Fuel cell simulation calibration system and method based on digital twinning

Abstract

The invention discloses a fuel cell simulation calibration system and method based on digital twinning. The method comprises the following steps: acquiring various working conditions and various first performance parameters of a fuel cell; adjusting working conditions in the fuel cell digital twinning body to enable the fuel cell digital twinning body to operate to obtain a plurality of second performance parameters; judging whether the second performance parameter is consistent with the first performance parameter or not under the same working condition; if yes, completing calibration, and storing the digital twin of the fuel cell; if inconsistency occurs, carrying out correction, and carrying out the step of adjusting the multiple working conditions in the simulation model on the corrected digital twin of the fuel cell. The high-precision sensor, the CVM itinerant detector and the thermal infrared imager are adopted to obtain comprehensive data, the digital twin of the fuel cell is calibrated and corrected, simulation optimization can be performed after correction, the entity of the fuel cell is further adjusted, the development efficiency is greatly improved, the test precision is high, and the reliability is good.

Description

technical field [0001] The invention relates to the technical field of fuel cells, in particular to a digital twin-based fuel cell simulation calibration system and method. Background technique [0002] A fuel cell is an energy conversion device that converts chemical energy in fuel and oxidant into electrical energy. It is composed of bipolar plates, sealing gaskets, membrane electrodes, etc. Disciplinary issues; in order to shorten the fuel cell development cycle and reduce development costs, the performance analysis and prediction of fuel cells are often carried out by means of testing and simulation. [0003] A digital twin is a digital model of an existing or future physical entity object. It perceives, diagnoses, and predicts the state of the physical entity object in real time through actual measurement, simulation, and data analysis. It regulates the behavior of the physical entity object through optimization and instructions. Digital models learn from each other to...

AI Technical Summary

Problems solved by technology

[0004] In order to meet the needs of the commercial market and reduce costs, the fuel cell test systems currently on the market use sensors with low test accuracy and relatively single test functions. Key parameters such as current density distribution and temperature field distribution cannot be measured, so they cannot Obtaining accurate test data as the calibration data of the simulation model leads to problems such as low precision of the simulation model, low confidence of the simulation results, and the inability to accurately correct the simulation model; and the cost of fuel cell research and development completely relying on physical testing is high. The development cycle is long, and it is difficult to predict performance. At the same time, a large amount of data cannot be effectively used to cause waste.

Images