Polymer electrolyte membrane fuel cells degradation prediction using multi-kernel relevance vector regression and whale optimization algorithm

Degradation and cost are the main factors affecting commercial applications of Polymer Electrolyte Membrane Fuel Cells (PEMFC). This paper proposes a novel degradation prediction for PEMFC in various by using Multi-kernel Relevance Vector Regression (MRVR) Whale Optimization Algorithm (WOA). method uses data from vehicle operating under real driving conditions laboratory to derive robust model that covers wide range operation. In order learn trends better, MRVR is adopted establish model. WOA used automatically adjust optimize weight kernel parameters improving precision. Proposed experimentally verified different operational conditions. The test results show compared with single function, multi-kernel function can predict more accurately. Compared other metaheuristic methods, greatly improves precision prediction.