Fuel cell fault diagnosis method based on BP neural network

Abstract

The invention discloses a fuel cell fault diagnosis method based on a BP neural network. The method comprises the steps of carrying out the normalization processing of data collected by a sensor, and enabling the data to be distributed in a [0, 1] interval; considering that the fault data do not certainly obey normal distribution, introducing Box-Cox transformation to carry out normalization processing on the data, and carrying out feature extraction on the normalized data by adopting linear discriminant analysis to screen fault features so as to realize dimension reduction of the fault data; and taking the extracted feature vector as an input layer variable of the BP neural network, taking the fault type of the fuel cell as an output layer variable, introducing a heuristic method to determine the optimal node number of a hidden layer, and obtaining a diagnosis result taking the fault type as the output variable.

Description

technical field [0001] The invention relates to a fuel cell fault diagnosis method. Background technique [0002] As a new type of clean energy using hydrogen as a raw material, fuel cells have been widely used in many fields including transportation and energy storage. However, it has problems such as short lifespan and poor reliability, which limit its large-scale industrialization development. During the operation of the fuel cell, water flooding and membrane dryness are frequent failures. Water flooding refers to the continuous accumulation of liquid water inside the stack, which blocks the gas diffusion layer, catalyst layer and even the gas flow channel, thus affecting the fuel flow in the stack. The phenomenon of the smooth progress of the electrochemical reaction; membrane dryness refers to the phenomenon that the liquid water in the stack is insufficient, resulting in the obstruction of the hydration of the membrane electrode, the decrease of the conductivity, and ...

AI Technical Summary

Problems solved by technology

However, it has problems such as short life and poor reliability, which limit its large-scale industrialization.

During the operation of the fuel cell, water flooding and membrane dryness are frequent failures. Water flooding refers to the continuous accumulation of liquid water inside the stack, which blocks the gas diffusion layer, catalyst layer and even the gas flow channel, thus affecting the fuel flow in the stack. The phenomenon of the smooth progress of the electrochemical reaction; membrane dryness refers to the phenomenon that the liquid water in the stack is insufficient, resulting in the obstruction of the hydration of the membrane electrode, the decrease of the conductivity, and the increase of the impedance of the membrane. High temperature occurs, which shortens the operating life of the fuel cell

At the same time, once these failures occur, the performance of the automation system or the vehicle equipped with fuel cells will be degraded, and it will lead to irreversible consequences.

Images