基于BP神经网络的鸡蛋货架期和贮藏时间预测模型研究

摘要/Abstract

摘要： 为探究贮藏于不同温度范围下的不同品种鸡蛋货架期，以京粉6号和海兰灰鸡蛋为研究对象，测量了冷藏（4℃）和常温（25℃）条件下的哈夫单位、气室高度、蛋黄指数、蛋清pH和失重率等指标。以哈夫单位低于60作为货架期的终点，发现两种鸡蛋在常温和冷藏条件下的货架期分别为12天和83天。将表征鸡蛋新鲜度最重要的指标哈夫单位作为模型的固定参数，其余输入参数的选择基于Pearson相关性分析结果，依据与哈夫单位的关联强度，从高到低依次作为输入参数构建了基于BP神经网络（back propagation artificial neural network，BP-ANN）的鸡蛋货架期和贮藏时间预测模型。根据模型在预测集上的表现确定具体的输入参数，将优化隐含层神经元数的BP-ANN与其他机器学习模型对比，如偏最小二乘回归（partial least squares regression, PLSR）和支持向量回归（support vector regression，SVR）模型。结果表明，相较于PLSR和SVR，经过优化隐含层神经元数的BP-ANN模型对鸡蛋剩余货架期和贮藏时间的预测精度最高。本研究可为鸡蛋在不同贮藏温度下的货架期制定提供参考，为剩余货架期和贮藏时间的快速、准确、同步预测提供技术支持。

关键词: 鸡蛋, 货架期, 贮藏时间, BP神经网络（BP-ANN）, 预测模型

Abstract: To investigate the shelf life of different types of eggs stored at various temperature ranges, Haugh units, air cell depth, yolk index, albumen pH and weight loss were examined under refrigerated (4°C) and room temperature (25°C) using Jingfen No. 6 and Hy-Line Grey eggs. Taking the Haugh unit below 60 as the end of shelf life, the shelf lives of the two types of eggs were found to be 12 and 83 days under ambient and refrigerated conditions, respectively. The most important indicator of egg freshness, Haugh units, was taken as a fixed parameter of the model, and the remaining input parameters were selected based on the results of Pearson correlation analysis. The back propagation artifical neural network (BP-ANN) prediction models for egg shelf life and storage time were constructed based on the strength of their correlation with Haugh units, in descending order. The specific input parameters were determined based on the performance of the model on the prediction set, and BP-ANN models with optimized number of neurons in the hidden layer were compared with other machine learning models, such as partial least squares regression (PLSR) and support vector regression (SVR) models. The results showed that BP-ANN models with optimized number of hidden layer neurons had the highest accuracy in predicting the remaining egg shelf life and storage time compared to PLSR and SVR. This study provided a guide for the development of shelf life of eggs at different storage temperatures and technical support for the rapid, accurate and simultaneous prediction of remaining shelf life and storage time.

Key words: eggs, shelf life, storage time, BP neural network (BP-ANN), prediction model

中图分类号:

TS253.7

陆逸峰何子豪曾宪明徐幸莲韩敏义. 基于BP神经网络的鸡蛋货架期和贮藏时间预测模型研究[J]. 食品科学, 0, (): 0-0.

参考文献

[1]何立超, 马素敏, 李成梁, 等.不同煮制时间对水煮鸡蛋质构及蛋黄脂质成分的影响[J].食品工业科技, 2018, 39(6):25-30 [2]张清, 袁诺, 赵金红, 等.鸡蛋哈夫值与其脂肪酸组成的相关关系[J].食品科技, 2021, 46(4):37-44 [3]赵梦莹, 刘雪, 张领先, 等.鸡蛋货架期的研究进展与展望[J].食品工业科技, 2013, 34(5):376-379 [4]刘雪, 李亚妹, 刘娇, 等.基于神经网络的鲜鸡蛋货架期预测模型[J].农业机械学报, 2015, 46(10):328-334 [5]LI J, ZHU S, JIANG S, et al.Prediction of egg storage time and yolk index based on electronic nose combined with chemometric methods[J].LWT , 2017, 82:369-376 [6]马惠玲, 曹梦柯, 王栋, 等.苹果货架期--预测模型研究[J].农业机械学报, 2021, 52(11):367-375 [7]XIA A, ZHANG Y, ZHAO L, et al.Simultaneous,rapid and nondestructive determination of moisture,fat content and storage time in leisure dried tofu using LF-NMR[JOL][J].Analytical Sciences, 2021, 37(2):301-307 [8]TAN M, WANG J, LI P, et al.Storage time prediction of glazed frozen squids during frozen storage at different temperatures based on neural network[JOL][J].International Journal of Food Properties, 2020, 23(1):1663-1677 [9]YANG J, HUANG Y, XU H, et al.Optimization of fungi co-fermentation for improving anthraquinone contents and antioxidant activity using artificial neural networks[J].Food Chemistry, 2020, 313:126-138 [10]FU Z, ZHAO S, ZHANG X, et al.Quality characteristics analysis and remaining shelf life prediction of fresh tibetan Tricholoma matsutake under modified atmosphere packaging in cold chain[JOL][J].Foods, 2019, 8(4):136- [11]LI Y, CHU X, FU Z, et al.Shelf life prediction model of postharvest table grape using optimized radial basis function (RBF) neural network[JOL][J].British Food Journal, 2019, 121(11):2919-2936 [12]RAN M, HE L, LI C, et al.Quality changes and shelf-life prediction of cooked cured ham stored at different temperatures[JOL][J].Journal of Food Protection, 2021, 84(7):1252-1264 [13]刘钰, 胡辉, 冉颖, 等.不同涂膜方式对贮藏鸡蛋品质影响及货架期模型的构建[J].石河子大学学报(自然科学版), 2021, 39(6):674-679 [14]吉小凤, 杨华, 汪建妹, 等.贮藏环境对鸡蛋新鲜度的影响及鲜鸡蛋货架期预测模型构建研究[J].农产品质量与安全, 2018, (2):59-65 [15]刘冬青, 陈朴, 臧鹏, 等.月饼品质指标变化规律研究和保质期预测模型的建立[J].食品科学, , :- [16]中华人民共和国农业部.鲜蛋等级规格：NY/T 1758-2009[S]. 2009: 1. [17]NO H K, PRINYAWIWATKUL W, MEYERS S P.Comparison of shelf life of eggs coated with chitosans prepared under various deproteinization and demineralization times[JOL][J].Journal of Food Science, 2006, 70(6):s377-s382 [18]饶珏睿, 韩佃刚, 董俊, 等.鸡蛋新鲜度指标与贮藏天数相关性研究[J].食品安全质量检测学报, 2021, 12(8):3041-3047 [19]马逸霄, 王巧华, 王贤波, 等.二氧化碳浓度对鸡蛋呼吸强度及品质的影响[J].分析化学, 2020, 48(12):1728-1736 [20]付丹丹, 王巧华, 马美湖, 等.贮藏期鸡蛋新鲜度指标与-卵白蛋白含量的相关关系[J].食品科学, 2018, 39(19):1-6 [21]李龙, 马政, 亢守亭, 等.鸡蛋不同贮藏温度的新鲜度变化以及货架期预测模型研究[J].中国家禽, 2021, 43(12):56-60 [22]余锦露, 张磊, 孙雅静, 等.阻抗法检测鸡蛋新鲜度[J].食品科学, 2017, 38(24):208-212 [23]薛艳蓉, 茂文, 赵瑞生, 等.鸡蛋在储存过程中微生物及蛋品质的变化研究[J].畜牧与饲料科学, 2017, 38(08):67-69 [24]姜国川, 闫晓慧, 谭传欣, 等.氨基丁酸对鸡蛋贮藏性能的影响[J].食品科学, 2019, 40(15):249-254 [25]王娇娇, 王巧华, 祝志慧, 等.鸡蛋内部品质与其呼吸强度的关系[J].食品科学, 2018, 39(23):36-40 [26]杜丹萌, 王风诺, 王世平.鸡蛋新鲜度随储藏条件变化规律的研究[J].食品科技, 2014, 39(5):26-29 [27]XINHUA J, HERU X, LINA Z, et al.Nondestructive detection of chilled mutton freshness based on multi-label information fusion and adaptive BP neural network[J].Computers and Electronics in Agriculture, 2018, 155:371-377 [28]CHEN Q, HU W, SU J, et al.Nondestructively sensing of total viable count (TVC) in chicken using an artificial olfaction system based colorimetric sensor array[J].Journal of Food Engineering, 2016, 168:259-266 [29]AL-BULUSHI N I, KING P R, BLUNT M J, et al.Artificial neural networks workflow and its application in the petroleum industry[JOL][J].Neural Computing and Applications, 2012, 21(3):409-421 [30]XIAO Z, YE S J, ZHONG B, et al.BP neural network with rough set for short term load forecasting[JOL][J].Expert Systems with Applications, 2009, 36(1):273-279 [31]WANG M, ZHANG J, ZHANG Z, et al.Simultaneous ultraviolet spectrophotometric determination of sodium benzoate and potassium sorbate by BP-neural network algorithm and partial least squares[J].Optik, 2021, 201:- [32]JIANG S, WANG J.Internal quality detection of Chinese pecans (Carya cathayensis) during storage using electronic nose responses combined with physicochemical methods[J].Postharvest Biology and Technology, 2016, 118:17-25 [33]LI J chao, ZHAO D ling, GE B F, et al.A link prediction method for heterogeneous networks based on BP neural network[J].Physica A: Statistical Mechanics and its Applications, 2018, 495:1-17 [34]白宗秀, 朱荣光, 王世昌, 等.高光谱图像结合特征变量筛选定量检测羊肉中狐狸肉掺假[J].农业工程学报, 2021, 37(17):276-284 [35]孙红, 郑涛, 刘宁, 等.高光谱图像检测马铃薯植株叶绿素含量垂直分布[J].农业工程学报, 2018, 34(1):149-156 [36]QIU L, ZHANG M, MUJUMDAR A S, et al.Convenient use of near-infrared spectroscopy to indirectly predict the antioxidant activitiy of edible rose (Rose chinensis Jacq “Crimsin Glory” H.T.) petals during infrared drying[J].Food Chemistry, 2022, 369:- [37]孙俊, 丛孙丽, 毛罕平, 等.基于高光谱的油麦菜叶片水分--预测模型[J].农业工程学报, 2017, 33(5):178-184 [38]朱玲, 唐杰, 许嘉东, 等.烟用爆珠内液质量稳定性检测——基于紫外光谱技术结合算法[J].中国烟草学报, 2019, 25(3):29-36