Framework based on number of basis functions complexity measure in investigation of the power characteristics of direct methanol fuel cell

摘要: Abstract A potential alternative to cell batteries is the air-breathing micro direct methanol fuel (μDMFC) because it environmental friendly, charging-free, possesses high energy density properties and provides easy storage of fuel. The effective functioning complex μDMFC system exhibits higher dependence on its operating conditions parameters. main challenge for experts determine optimum conditions. In this context, mathematical modeling approach based evolutionary framework genetic programming (GP) can be applied. However, successful implementation depends complexity chosen in structural risk minimization (SRM) objective function. work, two measures standardized number nodes basis functions splines chosen. Comparison between GP approaches these evaluated experimental procedure performed μDMFC. power characteristics considered study are open-circuit voltage three inputs flow rate, concentration temperature. statistical analysis cross-validation, error metrics hypothesis tests choose best models. Further, 2-D plots measuring individual effects 3-D interaction plotted parametric approach. It was found that influences (power OCV) most followed by temperature rate.