Remaining useful life prediction of PEMFC based on long short-term memory recurrent neural networks

Liu, Jiawei; Li, Qi; Chen, Weirong; Yan, Yu; Qiu, Yibin; Cao, Taiqiang

doi:10.1016/j.ijhydene.2018.10.042

Cited by 161 publications

(65 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The thermal transfer caused by thermal conduction and convection in the whole PEM fuel cells system can be quantified by the heat transfer rate equation .…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Numerical and Experimental Investigation of the Asymmetric Humidification and Dynamic Temperature in Proton Exchange Membrane Fuel Cell

et al. 2020

View full text Add to dashboard Cite

The relative humidity is an important parameter reflecting the performance of proton exchange membrane (PEM) fuel cells, which is often accompanied by changes in heat and temperature. In order to study the different humidification effects on the performance of PEM fuel cells, a temperature and heat transfer (T&HT) model is presented. The innovation of this paper is to study the performance of fuel cell (FC) from the perspective of temperature heat transfer by asymmetric humidification. Firstly, symmetrical humidification experiments are performed at three operating temperatures. After that, a three‐dimensional (3D) structure is built using fluent and T&HT model is imported through custom functions. Secondly, the asymmetric humidification experiment is put into practice with 60 °C operating temperature. Furthermore, the Taguchi method is used to optimize the performance of fuel cells in the crossover experiment. Finally, the experimental and numerical results are compared by the contours and polarization curves. The results show that T&HT model is in agreement with the experiment, and asymmetric humidification is more reasonable and flexible than symmetrical humidification. When the cathode relative humidity is 50% and the anode relative humidity is 75%, the maximum optimization rate of system efficiency is 17%.

show abstract

“…The thermal transfer caused by thermal conduction and convection in the whole PEM fuel cells system can be quantified by the heat transfer rate equation .…”

Section: Methodsmentioning

confidence: 99%

“…Nevertheless, this would dehydrate the membranes more quickly. Therefore, it can be seen that relative humidity need to satisfy certain range just like dynamic temperature, and the relative humidity is inextricably linked with dynamic temperature and heat .…”

Section: Introductionmentioning

confidence: 99%

Numerical and Experimental Investigation of the Asymmetric Humidification and Dynamic Temperature in Proton Exchange Membrane Fuel Cell

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In [25], a Restricted Boltzmann machine (RBM) was used as an unsupervised pre-training stage to learn abstract features for the LSTM input in a supervised RUL regression stage. The LSTM was also applied for the RUL prediction problem of proton exchange membrane fuel cell (PEMFC) [26,27]. In detail, the work proposed in [26] used the regular interval sampling and locally weighted scatterplot smoothing (LOESS) for data reconstruction.…”

Section: Introductionmentioning

confidence: 99%

“…The LSTM was also applied for the RUL prediction problem of proton exchange membrane fuel cell (PEMFC) [26,27]. In detail, the work proposed in [26] used the regular interval sampling and locally weighted scatterplot smoothing (LOESS) for data reconstruction. Then, the smoothing data is fed into a LSTM network to predict the RUL value.…”

Section: Introductionmentioning

confidence: 99%

“…In detail, we propose to use the LSTM network to estimate the probabilities that the system will fail in different time windows in the future. Although the LSTM network has been developed and improved in PHM literature, the previous studies [22][23][24][25][26][27] are based on a piece-wise linear (PWL) RUL target function, in which it is not trivial to define the RUL maximum value. Moreover, in these studies, the prognostics is treated as a regression problem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A new dynamic predictive maintenance framework using deep learning for failure prognostics

Nguyen

Medjaher

2019

Reliability Engineering & System Safety

218

View full text Add to dashboard Cite

show abstract

Designing AI‐Aided Analysis and Prediction Models for Nonprecious Metal Electrocatalyst‐Based Proton‐Exchange Membrane Fuel Cells

et al. 2020

View full text Add to dashboard Cite

Traditionally,alarger number of experiments are needed to optimize the performance of the membrane electrode assembly (MEA) in proton-exchange membrane fuel cells (PEMFCs) since it involves complex electrochemical, thermodynamic,a nd hydrodynamic processes.H erein, we introduce artificial intelligence (AI)-aided models for the first time to determine key parameters for nonprecious metal electrocatalyst-based PEMFCs,t hus avoiding unnecessary experiments during MEA development. Among 16 competing algorithms widely applied in the AI field, decision tree and XGBoost showed good accuracy (86.7 %and 91.4 %) in determining key factors for high-performance MEA. Artificial neural network (ANN) shows the best accuracy (R2 = 0.9621) in terms of predictions of the maximum power density and ad ecent reproducibility (R2 > 0.99) on uncharted I-V polarization curves with 26 input features.H ence,m achine learning is shown to be an excellent method for improving the efficiency of MEA design and experiments.

show abstract

Remaining useful life prediction of PEMFC based on long short-term memory recurrent neural networks

Cited by 161 publications

References 38 publications

Numerical and Experimental Investigation of the Asymmetric Humidification and Dynamic Temperature in Proton Exchange Membrane Fuel Cell

Numerical and Experimental Investigation of the Asymmetric Humidification and Dynamic Temperature in Proton Exchange Membrane Fuel Cell

A new dynamic predictive maintenance framework using deep learning for failure prognostics

Designing AI‐Aided Analysis and Prediction Models for Nonprecious Metal Electrocatalyst‐Based Proton‐Exchange Membrane Fuel Cells

Contact Info

Product

Resources

About