Performance analysis of a degraded PEM fuel cell stack for hydrogen passenger vehicles based on machine learning algorithms in real driving conditions

Raeesi, Mehrdad; Changizian, Sina; Ahmadi, Pouria; Khoshnevisan, Alireza

doi:10.1016/j.enconman.2021.114793

Cited by 71 publications

(15 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RNN works well with short‐term dependencies. There are several prediction methods such as deep neural network, simple recurrent neural network, LSTM network, and bidirectional long‐short term memory 39 . However, RNN has some shortcomings such as gradient descent and explosion 40 .…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Modeling of performance and thermodynamic metrics of a conceptual turboprop engine by comparing different machine learning approaches

Dursun

Toraman

Aygün

2022

Intl J of Energy Research

View full text Add to dashboard Cite

In this study, several performance and thermodynamics metrics of a conceptual turboprop engine (C-TPE) were computed at 50 (fifty) power settings. Based on these computations, these parameters were predicted by employing artificial neural networks (ANN) and long-short term memory (LSTM) approaches. The obtained parametrically data were subjected to preprocessing for normalization. After determining model inputs to estimate the engine outputs, these data were introduced to ANN and LSTM. Then, the findings by two methods were compared with each other. In this context, fuel flow, air mass flow, exhaust velocity, compressor pressure ratio, turbine outlet temperature, and revolutions per minute (RPM) were selected as model inputs to estimate several metrics such as net thrust, specific fuel consumption (SFC), overall efficiency, exergy efficiency, and environmental effect factor (EEF) regarding the C-TPE. For modeling of the mentioned metrics, 80% and 20% of the data were used for training and testing, respectively. According to the findings of energetic and exergetic computations, SFC value of the C-TPE increases from 16.205 to 17.737 g/ kNs whereas its overall efficiency varies from 23.63% to 22.31% owing to decrement in RPM. Moreover, exergy efficiency of C-TPE remains between 23.93% and 26.2% whilst its EFF value resides between 2.66 and 3.05 throughout power settings. Finally, the modeling results indicate that coefficient of determination (R 2 ) regarding overall efficiency of C-TPE was found as 0.951867 with respect to the ANN model whereas it was calculated as 0.999906 with the proposed LSTM. It could be deduced that since LSTM is capable of providing lower the model error than the ANN for the same set of data, this method could be implemented to predict thermodynamics metrics of different kinds of gas turbine engine where obtaining data is limited.

show abstract

Section: Methodsmentioning

confidence: 99%

“…There are several prediction methods such as deep neural network, simple recurrent neural network, LSTM network, and bidirectional long-short term memory. 39 However, RNN has some shortcomings such as gradient descent and explosion. 40 To overcome this problem, the three-gate LSTM model was designed.…”

Section: Long Short-term Memorymentioning

confidence: 99%

Modeling of performance and thermodynamic metrics of a conceptual turboprop engine by comparing different machine learning approaches

Dursun

Toraman

Aygün

2022

Intl J of Energy Research

View full text Add to dashboard Cite

show abstract

“…The analysis of fuel cell degradation in typical tests was carried out by Raeesi et al [30]. The degradation of the cells in both the NEDC and the FTP75 tests was found to lead to an increase in hydrogen consumption of about 14%.…”

Section: Fuel Cell Testing For Automotive Applicationsmentioning

confidence: 99%

Two Generations of Hydrogen Powertrain—An Analysis of the Operational Indicators in Real Driving Conditions (RDC)

Pielecha

Szałek²,

Tchorek

2022

Energies

View full text Add to dashboard Cite

Hydrogen fuel cells are systems that can be successfully used to partially replace internal combustion propulsion systems. For this reason, the article presents an operational analysis of energy flow along with an analysis of individual energy transmission systems. Two generations of the Toyota Mirai vehicle were used for the tests. The operational analyses were carried out on the same route (compliant with RDE test requirements), assessing the system’s operation in three driving sections (urban, rural and motorway). Both generations of the drive system with fuel cells are quite different, which affects the obtained individual systems operation results as well as the overall energy flow. Research was carried out on the energy flow in the fuel cells, FC converter, battery and electric motor using a dedicated data acquisition system. The analyses were carried out in relation to the energy of fuel cells, battery energy and recovered braking energy. It was found that in the urban drive section of the second-generation system (due to its much larger mass), a slightly higher energy consumption value was obtained (by about 2%). However, in the remaining phases of the test, consumption was lower (the maximum difference was 18% in the rural phase). Total energy consumption in the research test was 19.64 kWh/100 km for the first-generation system compared to 18.53 kWh/100 km for the second-generation system. Taking into account the increased mass of the second-generation vehicle resulted in significantly greater benefits in the second-generation drive (up to 37% in individual drive sections and about 28% in the entire drive test).

show abstract

“…They further computed the critical temperature (126.1°C and 139.2°C) that causes thermal runaway propagation. Few works on hybrid fuel cell technology to power hybrid vehicles is also found in 7,21 …”

Section: Introductionmentioning

confidence: 99%

“…So, MPC‐based power management appears to be a potential method for improving EV battery performance. Mehrdad et al 21 carried an experimental investigation on innovative Proton‐exchange membrane fuel cell stack and used four ML algorithms to forecast the stack’s potential future behaviour. DNN was chosen out of four alternative prediction neural network methods.…”

Section: Introductionmentioning

confidence: 99%

Machine learning prediction and study of hotspots and hotspots location for sustainable battery energy system

Afzal

Alahmadi

Razak

et al. 2022

Intl J of Energy Research

View full text Add to dashboard Cite

Summary Analysis of hotspots in battery system is important as it indicates the thermal stresses arising and the occurrence of thermal runways. The battery heat generation and coolant flow system are together studied in this work using finite volume method. The role of different class of coolants like nanofluids, gases, oils, and liquid metals combined with the variations in spacings between the battery cells is specifically focused. In addition, effect of battery aspect ratio, coolant velocity, and their thermal conductivity are analysed in detail. The hotspots intensity and their locations are accessed for all the factors mentioned above. Later, using modern algorithms like X‐gradient boosting (XGB) and decision tree (DT) the predictions of hotspots and their locations is performed. From the numerical analysis, it is found that the hotspots get affected by changes in the chosen parameters except aspect ratio. It is found that, in an operating range of battery system with different heat generations and coolants, there is always a limiting value above/below which simply increasing/decreasing the parameter, does not reduce battery hotspots for sustainable performance. Both the algorithms used, predict the hotspot with a low accuracy of R2 value 0.55 and 0.53 using DT and XGB algorithm. The hotspots location is predicted with high accuracy having R2 value close to 0.92 from both the models.

show abstract

Performance analysis of a degraded PEM fuel cell stack for hydrogen passenger vehicles based on machine learning algorithms in real driving conditions

Cited by 71 publications

References 40 publications

Modeling of performance and thermodynamic metrics of a conceptual turboprop engine by comparing different machine learning approaches

Modeling of performance and thermodynamic metrics of a conceptual turboprop engine by comparing different machine learning approaches

Two Generations of Hydrogen Powertrain—An Analysis of the Operational Indicators in Real Driving Conditions (RDC)

Machine learning prediction and study of hotspots and hotspots location for sustainable battery energy system

Contact Info

Product

Resources

About