PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Heliostat calibration is crucial for efficient solar tower power plant operation. Geometry-based models are reliable but yield moderate accuracy, while neural networks promise higher accuracy but need high amounts of data. We introduce a hybrid model that combines a reliable geometric model with a neural network disturbance model over a regularization sweep. Using real measurement data from the Jülich solar tower, we achieve higher accuracies than rigid body models starting from the first measurement, with a top performance below 0.7 milliradians. Our approach reduces data requirements of deep learning models, making them promising for heliostat calibration in solar tower power plants.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Max Pargmann, Moritz Leibauer, Daniel Maldonado Quinto, Vincent Nettelroth, Robert Pitz-Paal, "Reliable neural network heliostat calibration on low data," Proc. SPIE PC12671, Advances in Solar Energy: Heliostat Systems Design, Implementation, and Operation, PC1267106 (5 October 2023); https://doi.org/10.1117/12.2676698