Data-driven proton exchange membrane fuel cell degradation predication through deep learning method

Ma, Rui; Tao, Yang; Breaz, Elena; Li, Zhongliang; Briois, Pascal; Gao, Fei

doi:10.1016/j.apenergy.2018.09.111

Cited by 250 publications

(89 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To overcome this situation, we present in this section a new data-driven prognostic method that directly provides the probability of the system failure without prior knowledge of the failure mechanism. This method is based on the Long Short-Term Memory (LSTM) networks, one of Recurrent Neural Network (RNN) architectures, that has received increasing attention in recent prognostics studies [22][23][24][25][26][27]35]. One of the main advantages of the LSTM is the capacity of learning over Jong time sequences and retaining memory.…”

Section: New Dynamic Predictive Maintenance Frameworkmentioning

confidence: 99%

“…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%

“…Then, the smoothing data is fed into a LSTM network to predict the RUL value. On the other hand, in [27], the authors developed a two-dimensional (2D) grid LSTM to optimize the prediction accuracy of the fuel cell performance degradation.…”

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 3 more Smart Citations

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

Nguyen

Medjaher

2019

Reliability Engineering & System Safety

203

View full text Add to dashboard Cite

show abstract

Section: New Dynamic Predictive Maintenance Frameworkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Nguyen

Medjaher

2019

Reliability Engineering & System Safety

203

View full text Add to dashboard Cite

show abstract

“…The capability of artificial neural networks to expressively represent complex data and the prevalence of its usage in a wide range of applications inspired us to readdress its application in solving the inverse radiation problems. For machine learning using the artificial neural network, a large set of training data has to be routinely available [49,50]. These data can be either from experimental measurements or numerical simulations, or both.…”

Section: Introductionmentioning

confidence: 99%

Machine learning applied to retrieval of temperature and concentration distributions from infrared emission measurements

et al. 2019

View full text Add to dashboard Cite

Inversion of temperature and species concentration distributions from radiometric measurements involves solving nonlinear, ill-posed and high-dimensional problems. Machine Learning approaches allow solving such highly nonlinear problems, offering an alternative way to deal with complex and dynamic systems with good flexibility. In this study, we present a machine learning approach for retrieving temperatures and species concentrations from spectral infrared emission measurements in combustion systems. The training spectra for the machine learning model were synthesized through calculations from HITEMP 2010 for gas mixtures of CO 2 , H 2 O, and CO. The method was tested for different line-of-sight temperature and concentration distributions, different gas path lengths and different spectral intervals. Experimental validation was carried out by measuring spectral emission from a Hencken flat flame burner with a Fourier-transform infrared spectrometer with different spectral resolutions. The temperature fields above the burner for combustion with equivalence ratios of φ =1, φ = 0.8, and φ = 1.4 were retrieved and were in excellent agreement with temperatures deduced from Rayleigh scattering thermometry. performed to address the inverse radiation problems using gradient-based [14] optimization methods. Griffith et al. [15,16] were the first to recognize that measurements of the transmissivity or emissivity of rotational spectral lines of a gas can reveal its temperature. In order to extract temperature, a nonlinear least-square method was used to fit the integrated transmissivity minima. Best et al. [17,18] combined tomography and Fourier transform infrared (FTIR) spectrometer transmission and emission spectra to extract temperature, concentration and soot volume fraction fields. By measuring spectral intensity of the CO 2 4.3 µm band, temperature profiles were retrieved in a number of ways [19,20]. At their time these results were not accurate enough due to lack of an accurate radiation prediction model and robust inverse algorithms. Song et al. [21,22] developed a spectral remote sensing technique to reconstruct CO 2 temperature profiles based on radiative intensity measurements. An accurate narrow band radiation model was employed and several Newton-type regression methods were tested. Due to the nonlinearity and ill-posedness of the problem, regularization of the inverse problems was applied to enforce some degree of smoothness to the solution. It is always difficult to select an appropriate regularization parameter and empirical values for the regularization parameter were employed. Ren and Modest [23] applied the Levenberg-Marquardt optimization method with Tikhonov regularization to reconstruct CO 2 temperature profiles and average concentrations from synthetic line-of-sight spectral intensity data. Two types of temperature profiles were tested for different gas path lengths and different CO 2 spectral bands. A new regularization selection method based on the combination of the L-curve criterion and the discre...

show abstract

Reshaping the material research paradigm of electrochemical energy storage and conversion by machine learning

Yang

Zhang

et al. 2023

EcoMat

View full text Add to dashboard Cite

For a "Carbon Neutrality" society, electrochemical energy storage and conversion (EESC) devices are urgently needed to facilitate the smooth utilization of renewable and sustainable energy where the electrode materials and catalysts play a decisive role. However, the efficiency of the current trial-and-error research paradigm largely lags behind the imminent demands of EESC requiring increasingly improved performance. The emerged machine learning (ML), a subfield of artificial intelligence, is capable of evaluating and analyzing big data for hidden rules. In this regard, the relationships between the structure and performance of the key materials can be more efficiently revealed, which fundamentally revolutionizes the material research manner of the current EESC devices. In this review, the typical ML algorithms utilized in EESC development are first introduced. Then, focused attention has been paid to multiple aspects of applying ML to reshape the materials research for EESC. In addition to highlighting the emerging prospect, the challenges which are still hindering the further development of this emerging field are also discussed.

show abstract

Data-driven proton exchange membrane fuel cell degradation predication through deep learning method

Cited by 250 publications

References 35 publications

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

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

Machine learning applied to retrieval of temperature and concentration distributions from infrared emission measurements

Reshaping the material research paradigm of electrochemical energy storage and conversion by machine learning

Contact Info

Product

Resources

About