Solid oxide fuel cell stack fault diagnosis method and system

Abstract

The invention discloses a solid oxide fuel cell stack fault diagnosis method and system, wherein the method comprises: using an SOFC (solid oxide fuel cell) system model to simulate fault state and normal running state of a stack so as to obtain sample stack parameters under the fault state and normal running state of the stack; using the sample stack parameters to train a diagnosis model to obtain the strained diagnosis model; collecting real-time stack parameters, and entering in the trained diagnosis model to obtain a stack fault type. The SOFC system model is used herein to simulate the fault state and normal running state of the stack so as to obtain the stack parameters under the fault state and normal running state of the stack, and the collected stack parameters are entered in the trained diagnosis model to obtain one stack fault type. The diagnosis model herein is effective in diagnosing the normal running and fault type of the stack, the diagnostic results are highly accurate, and the method is high in practicality, identifiability and accuracy.

Description

technical field [0001] The invention belongs to the field of fuel cells, and more particularly relates to a fault diagnosis method and system for solid oxide fuel cell stacks. Background technique [0002] Solid Oxide Fuel Cell (SOFC) is a new type of energy power supply technology. It uses the chemical reaction between hydrogen hydrocarbons and air to convert the chemical energy in the fuel into electrical energy. It has the advantages of high efficiency, quietness, environmental protection and pollution-free. SOFC power generation technology is currently developing rapidly, and to realize the commercialization of SOFC, it is necessary to devote ourselves to the research of fault damage phenomena, in order to fully understand it, so as to improve the reliability of SOFC independent power generation system, ensure its stability, safe operation. As the stack is the core component of an independent power generation system, the research on its fault diagnosis method becomes a ...

AI Technical Summary

Problems solved by technology

[0006] In view of the above defects or improvement needs of the prior art, the present invention provides a solid oxide fuel cell stack fault diagnosis method and system, the purpose of which is to simulate the stack fault and the normal working state of the stack through the SOFC system model, Obtain stack failures and stack parameters under normal working conditions of the stack, collect stack parameters and input the trained diagnostic model, and obtain stack fault types and fault types, thereby solving the limitations of existing stack diagnosis methods and models , poor practicability, and low identification technical problems

Images