Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

HSMM and empirical model-based fuel cell fault prediction method

A fuel cell and empirical model technology, applied in forecasting, measuring electricity, measuring devices, etc., can solve problems such as low similarity and poor forecasting results, and achieve the effects of high forecasting accuracy, low cost, and improved forecasting speed.

Active Publication Date: 2017-09-15
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the voltage degradation trend of the fuel cell is less similar to the voltage degradation trend of the HSMM full-life training data, the prediction results based on HSMM are poor

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • HSMM and empirical model-based fuel cell fault prediction method
  • HSMM and empirical model-based fuel cell fault prediction method
  • HSMM and empirical model-based fuel cell fault prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0052] figure 1 It is a flow chart of the fuel cell failure prediction method based on HSMM and empirical model in the present invention.

[0053] In this example, if figure 1 Shown, a kind of fuel cell fault prediction method based on HSMM and empirical model of the present invention comprises the following steps:

[0054] S1. Randomly set the initial state probability matrix π 0 , initial state transition probability matrix A 0 , initial observation probability matrix B 0 , initial state duration probability matrix P 0 , and the number of hidden states N is 3 and the number of observations M is 10, construct the HSMM model λ 0 =(N,M,A 0 ,B 0 , π 0 ,P 0 ).

[0055] PAI 0 :[3×1double]

[0056] A 0 :[3×3double]

[0057] B 0 :[3×10double]

[0058] P 0 :[3×300double]

[0059] S2. Collect a set of full-life voltage data of fuel cells as training data, and use the Welch-Baum algorithm to update A in the HSMM model 0 , B 0 , π 0 and P 0 The value of , get the u...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an HSMM and empirical model-based fuel cell fault prediction method. The method comprises the steps of firstly collecting full life voltage data of a group of fuel cells to serve as training data, and training an HSMM by utilizing the training data through a Welch-Baum algorithm; then collecting voltage degradation data of the group of the fuel cells to serve as test data; inputting the test data to the HSMM, estimating current health states through a forward algorithm, and calculating residual lives of the fuel cells according to state durations; building an empirical model according to the test data, estimating parameters, predicting a future trend, and calculating the residual lives of the fuel cells according to the future voltage trend; and by taking the similarities of voltage gradient values of the training data and the test data as standards, combining the residual lives obtained by the HSMM with the residual lives calculated by the empirical model to estimate final residual lives of the fuel cells.

Description

technical field [0001] The invention belongs to the technical field of fuel cells, and more specifically relates to a fuel cell fault prediction method based on HSMM and empirical models. Background technique [0002] A fuel cell is a device that directly converts chemical energy in fuel into electrical energy through an electrochemical reaction. It has the advantages of environmental friendliness and high energy conversion rate. However, reliability and durability are one of the main reasons hindering the development of fuel cells. [0003] Fault prediction technology can timely diagnose the health status of the fuel cell in the early stage of failure and predict its remaining usable life, so that we can repair it in time to prolong the life of the fuel cell. In recent decades, failure prediction techniques have shown great potential in addressing the relatively short lifetime of fuel cells. [0004] The failure prediction method based on the Hidden Semi-Markov Model (HSMM...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F17/50G06Q10/04G01R31/36
CPCG01R31/367G06F30/20G06Q10/04
Inventor 吴小娟叶倩文
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com