DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Towards a Neural Network Based Flux Density Prediction - Using Generative Models to Enhance CSP Raytracing

Pargmann, Max and Maldonado Quinto, Daniel and Kesselheim, Stefan and Ebert, Jan (2021) Towards a Neural Network Based Flux Density Prediction - Using Generative Models to Enhance CSP Raytracing. In: Solar P. Solar PACES 2021, 27.-30. September 2021, Albuquerque (Vollständig Online). (Submitted)

[img] PDF


Each solar tower power plant is designed for a pre-calculated optimal flux density distribution. Any deviation from this has a direct impact on the output power as well as the durability of the components. An accurate knowledge of the current and predicted flux density is therefore essential. Also, because this is one of the most important input variables for all subsequent power plant processes. But due to individual errors of each heliostat, this theoretical flux density is very difficult to obtain. This includes, that common methods for measuring the flux density are either inaccurate, complicated, or expensive. Although raytracers exists, which can predict a flux density by analytical calculations, such an approach does not reflect reality sufficiently. We present a novel AI based method to predict the flux density map, which is capable to include heliostat specific errors, without having to measure the heliostats surface. Furthermore, we compare the advantages and disadvantages of different network structures for this approach and show first results archiving at best a Peak Signal to Noise Ratio (PSNR) value of up to 27.8 using neural radiance fields (NeRFs) .

Item URL in elib:https://elib.dlr.de/147258/
Document Type:Conference or Workshop Item (Speech)
Title:Towards a Neural Network Based Flux Density Prediction - Using Generative Models to Enhance CSP Raytracing
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Pargmann, MaxUNSPECIFIEDhttps://orcid.org/0000-0002-4705-6285UNSPECIFIED
Kesselheim, StefanJülich Supercomputing CentreUNSPECIFIEDUNSPECIFIED
Ebert, JanJülich Supercomputing CentreUNSPECIFIEDUNSPECIFIED
Date:September 2021
Journal or Publication Title:Solar P
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:No
Keywords:Neural Networks, NeRF, GAN, Flux Density Map, Heliostat
Event Title:Solar PACES 2021
Event Location:Albuquerque (Vollständig Online)
Event Type:international Conference
Event Dates:27.-30. September 2021
HGF - Research field:Energy
HGF - Program:Energy System Design
HGF - Program Themes:Digitalization and System Technology
DLR - Research area:Energy
DLR - Program:E SY - Energy System Technology and Analysis
DLR - Research theme (Project):E - Energy System Technology
Location: Köln-Porz
Institutes and Institutions:Institute of Solar Research > Solar Power Plant Technology
Deposited By: Pargmann, Max
Deposited On:13 Dec 2021 14:40
Last Modified:13 Dec 2021 14:40

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.