A Combined Computer Vision and Deep Learning Approach for Rapid Drone-Based Optical Characterization of Parabolic Troughs

Abstract

Optical accuracy is a primary driver of parabolic trough concentrating solar power (CSP) plant performance, but can be damaged by wind, gravity, error during installation, and regular plant operation. Collecting and analyzing optical measurement over an entire operating parabolic trough plants is difficult, given the large scale of typical installations. The Distant Observer (DO) software tool uses images and video to measure surface slope in the parabolic mirror and absorber tube offset from the ideal focal point. DO has been adapted for fast data collection using low-cost commercial drones, but until recently still required substantial human labor to process large amounts of data. A new method leveraging deep learning and computer vision tools can drastically reduce the time required to process images. This method identifies the featureless corners of trough mirrors to a high degree of accuracy. Previous work has shown promising results using computer vision. The combined deep learning and computer vision approach presented here proved effective, and has the potential to further automate data collection and analysis, making the tool more robust. This method automatically identified 74.3% of mirror corners within 2 pixels of their manually marked counterparts and 91.9% within 3 pixels. This level of accuracy is sufficient for practical DO analysis within a target uncertainty. DO successfully analyzed video of over 100 parabolic trough modules collected at an operating CSP plant, and can provide plant operators and trough designers with valuable insight about plant performance, operating strategies, and plant-wide optical error trends.