基于RF-LSTM的鸡舍恶臭气体预测研究

Abstract
Figure/Table
References
Related Citation (4)

Download: PDF (1742 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract In this paper, the concentration of stench gas in chicken house was studied in order to construct prediction model. First, random forest (RF) algorithm was used to rank the importance of environmental variables that affect chicken house ammonia gas concentration, temperature, humidity, light, meteorological temperature and rainfall were selected as input variables of the model; Based on this, a model for predicting ammonia concentration in chicken houses based on long-term and short-term memory neural network (LSTM) was constructed. The prediction model proposed in this paper was applied to the ammonia concentration prediction of a chicken farm in Yixing experimental base of Jiangsu Province. The results were compared with LSTM model, RF-Elman model and RF-BP model. The results showed that the prediction effect based on RF-LSTM model was the best. The average absolute error (MAE), average absolute percentage error (MAPE) and root mean square error (RMSE) were 0.9183, 4.9637% and 1.4262, respectively. At the same time, in order to validate the performance of the model, the ammonia concentration prediction in chicken houses at different time scales was also realized. The average absolute errors (MAE) of ammonia prediction in advance of 2hours, 3hours, 4hours and 5hours were 1.6218, 2.1991, 2.8553 and 3.0677, respectively. The prediction model proposed in this paper improves the prediction accuracy of ammonia concentration in chicken houses, and provides scientific basis for reducing the odor emissions from chicken houses.

Key words： chicken house ammonia concentration random forest long short-term memory

Received: 08 November 2019

PACS:

X513

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	GUO Yu-chen
	YANG Liang
	LIU Chun-hong
	YE Rong-ke
	DUAN Qing-ling

Cite this article:

GUO Yu-chen,YANG Liang,LIU Chun-hong等. Prediction of stench gas in chicken house based on RF-LSTM[J]. CHINA ENVIRONMENTAL SCIENCECE, 2020, 40(7): 2850-2857.

URL:

http://www.zghjkx.com.cn/EN/ OR http://www.zghjkx.com.cn/EN/Y2020/V40/I7/2850

[1]	徐彬,魏凤仙,李绍钰.氨气的产生及其对肉鸡健康与生产性能的影响[J]. 中国家禽, 2018,40(7):1-5. Xu B, Wei F X, Li S Y. Production of ammonia and its effect on health and production performance of broiler chickens[J]. China Poultry, 2018,40(7):1-5.
[2]	周忠凯,朱志平,董红敏,等.笼养肉鸡生长过程NH3、N2O、CH4和CO2的排放[J]. 环境科学, 2013,34(6):2098-2106. Zhou Z K, Zhu Z P, Dong H M. NH3、N2O、CH4 and CO2 emissions from growing process of caged broilers[J]. Environmental Science, 2013,34(6):2098-2106.
[3]	介邓飞,魏萱,叶章颖,等.肉鸡密闭养殖箱的氨气排放检测方法[J]. 农业工程学报, 2015,31(22):235-239. Jie D F, Wei X, Ye Z Y, et al. Detection method of ammonia emissions from broiler chamber[J].Transactions of the CSAE, 2015,31(22):235-239.
[4]	孙瑞锋,李同树,步长英,等.影响肉鸡鸡粪产氨量相关因素的线性分析与氨气生成量的预测[C]//第十四次全国家禽科学学术讨论会, 2009. Sun R F, Li T S, Bu C Y, et al. Linear analysis of factors affecting ammonia production in broiler chicken manure and prediction of ammonia generation[C]//The 14th National Symposium on Poultry Science, 2009.
[5]	王晓宁,王世鹏,王新忠.风机通风作用下鸡舍内NH3浓度变化数学模型研究[J]. 安徽农业科学, 2008,36(14):5695,5746. Wang X N, Wang S P, Wang X Z. Study on mathematical model of NH3 concentration changes in henhouse under ventilation effect fan[J]. Journal of Anhui Agri. Sci., 2008,36(14):5695,5746.
[6]	王世鹏.鸡舍内NH3和CO2变化规律及机械通风下动态模型的研究[D]. 镇江:江苏大学, 2008. Wang S P. Study on the variation of NH3 and CO2 in chicken house and dynamic model under mechanical ventilation[D]. Zhengjiang:Jiangsu University, 2008.
[7]	许晨曦,李丽华,黄孟选,等.鸡舍环境参数实时监测预警系统的设计及应用[J]. 家畜生态学报, 2017,38(10):43-50. Xu C X, Li L H, Huang M X, et al. Design and application of environment monitoring and alarm system for chicken house parametres based on the internet[J]. Acta Ecologiae Animails Domastici, 2017,38(10):43-50.
[8]	Chen Y X, Xin H W, Li H, et al. Comparison of ammonia emissions from poultry houses based on diurnal integration vs. daily means of gas concentration and building ventilation rate[C]//The Ninth International Livestock Environment Sym posium (ILES IX), 2012.
[9]	白士宝,滕光辉,杜晓东,等.基于LabVIEW平台的蛋鸡舍环境舒适度实时监测系统设计与实现[J]. 农业工程学报, 2017,33(15):237-244. Bai S H, Teng G H Du X D, et al. Design and implementation on real-time monitoring system of laying hens environmental comfort based on LabVIEW[J]. Transactions of the CSAE, 2017,33(15):237-244.
[10]	Lima N D S, Garcia R G, Naas I A, et al. Model-predicted ammonia emission from two broiler houses with different rearing systems[J]. Scientia Agricola, 2015,72(5):393-399.
[11]	E F Wheeler, K D Casey, R S Gates, et a1. Ammonia emissions from twelve U.S. broiler chicken houses[J]. Transactions of the ASABE, 2006,49(5):1495-1512.
[12]	Roumeliotis T S, Dixon B J,Van Heyst B J. Characterization of gaseous pollutant and particulate matter emission rates from a commercial broiler operation part I:Observed trends in emissions[J]. Atmospheric Environment, 2010,44(31):3770-3777.
[13]	Bjerg B, Norton T, Banhazi T, et al. Modelling of ammonia emissions from naturally ventilated livestock buildings. Part 1:Ammonia release modeling[J]. Biosystems Engineering, 2013,116(3):232-245.
[14]	Liu Z, Wang L, D B Beasley, et a1. Modeling ammonia emissions from broiler litter at laboratory scale[J]. Transactions of the ASABE, 2009,52(5):1683-1694.
[15]	Breiman L. Random forests[J]. Machine Learning, 2001,45(1):5-32.
[16]	Adele Cutler, Richard Cutler D, John R Stevens. Random forests[J]. Ensemble Machine Learning, 2011:157-175.
[17]	宋荣杰,宁季锋,常庆瑞,等.基于小波纹理和随机森林的猕猴桃果园遥感提取[J]. 农业机械学报, 2018,49(4):222-231. Song R J, Ning J F, Chang Q R, et a1. Kiwfruit orchard maping based on wavelet textures and randomforest[J]. Transactions of the Chinese Society for Agricultural Machinnery, 2018,49(4):222-231.
[18]	姚登举,杨静,詹晓娟.基于随机森林的特征选择算法[J]. 吉林大学学报(工学版), 2014,44(1):137-141. Yao D J, Yang J, Shan X J. Feature selection algorithm based on random forest[J]. Journal of Jilin University (Engineering and Technology Edition), 2014,44(1):137-141.
[19]	陈强,蒋卫国,陈曦,等.基于支持向量回归模型的水稻田甲烷排放通量预测研究[J]. 环境科学, 2013,34(8):2876-2982. Chen Q, Jiang W G, Chen X, et a1. Prediction of methane emission of paddy field based on the support vector regression model[J]. Environmental Science, 2013,34(8):2876-2982.
[20]	Carolin Strobl, Anne-Laure Boulesteix, Thomas Kneib, et a1. Conditional variable importance for random forests[J]. BMC Bioinformatics, 2008,9(1):1-11.
[21]	王平,张红,秦作栋,等.基于wavelet-SVM的PM10浓度时序数据预测[J]. 环境科学, 2017,38(8):3153-3161. Wang P, Zhang H, Qin Z D, et a1. PM10 concentration forecasting model based on wavelet-SVM[J]. Environmental Science, 2017, 38(8):3153-3161.
[22]	Bedi J, Toshniwal D. Empirical mode decomposition based deep learning for electricity demand forecasting[J]. IEEE Access, 2018,6:49144-49156.
[23]	Sepp Hochreiter, Jurgen Schmidhuber, Fakultat fur Informatik, et al. Long Short-Term Memory[J]. Neural Computation, 1997,9(8):1735-1780.
[24]	陈英义,程倩倩,方晓敏,等.主成分分析和长短时记忆神经网络预测水产养殖水体溶解氧[J]. 农业工程学报, 2018,34(17):183-191. Chen Y Y, Cheng Q Q, Fang X M, et a1. Principal component analysis and long short-term memory neural network for predicting dissolved oxygen in water for aquaculture[J]. Transactions of the CSAE, 2018, 34(17):183-191.
[25]	肖璐,郎艺超,夏浪,等.基于多源数据的PM2.5浓度时空分布预测与制图[J]. 环境科学, 2017,38(12):4913-4923. Xiao L, Lang Y C, Xia L, et a1. Space-time estimations and mapping of PM2.5 fine particulates based on multi-source data[J]. Environmental Science, 2017,38(12):4913-4923.