Method for predicting life of fuel cell based on long short-term memory network

By synchronizing and analyzing the correlation between fuel cell voltage decay data and operating status data, and combining long short-term memory networks and artificial hummingbird algorithms for optimization, the adaptability problem of fuel cell life prediction models was solved, improving prediction accuracy and fitting ability.

CN121917981BActive Publication Date: 2026-06-26HYDROGEN (BEIJING) HYDROGEN ENERGY TECH CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202511975023.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-12-25
Publication Date
2026-06-26
Estimated Expiration
2045-12-25

AI Technical Summary

Technical Problem

Existing fuel cell life prediction models lack data-driven feature recognition mechanisms. The structural parameters of LSTM models rely on manual settings and cannot achieve adaptive adjustment. Furthermore, the lack of a closed-loop network architecture search-training-validation mechanism leads to large prediction errors and significant limitations in engineering applications.

Method used

By collecting voltage decay data and operating status data of fuel cells, synchronous alignment and correlation analysis are performed to construct an input feature set. The network architecture is optimized using a long short-term memory network and an artificial hummingbird algorithm. Features are dynamically selected and structural parameters are adjusted to construct a fitness function to optimize the model.

Benefits of technology

The adaptive and efficient nature of the fuel cell lifetime prediction model has been achieved, improving prediction accuracy and generalization ability, reducing errors, and enhancing the fitting ability to complex voltage decay processes.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application relates to the field of battery life prediction, in particular to a multi-feature fuel cell life prediction method based on a long short-term memory network; the method comprises the following steps: collecting voltage attenuation data and collecting running state data to construct an original input data set; analyzing the running state data, calculating a correlation coefficient according to the voltage attenuation data and each running state data, analyzing the correlation coefficient, and obtaining an input feature set; processing the input feature set and the voltage attenuation data to construct a neural network training data structure; dividing the training data structure into a training set and a test set; constructing a network architecture solution space to be searched, analyzing the network architecture solution space, constructing a fitness function, and determining an optimal network architecture parameter combination based on the fitness function; and inputting the training set into the optimal network architecture parameter combination for training to generate a target detection prediction result. The application can improve the prediction accuracy of the voltage attenuation trend.
Need to check novelty before this filing date? Find Prior Art