BR), carbon (C), hydrogen (H), and oxygen (O) percentages, alongside experimental HHV data, through multiple linear regression and elemental composition data acquired from proximal analysis, the model aims to forecast HHV. The model’s modest positive Mean Bias Error (MBE) and satisfactory Root Mean Square Error (RMSE) suggest a good fit. The substantial R-squared value indicates the model’s capability to adeptly capture HHV variability. Ultimately, this approach grounded in fundamental principles contributes significantly to the sustainable exploitation of biomass resources by providing a pragmatic and effective technique for predicting HHV for kesambi leaf biobriquettes.

show abstract

Prediction of energy content of biomass based on hybrid machine learning ensemble algorithm

Cited by 16 publications

References 27 publications

Performance Evaluation of Benzyl Alcohol Oxidation with tert-Butyl Hydroperoxide to Benzaldehyde Using the Response Surface Methodology, Artificial Neural Network, and Adaptive Neuro-Fuzzy Inference System Model

Performance Evaluation of Benzyl Alcohol Oxidation with tert-Butyl Hydroperoxide to Benzaldehyde Using the Response Surface Methodology, Artificial Neural Network, and Adaptive Neuro-Fuzzy Inference System Model

Ensemble hybrid machine learning to simulate dye/divalent salt fractionation using a loose nanofiltration membrane

Predicting a Higher Heating Value for Torrefied Kesambi Leaf Biobriquettes through Ultimate Analysis

Contact Info

Product

Resources

About