CN113033890A - Method for analyzing laying performance of laying hens based on vector autoregressive model - Google Patents
Method for analyzing laying performance of laying hens based on vector autoregressive model Download PDFInfo
- Publication number
- CN113033890A CN113033890A CN202110299017.1A CN202110299017A CN113033890A CN 113033890 A CN113033890 A CN 113033890A CN 202110299017 A CN202110299017 A CN 202110299017A CN 113033890 A CN113033890 A CN 113033890A
- Authority
- CN
- China
- Prior art keywords
- laying
- data
- temperature
- model
- performance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims description 40
- 230000000694 effects Effects 0.000 claims abstract description 19
- 241000287828 Gallus gallus Species 0.000 claims abstract description 11
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 8
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 230000004044 response Effects 0.000 claims abstract description 5
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 235000013601 eggs Nutrition 0.000 claims description 36
- 230000017448 oviposition Effects 0.000 claims description 22
- 235000021050 feed intake Nutrition 0.000 claims description 13
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 13
- 230000036750 egg laying performance Effects 0.000 claims description 11
- 230000004083 survival effect Effects 0.000 claims description 9
- 238000004519 manufacturing process Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000009395 breeding Methods 0.000 abstract description 8
- 230000001488 breeding effect Effects 0.000 abstract description 8
- 238000013135 deep learning Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 5
- 235000021316 daily nutritional intake Nutrition 0.000 description 4
- 238000003066 decision tree Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 238000005286 illumination Methods 0.000 description 4
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 4
- 238000007418 data mining Methods 0.000 description 3
- 230000001976 improved effect Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 210000003608 fece Anatomy 0.000 description 2
- 239000010871 livestock manure Substances 0.000 description 2
- 230000008092 positive effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241001123248 Arma Species 0.000 description 1
- 241000282414 Homo sapiens Species 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 235000012000 cholesterol Nutrition 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 230000000378 dietary effect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000035622 drinking Effects 0.000 description 1
- 239000003651 drinking water Substances 0.000 description 1
- 235000020188 drinking water Nutrition 0.000 description 1
- 230000001584 effect on egg Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000037406 food intake Effects 0.000 description 1
- 235000012631 food intake Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 230000000050 nutritive effect Effects 0.000 description 1
- 244000144977 poultry Species 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000013112 stability test Methods 0.000 description 1
- 230000002311 subsequent effect Effects 0.000 description 1
- 238000001744 unit root test Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Biophysics (AREA)
- Educational Administration (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Primary Health Care (AREA)
- Mining & Mineral Resources (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the field of laying hen breeding, in particular to a laying hen performance analysis method based on a vector autoregressive model, which aims at the problems that the existing deep learning has higher requirements on data size and is not suitable for the prediction of a small sample time sequence, and provides the following scheme, comprising the following steps: s1, collecting historical laying rate data and historical laying rate influence factor data of laying hens in a modern chicken house; s2, preprocessing the data: the outlier is removed, interpolation filling is carried out on missing data, stability detection is carried out on the data, S3, a VAR model is estimated, future laying rate is predicted, S4, influence degree and time delay effect of influence factors on laying performance are analyzed through impulse response and variance decomposition, and the laying rate prediction model based on the vector autoregressive model has good prediction and analysis performance, high stability and reliability and popularization value.
Description
Technical Field
The invention relates to the technical field of laying hen breeding, in particular to a laying hen performance analysis method based on a vector autoregressive model.
Background
The eggs are high in nutritive value, rich in cholesterol and protein, and are one of the common foods for human beings. China is a big country for livestock breeding and export, and is also the largest poultry egg production and consumption country in the world. In recent years, the laying hen industry is gradually transformed and upgraded to digitalization under the support of various national policies. Under the automatic development of cultivation, the stacked layer type layer cage cultivation mode is widely accepted by a large number of layer farms, the cultivation mode is small in occupied area and high in space utilization rate, the chicken manure is cleaned in a layered mode, the utilization rate of the chicken manure can be improved, and the pollution degree of the environment is reduced. Meanwhile, the labor intensity is reduced, and the production efficiency is improved. In order to get rid of the dependence of the breeding environment on the outside climate, the chicken house type in China is basically changed from the initial open type chicken house to the closed type stacked chicken house. With the expansion of the laying hen breeding scale, risks faced by laying hen farmers are larger, laying hen benefits are low, laying hen epidemic diseases bring great economic losses to the laying hen farmers, and data mining refers to a process of searching information hidden in a large amount of data through an algorithm. Data mining, which is a nontrivial process that reveals implicit, previously unknown, and potentially valuable information from large amounts of data, is a hot problem for research in the fields of artificial intelligence and databases. Data mining is a decision support process, and the data of enterprises are analyzed highly automatically, inductive reasoning is made, potential patterns are mined out, and a decision maker is helped to adjust market strategies, reduce risks and make correct decisions.
On one hand, the time series prediction is a regression prediction method, which belongs to quantitative prediction and has the basic principle that on the one hand, the continuity of the development of things is admitted, and the development trend of things is estimated by using the past time series data for statistical analysis; on the other hand, randomness caused by accidental factors is fully considered, and in order to eliminate the influence caused by random fluctuation, statistical analysis is carried out by using historical data, and the data is appropriately processed to carry out trend prediction.
Researchers developed a plurality of time series prediction models since the last century, and the linear models are typical, such as ARMA, GARCH, ETS, SSM and the like, and are widely applied in the fields of engineering control, finance and the like. In recent years, with the development of deep learning research, many scholars convert the time series prediction problem into the supervised learning problem, and adopt the bp neural network model for prediction to obtain good effect, but deep learning has high requirements on data volume and is not suitable for prediction of small sample time series.
Disclosure of Invention
The invention aims to solve the defects that deep learning has high requirements on data volume and is not suitable for prediction of a small sample time sequence in the prior art, and provides a method for analyzing the laying performance of laying hens based on a vector autoregressive model.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for analyzing laying performance of laying hens based on a vector autoregressive model comprises the following steps:
s1, collecting historical egg laying data and historical egg laying influence factor data of laying hens in a modern chicken house;
s2, preprocessing the data;
s3, estimating a VAR model, and predicting future laying rate;
and S4, analyzing the influence degree and the time delay effect of the influence factors on the egg laying performance through impulse response and variance decomposition.
Preferably, in S1, the egg laying data includes egg laying rate and average egg weight, the influencing factors include egg laying rate, egg laying amount, egg laying day age, indoor temperature and indoor humidity, and the egg laying rate collecting method includes: dividing the total egg yield of the laying hens per day by the survival number of the laying hens to obtain the daily average egg laying rate, wherein the average egg weight is acquired by dividing the total weight of qualified eggs per day of the laying hens by the number of the qualified eggs.
Preferably, the method for collecting the feed intake of the laying hens comprises the following steps: dividing the total daily feed intake of the laying hens by the survival number of the laying hens to obtain the daily feed intake of each laying hen.
Preferably, the method for collecting the water collected by the laying hens comprises the following steps: dividing the total daily water collection of the laying hens by the survival number of the laying hens to obtain the daily water collection of each laying hen.
Preferably, the temperature acquisition method comprises: the method comprises the following steps of collecting the highest temperature, the lowest temperature and the average temperature of the henhouse on the day, wherein the humidity collection method comprises the following steps: the maximum humidity, minimum humidity and average humidity of the henhouse on the day were collected.
Preferably, the S2 is specifically: and removing outliers, carrying out interpolation filling on missing data, carrying out stability detection on the data, and carrying out differential processing on unstable data until the data are stable.
Preferably, the S3 is specifically: before a VAR model is established, a hysteresis order p needs to be determined, the hysteresis order is determined according to AIC, FPEC and HQC detection criteria, an unconstrained VAR model is established, the stability of the model is checked by calculating the sum of residual errors, if the sum of the residual errors fluctuates in a stable interval, the result shows that the model is stable, and the final prediction result is obtained after the obtained prediction value is subjected to inverse difference processing.
Preferably, the S4 is specifically: and performing pulse correspondence and variance decomposition analysis on the obtained model, visualizing the obtained result in a drawing and tabulating mode and the like, and visually presenting the influence degree and the time delay effect of each influence factor on the egg laying performance to a breeder.
Preferably, the indoor temperature is collected through sensors, the number of the sensors is 5, the 5 sensors respectively collect the indoor temperatures of five positions, the data collected by the five sensors are all transmitted to a control center, the data are analyzed, the five highest temperature data and the five lowest temperature data are extracted, if the difference between the five highest temperature data is not greater than 2 ℃, the maximum value of the highest temperature data is taken as the highest temperature, similarly, the lowest value of the five lowest temperature data is taken as the lowest temperature data, if the data difference is greater than 2 ℃, the average value of the five highest temperature data is taken as the highest temperature, the average value of the five lowest temperature data is taken as the lowest temperature, the precision of data collection is further improved, and the humidity data can be collected in the same manner.
Preferably, the five positions are the four-side position and the central position respectively, 5 sensors are arranged at the five positions respectively, the 5 sensors are marked simultaneously, when the control center receives data transmitted by the sensors, the control center classifies the data according to the marks simultaneously, the data are divided into five groups, the data collected at the same time are analyzed, and a temperature curve graph is formulated for observing temperature changes.
Compared with the prior art, the invention has the beneficial effects that:
the method is based on a vector autoregressive model, the historical laying rate and the influence factors are used as input samples of the VAR, the model is estimated and analyzed to obtain various data of a future day, a vector autoregressive-based laying rate prediction model of the laying hens is established and provided for the first time, the laying rate is predicted through the model, the influence degree and the time delay effect of the influence factors in the historical data on the laying performance are analyzed, and in order to further evaluate the performance of the VAR laying rate prediction model, an ARIMA (1, 1) model, a BP neural network model and a decision tree regression model are respectively established and compared with the model. The precision of the VAR model is higher than that of ARIMA, BP neural network and decision tree regression models, and in conclusion, the VAR model can better simulate the relation between each variable and the egg laying performance.
The method has good prediction performance on the laying rate of the laying hens and quantitative analysis performance on influence factors, and has reliability and popularization value.
Drawings
FIG. 1 is a flow chart of a method for analyzing laying performance of laying hens based on a vector autoregressive model according to the present invention;
FIG. 2 is a pulse corresponding result diagram of the method for analyzing laying performance of laying hens based on the vector autoregressive model;
FIG. 3 is a diagram of a result of variance decomposition of the method for analyzing laying hen laying performance based on the vector autoregressive model.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments.
Referring to fig. 1-3, a method for analyzing laying performance of laying hens based on a vector autoregressive model comprises the following steps:
s1, collecting historical laying performance data and historical laying rate influence factor data of laying hens in the modern chicken house. Egg laying performance includes laying rate and average egg weight; factors influencing the egg laying performance of the laying hens comprise feed intake of the laying hens, water intake, age (day) of the laying hens, indoor temperature, indoor humidity, illumination duration and illumination intensity. The applicant cooperates with a limited company of modern agriculture science and technology in Nantong City of Jiangsu province. The modern breeding mode is adopted in the breeding of the company, and full-automatic feeding and drinking and automatic egg picking are realized. From the beginning of laying eggs of each batch of laying hens to the elimination, the egg laying data of the laying hens in the whole egg laying period and external influencing factors are recorded and analyzed in a mode of uploading data in real time by a sensor and manually checking.
Because the number of laying hens in each henhouse is different and the laying hens die naturally in the investigation process, the egg yield is acquired by dividing the total egg yield of the laying hens per day by the survival number of the laying hens on the day to obtain the daily average egg yield. The average egg weight is acquired by dividing the total weight of qualified eggs of the laying hens per day by the number of the qualified eggs to obtain the daily average egg weight. The method for collecting the feed intake of the laying hens comprises the step of dividing the total feed intake of the laying hens in each day by the survival number of the laying hens in the same day to obtain the daily average feed intake. The method for collecting the water collection amount of the laying hens comprises the step of dividing the total water collection amount of the laying hens in each day by the survival number of the laying hens in the same day to obtain the daily average water collection amount. Because the illumination condition of the henhouse is kept unchanged according to the breeding standard, the application ignores the factor of illumination intensity, which influences the laying rate. The method for collecting the temperature in the henhouse comprises the steps of recording the temperature in the henhouse every 2 minutes through a temperature sensor, and obtaining the highest temperature, the lowest temperature and the average temperature through statistics. The humidity in the henhouse is acquired by recording the humidity in the henhouse every 2 minutes through a humidity sensor and obtaining the highest humidity, the lowest humidity and the average humidity through statistics. The above are all the required data, the indoor temperature is collected by the sensors, the number of the sensors is 5, the 5 sensors respectively collect the temperature of five indoor positions, the data collected by the five sensors are all transmitted to the control center, the data are analyzed, the highest five temperature data and the lowest five temperature data are extracted, if the difference between the highest temperature data is not more than 2 ℃, the maximum value in the highest temperature data is taken as the highest temperature, similarly, the lowest value in the five lowest temperature data is taken as the lowest temperature data, if the data difference is more than 2 ℃, the average value of the five highest temperature data is taken as the highest temperature, the average value of the five lowest temperature data is taken as the lowest temperature, the five positions are respectively the surrounding position and the central position, and the 5 sensors are respectively arranged at the five positions, the 5 sensors are marked simultaneously, the control center classifies the data according to the marks when receiving the data transmitted by the sensors, the data are divided into five groups, the data collected at the same time are analyzed, and a temperature curve graph is formulated for observing temperature changes.
S2, preprocessing the data: and removing outliers and carrying out interpolation filling on missing data. According to the requirement of the model on data stability, a unit root test (ADF) is selected to carry out stability test on the variables. The ADF inspection shows that the original data is not stable, and the data is subjected to differential processing in order to eliminate the severe fluctuation of the data. All data were first differentiated to reject the original hypothesis to plateau at a significance level of 10%.
S3, estimating a VAR model, and predicting future laying rate: the hysteresis order p needs to be determined before the VAR model is built. Increasing the p-value can ensure that the residuals of the VAR model are not self-correlated. The increase of the lag order can cause the increase of the parameters to be estimated, which directly influences the effectiveness of model parameter estimation. The results of model prediction with different hysteresis orders are shown in table 1 (optimal) according to AIC, FPEC, HQC detection criteria by unconstrained VAR model. Therefore, the hysteresis order can be determined to be 2.
Table 1 prediction results of VAR models of different hysteresis orders:
and (3) constructing a VAR (2) model for analysis, checking the stability of the model by calculating the accumulated sum of residual errors, wherein the accumulated sum of residual errors fluctuates in a stable interval, and the result shows that the model is stable and the laying rate and all variables have long-term equilibrium relation. Variable exogenesis tests are further performed, and the results show that the overall granger test of each decomposition equation of VAR rejects the original hypothesis at a significant level of 10%, indicating that the combination of variables has a causal relationship with egg production. The experiment adopts the data modeling of 7-11 months of Tiancheng No. 5 commercial chicken to predict the egg laying performance of 12 months. To further evaluate the performance of the VAR laying rate prediction model, ARIMA (1, 1) model, BP neural network model, and decision tree regression model were established separately and compared. The Mean Absolute Percentage Error (MAPE) and Mean Square Error (MSE) were chosen as evaluation criteria for the experiment. The results are shown in table 2, the precision of the VAR model is higher than that of the ARIMA, BP neural network and decision tree regression model, and the VAR model can better simulate the relationship between each variable and egg laying performance.
TABLE 2 prediction results of different models
S4, impulse response and variance decomposition analysis: in order to study the influence of each factor on the average egg weight, the laying rate is changed into the average egg weight, the process is repeated, a VAR model with the average egg weight as the main output is constructed to analyze the continuous influence of each factor on the VAR model, and fig. 2 is a pulse response result graph of the two models. As can be seen from fig. 2, the effect of the maximum indoor temperature on the laying rate is most remarkable, the effect of the increase of the factor on the laying rate of the laying hens is negative overall, the effect reaches a peak on day 1, the duration is 3-4 days, and the effect is gradually weakened. The rising of the indoor highest temperature also has negative influence on the average egg weight, the influence effect reaches a peak in day 1, the duration is 4-5 days, and the influence is gradually weakened later. The indoor maximum humidity of the henhouse is negatively related to the laying rate of the laying hens and the average egg weight, but the influence effect is small compared with the maximum temperature and the feed intake, the influence on the laying rate lasts for only 1-2 days, and the influence on the egg weight lasts for about 5 days. The effect of the average daily food intake on the average egg weight is most obvious, the increase of the average daily food intake has positive effect on the average egg weight, the effect on the laying rate reaches a peak on day 1, the effect lasts for 4-5 days, and the subsequent effect is gradually weakened. The increase of daily food intake has positive effect on the egg laying rate of the laying hens, the effect on the egg laying rate reaches a peak at day 1, the effect lasts for only 1-2 days,
the result of the anova is shown in fig. 3. As can be seen from fig. 3, the contribution rates of the factors substantially stabilized on day 6, and the contribution rates were, in order from the highest daily temperature (about 0% to 3%), the average daily food intake (about 0% to 2%), the average daily water intake (about 0% to 2%) and the highest daily humidity (about 0% to 1.2%) except for the contribution rate of the laying rate itself (about 100% to 90%). Among the environmental factors of temperature and humidity, the influence of temperature on the laying rate is much higher than the influence of humidity on the laying rate. The influence degree of the intake and drinking water on the laying rate is relatively similar. Of the four factors, temperature has the greatest effect on egg production and, therefore, it is important to control the temperature of the chicken house. For the egg weight, the contribution degrees are, in order from large to small, daily average food intake (about 0% to 1.6%), daily average water intake (about 0% to 1.3%), daily maximum temperature (about 0% to 0.2%) and daily maximum humidity (about 0% to 0.1%), except for the contribution rate of the egg weight itself (about 100% to 90%). Dietary factors have much greater influence on egg weight than environmental factors. Therefore, the improvement of the nutrition of the feed is more helpful for improving the quality of the eggs.
In conclusion, the egg laying rate prediction model based on vector autoregressive has good predictive performance, and the influence of various factors on the egg laying performance can be quantitatively analyzed, so that valuable suggestions can be provided for breeders through analysis.
By utilizing the established vector autoregression-based egg laying rate prediction analysis method, the future egg laying rate of the egg laying hens is predicted and analyzed according to the influence factors, and the future change of the egg laying rate index of the egg laying hens, the influence degree of each factor on the egg laying performance and the time delay effect are obtained.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and equivalent alternatives or modifications according to the technical solution and the inventive concept of the present invention should be covered by the scope of the present invention.
Claims (10)
1. A method for analyzing laying performance of laying hens based on a vector autoregressive model is characterized by comprising the following steps:
s1, collecting historical egg laying data and historical egg laying influence factor data of laying hens in a modern chicken house;
s2, preprocessing the data;
s3, estimating a VAR model, and predicting future laying rate;
and S4, analyzing the influence degree and the time delay effect of the influencing factors on the egg laying performance through impulse response and variance decomposition.
2. The method for analyzing laying performance of laying hens based on the vector autoregressive model of claim 1, wherein in the step S1, laying data includes laying rate and average egg weight, influence factors include laying rate feed intake, laying rate water intake, laying date age, indoor temperature and indoor humidity, and the laying rate is acquired by: dividing the total egg yield of the laying hens per day by the survival number of the laying hens to obtain the daily average egg laying rate, wherein the average egg weight is acquired by dividing the total weight of qualified eggs per day of the laying hens by the number of the qualified eggs.
3. The method for analyzing laying hen feed intake performance based on the vector autoregressive model of claim 2, wherein the method for collecting the feed intake of the laying hen comprises the following steps: dividing the total daily feed intake of the laying hens by the survival number of the laying hens to obtain the daily feed intake of each laying hen.
4. The method for analyzing laying hen egg production performance based on the vector autoregressive model of claim 2, wherein the method for collecting the water collection amount of the laying hen is as follows: dividing the total daily water collection of the laying hens by the survival number of the laying hens to obtain the daily water collection of each laying hen.
5. The method for analyzing laying hen performance based on the vector autoregressive model as claimed in claim 2, wherein the temperature collection method comprises: the method comprises the following steps of collecting the highest temperature, the lowest temperature and the average temperature of the henhouse on the day, wherein the humidity collection method comprises the following steps: the highest humidity, the lowest humidity and the average humidity of the henhouse on the day were collected.
6. The method for analyzing laying hen performance based on vector autoregressive model of claim 1, wherein the step S2 specifically comprises: and (4) removing outliers, carrying out interpolation filling on missing data, carrying out stability detection on the data, and carrying out differential processing on unstable data until the data are stable.
7. The method for analyzing laying hen performance based on vector autoregressive model of claim 1, wherein the step S3 specifically comprises: before a VAR model is established, a hysteresis order p needs to be determined, the hysteresis order is determined according to AIC, FPEC and HQC detection criteria, an unconstrained VAR model is established, the stability of the model is checked by calculating the sum of residual errors, if the sum of the residual errors fluctuates in a stable interval, the result shows that the model is stable, and the final prediction result is obtained after the obtained prediction value is subjected to inverse difference processing.
8. The method for analyzing laying hen performance based on vector autoregressive model of claim 1, wherein the step S4 specifically comprises: and performing pulse correspondence and variance decomposition analysis on the obtained model, visualizing the obtained result in a drawing and tabulating mode and the like, and visually presenting the influence degree and the time delay effect of each influence factor on the egg laying performance to a breeder.
9. The method for analyzing laying performance of laying hens based on the vector autoregressive model as claimed in claim 2, wherein the indoor temperature is collected by sensors, the number of the sensors is 5, the 5 sensors respectively collect the temperature of five positions in the room, the data collected by the five sensors are all transmitted to the control center, the data are analyzed, the highest five temperature data and the lowest five temperature data are extracted, if the difference between each highest temperature data is not greater than 2 ℃, the maximum value in the highest temperature data is taken as the highest temperature, and similarly, the lowest value in the five lowest temperature data is taken as the lowest temperature data, if the difference between the data is greater than 2 ℃, the average value of the five highest temperature data is taken as the highest temperature, and the average value of the five lowest temperature data is taken as the lowest temperature.
10. The method as claimed in claim 9, wherein the five positions are the four-around position and the central position, the 5 sensors are respectively disposed at the five positions, the 5 sensors are labeled, the control center classifies the data according to the labels when receiving the data transmitted by the sensors, the data are divided into five groups, the data collected at the same time are analyzed, and a temperature curve graph is prepared for observing temperature changes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110299017.1A CN113033890A (en) | 2021-03-20 | 2021-03-20 | Method for analyzing laying performance of laying hens based on vector autoregressive model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110299017.1A CN113033890A (en) | 2021-03-20 | 2021-03-20 | Method for analyzing laying performance of laying hens based on vector autoregressive model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113033890A true CN113033890A (en) | 2021-06-25 |
Family
ID=76472076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110299017.1A Pending CN113033890A (en) | 2021-03-20 | 2021-03-20 | Method for analyzing laying performance of laying hens based on vector autoregressive model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113033890A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114593411A (en) * | 2022-02-28 | 2022-06-07 | 中国大唐集团科学技术研究院有限公司西北电力试验研究院 | Water supply control method and system for optimizing direct current furnace based on vector autoregression water-coal ratio |
| CN115979339A (en) * | 2022-12-07 | 2023-04-18 | 吉林农业科技学院 | Laying hen breeding environment intelligent supervision system based on big data analysis |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106872658A (en) * | 2017-01-22 | 2017-06-20 | 华南理工大学 | A kind of method of the COD of sewage load prediction based on vector time series model |
| RU2648149C1 (en) * | 2017-01-10 | 2018-03-22 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Кубанский государственный аграрный университет имени И.Т. Трубилина" | Method for predicting the egg productivity in hens |
| CN109034466A (en) * | 2018-07-16 | 2018-12-18 | 浙江师范大学 | A kind of laying rate of laying hen prediction technique based on Support vector regression |
| CN111191193A (en) * | 2020-01-17 | 2020-05-22 | 南京工业大学 | Long-term soil temperature and humidity high-precision prediction method based on autoregressive moving average model |
| CN111985714A (en) * | 2020-08-19 | 2020-11-24 | 山东省齐鲁大数据研究院 | Pork price prediction method and system based on correlation analysis and machine learning |
-
2021
- 2021-03-20 CN CN202110299017.1A patent/CN113033890A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2648149C1 (en) * | 2017-01-10 | 2018-03-22 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Кубанский государственный аграрный университет имени И.Т. Трубилина" | Method for predicting the egg productivity in hens |
| CN106872658A (en) * | 2017-01-22 | 2017-06-20 | 华南理工大学 | A kind of method of the COD of sewage load prediction based on vector time series model |
| CN109034466A (en) * | 2018-07-16 | 2018-12-18 | 浙江师范大学 | A kind of laying rate of laying hen prediction technique based on Support vector regression |
| CN111191193A (en) * | 2020-01-17 | 2020-05-22 | 南京工业大学 | Long-term soil temperature and humidity high-precision prediction method based on autoregressive moving average model |
| CN111985714A (en) * | 2020-08-19 | 2020-11-24 | 山东省齐鲁大数据研究院 | Pork price prediction method and system based on correlation analysis and machine learning |
Non-Patent Citations (2)
| Title |
|---|
| 中国票据研究中心: "《中国票据市场》", 31 July 2020, 中国金融出版社, pages: 27 - 30 * |
| 孙万鑫，薛镇: "基于VAR 模型分析GDP 对钢材产量的影响", 特区经济, pages 118 - 120 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114593411A (en) * | 2022-02-28 | 2022-06-07 | 中国大唐集团科学技术研究院有限公司西北电力试验研究院 | Water supply control method and system for optimizing direct current furnace based on vector autoregression water-coal ratio |
| CN114593411B (en) * | 2022-02-28 | 2024-03-29 | 中国大唐集团科学技术研究院有限公司西北电力试验研究院 | Vector autoregressive water-coal ratio optimizing direct-current furnace water supply control method and system |
| CN115979339A (en) * | 2022-12-07 | 2023-04-18 | 吉林农业科技学院 | Laying hen breeding environment intelligent supervision system based on big data analysis |
| CN115979339B (en) * | 2022-12-07 | 2023-08-15 | 吉林农业科技学院 | Intelligent monitoring system for laying hen breeding environment based on big data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113033890A (en) | Method for analyzing laying performance of laying hens based on vector autoregressive model | |
| CN111639823B (en) | Building cold and heat load prediction method constructed based on feature set | |
| Mertens et al. | Statistical control charts as a support tool for the management of livestock production | |
| CN111325522B (en) | Intelligent fishery breeding management method and system based on Internet of things | |
| CN114862032B (en) | XGBoost-LSTM-based power grid load prediction method and device | |
| CN114169638A (en) | Water quality prediction method and device | |
| CN107238638A (en) | The assay method contacted based on each composition physical and chemical index of Daqu and liquor output and vinosity | |
| CN110119767A (en) | A kind of cucumber green house temperature intelligent detection device based on LVQ neural network | |
| CN112801388A (en) | Power load prediction method and system based on nonlinear time series algorithm | |
| CN113888011A (en) | Chicken coop internal environment evaluation method based on grey correlation analysis and analytic hierarchy process | |
| CN115456245A (en) | Prediction method for dissolved oxygen in tidal river network area | |
| CN113962819A (en) | Method for predicting dissolved oxygen in industrial aquaculture based on extreme learning machine | |
| CN110533249A (en) | A kind of smelter energy consumption prediction technique based on integrated shot and long term memory network | |
| CN117408833A (en) | Short-term load prediction method based on load identification | |
| CN116579504A (en) | Prediction method for pond mariculture water temperature based on machine learning | |
| CN116484193A (en) | Crop yield prediction method, system, equipment and medium | |
| CN116579873A (en) | Method and system for evaluating crop disaster yield reduction condition based on high-temperature drought weather | |
| CN116247658A (en) | Photovoltaic power generation amount prediction method based on DLRM deep learning model | |
| Qu et al. | Application of Deep Neural Network on Net Photosynthesis Modeling | |
| CN113935542A (en) | Method for predicting cotton yield per unit based on climate suitability | |
| Kaburlasos et al. | Intelligent clustering techniques for prediction of sugar production | |
| CN113919600A (en) | Resident load ultra-short term prediction method | |
| CN111401727A (en) | Visual expression method for economic conduction effect of snow disaster on grassland livestock | |
| CN112767048A (en) | Chicken price prediction method based on multidimensional factors | |
| Huang et al. | Seasonal Broiler Growth Performance Prediction Based on Observational Study. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210625 |