Online fault diagnosis method for fuel cell system

Abstract

The present invention discloses an online fault diagnosis method for a fuel cell system. The method comprises the steps of: obtaining a first fault diagnosis model which is obtained based on the real-time data of a galvanic pile and through adoption of a machine learning method, the real-time data of the galvanic pile is obtained through a galvanic pile reference test experiment; in the operationprocess of the fuel cell system, the operation data of the galvanic pile is measured in real time and is taken as the input parameter of the first fault diagnosis model to obtain the fault diagnosis result of the galvanic pile; and a second fault diagnosis model is obtained, the second fault diagnosis model comprises standard data corresponding to secondary parts in the fuel cell system, the real-time operation data of the secondary parts in the fuel cell system are obtained and taken as the input parameters of the second fault diagnosis model to obtain the fault diagnosis results of the secondary parts. The current fuel cell system is taken as a basis with no need for extra addition of a sensor and a test device, the operation of the fuel cell system cannot be interfered, and therefore, the implementation cost is low, and promotion is easy.

Description

Technical field [0001] The invention belongs to the technical field of fuel cells, and specifically relates to an online fault diagnosis method for a fuel cell system. Background technique [0002] The fuel cell is a device that directly converts the chemical energy of the fuel into electrical energy. It has the advantages of high operating efficiency, clean and pollution-free, and low noise. It is expected to replace the traditional heat engine to solve the environmental pollution problem of the energy system. At present, fuel cells have been promoted and applied in fields such as automobiles, drones, and stationary power generation, and they have broad application prospects in the future. [0003] The fuel cell system includes a stack, an air supply system, a hydrogen supply system, and a thermal management system. It is a complex nonlinear system. Failures such as water flooding, membrane dryness, gas shortage, short circuit, and catalyst poisoning may occur during operation, w...

AI Technical Summary

Problems solved by technology

[0004] Although a variety of fault diagnosis methods for fuel cell systems have been proposed in the prior art, they still cannot meet the needs of practical applications. There are mainly the following problems: 1) Most of the diagnostic methods are only proposed for one type of fault and cannot be directly used in practice. 2) Most of the fault diagnosis methods are only for fuel cell stacks, but in fact the fault detection of key components such as air compressors and hydrogen circulation pumps is also indispensable; 3) The diagnostic methods are complicated and costly to implement. Cannot be used for online troubleshooting

Due to the above reasons, a standardized and unified fault diagnosis method that can be popularized and used has not yet been formed in the field of fuel cell technology.

Images