Assessment of the metal grain size of 12Cr1MoV steel by LIBS coupled with acoustic wave information

Abstract

Laser-induced breakdown spectroscopy (LIBS) has the potential to serve as a valuable tool in the field of metal failure estimation. In this work, 12Cr1MoV steel, a material with different grain size grades, was selected as the experimental sample. Spectral and acoustic data were recorded during the laser ablation process. Initially, it was revealed that the acoustic energy did not exhibit a significant downward trend with the continuous laser shots, but the acoustic energy fluctuations became more intense. In order to enhance the capacity to assess the grain size grade of heat-resistant steel, we advanced a novel proposition to integrate acoustic data with spectral data. Two data fusion strategies were proposed for the integration of spectral and acoustic data: first, dimensionality reduction followed by combination, and second, combination followed by dimensionality reduction. Subsequently, two classification models, linear discriminant analysis (LDA) and support vector machines (SVM), were constructed utilising three data types: spectral data, acoustic spectral data, and the aforementioned combined data set. The performance of the model trained on the combined data obtained based on the first strategy is superior to models trained on a single data type (spectral data or acoustic spectral data), achieving a classification accuracy of 92.29%. The second strategy yielded unsatisfactory results due to the significant difference in dimensions between spectral data and acoustic spectral data. To address this, a modification was proposed by carrying out spectral feature screening on spectra data using RFE before data fusion and studying the impact of the number of remaining variables after RFE processing on model performance. The results showed that the model achieved the highest classification accuracy of 98.85%. The measurement illustrates the effectiveness of integrating spectral and acoustic spectral data for enhanced metal assessment.