Scalable heliostat surface predictions from focal spots: Sim-to-Real transfer of inverse Deep Learning Raytracing

IF 6 2区 工程技术 Q2 ENERGY & FUELS
Jan Lewen , Max Pargmann , Mehdi Cherti , Jenia Jitsev , Robert Pitz-Paal , Daniel Maldonado Quinto
{"title":"Scalable heliostat surface predictions from focal spots: Sim-to-Real transfer of inverse Deep Learning Raytracing","authors":"Jan Lewen ,&nbsp;Max Pargmann ,&nbsp;Mehdi Cherti ,&nbsp;Jenia Jitsev ,&nbsp;Robert Pitz-Paal ,&nbsp;Daniel Maldonado Quinto","doi":"10.1016/j.solener.2025.113726","DOIUrl":null,"url":null,"abstract":"<div><div>Concentrating Solar Power (CSP) plants are a key technology in the transition toward sustainable energy. A critical factor for their safe and efficient operation is the accurate distribution of concentrated solar flux on the receiver. However, flux densities from individual heliostats are highly sensitive to surface imperfections, such as canting and mirror deformations. Measuring these surfaces across hundreds or thousands of heliostats remains impractical in real-world deployments. As a result, control systems often assume idealized heliostat surfaces, leading to suboptimal performance and potential safety risks. To address this, inverse Deep Learning Raytracing (iDLR) has recently been introduced as a novel method for inferring heliostat surfaces from target images of focal spots captured during routine calibration procedures. However, until now, iDLR had only been demonstrated in simulation. In this work, we present the first successful Sim-to-Real transfer of iDLR, enabling accurate surface predictions directly from real-world target images. Remarkably, this was achieved through a zero-shot Sim-to-Real transfer, in which the model is trained exclusively with simulated flux density data and applied directly to real target images of heliostat focal spots without the need for additional training on real target images. We evaluate our method on 63 heliostats under real operational conditions. iDLR surface predictions achieve a median mean absolute error (MAE) of only 0.17 mm and show good agreement with deflectometry ground truth in 84% of cases. When used in raytracing simulations, it enables flux density predictions with a mean accuracy of 90% compared to deflectometry over our dataset, and outperforms the commonly used ideal heliostat surface assumption by 26%. We tested this approach in a challenging double-extrapolation scenario, involving unseen sun positions and receiver projections, and found that iDLR maintains high predictive accuracy, highlighting its generalization capabilities. Our results demonstrate that iDLR is a scalable, automated, and cost-effective solution for integrating realistic heliostat surface models into digital twins. This opens the door to an optimized heliostat control, improved flux density distributions on the receiver, and ultimately, enhanced efficiency and safety in future CSP plants.</div></div>","PeriodicalId":428,"journal":{"name":"Solar Energy","volume":"300 ","pages":"Article 113726"},"PeriodicalIF":6.0000,"publicationDate":"2025-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Solar Energy","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0038092X2500489X","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0

Abstract

Concentrating Solar Power (CSP) plants are a key technology in the transition toward sustainable energy. A critical factor for their safe and efficient operation is the accurate distribution of concentrated solar flux on the receiver. However, flux densities from individual heliostats are highly sensitive to surface imperfections, such as canting and mirror deformations. Measuring these surfaces across hundreds or thousands of heliostats remains impractical in real-world deployments. As a result, control systems often assume idealized heliostat surfaces, leading to suboptimal performance and potential safety risks. To address this, inverse Deep Learning Raytracing (iDLR) has recently been introduced as a novel method for inferring heliostat surfaces from target images of focal spots captured during routine calibration procedures. However, until now, iDLR had only been demonstrated in simulation. In this work, we present the first successful Sim-to-Real transfer of iDLR, enabling accurate surface predictions directly from real-world target images. Remarkably, this was achieved through a zero-shot Sim-to-Real transfer, in which the model is trained exclusively with simulated flux density data and applied directly to real target images of heliostat focal spots without the need for additional training on real target images. We evaluate our method on 63 heliostats under real operational conditions. iDLR surface predictions achieve a median mean absolute error (MAE) of only 0.17 mm and show good agreement with deflectometry ground truth in 84% of cases. When used in raytracing simulations, it enables flux density predictions with a mean accuracy of 90% compared to deflectometry over our dataset, and outperforms the commonly used ideal heliostat surface assumption by 26%. We tested this approach in a challenging double-extrapolation scenario, involving unseen sun positions and receiver projections, and found that iDLR maintains high predictive accuracy, highlighting its generalization capabilities. Our results demonstrate that iDLR is a scalable, automated, and cost-effective solution for integrating realistic heliostat surface models into digital twins. This opens the door to an optimized heliostat control, improved flux density distributions on the receiver, and ultimately, enhanced efficiency and safety in future CSP plants.
可扩展定日镜表面预测焦点:模拟到真实的反向深度学习光线追踪转移
聚光太阳能(CSP)电站是向可持续能源过渡的关键技术。其安全高效运行的一个关键因素是集中太阳通量在接收器上的准确分布。然而,来自单个定日镜的通量密度对表面缺陷非常敏感,例如倾斜和镜面变形。在现实世界的部署中,通过数百或数千个定日镜测量这些表面仍然是不切实际的。因此,控制系统通常采用理想化的定日镜表面,从而导致性能不理想,并存在潜在的安全风险。为了解决这个问题,最近引入了逆深度学习光线追踪(iDLR)作为一种新方法,从常规校准过程中捕获的焦点目标图像中推断定日镜表面。然而,到目前为止,iDLR只在模拟中得到了证明。在这项工作中,我们首次成功地实现了iDLR从模拟到真实的传输,从而能够直接从真实世界的目标图像中进行准确的表面预测。值得注意的是,这是通过零射击模拟到真实的转换来实现的,其中模型只使用模拟的通量密度数据进行训练,并直接应用于定日镜焦点的真实目标图像,而无需对真实目标图像进行额外的训练。在实际操作条件下,对63个定日镜进行了评价。iDLR地表预测的中位平均绝对误差(MAE)仅为0.17 mm,在84%的情况下与偏转仪地面真实情况吻合良好。当用于光线追踪模拟时,与我们数据集上的偏转法相比,它使通量密度预测的平均精度达到90%,并且比常用的理想定日镜表面假设高出26%。我们在一个具有挑战性的双外推场景中测试了这种方法,包括看不见的太阳位置和接收器投影,发现iDLR保持了很高的预测精度,突出了它的泛化能力。我们的研究结果表明,iDLR是一种可扩展的、自动化的、经济高效的解决方案,可将现实定日镜表面模型集成到数字双胞胎中。这为优化定日镜控制打开了大门,改善了接收器上的通量密度分布,最终提高了未来CSP发电厂的效率和安全性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Solar Energy
Solar Energy 工程技术-能源与燃料
CiteScore
13.90
自引率
9.00%
发文量
0
审稿时长
47 days
期刊介绍: Solar Energy welcomes manuscripts presenting information not previously published in journals on any aspect of solar energy research, development, application, measurement or policy. The term "solar energy" in this context includes the indirect uses such as wind energy and biomass
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信