基于VAR模型的蛋鸡产蛋性能及其影响因素分析

doi:10.3969/j.issn.1004-1524.2022.04.19

浙江农业学报 ›› 2022, Vol. 34 ›› Issue (4): 824-830.DOI: 10.3969/j.issn.1004-1524.2022.04.19

基于VAR模型的蛋鸡产蛋性能及其影响因素分析

吉训生¹(), 黄琪琳¹^,^*(), 夏圣奎²

1.江南大学物联网工程学院,江苏无锡 214122
2.南通天成现代农业科技有限公司,江苏南通 226000

收稿日期:2020-11-02 出版日期:2022-04-25 发布日期:2022-04-28
通讯作者: 黄琪琳
作者简介:*黄琪琳,E-mail: qilin_h@yeah.net
吉训生(1969—),男,江苏海安人,博士,教授,主要从事微弱信号处理方面的研究。E-mail: jixunsheng@163.com
基金资助:
国家自然科学基金(617712223);江苏省重点研发计划(BE2018334)

Analysis of laying performance and influencing factors of laying hens based on VAR model

JI Xunsheng¹(), HUANG Qilin¹^,^*(), XIA Shengkui²

1. College of Internet of Things Engineering, Jiangnan University, Wuxi 214122, Jiangsu, China
2. Nantong Tiancheng Modern Agricultural Technology Co., Ltd., Nantong 226000, Jiangsu, China

Received:2020-11-02 Online:2022-04-25 Published:2022-04-28
Contact: HUANG Qilin

摘要/Abstract

摘要：

蛋鸡产蛋性能指标包括产蛋率和合格鸡蛋的平均蛋重,该性能受蛋鸡个体、饲养管理、养殖环境、疫病等诸多因素影响。研究各因素对产蛋性能的影响及其时延效果对蛋鸡养殖过程管理十分重要。将蛋鸡的采食、饮水、环境温度和湿度作为主要影响因素,建立向量自回归(vector auto-regressive, VAR)模型,实现了产蛋率的中短期预测,预测准确率达98.6%。在该模型基础上,分析得出对产蛋率影响最大的是环境温度,影响持续3~4 d,并在第1天达到高峰;采食量对平均蛋重影响最大,影响持续4~5 d,也是在第1天达到高峰。

关键词: 产蛋性能, VAR模型, 脉冲响应, 方差分解

Abstract:

The laying performance indicators of laying hens include laying rate and average egg weight of qualified eggs. The laying performance of laying hens is affected by many factors such as the individual laying hens, feeding management, breeding environment, disease and other factors. It is very important to study the influence of various factors on laying performance and its time delay effect for laying hen breeding. A vector auto-regressive (VAR) model was established with laying hens’ feeding, drinking water, environmental temperature and humidity as the main influencing factors to realize the medium and short-term prediction of egg production rate. The prediction accuracy rate was 98.6%. Based on this model, the analysis showed that the environmental temperature had the greatest impact on the laying rate of laying hens and the impact lasted for 3-4 days and reached the peak on the first day. The food intake had the greatest impact on the average egg weight and the impact lasted for 4-5 days, also peaking on the first day.

Key words: laying performance, VAR model, impulse response, variance decomposition

中图分类号:

S831

吉训生, 黄琪琳, 夏圣奎. 基于VAR模型的蛋鸡产蛋性能及其影响因素分析[J]. 浙江农业学报, 2022, 34(4): 824-830.

JI Xunsheng, HUANG Qilin, XIA Shengkui. Analysis of laying performance and influencing factors of laying hens based on VAR model[J]. Acta Agriculturae Zhejiangensis, 2022, 34(4): 824-830.

图/表 8

图1 完整产蛋周期的产蛋率、日均采食量和日均饮水量 a,产蛋率; b, 日均采食量; c, 日均饮水量。

Fig.1 Laying rate, average daily feed intake and average daily water intake for the complete laying cycle a, Laying rate; b, Average daily feed intake; c, Average daily water intake.

图2 2019-07-16至2019-12-16室内最高温湿度变化趋势 a,日最高温度;b,日最高湿度。

Fig.2 Indoor maximum temperature and humidity changes from 2019-07-16 to 2019-12-16 a, Indoor maximum temperature; b, Indoor maximum humidity.

图3 产蛋率预测流程图

Fig.3 Flow chart of laying rate prediction

表1 不同滞后阶数的VAR模型的预测结果

Table 1 The prediction results of the VAR model with different lag orders

Lag order	AIC	FPEC	HQC	MAPE/%	MSE
0	-19.57	3.174×10^-9	-19.51	1.749	2.417
1	-20.14	1.797×10^-9	-19.80	1.680	2.322
2	-20.43^*	1.345×10^-9*	-19.81^*	1.376^*	1.825^*
3	-20.41	1.404×10^-9	-19.49	1.990	2.460
4	-20.39	1.469×10^-9	-19.19	1.696	2.294

图4 基于VAR模型的蛋鸡产蛋率预测结果

Fig.4 Prediction of laying rate of laying hens based on VAR model

表2 不同模型的预测结果

Table 2 Forecast results of different models

模型Models	精度Precision/%	MAPE/%	MSE
ARIMA	97.8	2.17	0.060
BP Neural Networks	98.5	1.46	0.022
SVM	97.9	2.06	0.058
LSTM	98.6	1.32	0.016
VAR	98.6	1.37	0.018

图5 脉冲响应结果 a,4个因素对产蛋率的脉冲响应;b,4个因素对平均蛋重的脉冲响应。

Fig.5 Impulse response results a, Impulse response results of laying rate; b, Impulse response results of egg weight.

图6 方差分解结果 a, 产蛋率的方差分解;b, 平均蛋重的方差分解。

Fig.6 Variance decomposition results a, Variance decomposition results of laying rate; b, Variance decomposition results of egg weight.

参考文献 16

[1]	于琦, 李华. 中国蛋鸡产业现状及发展思路[J]. 农业展望, 2018, 14(4): 32-37.
	YU Q, LI H. Status quo and development ideas of China’s layer industry[J]. Agricultural Outlook, 2018, 14(4): 32-37. (in Chinese with English abstract)
[2]	王海涛. 蛋鸡产蛋率影响因素及提高措施[J]. 畜禽业, 2019, 30(4): 31.
	WANG H T. Influencing factors and improving measures of laying hen egg production rate[J]. Livestock and Poultry Industry, 2019, 30(4): 31. (in Chinese)
[3]	刘先旺, 李华龙, 李淼, 等. 基于CS和BP的鸡舍环境与产蛋性能关系模型研究[J]. 江苏农业科学, 2019, 47(11): 267-270.
	LIU X W, LI H L, LI M, et al. Study on relationship model between chicken house environment and egg production performance based on CS and BP[J]. Jiangsu Agricultural Sciences, 2019, 47(11): 267-270. (in Chinese with English abstract)
[4]	李飞, 蒋敏兰. 基于支持向量机回归的蛋鸡产蛋率预测模型[J]. 江苏农业科学, 2019, 47(13): 249-252.
	LI F, JIANG M L. Prediction model of laying rate based on support vector machine regression[J]. Jiangsu Agricultural Sciences, 2019, 47(13): 249-252. (in Chinese with English abstract)
[5]	李飞, 蒋敏兰. 基于极限学习机的蛋鸡产蛋性能预测[J]. 中国家禽, 2019, 41(2): 62-64.
	LI F, JIANG M L. Prediction of laying performance of laying hens based on extreme learning machine[J]. China Poultry, 2019, 41(2): 62-64. (in Chinese with English abstract)
[6]	李飞. 机器学习在鸡蛋产量预测与品质检测中的应用[D]. 金华: 浙江师范大学, 2019.
	LI F. Application of machine learning in egg yield prediction and quality detection[D]. Jinhua: Zhejiang Normal University, 2019. (in Chinese with English abstract)
[7]	OMOMULE T G, DE AJAYI O O, OROGUN A O. Fuzzy prediction and pattern analysis of poultry egg production[J]. Computers and Electronics in Agriculture, 2020, 171: 105301. DOI URL
[8]	AHMAD H A. Poultry growth modeling using neural networks and simulated data[J]. Journal of Applied Poultry Research, 2009, 18(3): 440-446. DOI URL
[9]	AHMAD H A. Egg production forecasting: determining efficient modeling approaches[J]. Journal of Applied Poultry Research, 2011, 20(4): 463-473. DOI URL
[10]	FELIPE V P S, SILVA M A, VALENTE B D, et al. Using multiple regression, Bayesian networks and artificial neural networks for prediction of total egg production in European quails based on earlier expressed phenotypes[J]. Poultry Science, 2015, 94(4): 772-780. DOI URL
[11]	黄红梅. 应用时间序列分析[M]. 北京: 清华大学出版社, 2016: 188.
[12]	LI Y J, YUAN X L, XU J Y, et al. Medium-term forecasting of cold, electric and gas load in multi-energy system based on VAR model[C]// 2018 13th IEEE Conference on Industrial Electronics and Applications (ICIEA). May 31-June 2, 2018, Wuhan, China. IEEE, 2018: 1676-1680.
[13]	郑莉, 段冬梅, 陆凤彬, 等. 我国猪肉消费需求量集成预测: 基于ARIMA、VAR和VEC模型的实证[J]. 系统工程理论与实践, 2013, 33(4): 918-925. DOI
	ZHENG L, DUAN D M, LU F B, et al. Integration forecast of Chinese pork consumption demand: empirical based on ARIMA, VAR and VEC models[J]. Systems Engineering-Theory & Practice, 2013, 33(4): 918-925. (in Chinese with English abstract)
[14]	张延群. 向量自回归模型的理论方法及应用实例[M]. 北京: 中国社会科学出版社, 2013: 4-5.
[15]	郭学伟. 蛋鸡产蛋高峰期的科学管理[J]. 中国畜禽种业, 2020, 16(9): 188.
	GUO X W. Scientific management during the peak period of laying hens[J]. The Chinese Livestock and Poultry Breeding, 2020, 16(9): 188. (in Chinese)
[16]	张海林. 蛋鸡蛋重的影响因素和控制措施[J]. 现代畜牧科技, 2020(5): 29-30.
	ZHANG H L. Influencing factors and control measures of egg weight[J]. Modern Animal Husbandry Science & Technology, 2020(5): 29-30. (in Chinese)

基于VAR模型的蛋鸡产蛋性能及其影响因素分析

Analysis of laying performance and influencing factors of laying hens based on VAR model

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 16

相关文章 6

编辑推荐

Metrics

本文评价

[1]	张菁菁1，沈根明2，华国浩3，杨建生3，林雨鑫1，3，安婷婷1，戴国俊1，*，宋申申1. 高温应激下添加维生素E对蛋鸡血液生化指标和产蛋性能的影响[J]. 浙江农业学报, 2016, 28(2): 228-.
[2]	吴琪, 蔡勋, 冯中朝. 中加油菜籽期货与现货价格动态关系研究[J]. 浙江农业学报, 2016, 28(10): 1796-1802.
[3]	李敬锁a，王晓雷b，牟少岩a，*. 农业科技计划投入与农业经济增长关系的实证研究——以青岛市为例[J]. 浙江农业学报, 2015, 27(7): 1288-.
[4]	黄江南;韦启鹏;王德前;刘林秀;谢金防;田勇;卢立志;*. 不同饲养方式对蛋鸭产蛋性能的影响及其机制[J]. , 2013, 25(4): 0-723.
[5]	曾涛;李国勤;王德前;李进军;田勇;陈黎;黄爱霞;石放雄;;沈军达;陶争荣;卢立志;. 热休克蛋白70基因（HSP70）部分片段的单核苷酸多态性及其与蛋鸭产蛋性能的关联性[J]. , 2013, 25(2): 0-234.
[6]	邹晓庭;马玉龙;许梓荣. 碘化酪蛋白对蛋鸡产蛋性能的影响及作用机理[J]. , 2001, 13(02): 0-90.