Applying machine learning algorithms in estimating the performance of heterogeneous, multi-component materials as oxygen carriers for chemical-looping processes

Yan, Yongliang; Mattisson, Tobias; Moldenhauer, Patrick; Anthony, Edward J.; Clough, Peter T.

doi:10.1016/j.cej.2020.124072

Cited by 56 publications

(35 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to the above processes, the configuration of SMR+MEA+PSA can only capture 90 % CO2 emission and the lower CH4 conversion and cold gas efficiency. It is also worth noting that the SE-SMR has a joint reformer and water-gas shift reactor and its H2 purity from the reformer to the PSA unit is much higher (98%) than that of SMR, which means lower operational expenditure and a reduced energy penalty from the PSA system[50].Currently, the overall technology readiness level (TRL) for CLC is estimated as TRL 6, and a large number of materials have been successfully tested in continuous operation in CLC facilities from 0.3 kWth to 1 MWth worldwide[51]. The current TRL for SE-SMR is at 4, and it has been intensively investigated from the batch-scale to the lab-scale reactors[8,10,11,52].…”

mentioning

confidence: 99%

Process simulations of blue hydrogen production by upgraded sorption enhanced steam methane reforming (SE-SMR) processes

Yan

Thanganadar

Clough

et al. 2020

Energy Conversion and Management

Self Cite

View full text Add to dashboard Cite

Clean and carbon-free hydrogen production is expected to play a vital role in future global energy transitions. In this work, six process arrangements for sorption enhanced steam methane reforming (SE-SMR) are proposed for blue H2 production: 1) SE-SMR with an air fired calciner, 2) SE-SMR with a Pressure Swing Adsorption (PSA) unit, 3) SE-SMR thermally coupled with Chemical-Looping Combustion (CLC), 4) SE-SMR+PSA+CLC, 5) SE-SMR+PSA with an oxy-fired calciner, 6) SE-SMR+PSA and indirect firing H2 combustion from the product stream recycle. The proposed process models with rigorous heat exchanger network design were simulated in Aspen Plus to understand the thermodynamic limitations in achieving the maximum CH4 conversion, H2 purity, CO2 capture efficiency, cold gas efficiency and net operating efficiency. A sensitivity study was also performed for changes in the reformer temperature, pressure, and steam to carbon (S/C) ratio to explore the optimal operating space for each case. The SE-SMR+PSA+H2 (Case 6) recycle process can achieve a maximum of 94.2% carbon capture with a trade-off in cold gas efficiency (51.3%), while a near 100% carbon capture with the maximum net efficiency of up to 76.3% is realisable by integrating CLC and PSA (Case 4) at 25 bar. Integration of oxy-fuel combustion lowered the net efficiency by 2.7% points due to the need for an air separation unit. In addition, the SE-SMR with the PSAOG process can be designed as a self-sustaining process without any additional fuel required to meet the process heat utility when the S/C ratio is ~3-3.5.

show abstract

mentioning

confidence: 99%

Process simulations of blue hydrogen production by upgraded sorption enhanced steam methane reforming (SE-SMR) processes

Yan

Thanganadar

Clough

et al. 2020

Energy Conversion and Management

Self Cite

View full text Add to dashboard Cite

show abstract

“…To be more cost competitive, a suitable metal/metal-oxide pair as the oxygen carrier plays a critical role in the chemical looping process. More recently, the machine learning algorithms and artificial neural networks have been utilized to estimate the performance of hetero-and multi-component materials as oxygen carriers for CLC (Yan et al, 2020). • DACC represents a process for CO 2 extraction or removal directly from the atmosphere, which was first introduced for the mitigation of climate change by Lackner in 1999(Lackner et al, 1999.…”

Section: Current Status Of Carbon Capture Technologiesmentioning

confidence: 99%

Carbon Capture From Flue Gas and the Atmosphere: A Perspective

2020

View full text Add to dashboard Cite

Climate change has become a worldwide concern with the rapid rise of the atmospheric Co2 concentration. To mitigate Co2 emissions, the research and development efforts in Co2 capture and separation both from the stationary sources with high Co2 concentrations (e.g., coal-fired power plant flue gas) and directly from the atmosphere have grown significantly. Much progress has been achieved, especially within the last twenty years. In this perspective, we first briefly review the current status of carbon capture technologies including absorption, adsorption, membrane, biological capture, and cryogenic separation, and compare their advantages and disadvantages. Then, we focus mainly on the recent advances in the absorption, adsorption, and membrane technologies. Even though numerous optimizations in materials and processes have been pursued, implementing a single separation process is still quite energy-intensive or costly. To address the challenges, we provide our perspectives on future directions of Co2 capture research and development, that is, the combination of flue gas recycling and hybrid capture system, and one-step integrated Co2 capture and conversion system, as they have the potential to overcome the technical bottlenecks of single capture technologies, offering significant improvement in energy efficiency and cost-effectiveness.

show abstract

“…Figure 6 Diagram of PCA-RWN model for multi-mode combustion process monitoring 149 Yan et al 17 used the experimental data of nineteen manganese ores to train the ANN models to predict the reactivity of manganese ores as oxygen carriers in CLC. The results indicated the optimal ANN models can provide very good performance predictions for both training and new dataset and the authors proposed a general workflow in applying ML model to predict the performance and aid the design of the oxygen carriers as shown in Figure 7.…”

Section: Machine Learning In Oxyfuel and Chemical-looping Combustionmentioning

confidence: 99%

“…ML offers the potential to identify links between data/results that aren't readily identifiable, and it also provides alternative lower computing cost pathways. Within the field of CCUS, ML has begun to be utilised to evaluate new CO 2 sorbents and oxygen carrier materials 17 , simulate, control and operate capture processes [18][19][20][21][22][23] and simplify process economics, predict CO 2 solubilities in solvents and CO 2 capture capacities in adsorbents [24][25][26] , improve the accuracy of multiphase flowmeters used for CO 2 pipelines 27 , and predict leaks from CO 2 wells 28 ; each with the aim of advancing the field of CCUS in a cost and time effective manner. Meantime, it is also worth noting that ML is data-driven technology, and its performance usually depends on the size and quality of database.…”

Section: Introductionmentioning

confidence: 99%

Harnessing the power of machine learning for carbon capture, utilisation, and storage (CCUS) – a state-of-the-art review

Yan

Borhani

Subraveti

et al. 2021

Energy Environ. Sci.

Self Cite

130

View full text Add to dashboard Cite

show abstract

Applying machine learning algorithms in estimating the performance of heterogeneous, multi-component materials as oxygen carriers for chemical-looping processes

Cited by 56 publications

References 50 publications

Process simulations of blue hydrogen production by upgraded sorption enhanced steam methane reforming (SE-SMR) processes

Process simulations of blue hydrogen production by upgraded sorption enhanced steam methane reforming (SE-SMR) processes

Carbon Capture From Flue Gas and the Atmosphere: A Perspective

Harnessing the power of machine learning for carbon capture, utilisation, and storage (CCUS) – a state-of-the-art review

Contact Info

Product

Resources

About