Performance evaluation of microbial fuel cell by artificial intelligence methods

• Published in: Expert systems with applications Vol. 41; no. 4; pp. 1389 - 1399
• Main Authors: Garg, A., Vijayaraghavan, V., Mahapatra, S.S., Tai, K., Wong, C.H.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 01-03-2014; Elsevier
• Subjects: Aluminum; Applied sciences; Artificial intelligence; Biochemical fuel cells; Biological and medical sciences; Bioreactors; Biotechnology; Computer science; control theory; systems; Connectionism. Neural networks; Data processing. List processing. Character string processing; Electric potential; Energy; Energy. Thermal use of fuels; Equipments for energy generation and conversion: thermal, electrical, mechanical energy, etc; Exact sciences and technology; Expert systems; Fuel cells; Fundamental and applied biological sciences. Psychology; GPTIPS; LS-SVM; Mathematical models; Memory organisation. Data processing; Methods. Procedures. Technologies; MFC modeling; MFC prediction; Microorganisms; Multi-gene genetic programming; Software; Various methods and equipments; Voltage; MFC prediction; Multi-gene genetic programming; LS-SVM; MFC modeling; GPTIPS; Performance evaluation; Regression analysis; Neural network; Experimental study; Sulfates; Modeling; Operating conditions; Biochemical fuel cell; Genetic algorithm; Voltage; Vector support machine; Artificial intelligence
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2013.08.038

•Three artificial intelligence (AI) methods for modeling output voltage of microbial fuel cell (MFC) system is discussed.•AI models efficiently establish the relationship between output voltage and input factors of MFC.•Out of three methods, MGGP evolves a model with better generalization ability.•MGGP shows excellent potential to predict performance of MFC and can be used to gain better insights into MFC system.
In the present study, performance of microbial fuel cell (MFC) has been modeled using three potential artificial intelligence (AI) methods such as multi-gene genetic programming (MGGP), artificial neural network and support vector regression. The effect of two input factors namely, temperature and ferrous sulfate concentrations on the output voltage were studied independently during two operating conditions (before and after start-up) using the three AI models. The data is randomly divided into training and testing samples containing 80% and 20% sets respectively and then trained and tested by three AI models. Based on the input factor, the proposed AI models predict output voltage of MFC at two operating conditions. Out of three methods, the MGGP method not only evolve model with better generalization ability but also represents an explicit relationship between the output voltage and input factors of MFC. The models generated by MGGP approach have shown an excellent potential to predict the performance of MFC and can be used to gain better insights into the performance of MFC.