Real-Time Image Enhanced Data-Driven Digital Twin (Real-TImE 3DT) for Flux Density Measurements : A Novel Non-Disruptive Universal Approach

Sergio Díaz Alonso; Christian Raeder; Kai Wieghardt; Bernhard Hoffschmidt

doi:10.52825/solarpaces.v3i.2311

Authors

Sergio Díaz Alonso Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR) https://orcid.org/0009-0001-1283-5502
Christian Raeder Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR) https://orcid.org/0009-0009-4903-6200
Kai Wieghardt Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)
Bernhard Hoffschmidt Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR) https://orcid.org/0000-0003-4068-2053

DOI:

https://doi.org/10.52825/solarpaces.v3i.2311

Keywords:

Flux Density Measurement (FDM), Digital Twin, Machine Learning, Concentrating Solar Power, Renewable Energies

Abstract

Concentrated solar power (CSP) plants are considered one of the most attractive renewable energy producers (used for green fuel and electric power). Consequently, it is essential to enhance the different elements of their power cycles, especially the central receiver and the heliostat field. To achieve this, flux density measurement (FDM) is highly recommended. In this work, a novel methodology for FDM is presented, based on the usage of real-time data-driven simulation models in parallel with the traditional camera methods for the real-time enhancement of the results. In order to improve the output, a graph neural network is used, giving as a result a Real-Time Image-Enhanced Data-Driven Digital Twin (Real-TImE 3DT). All the data are obtained from a pre-existing data platform, where the signals from the sensors of the power plant are logged and stored. This way, it is possible to operate the model manually, or to let it work automatically with these sensors' outputs. Latencies smaller than 10 seconds are achieved and the results from the digital twin showed coherence, easy handling and great inter-operability with the neural network enhancement. On the AI-enhancement’s side, the suppression of up-to 80% of the inaccuracies can be expected under parametrically semi-controlled conditions. Further work is being performed in Solar Tower Jülich (STJ) in order to contrast these results against real experimental measurements.

Downloads

Download data is not yet available.

References

[1] F. J. Collado and J. Guallar, "A review of optimized design layouts for solar power tower plants with campo code," Renewable and Sustainable Energy Reviews, vol. 20, pp. 142-154, 2013, doi: 10.1016/j.rser.2012.11.076.

[2] R. Schappi et al., "Drop-in fuels from sunlight and air," Nature, vol. 601, no. 7891, pp. 63-68, Jan 2022, doi: 10.1038/s41586-021-04174-y.

[3] A. H. Alami et al., "Concentrating solar power (CSP) technologies: Status and analysis," International Journal of Thermofluids, vol. 18, p. 100340, 2023.

[4] S. A. Zavattoni et al., "Synhelion absorbing gas solar receiver – Design advancement," AIP Conference Proceedings, vol. 2815, no. 1, 2023, doi: 10.1063/5.0149049.

[5] M. I. Alam, M. M. Nuhash, A. Zihad, T. H. Nakib, and M. M. Ehsan, "Conventional and Emerging CSP Technologies and Design Modifications: Research Status and Recent Advancements," International Journal of Thermofluids, vol. 20, 2023, doi: 10.1016/j.ijft.2023.100406.

[6] M. Röger, P. Herrmann, S. Ulmer, M. Ebert, C. Prahl, and F. Göhring, "Techniques to Measure Solar Flux Density Distribution on Large-Scale Receivers," Journal of Solar En-ergy Engineering, vol. 136, no. 3, 2014, doi: 10.1115/1.4027261.

[7] R. Osuna, R. Morillo, J. M. Jiménez, and V. Fernández-Quero, "Control and Operation Strategies in PS10 Solar Plant," in 13th SolarPACES, Sevilla, Spain, Jun. 20-23 2006, pp. 1-5.

[8] M. Offergeld, M. Röger, H. Stadler, P. Gorzalka, and B. Hoffschmidt, "Flux density measurement for industrial-scale solar power towers using the reflection off the absorb-er," presented at the SOLARPACES 2018: International Conference on Concentrating Solar Power and Chemical Energy Systems, 2019.

[9] M. Thelen, C. Raeder, C. Willsch, and G. Dibowski, "A high-resolution optical measure-ment system for rapid acquisition of radiation flux density maps.," in SolarPACES 2016, Abu Dhabi, UAE, 2016, vol. 1850, no. 12: AIP Publishing, 2017, doi: 10.1063/1.4984534.

[10] G. von Tobel, C. Schelders, and M. Real, "Concentrated solar-flux measurements at the IEA-SSPS solar-central-receiver power plant, Tabernas - Almeria (Spain). Final report. Technical report No. 2/82," 1982.

[11] S. Ulmer, E. Lüpfert, M. Pfänder, and R. Buck, "Calibration corrections of solar tower flux density measurements," Energy, vol. 29, no. 5-6, pp. 925-933, 2004, doi: 10.1016/s0360-5442(03)00197-x.

[12] M. R. Rodríguez-Sánchez, A. Sánchez-González, and D. Santana, "Field-receiver model validation against Solar Two tests," Renewable and Sustainable Energy Reviews, vol. 110, pp. 43-52, 2019/08/01/ 2019, doi: https://doi.org/10.1016/j.rser.2019.04.054.

[13] M. Kuhl, M. Pargmann, M. Cherti, J. Jitsev, D. M. Quinto, and R. Pitz-Paal, "In-Situ UNet-Based Heliostat Beam Characterization Method for Precise Flux Calculation Using the Camera-Target Method," ed: Research Square, 2024.

[14] I. Miadowicz, D. M. Quinto, R. Pitz-Paal, and M. Felderer, "An action research study on the digital transformation of concentrated solar thermal plants," Solar Energy Advances, vol. 5, p. 100102, 2025/01/01/ 2025, doi: https://doi.org/10.1016/j.seja.2025.100102.

[15] K. Arafet and R. Berlanga, "Digital Twins in Solar Farms: An Approach through Time Se-ries and Deep Learning," Algorithms, vol. 14, no. 5, p. 156, 2021. [Online]. Available: https://www.mdpi.com/1999-4893/14/5/156.

[16] J. Yu, P. Liu, and Z. Li, "Hybrid modelling and digital twin development of a steam turbine control stage for online performance monitoring," Renevable and Sustainable Energy Reviews, vol. 133, 2020.

[17] T. I. Zohdi, "A machine-learning digital-twin for rapid large-scale solar-thermal energy system design," Computer Methods in Applied Mechanics and Engineering, 2023.

[18] O. Ronneberger, P. Fischer, and T. Brox, "U-Net: Convolutional Networks for Biomedical Image Segmentation," ArXiv, vol. abs/1505.04597, 2015.

[19] B. Belhomme, R. Pitz-Paal, P. Schwarzbözl, and S. Ulmer, "A new fast ray tracing tool for high-precision simulation of heliostat fields," Journal of Solar Energy Engineering, vol. 131, 2009, doi: 10.1115/1.3139139.

[20] J. Lewen, M. Pargmann, M. Cherti, J. Jitsev, R. Pitz-Paal, and D. M. Quinto, "Inverse Deep Learning Raytracing for heliostat surface prediction," Solar Energy, vol. 289, p. 113312, 2025/03/15/ 2025, doi: https://doi.org/10.1016/j.solener.2025.113312.

[21] M. Kuhl, M. Pargmann, M. Cherti, J. Jitsev, D. Maldonado Quinto, and R. Pitz-Paal, "Flux density distribution forecasting in concentrated solar tower plants: A data-driven ap-proach," Solar Energy, vol. 282, p. 112894, 2024/11/01/ 2024, doi: https://doi.org/10.1016/j.solener.2024.112894.

Real-Time Image Enhanced Data-Driven Digital Twin (Real-TImE 3DT) for Flux Density Measurements

A Novel Non-Disruptive Universal Approach

Authors

DOI:

Keywords:

Abstract

Downloads

References

Downloads

Published

How to Cite

Conference Proceedings Volume

Section

License

Funding data