Automatic classification of true and false laser-induced damage in large aperture optics

Abstract

Abstract. An automatic classification method based on machine learning is proposed to distinguish between true and false laser-induced damage in large aperture optics. First, far-field light intensity distributions are calculated via numerical calculations based on both the finite-difference time-domain and the Fourier optical angle spectrum theory for Maxwell's equations. The feature vectors are presented to describe the possible damage sites, which include true and false damage sites. Finally, a kernel-based extreme learning machine is used for automatic recognition of the true sites and false sites. The method studied in this paper achieves good recognition of false damage, which includes a variety of types, especially attachment-type false damage, which has rarely been studied before. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

Estimating and monitoring laser-induced damage size on glass windows with a deep-learning-based pipeline

“…The effective and optimal use of these methods relies on the early detection of the growth of damage sites ranging from 50 µm to 750 µm in diameter. These damage diameters are close to the field of view of one pixel for observation systems of high energy laser facilities such as the Final Optics Damage Inspection (FODI) at NIF [18], the SG-III FODI [19] and the Chamber Center Diagnostic Module 25 (MDCC) on the LMJ facility [15,20]. In order to make damage sites visible, observed optics are illuminated by their edges, resulting in dark-field pictures on which damage sites appear as bright spots.…”

LMJ 2023 facility status

“…The bare measurement of the site diameter does not reach the accuracy level required to characterize the growth of damage sites before they reach the mitigation size limit (750 μm). Previous works have shown that the grey levels of acquired images are directly related to the damage size [8], [9], [10]. This technique provides a much higher accuracy on the estimated damage size than counting the number of lit pixels.…”

Detection and tracking of laser damage sites on fused silica components by digital image correlation

“…Thus, observation systems have been developed to track laser damage sites without removing fused silica components after each laser shot. NIF, SG-III and LMJ facilities use similar observation systems that are called Final Optics Damage Inspection (FODI) [20,21] for NIF and SG-III, and Chamber Center Diagnostic Module (or MDCC) for LMJ [22]. FODI and MDCC were both designed to image each UV final optics from the center of the experiment chamber after each laser shot.…”

“…FODI and MDCC were both designed to image each UV final optics from the center of the experiment chamber after each laser shot. These optics are illuminated through the edge of the component [20,22,21] resulting in dark-field pictures on which damage sites are visible as bright spots.…”