GA-BP neural network and its application in safety evaluation of liquid milk
-
摘要: 利用遗传算法（Genetic Algorithm,GA）优化BP（Back Propagation,BP）神经网络的初始权值、阈值,以期加快网络收敛,提高预测精度。以乳制品中的液体乳为实验材料,建立安全评价指标体系;将优化后的GA-BP神经网络作为评价模型,对液体乳的日常检测数据进行拟合;以测试数据作为验证,检测模型的收敛速度和拟合度。结果表明GA-BP较BP神经网络来讲更稳定,能较快收敛,且仿真误差较小;在隐层节点数为9时,GA-BP神经网络对液体乳的拟合效果最好,预测精度较高,是一种可行的液体乳安全状况评价方法。Abstract: The initial weights and thresholds of back propagation ( BP) neural network were optimized by genetic algorithm ( GA) to accelerate the network convergence and improve the prediction precision.The liquid milk in dairy products was used as the experimental material to establish the safety evaluation index system. The GA-BP neural network was used as the evaluation model to fit the daily data of liquid milk.The convergence rate and the fitting degree of the model were verified by the test data.The results showed that GA-BP was more stable than BP neural network and could converge quickly, and the simulation error of GA-BP neural network was smaller.When the number of nodes was 9, GA-BP neural network had the best fitting effect to liquid milk, and the prediction precision was high. So GA-BP neural network was a feasible method to evaluate the safety of liquid milk.
-
[1] Liao J Y.Research of food quality safety control system based on HACCP[J].Journal of Anhui Agricultural Sciences, 2012, 23:11843-11845.
[2] 蔡强, 王君君, 李海生, 等.基于神经网络的食品安全评价模型构建研究[J].食品科学技术学报, 2014, 01:69-77. [3] 雷勋平, Robin Qiu, 吴杨.基于供应链和可拓决策的食品安全预警模型及其应用[J].中国安全科学学报, 2011, 11:136-143. [4] 周萍萍, 张磊, 焦阳, 等.应用德尔菲法建立进口食品中化学性危害物质风险分级指标体系[J].食品安全质量检测学报, 2016, 05:2114-2119. [5] Liu Q J, Chen T, Zhang J H, et al.Risk matrix-based risk monitoring model of food safety[J].Food Science, 2010.05:86-90.
[6] Gong Y X, Wang D H.View on the food safety emergencies risk pre-warning system based on case-based reasoning[J].Food Science&Technology, 2012, 07:311-315.
[7] 周乃元, 潘家荣, 汪明.食品安全综合评估数学模型的研究[J].中国食品卫生杂志, 2009, 03:198-203. [8] 王媛媛, 洪思慧, 房晓倩, 等.基于因子分析的食品监管风险评价模型研究[J].食品工业科技, 2016, 13:266-270. [9] 董笑, 白宝光.基于时间序列分解法对原料乳质量安全预测的探究[J].食品工业, 2016, 05:188-191. [10] 张丽, 滕飞, 王鹏.基于贝叶斯网络的食品供应链风险评价研究[J].食品研究与开发, 2014, 18:179-182. [11] Zhang F Y, Dong Q L, Huang S L, et al.Modeling the qualifying criteria of pork based on Bayesian network[J].Science&Technology of Food Industry, 2012, 10:52-54, 93.
[12] Wang J, Tang Z, Jin X.Food Safety Evaluation System Construction Based on Artificial Neural Network[J].Advance Journal of Food Science and Technology, 2015, 02:98-100.
[13] 章德宾, 徐家鹏, 许建军, 等.基于监测数据和BP神经网络的食品安全预警模型[J].农业工程学报, 2010, 01:221-226. [14] 唐晓纯, 苟变丽.食品安全预警体系框架构建研究[J].食品科学, 2005, 12:246-250. [15] 武力.“从农田到餐桌”的食品安全风险评价研究[J].食品工业科技, 2010, 09:304-306. [16] 徐超, 杜树新, 罗祎, 等.基于集对分析理论的进出口食品安全风险评价方法[J].科技通报, 2013, 03:208-211, 230. [17] 刘於勋.食品安全综合评价指标体系的层次与灰色分析[J].河南工业大学学报 (自然科学版) , 2007, 05:53-57. [18] 金剑, 齐思源, 彭亚拉.神经网络法在食品安全预警中的应用[J].食品科技, 2011, 11:306-309. [19] 王辉, 王斌, 徐静, 等.基于BP神经网络的乳制品质量预测研究[J].农机化研究, 2013, 03:218-220. [20] 韩力群.人工神经网络理论、设计及应用[M].北京:化学工业出版社, 2007:47-62. [21] 吴聪.乳制品供应链的溯源体系与预警模型研究[D].广州:华南理工大学, 2014. [22] 仲伟峰, 马丽霞, 何小溪.PCA和改进BP神经网络的大米外观品质识别[J].哈尔滨理工大学学报, 2015, 04:76-81. [23] 雷英杰, 等.MATLAB遗传算法工具箱及应用[M].西安:西安电子科技大学出版社, 2005:146-207. [24] 刘春艳, 凌建春, 寇林元, 等.GA-BP神经网络与BP神经网络性能比较[J].中国卫生统计, 2013, 02:173-176. [25] 国家国家食品安全风险评估中心.食品安全国家标准汇编[M].北京:中国人口出版社, 2014:1-563. -
期刊类型引用(6)
1. 葛增跃. 绿茶多酚的提取工艺研究进展. 食品安全导刊. 2025(03): 165-168+172 . 
百度学术
2. 徐锦添，张晨曦，张宇. 茶多酚的提取分离技术与其体外抗氧化活性研究. 农产品加工. 2024(06): 78-85 . 百度学术
3. 龙娇，王铭海，李丹，孙育，汪建超. 茶多酚提取工艺研究进展. 食品安全导刊. 2024(10): 187-189 . 百度学术
4. 张文婷，孙健，徐飞，朱红，岳瑞雪，张毅，马晨，钮福祥. 超声辅助离子液体混合溶剂提取甘薯叶片多酚物质. 浙江农业科学. 2022(01): 16-19 . 百度学术
5. 吕子瀚，扈本荃，唐一梅，钟兰，郑立昊，赵祺祺. 烷基咪唑溴盐对金银花酚酸类成分提取的影响. 化工科技. 2022(06): 52-57 . 百度学术
6. 魏梓晴，王阿利，黄桂东，黄珍金，王子谦，蒋木培，钟先锋. 茶多酚活性膜的制备及应用进展. 食品研究与开发. 2021(24): 193-199 . 百度学术
其他类型引用(3)
计量
- 文章访问数: 143
- HTML全文浏览量: 17
- PDF下载量: 125
- 被引次数: 9
下载:
