Algorithms for clustering data
Algorithms for clustering data
A fuzzy clustering-based rapid prototyping for fuzzy rule-based modeling
IEEE Transactions on Fuzzy Systems
| Hi-index | 0.00 |
Today, the satisfaction of the desire for personal transportation requires developing vehicles that minimize the consequences on the environment and maximize highway and fuel resources. Hybrid electric vehicles (HEVs) could be an answer to this demand. Their use can contribute significantly to reduce their environmental impact, achieving at the same time a rational energy employment. Controlling an HEV requires a lot of experimentations. Experts and training engineers can ensure the good working of the powertrains, but the research of optimality for some criteria combining fuel needs and power requirements is mainly empirical due to the nonlinearity of the driving conditions and vehicle loads. Consequently, in the paper a fuzzy modeling identification approach is applied for modeling the power flow management process. Amongst the various methods for the identification of fuzzy model structure, fuzzy clustering is selected to induce fuzzy rules. With such an approach the fuzzy inference system (FIS) structure is generated from data using fuzzy C-Means (FCM) clustering technique. As model type for the FIS structure a first order Takagi-Sugeno-Kang (TSK) model is considered. From this architecture a fuzzy energy flow management unit based on a TSK-type fuzzy inference is derived. Further, some interesting comparisons and simulations are discussed to prove the validity of the methodology.