摘要
由一名新闻记者-机器人与机器学习每日新闻编辑-研究人员详细介绍了人工智能的新数据。据新华社济南新闻报道，NewsRx记者称，“生料成分分析对水泥质量至关重要。”记者从山东师范大学的研究中得到一句话：“近年来，利用近红外光谱技术结合机器学习技术和化学计量学技术对水泥生料中氧化物含量进行预测,采用Savitzky-Golay卷积平滑法消除噪声干扰,对碳酸钙(CaCO3)、二氧化硅(SiO2)、二氧化硅、氧化钙采用不同的波长选择技术对模型进行了综合分析，比较了几种波长选择技术的性能，并应用基于粒子群算法的BP神经网络回归模型对提取和筛选的特征波长进行了优化。结果表明,近红外光谱结合ML和化学计量学对提高原料中氧化物含量的预测性能具有很大的潜力,并强调了建模和波长选择技术的重要性。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Researchers detail new data in artific ial intelligence. According to news reporting from Jinan, People's Republic of C hina, by NewsRx journalists, research stated, "The component analysis of raw mea l is critical to the quality of cement." The news correspondents obtained a quote from the research from Shandong Normal University: "In recent years, near-infrared (NIR) has been emerged as an innovat ive and efficient analytical method to determine the oxide content of cement raw meal. This study aims to utilize NIR spectroscopy combined with machine learnin g 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 (CaCO3), silicon dioxide (SiO 2), aluminum oxide (Al2O3), and ferric oxide (Fe2O3) in cement raw materials. Di fferent wavelength selection techniques are used to perform a comprehensive anal ysis of the model, comparing the performance of several wavelength selection tec hniques. The back-propagation neural network regression model based on particle swarm optimization algorithm was also applied to optimize the extracted and scre ened feature wavelengths, and the model prediction performance was checked and e valuated using Rp and RMSE. In conclusion, the results indicate that NIR spectro scopy in combination with ML and chemometrics has great potential to effectively improve the prediction performance of oxide content in raw materials and highli ght the importance of modeling and wavelength selection techniques."
NETL
NSTL