Dynamic fuzzy cognitive network approach for modelling and control of PEM fuel cell for power electric bicycle system. (15th September 2017)

• Record Type: Journal Article
• Authors: Kheirandish, Azadeh; Motlagh, Farid; Shafiabady, Niusha; Dahari, Mahidzal; Khairi Abdul Wahab, Ahmad
• Is Part Of: Applied energy. Volume 202(2017)
• Page Start: 20
• Page End: 31
• Publication Date: 2017-09-15
• Subjects: PEM fuel cell -- Modelling -- Fuzzy cognitive map -- Rule-based FCM; Power (Mechanics) -- Periodicals; Energy conservation -- Periodicals; Energy conversion -- Periodicals; 621.042
• DOI: 10.1016/j.apenergy.2017.05.084
• Languages: English
• ISSNs: 0306-2619

Abstract

Highlights: Fuzzy cognitive map was proposed for the first time to describe the behaviour of fuel cell electric bicycle system. Fuzzy rules were applied to explain the cause and effect between concepts. To predict and analyse the cognitive map involved in the negotiation process. Abstract: Modelling Proton Exchange Membrane Fuel Cell (PEMFC) is the fundamental step in designing efficient systems for achieving higher performance. Among the development of new energy technologies, modelling and optimization of energy processes with pollution reduction, sufficient efficiency and low emission are considered one of the most promising areas of study. Despite affecting factors in PEMFC functionality, providing a reliable model for PEMFC is the key of performance optimization challenge. In this paper, fuzzy cognitive map has been used for modelling PEMFC system that is directed to provide a dynamic cognitive map from the affecting factors of the system. Controlling and modification of the system performance in various conditions is more practical by correlations among the performance factors of the PEMFC derived from fuzzy cognitive maps. On the other hand, the information of fuzzy cognitive map modelling is applicable for modification of neural networks structure for providing more accurate results based on the extracted knowledge from the cognitive map and visualization of the system's performance. Finally, a rule based fuzzy cognitive map has been used that can be implemented for decision-making to control the system. This rule-based approach provides interpretability while enhancing the performance of the overall system.