JERAJournal of Electronic Research and Application2208-35022208-3510Bio-Byword Scientific Publishing Pty. Ltd.10.26689/jera.v10i2.14389ArticleStudy on pH Value Detection of Silage Corn Feed Based on Micro Near Infrared Spectrometerhttps://artdesignp.com/journal/JERA/10/2/10.26689/jera.v10i2.14389LiXiao,ZhuWenjing,ShaoChangfeng20261022026-04-03Silage corn feed is an important source of roughage for cattle and sheep breeding. Its pH value can quickly reflect the quality of feed and is one of the main indicators for evaluating the fermentation quality of feed. In this study, the pH value of silage corn feed was non-destructively and rapidly detected based on near-infrared spectroscopy analysis technology. The silage corn feed of dairy farms in Tai’an City, Shandong Province was taken as the research object. The spectra of 855~1890 nm of samples were collected based on a miniature near-infrared spectroscopy acquisition system, and the pH value prediction model of silage corn feed was established by combining chemometrics methods. Firstly, a miniature near-infrared spectroscopy acquisition system was introduced. The system was used to collect the near-infrared spectral data of 260 silage corn feed samples. The near-infrared spectral data were preprocessed by standard normal transformation, moving mean filtering, and multiple scattering correction. The wavelength was optimized by algorithms such as elimination of uninformative variables, competitive adaptive reweighted sampling algorithm, and variable iterative space shrinkage. The support vector regression (SVR) model based on snake optimization (SO) was used. The model was established by combining the pH value of the leaching solution of silage corn feed with the pH meter. The results show that the full-band modeling based on multiple scattering correction (MSC) pretreatment is the best, the modeling effect of the characteristic wavelength selected based on variable iterative space shrinkage approach (VISSA) is the best, and the modeling effect of MSC-VISSA-SO-SVR model is the best, and the correction correlation coefficient is 0.990531. The corrected root mean square error is 0.083545, the predicted correlation coefficient is 0.980487, and the predicted root mean square error is 0.127718. The results of this study show that the combination of MSC-VISSA-SO-SVR model based on micro near-infrared spectroscopy acquisition system can provide a reference for non-destructive detection of pH value of silage corn feed by near-infrared spectroscopy.

Zhang W, Fan P, Wu K, 2025, Application of Silage Corn Feed in Beef Cattle Breeding. Animal Industry and Environment, 2025(2): 18–19.

Liu N, Wang J, Tu Y, et al., 2019, Quality Evaluation of Corn Silage and Establishment of Rapid Detection Method for its Nutritional Components. Journal of Domestic Animal Ecology, 40(10): 1–7.

Ning H, Wang J, Jiang H, et al., 2022, Quantitative Detection of Zearalenone in Wheat Grains based on Near-Infrared Spectroscopy. Spectrochimica acta, Part A, Molecular and Biomolecular Spectroscopy, 2022(280): 121545–121545.

Wang J, Zareef M, He P, et al., 2019, Evaluation of Matcha Tea Quality Index using Portable NIR Spectroscopy Coupled with Chemometric Algorithms. Journal of the Science of Food and Agriculture, 99(11): 5019–5027.

Yanna R, Muhammad Z, Lihua L, et al., 2023, Application of Portable Vis-NIR Spectroscopy for Rapid Detection of Myoglobin in Frozen Pork. Meat Science, 2023(201): 109170–109170.

Na R, Yin H, Hu B, 2022, Application of Near-Infrared Spectroscopy in the Field of Rapid Detection of Feed. Feed Review, 2022(2): 44–46+50.

Dai C, Xu X, Huang W, et al., 2022, Monitoring of Critical Parameters in Thermophilic Solid-State Fermentation Process of Soybean Meal using NIR Spectroscopy and Chemometrics. Journal of Food Measurement and Characterization, 17(1): 576–585.

Luca M, James D, 2018, The Use of Mobile Near-Infrared Spectroscopy for Real-Time Pasture Management. Frontiers in Sustainable Food Systems, 2018, 2.

Tian L, Chen F, Lin Y, et al., 2023, Study on Nutritional Quality of Oat Forage Silage by Near Infrared Spectroscopy. Acta Agrestia Sinica, 31(12): 3841–3850.

Wang X, Guo T, Pan F, et al., 2021, Near Infrared Spectroscopy was used to Rapidly Analyze the Nutritional Components of Whole Corn Silage. Journal of Domestic Animal Ecology, 42(1): 52–55.

Zhang M, Zhao C, Shao Q, et al., 2019, Determination of Water Content in Corn Stover Silage using Near-Infrared Spectroscopy. International Journal of Agricultural and Biological Engineering, 12(6): 143–148.

Liu X, Han L, Yang Z, et al., 2007, Rapid Analysis of Silage pH Value and Fermentation Products by Near Infrared Spectroscopy. Chinese Journal of Analytical Chemistry, 2007(9): 1285–1289.

Zhang M, Hao M, Tian H, et al., 2023, Nondestructive Detection of pH Value of Silage Corn Feed based on Hyperspectral Imaging Technology. Transactions of the Chinese Society of Agricultural Engineering, 39(4): 239–247.

Yu Y, Tian H, Zhao K, et al., 2024, Rapid pH Value Detection in Secondary Fermentation of Maize Silage Using Hyperspectral Imaging. Agronomy, 14(6): 1204.

Wang F, Li Y, Peng Y, et al., 2018, Study on Nondestructive Detection Method of Lycopene Content based on Visible/ Near Infrared Transmission Spectroscopy. Chinese Journal of Analytical Chemistry, 46(9): 1424–1431.

Zhang F, Wang M, Yan B, et al., 2025, Identification of Egg Varieties by Hyperspectral Imaging Combined with ELM. Spectroscopy and Spectral Analysis, 45(3): 836–841.

Wang F, Wang C, Shi S, 2022, Rapid and Low-Cost Detection of Millet Quality by Miniature Near-Infrared Spectroscopy and Iteratively Retaining Informative Variables. Foods, 11(13): 1841–1841.

Ma Y, Li L, Shi Y, et al, 2023, Rapid Detection of Cotton Seed Protein and Oil Content based on Near Infrared Spectroscopy. Cotton Science, 35(3): 211–219.

Hashim F, Hussien G, 2022, Snake Optimizer: A Novel Meta-Heuristic Optimization Algorithm. Knowledge-Based Systems, 2022(242).

Sun J, Zhou X, Hu Y, et al., 2019, Visualizing Distribution of Moisture Content in Tea Leaves Using Optimization Algorithms and NIR Hyperspectral Imaging. Computers and Electronics in Agriculture, 2019(160): 153–1.