Abstract：Moisture content significantly impacts the properties (e.g., stability and compressibility) of chemical and pharmaceutical granular products. The traditional fluidized bed drying process moisture detection uses traditional instrumentation to detect the process of humidity, temperature, and other characterization variables and then infer the moisture content; this method often produces inaccurate detection, has a lag and other shortcomings, it has been difficult to meet the needs of modern production. Near-infrared (NIR) spectroscopy, as a new sensor technology, can be obtained from the molecular level of process information; its operation is simple, has fast analysis speed, and there is no need for sample pre-processing and other advantages, so it is widely used in many fields. However, existing NIR spectroscopic analysis methods are mainly based on offline detection of collected samples, which makes it difficult to reflect the real-time status of the production process. At the same time, in most cases, the absorption peaks of the collected NIR spectra overlap severely, resulting in the effective information of the NIR spectra being masked by various noises. Therefore, it is necessary to use suitable analysis tools for NIR data analysis and effective information extraction. Traditional algorithmic models mostly use linear or single-model methods, which makes it difficult to effectively solve the problem of effective information extraction from NIR spectra. Thus, in this paper, the fluidized bed drying (FBD) process of batch particles is used as the detection object, and near-infrared spectroscopy is applied to the fluidized bed granulation and drying process, which is combined with the XGBoost algorithm to establish an on-line measurement model of moisture content of particles. The Beluga whale optimization obtained the optimal parameters of the model, and then the validity of this approach was verified by the real fluidized bed drying experiments. For the validation experiments, the wave numbers (4 798 to 9 423 cm-1), which include the characteristic peaks of moisture and have more stable signals, are selected for modelling. Three independent batches of data out of the four batches collected are used as training sets to train the model, and the fourth batch is used to test the model. The models are evaluated in terms of Root Mean Squared Error (RMSE) and Coefficient of Determination R2 (R-Square), which show that the optimized XGBoost model outperforms the models built by PLS and BP-ANN algorithms in all the metrics. The online moisture content detection model based on near-infrared spectroscopy and XGBoost proposed in this paper provides a new approach for online moisture content detection in the fluidized bed drying process.
Key words：Near-infrared spectroscopy; Fluidized bed drying; On-line detection; XGBoost
何 帅，周 杰，张福林，穆国庆. 近红外光谱和XGBoost的流化床干燥过程水分含量在线检测[J]. 光谱学与光谱分析, 2024, 44(12): 3347-3352.
HE Shuai, ZHOU Jie, ZHANG Fu-lin, MU Guo-qing. Moisture Content Online Detection in Fluidized Bed Drying Process Based on Near Infrared Spectroscopy and XGBoost. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(12): 3347-3352.
[1] JIANG Shuang, YANG Hai-long, ZANG Heng-chang(姜 爽, 杨海龙, 臧恒昌). Food and Drug(食品与药品), 2013, 15(2): 135.
[2] Blanco M, Villarroya I. TrAC Trends in Analytical Chemistry, 2002, 21(4): 240.
[3] Saeki K, Funatsu K, Tanabe K, et al. Analytical Sciences, 2003, 19(2): 309.
[4] Benot I, Drennen III J K, Anderson C A. Applied Spectroscopy, 2014, 68(12): 1348.
[5] Velvarská R, Fiedlerová M, Hidalgo-Herrador J M, et al. Spectroscopy Letters, 2019, 52 (9): 533.
[6] LUO Qi, TOU Xian-guo, ZHANG Gui-yu, et al(罗 琪, 庹先国, 张贵宇, 等). Modern Food Science & Technology, 2023, 39(4): 311.
[7] LIU Yu, QIAO Mu(刘 宇, 乔 木). Computer System Applications(计算机系统应用), 2019, 28(1): 228.
[8] ZHANG Mei-zhi, ZHANG Ning, QIAO Zong, et al(张美志, 张 宁, 乔 聪, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2023, 43(6): 1711.
[9] Si C D, Wu J J, Wang Y, et al. Drying Technology, 2015, 33(3): 277.
[10] Mu G Q, Liu T, Liu J X, et al. Industrial & Engineering Chemistry Research, 2019, 58(16): 6476.
[11] Zhong C T, Li G, Meng Z. Knowledge-Based Systems, 2022, 251: 109215.
