[22p-A602-1~17] 3.7 Optical measurement, instrumentation, and sensor (formerly 3.8)

2:15 PM - 2:30 PM JST(5:15 AM - 5:30 AM UTC)

[22p-A602-6] Analysis of spectra using processed data as training data in the neural network

〇Masaki Oba¹ (1.JAEA)

Keywords:

neural network,spectrum,processed data

As a method of analyzing multi-element spectral data obtained by LIBS, etc., we are constructing an analysis system using a neural network. More learning data is expected to improve accuracy, but it takes time and effort to prepare many actual samples. Therefore, 462 types of processed training data were created by mixing the spectra of Gd₂O₃, TiO₂ and ZrO₂ on the data by changing the ratio, and the system was trained. After training, we analyzed the content ratio of each element in 62 types of actual sample data obtained by microwave LIBS measurement, and examined its characteristics. As a result, the content ratio was obtained with a difference of about ±10% from the true value.