Enhanced prediction of cement raw meal oxides by near-infrared spectroscopy using machine learning combined with chemometric techniques Provisionally Accepted

Yongzhen Zhang¹ Zhenfa Yang² Yina Wang³ Xinting Ge¹ Jianfeng Zhang¹ Hang Xiao^1*

• ¹School of Information Science and Engineering, Shandong Normal University, China
• ²Shandong University, China
• ³College of Mechanical and Electronic Engineering, Nanjing Forestry University, China

The component analysis of raw meal is critical to the quality of cement. In recent years, Near Infrared (NIR) has been emerged as an innovative and efficient analytical method to determine the oxide content of cement raw meal. This study aims to utilize NIR spectroscopy combined with machine learning and chemometrics to improve the prediction of oxide content in cement raw meal. The Savitzky-Golay convolution smoothing method is applied to eliminate noise interference for the analysis of calcium carbonate (𝐶𝑎𝐶𝑂 ! ), silicon dioxide (𝑆𝑖𝑂 " ), aluminum oxide (𝐴𝑙 " 𝑂 ! ), and ferric oxide (𝐹𝑒 " 𝑂 ! ) in cement raw materials. Different wavelength selection techniques are used to perform a comprehensive analysis of the model, comparing the performance of several wavelength selection techniques. The back-propagation neural network regression model based on particle swarm optimization algorithm was also applied to optimize the extracted and screened feature wavelengths, and the model prediction performance was checked and evaluated using 𝑅 # and RMSE. In conclusion, the results indicate that NIR spectroscopy in combination with ML and chemometrics has great potential to effectively improve the prediction performance of oxide content in raw materials and highlight the importance of modeling and wavelength selection techniques.