Bimodal data fusion of LIBS spectroscopy and plasma acoustic emission signals: improving the accuracy of machining process identification for low roughness samples

Abstract

The identification of machining processes for low roughness samples is extremely challenging, and a reasonably quick identification of machining processes for low roughness parts is critical for ensuring that the samples are employed under the appropriate conditions and improving work efficiency. In this work, a new identification method of fusion of LIBS spectra and plasma acoustic emission signals (PAESs) with bimodal information is proposed, and the LIBS spectral data and PAES data of nine types of low roughness samples processed by three machining processes, namely horizontal milling, plain grinding, and vertical milling, are recorded and analyzed. The spectral intensities of the primary element Fe and trace element Mn are compared and analyzed. The spectrum intensities of the primary element Fe and trace element Mn, as well as the PAES maximum peak, are compared and examined. Using the PCA-SVM machine learning technique, the three recognition impacts of single LIBS data, single PAES data, and LIBS-PAES bimodal data fusion are examined and compared. At R_a = 0.4 μm and 0.8 μm, vertical milling produces significantly higher spectral intensities than plain grinding and horizontal milling, while horizontal milling produces significantly higher intensities than plain grinding. When the surface roughness of the samples is the same, variations in the machining process cause changes in the PAES. The recognition accuracy was 86.67% for the test set of single LIBS spectral data, 78.89% for the test set of single PAES data, and 97.11% for the training set, and 91.11% for the test set of LIBS-PAES bimodal data fusion, respectively. When compared to single-modal data recognition, bimodal data fusion greatly improves recognition ability, fully reflecting the benefits of bimodal data fusion. Based on the results of this study, it can be preliminarily concluded that the fusion of spectral and acoustic information in laser-induced breakdown spectroscopy detection is very promising for recognizing the surface state of parts in the machining field.