Detail publikace

Catalytic thermal degradation of Chlorella vulgaris: Evolving deep neural networks for optimization

TENG, S. LOY, A. LEONG, W. HOW, B. CHIN, B. MÁŠA, V.

Anglický název

Catalytic thermal degradation of Chlorella vulgaris: Evolving deep neural networks for optimization

Typ

článek v časopise ve Web of Science, Jimp

Jazyk

en

Originální abstrakt

The aim of this study is to identify the optimum thermal conversion ofChlorella vulgariswith neuro-evolu-tionary approach. A Progressive Depth Swarm-Evolution (PDSE) neuro-evolutionary approach is proposed tomodel the Thermogravimetric analysis (TGA) data of catalytic thermal degradation ofChlorella vulgaris.Results showed that the proposed method can generate predictions which are more accurate compared toother conventional approaches (> 90% lower in Root Mean Square Error (RMSE) and Mean Bias Error (MBE)).In addition, Simulated Annealing is proposed to determine the optimal operating conditions for microalgaeconversion from multiple trained ANN. The predicted optimum conditions were reaction temperature of900.0 °C, heating rate of 5.0 °C/min with the presence of HZSM-5 zeolite catalyst to obtain 88.3% ofChlorellavulgarisconversion.

Anglický abstrakt

The aim of this study is to identify the optimum thermal conversion ofChlorella vulgariswith neuro-evolu-tionary approach. A Progressive Depth Swarm-Evolution (PDSE) neuro-evolutionary approach is proposed tomodel the Thermogravimetric analysis (TGA) data of catalytic thermal degradation ofChlorella vulgaris.Results showed that the proposed method can generate predictions which are more accurate compared toother conventional approaches (> 90% lower in Root Mean Square Error (RMSE) and Mean Bias Error (MBE)).In addition, Simulated Annealing is proposed to determine the optimal operating conditions for microalgaeconversion from multiple trained ANN. The predicted optimum conditions were reaction temperature of900.0 °C, heating rate of 5.0 °C/min with the presence of HZSM-5 zeolite catalyst to obtain 88.3% ofChlorellavulgarisconversion.

Klíčová slova anglicky

Microalgae, Thermogravimetric analysis, Artificial neuron network, Particle swarm optimization, simulated annealing

Vydáno

01.11.2019

Nakladatel

Elsevier

Místo

Oxford, England

ISSN

0960-8524

Ročník

292

Číslo

121971

Strany od–do

1–9

Počet stran

292

BIBTEX


@article{BUT160578,
  author="Sin Yong {Teng} and Vítězslav {Máša},
  title="Catalytic thermal degradation of Chlorella vulgaris: Evolving deep neural networks for optimization",
  year="2019",
  volume="292",
  number="121971",
  month="November",
  pages="1--9",
  publisher="Elsevier",
  address="Oxford, England",
  issn="0960-8524"
}