Energy value estimation of silages for substrate in biogas plants using an artificial neural network

Kowalczyk-Juśko, Alina; Pochwatka, Patrycja; Zaborowicz, Maciej; Czekała, Wojciech; Mazurkiewicz, Jakub; Mazur, Andrzej; Janczak, Damian; Marczuk, A.; Dach, Jacek

doi:10.1016/j.energy.2020.117729

Cited by 35 publications

(19 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our experiment, biogas efficiency was investigated by applying methane fermentation under mesophilic conditions (the most popular technology in Europe), in three replications, using a proprietary biofermenter (Figure 1). The pretreated samples were analyzed for biogas efficiency according to standard methodologies (DIN 38414/S8 and VDI 4630) [21]. The biogas production experiment was carried out under standard methane fermentation conditions in sets of 3 tank biofermenters [31].…”

Section: Methane Fermentation Of the Processed Raw Materialsmentioning

confidence: 99%

“…The pretreated samples were analyzed for biogas efficiency according to standard methodologies (DIN 38414/S8 and VDI 4630) [21]. The biogas production experiment was carried out under standard methane fermentation conditions in sets of 3 tank biofermenters [31].…”

Section: The Energy Potential Of the Substratementioning

confidence: 99%

“…Unfortunately, more and more frequent droughts, as well as the mass occurrence of pests and diseases of maize are not conducive to increasing the area of its cultivation. Moreover, high demand for raw materials for biogas plants may result in the emergence of maize monocultures, which has a negative impact on agroecosystems [21]. Thus, as an alternative biogas substrate, it was decided to use corn wastes, but still those derived from crops grown for food purposes in the form of corn bran.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The Influence of the Pressure-Thermal Agglomeration Methods of Corn Bran on Their Selected Physicochemical Properties and Biogas Efficiency

et al. 2021

Self Cite

View full text Add to dashboard Cite

The article presents the research made on the effects of methods of pressure-thermal agglomeration of corn bran, as well as the influence of processing parameters on selected physicochemical properties and biogas efficiency. Corn bran moistened to four levels of moisture content was used for the tests: 20%, 25%, 30% and 35% of dry matter. The pressure-thermal treatment was carried out with the use of a Brikol SJ25 pellet maker and a TS-45 single-screw extruder. In the tests of the extrusion-cooking process, three rotational speeds of the extruder screw were applied: 70, 90 and 110 rpm. The following characteristics were examined: efficiency of the extrusion-cooking and pelleting process, as well as the energy consumption. The water absorption index (WAI), the water solubility index (WSI), bulk density, kinetic strength, structure analysis by the ART/FTIR method, energy potential and the efficiency of cumulated biogas and cumulated methane per dry mass, as well as fresh mass and fresh organic matter and a series of microscopic pictures were completed. The analysis of the ATR/FTIR infrared spectra of the tested pelleted and extruded samples showed clear changes at the molecular level. Biogas production of extruded corn bran increased by several percent, as compared to untreated material.

show abstract

Section: Methane Fermentation Of the Processed Raw Materialsmentioning

confidence: 99%

Section: The Energy Potential Of the Substratementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Influence of the Pressure-Thermal Agglomeration Methods of Corn Bran on Their Selected Physicochemical Properties and Biogas Efficiency

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…21 Supervised machine learning models can learn and understand existing relationships between dependent and independent variables, finding widely generalizable standards for many conditions. 21,22 In agricultural science, artificial neural networks (ANNs) are the most popular and have been successfully applied to predict potato yield, 23 estimation of agricultural drought in south-eastern Australia, 24 energy value of silages for substrate in biogas plants, 25 identification of haploid and diploid corn seeds, 26 and classification of crop diseases. 27 In weed science, ANNs have been used for digital weed recognition 28,29 and its spatial distribution for herbicide application.…”

Section: Introductionmentioning

confidence: 99%

Machine learning models as an alternative to determine productivity losses caused by weeds

Souza

Monteiro

Silva

et al. 2021

Pest Management Science

View full text Add to dashboard Cite

BACKGROUND Weed control can be economically viable if implemented at the necessary time to minimize interference. Empirical mathematical models have been used to determine when to start the weed control in many crops. Furthermore, empirical models have a low generalization capacity to understand different scenarios. However, computational development facilitated the implementation of supervised machine learning models, as artificial neural networks (ANNs), capable of understanding complex relationships. The objectives of our work were to evaluate the ability of ANNs to estimate yield losses in onion (model crop) due to weed interference and compare with multiple linear regression (MLR) and empirical models. RESULTS MLR constructed from non‐destructive and destructive methods show R2 and root mean square error (RMSE) values varying between 0.75% and 0.82%, 13.0% and 19.0%, respectively, during testing step. The ANNs has higher R2 (higher than 0.95) and lower RMSE (less than 6.95%) compared to MLR and empirical models for training and testing steps. ANNs considering only the coexistence period and system have similar performance to MLR models. However, the insertion of variables related to weed density (non‐destructive ANN) or fresh matter (destructive ANN) increases the predictive capacity of the networks to values close to 99% correct. CONCLUSION The best performing ANNs can indicate the beginning of weed control since they can accurately estimate losses due to competition. These results encourage future studies implementing ANNs based on computer vision to extract information about the weed community.

show abstract

“…Using artificial neural networks as a prediction model, it can estimate the amount of methane produced by different substrates in the form of silages. The methane production prediction model developed was a Radial Basis Function (RBF) with five inputs, two neurons in a hidden layer, and one output [16]. The purpose of this study was to optimize biogas production utilizing response surface technique and an artificial neural network (ANN).…”

Section: Introductionmentioning

confidence: 99%

Optimization and Prediction of Daily Methane Production for Food Waste By using The Artificial Neural Network (ANN)

A.Radhi¹,

Hussien²,

Faraj³

2021

JUSST

View full text Add to dashboard Cite

This study aimed to know how a neural network model can be used to predict the behaviour of particular methane production using a three-layer (3:12:1) feed forward back-propagation algorithm and the logsig-purelin transfer function to maximize maximum methane prediction. The artificial neural network performs admirably compared to the daily methane generation of (vegetable waste 5%, lipids 12.5%, meat residues 12.5%, cow dung 10% and water 60%) at various temperatures (19–30 °C) for 64 days. Among the three input variables (feedstock, temperature, and time), feedstock has the strongest correlation with the particular methane production value. Thus, the research validates the ANN model’s ability to anticipate the biogas production curve’s behaviour and forecast the optimal substrate temperature for maximum biogas production. The regression value(R) for the digester was 0.95769. The capability of ANN modelling acts as a preliminary draft and significantly lowers the time required for methane generation in-line control. The daily methane production was predicted at three temperatures (20, 25, and 30 oC) for 75 days, and it found out the best temperature reaction was 30 oC.

show abstract

Energy value estimation of silages for substrate in biogas plants using an artificial neural network

Cited by 35 publications

References 55 publications

The Influence of the Pressure-Thermal Agglomeration Methods of Corn Bran on Their Selected Physicochemical Properties and Biogas Efficiency

The Influence of the Pressure-Thermal Agglomeration Methods of Corn Bran on Their Selected Physicochemical Properties and Biogas Efficiency

Machine learning models as an alternative to determine productivity losses caused by weeds

Optimization and Prediction of Daily Methane Production for Food Waste By using The Artificial Neural Network (ANN)

Contact Info

Product

Resources

About