Modeling system of proton exchange membrane fuel cell (PEMFC) and intelligent predictive control method thereof

Abstract

The invention discloses a modeling system of a proton exchange membrane fuel cell (PEMFC) and an intelligent predictive control method thereof. The modeling system at least comprises an input-output nonlinear function structuring and implementing module and an intelligent predicative control module, wherein the input-output nonlinear function structuring and implementing module is used for structuring an input-output nonlinear function relationship and identifying the function by using a least square support vector machine method; and the intelligent predicative control module is used for carrying out nonlinear rolling optimization on a predicated target function by using a particle swarm optimization algorithm to acquire the optimal controlled quantity so as to realize the intelligent predicative control over the PEMFC. According to the invention, by means of establishing an output power characteristic model of a PEMFC stack by using input-output data, a complex reaction mechanism inside the PEMFC stack is avoided, and the modeling speed and the modeling precision are high.

Description

technical field [0001] The invention relates to a proton exchange membrane fuel cell modeling system and its predictive control method, in particular to an identification model-based proton exchange membrane fuel cell modeling system and its intelligent predictive control method. Background technique [0002] A fuel cell is a clean and efficient distributed power source that converts the chemical energy of hydrogen-containing fuel directly into electrical energy without a combustion process under the action of a catalyst. Proton exchange membrane fuel cell (protonexchange membrane fuel cell, PEMFC), as the most likely commercial fuel cell, has the advantages of low operating temperature, high current density, and fast response, and has broad application prospects. The operation process of PEMFC is relatively complicated. Its working principle involves fluid dynamics, thermodynamics, mass transfer, electrochemistry, materials science, process control and other disciplines. It...

AI Technical Summary

Problems solved by technology

Usually, the traditional fuel cell modeling method is to carry out spatial three-dimensional modeling of the fuel cell according to the structural flow field distribution, and analyze the structure and parameters of the PEMFC component components, the mass transfer and heat transfer process of the cell, the reaction gas flow rate, and the pressure through simulation. , humidity, battery temperature and other operating conditions or parameters on battery performance, and calculate the distribution of gas pressure, flow and temperature characteristics in the space field, but this method has a large amount of computation, and the simulation takes a long time, and the simulation results are consistent with There is a large gap in actual operation, which is not conducive to the design of real-time controllers

Images