IEEE PHM Data Challenge 2014 (2021)

Available

Dataset

Licence : CC BY-NC-SA doi:10.25666/DATAUBFC-2021-07-19

Data creator : Fabien Harel ^[1]

Project member : Daniel Hissel ^[2], Christophe Turpin ^[3], Jacques Rozière ^[4], Fabien Harel ^[1]

[1] : Fuel Cell Lab (UAR 2200)

[2] : Franche-Comté Electronique Mécanique Thermique et Optique - Sciences et Technologies (UMR 6174) (Université de Franche-Comté)

[3] : LAboratoire PLasma et Conversion d'Energie (UMR 5213)

[4] : Institut Charles Gerhardt Montpellier (UMR 5253)

Description :

This data set is divided in two parts in the framework of the IEEE PHM Data Challenge 2014.
The first part is a 1kW proton exchange membrane fuel cell on which long-term tests (1,000 hours) have been carried out under quasi-stationary conditions.
The second part also deals with a fresh 1kW proton exchange membrane fuel cell. On this second fuel cell, long-term tests (1,000 hours) with current ripples were performed.

Disciplines :

electrochemistry (chemistry), energy & fuels (engineering science), engineering, electrical & electronic (engineering science)

Keywords :

durability, fuel cell, hydrogen

General metadata

Data acquisition date : from 1 Jan 2007 to 1 Jan 2010

Data acquisition methods :

Experimental data :
Fuel Cell 1 (without ripple) testing protocol:
1. Electrochemical Impedance Spectra (EIS) performed before polarization at nominal current density (0.7A/cm²)
2. Polarization curve from 0 to 1A/cm² of 1,000s
3. EIS performed after polarization (0.7; 0.45; 0.20A/cm²)
Characterizations @ t = 0; 48; 185; 348; 515; 658; 823; 991h
Fuel Cell 2 (with ripples) testing protocol:
1. Polarization curve from 0 to 1A/cm² of 1,000s
2. EIS performed after polarization (0.7; 0.45; 0.20A/cm²)
Characterizations @ t = 0; 35; 182; 343; 515; 666; 830; 1016h

Update periodicity : no update

Language : English (eng)

Formats : application/pdf, application/vnd.openxmlformats-officedocument.spreadsheetml.sheet

Audience : University: licence, University: master, Research

Publications :

ANOVA method applied to proton exchange membrane fuel cell ageing forecasting using an echo state network (doi:10.1016/j.matcom.2015.06.009)
Prognostics of PEM fuel cell in a particle filtering framework (doi:10.1016/j.ijhydene.2013.10.054)
Impact of current ripples on the durability of proton exchange membrane fuel cells based on two ageing datasets (doi:10.1016/j.dib.2022.108601)
Voltage prognosis of PEMFC estimated using Multi-Reservoir Bidirectional Echo State Network (doi:10.1109/ICSC57768.2022.9993961)
A Short-Term and Long-Term Prognostic Method for PEM Fuel Cells Based on Gaussian Process Regression (doi:10.3390/en15134844)
Exposing Deep Representations to a Recurrent Expansion with Multiple Repeats for Fuel Cells Time Series Prognosis (doi:10.3390/e24071009)
Improving Small-scale Machine Learning with Recurrent Expansion for Fuel Cells Time Series Prognosis (doi:10.1109/IECON49645.2022.9968566)

Collection :

Publisher : dataUBFC - Atelier de la donnée de Bourgogne-Franche-Comté

Labels : Plateforme Hydrogène-Energie, Plateforme UBFC

Project and funder :

CO-CONPAC
- PIE - Programme Interdisciplinaire Energie (CNRS)

Additional information :

The IEEE PHM Data Challenge is a competition open to all potential conference attendees. In 2014, the challenge is focused on tracking the health state of a proton exchange membrane fuel cell. Participants will be scored based on their ability to predict the remaining useful lifetime at particular tool settings and as the performance of the tool degrades over time.