Laser-induced breakdown spectroscopy as a method for millimeter-scale inspection of surface flatness

• Published in: Plasma science & technology Vol. 26; no. 9; pp. 95501 - 95508
• Main Authors: YE, Jinrui, LI, Yaju, ZHANG, Zhao, WANG, Xinwei, TAO, Kewei, ZENG, Qiang, CHEN, Liangwen, QIAN, Dongbin, ZHANG, Shaofeng, YANG, Lei, MA, Xinwen
• Format: Journal Article
• Language: English
• Published: Plasma Science and Technology 01.09.2024
• Subjects: laser-induced breakdown spectroscopy; machine learning; surface flatness
• ISSN: 1009-0630
• DOI: 10.1088/2058-6272/ad5067

A non-contact method for millimeter-scale inspection of material surface flatness via Laser-Induced Breakdown Spectroscopy (LIBS) is investigated experimentally. The experiment is performed using a planished surface of an alloy steel sample to simulate its various flatness, ranging from 0 to 4.4 mm, by adjusting the laser focal plane to the surface distance with a step length of 0.2 mm. It is found that LIBS measurements are successful in inspecting the flatness differences among these simulated cases, implying that the method investigated here is feasible. It is also found that, for achieving the inspection of surface flatness within such a wide range, when univariate analysis is applied, a piecewise calibration model must be constructed. This is due to the complex dependence of plasma formation conditions on the surface flatness, which inevitably complicates the inspection procedure. To solve the problem, a multivariate analysis with the help of Back-Propagation Neural Network (BPNN) algorithms is applied to further construct the calibration model. By detailed analysis of the model performance, we demonstrate that a unified calibration model can be well established based on BPNN algorithms for unambiguous millimeter-scale range inspection of surface flatness with a resolution of about 0.2 mm.