From the Cultivation of Arthrospira platensis at an Increased CO2 Concentration to the Bio-Oil Production by Hydrothermal Liquefaction

Ryndin, Kirill G.; Butyrin, Aleksey V.; Grigorenko, Anatoly V.; Chunzhuk, Elizaveta A.; Chernova, Nadezhda I.; Kiseleva, Sofya V.; Malaniy, Sergey Y.; Bakumenko, Ekaterina A.; Slavkina, Olga V.; Ossipov, Konstantin; Maryutina, Tatiana A.; Kumar, Vinod; Vlaskin, Mikhail S.

doi:10.3390/app13179950

Cited by 1 publication

(2 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several factors, including pyrolysis temperature, heating rate, and the presence of catalysts, influence the characteristics of the bio-oil obtained from RHA . As the demand for sustainable energy intensifies and efficient waste utilization practices grow, exploring RHA’s conversion into bio-oil becomes a scientific endeavor and a crucial step toward a more environmentally conscious and sustainable future …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimization of Operational Parameters Using Artificial Neural Network and Support Vector Machine for Bio-oil Extracted from Rice Husk

Ahmed,

Yub Harun,

Waqas

et al. 2024

ACS Omega

View full text Add to dashboard Cite

Bio-oil production from rice husk, an abundant agricultural residue, has gained significant attention as a sustainable and renewable energy source. The current research aims to employ artificial neural network (ANN) and support vector machine (SVM) modeling techniques for the optimization of operating parameters for bio-oil extracted from rice husk ash (RHA) through pyrolysis. ANN and SVM methods are employed to model and optimize the operational conditions, including temperature, heating rate, and feedstock particle size, to enhance the yield and quality of bio-oil. Additionally, ANN modeling is utilized to create a predictive model for bio-oil properties, allowing for the efficient optimization of pyrolysis conditions. This research provides valuable insights into the production and properties of bio-oil from RHA. By harnessing the capabilities of ANN and SVM, this research not only aids in understanding the intricate relationships between process variables and bio-oil properties but also provides a means to systematically enhance the production process. The predictive results obtained from the ANN were found to be good when compared with the SVM. Several models with different numbers of neurons have been trained with different transfer functions. R values for the training, validation, and test phases are around 1.0, i.e., 0.9981, 0.9976, and 0.9978, respectively. The overall R-value was 0.9960 for the proposed network. The findings were considered acceptable, as the overall R-value was close to 1.0. The optimized operational parameters contribute to the efficient conversion of RHA into bio-oil, thereby promoting the use of this sustainable resource for renewable energy production. This approach aligns with the growing emphasis on reducing the environmental impact of traditional fossil fuels and advancing the utilization of alternative and environmentally friendly energy sources.

show abstract

Section: Introductionmentioning

confidence: 99%

“… 9 As the demand for sustainable energy intensifies and efficient waste utilization practices grow, exploring RHA’s conversion into bio-oil becomes a scientific endeavor and a crucial step toward a more environmentally conscious and sustainable future. 10 …”

Section: Introductionmentioning

confidence: 99%