Cascaded machine learning model for reconstruction of surface topography from light scattering

Abstract

In this paper, we propose a light scattering method to identify classes of structured surface topographies and estimate their main geometric properties. The method is based on a cascaded machine learning model, designed as a two-layer architecture implemented using neural networks. The first layer consists of a classification model designed to determine which type/class of surface is being observed amongst a set of predefined surfaces The second layer, cascaded to the first one, is designed to infer geometric properties specific to the individual structured surface being measured within each class, for example, pitch and height for a grating-type surface. The training datasets for the cascaded machine learning model, i.e. scattering signals from different surfaces, are generated through rigorous scattering simulation applied to computer-generated surfaces and based on a boundary element method. Once the model is trained, any scattering signal obtained from a real surface belonging to the considered classes can be fed into the model, and both the surface class and specific values for its geometric properties can be quickly estimated. For validation, we developed a prototype experimental apparatus to generate light scattering data from real surface samples. Different grating patterns (classes) were considered, as well as different values for the main geometric properties specific to each class. Validation consisted both in the assessment of classification performance in recognising instances of each specific class and in quantification of estimation accuracy in determining the geometric properties of each instance, by comparison with measurements performed with atomic force microscopy.

Deep learning classification and recognition method for milling surface roughness combined with simulation data

“…is very significant. The information is extracted and used by the neural network in the model training, making the model more accurate and effective [16]. Therefore, in this paper, the simulated texture was matched with the actual texture first, and then the simulated images and the actual images were input into the Xception model to predict the roughness.…”

“…To overcome the difficulty of obtaining samples of various roughness levels and compensate for the absence of training sample data, simulation can be used to generate a large number of surface images with roughness labels. Liu et al [16] proposed a light scattering method to identify classes of structured surface topographies and estimate their main geometric properties.…”

Measurement of laser powder bed fusion surfaces with light scattering and unsupervised machine learning

“…We have previously developed a method to detect defects on surfaces featuring regular topographic patterns (e.g. gratings), based on using a light source to illuminate the surface, collect the scattered reflection pattern by using a sensor array, and finally analyse the pattern using machine learning to perform pattern classification and thus detect anomalies [23][24][25]. We have shown that using machine learning can solve the complex inverse scattering problem efficiently (compared to the traditional library search method [26]) and our solution based on combining light scattering and machine learning is relatively fast (compared to fringe projection methods [15,16]), thus suitable for application to in-process monitoring, and introduces minimal concerns in terms of process disturbance or accessibility issues.…”