Laying hen breeding environment parameter optimization method based on big data

Abstract

The invention provides a laying hen breeding environment parameter optimization method based on big data, and relates to the technical field of livestock breeding environment intelligent regulation and control, and the method comprises the steps: dividing laying hens into a young group, a middle-aged group and an aged group according to the age, and constructing a quality comprehensive score model based on the laying rate and the feed conversion rate; secondly, counting a quality comprehensive score under each environment parameter; thirdly, constructing a data set based on the environmental parameters and the quality comprehensive score, and optimizing an optimal environmental parameter combination of the laying hens of all age groups by adopting a genetic algorithm; and finally, adjusting environmental parameters according to an optimization result, and updating the data set and the optimization algorithm in real time. Meanwhile, by introducing time period constraint and a dynamic optimization mechanism, the timeliness and practicability of an optimization result are ensured, meanwhile, the efficient search capability of the genetic algorithm is utilized, the optimal environment parameter combination is accurately found, and the production efficiency and the breeding benefits of laying hens are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent regulation of livestock breeding environment, and particularly to an optimization method for breeding environment parameters of laying hens based on big data. Background Art

[0002] Laying hen breeding is an important part of agricultural production, and its production performance is directly related to economic benefits. With the development of large-scale and intensive breeding, the impact of environmental parameters (such as temperature, stocking density, carbon dioxide concentration) on the health and production performance of laying hens has become increasingly significant. Research shows that appropriate environmental parameters can significantly improve the egg production rate and feed conversion rate of laying hens, while adverse environmental conditions may lead to stress, diseases and even death of laying hens, seriously affecting the breeding efficiency.

[0003] At present, some breeders have realized the importance of environmental parameters for laying hen breeding and taken some measures to monitor and regulate the environment. Some farms have installed simple temperature and humidity sensors and ventilation equipment, and adjust the temperature and ventilation through manual observation and empirical judgment to control the carbon dioxide concentration. However, these traditional breeding environment regulation methods have obvious deficiencies and lack scientific data support. In the prior art, some studies have tried to analyze the relationship between environmental parameters and laying hen production performance through experimental data, but these methods have the following deficiencies:

[0004] On the one hand, the traditional method lacks accuracy. Manual observation and empirical judgment are easily affected by subjective factors and it is difficult to accurately grasp the subtle changes of environmental parameters. For example, breeders may not be able to detect the slight fluctuations in temperature or the slow rise in carbon dioxide concentration in time, thus unable to take effective regulation measures in time, resulting in laying hens being in an unsuitable environment for a long time, affecting their production performance and health.

[0005] On the other hand, the traditional method lacks pertinence. Laying hens of different ages have different requirements for environmental parameters. Young laying hens, middle-aged laying hens and old laying hens are different in growth and development, egg production performance and physiological functions, and their suitable ranges for temperature, stocking density and carbon dioxide concentration are also different. However, the existing regulation methods often adopt a unified standard and cannot carry out personalized environmental regulation according to the different ages of laying hens, and cannot fully meet the needs of laying hens at different growth stages, restricting the exertion of laying hen production performance. The production performance of laying hens changes significantly with age, and the existing methods do not optimize laying hens of different ages specifically, resulting in unsatisfactory regulation effects.

[0006] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and therefore it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0007] The purpose of the present invention is to provide an optimization method for laying hen breeding environment parameters based on big data to solve the problems raised in the above background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] An optimization method for laying hen breeding environment parameters based on big data, the specific steps include:

[0010] Step 1: Preset multiple time periods, group laying hens of each age into young laying hens, middle-aged laying hens and old laying hens, and construct a quality comprehensive score model through weighted summation based on the egg production rate and feed conversion rate within the same time period to obtain the quality comprehensive score;

[0011] Step 2: Statistically analyze the environmental parameters within each time period, and map them to the quality comprehensive scores of laying hens of each age in the same time period to construct an environmental parameter data set for each period. The environmental parameters include temperature, breeding density and carbon dioxide concentration;

[0012] Step 3: Preset the constraint conditions of the environmental parameters, and use the genetic algorithm to output the optimal temperature, breeding density and carbon dioxide concentration corresponding to laying hens of each age based on the constraint conditions;

[0013] Step 4: After adjusting the environmental parameters according to the results output by the genetic algorithm, record the quality comprehensive scores of laying hens of each age and update the environmental parameter data set, and optimize the genetic algorithm in real time.

[0014] Further, the length of the time period T in the preset multiple time periods s is 7 days.

[0015] Further, grouping laying hens of each age into young laying hens, middle-aged laying hens and old laying hens includes the following steps:

[0016] Laying hens aged 20 - 30 weeks are classified as young laying hens, laying hens aged 31 - 50 weeks are classified as middle-aged laying hens, and laying hens aged 51 - 70 weeks are classified as old laying hens.

[0017] Further, within the same time period T s , for young laying hens, middle-aged laying hens and old laying hens, count the total number of laying hens and the total number of eggs laid, and calculate the egg production rate:

[0018]

[0019] In the formula, R ij represents the egg production rate of the i-th group of laying hens of age in the j-th time period, N ij represents the total number of the i-th group of laying hens of age in the j-th time period, Eij It represents the total number of eggs laid by the i-th group of laying hens in the j-th time period, where i = 1, 2, 3, representing young laying hens, middle-aged laying hens, and old laying hens respectively;

[0020] Record the feed consumption and the total weight of eggs produced by the i-th group of laying hens in the j-th time period, and calculate the feed conversion rate:

[0021]

[0022] In the formula, F ij represents the feed conversion rate of the i-th group of laying hens in the j-th time period, M ij represents the total weight of feed consumed by the i-th group of laying hens in the j-th time period, E ij represents the total weight of eggs produced by the i-th group of laying hens in the j-th time period;

[0023] Based on the egg production rate and feed conversion rate of the i-th group of laying hens in the j-th time period, construct a comprehensive quality score model through weighted summation:

[0024]

[0025] In the formula, Q ij represents the comprehensive quality score of the i-th group of laying hens in the j-th time period, β represents the weight coefficient, and

[0026] Furthermore, from 8 am to 5 pm every day within each time period, measure the temperature of the breeding environment every 1 hour, and record the measured temperature as T a , a represents the number for recording each temperature, a = 1, 2,..., 70, and calculate the temperature of the j-th time period:

[0027]

[0028] In the formula, T j represents the temperature of the j-th time period;

[0029] The method for obtaining the feeding density value is to record the number of laying hens in the breeding area and the area of the breeding area within each time period, and calculate the feeding density of the j-th time period:

[0030]

[0031] In the formula, D j represents the feeding density of the j-th time period, S ad represents the area of the breeding area;

[0032] The method for obtaining the carbon dioxide concentration value is to measure the carbon dioxide concentration in the breeding environment every 2 hours from 8:00 am to 6:00 pm every day within each time period, and record the measured carbon dioxide concentration as C b , where b represents the number for recording the carbon dioxide concentration of each environment, b = 1, 2, …, 42, and calculate the carbon dioxide concentration in the j-th time period:

[0033]

[0034] In the formula, C j represents the carbon dioxide concentration in the j-th time period.

[0035] Furthermore, for young laying hens, construct the data set ε j1 , where each sample is (T j , D j , C j , F 1j , Q 1j ). For middle-aged laying hens, construct the data set ε j2 , where each sample is (T j , D j , C j , F 2j , Q 2j ). For old laying hens, construct the data set ε j3 , where each sample is (T j , D j , C j , F 3j , Q 3j ).

[0036] Furthermore, set the temperature constraint condition as: 18 ≤ T ≤ 24, set the breeding density constraint condition as: 5 ≤ d ≤ 10, and set the carbon dioxide concentration constraint condition as: 1500 ≤ C ≤ 3000.

[0037] Furthermore, for laying hens of each age group, encode the environmental parameters temperature T, breeding density D, and carbon dioxide concentration C into an individual: [T, D, C], and satisfy the set constraint conditions. Set the population size N, use the random number generation function to generate temperature values in the range of 18 ≤ T ≤ 24, generate breeding density values in the range of 5 ≤ D ≤ 10, and generate carbon dioxide concentration values in the range of 1500 ≤ C ≤ 3000. For the i-th group of age laying hens, use the matching value of the quality comprehensive score Q ij as the fitness value, that is, find the Q ji value of the data point closest to [T, D, C] from the data set ε ij . For each individual [T, D, C] in the population, based on the Euclidean distance, in ε jiFind the data point closest to the combination of the individual environmental parameters in it. Each time, randomly select 3 individuals from the population, compare their fitness values, and select the individual with the highest fitness as the parent. Repeat this process until 100 parent individuals are selected. Set the crossover probability P c = 0.7, select the single-point crossover method, exchange the parts of the two parent individuals before and after the crossover point to generate two offspring individuals. Set the mutation probability P m = 0.2, use the uniform mutation method to determine whether the parameters (T, D, C) in the individual mutate. Set the maximum number of iterations G = 50. After the algorithm terminates, finally select the individual with the highest fitness from the populations corresponding to the young, middle-aged, and old age groups respectively, and the corresponding [T, D, C] is the optimal environmental parameter combination for laying hens of different ages.

[0038] Furthermore, continuously collect the environmental parameters of laying hens of each age group in each cycle, and at the same time record the results calculated based on the quality comprehensive score model. Add the newly collected environmental parameters and the corresponding results of the quality comprehensive score model to the environmental parameter dataset ε ji for each age group of laying hens respectively, and then restart the genetic algorithm for iterative calculation using the updated environmental parameter dataset.

[0039] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0040] The present invention constructs datasets for laying hens of each age group, records the temperature, feeding density, and carbon dioxide concentration of laying hens of each age, constructs a quality comprehensive score model, and constructs an environmental parameter dataset with environmental parameters, namely temperature, feeding density, and carbon dioxide concentration. In the selection of temperature, feeding density, and carbon dioxide concentration, the genetic algorithm is used, which can effectively capture the non-linear relationship between environmental parameters and production performance. Through the real-time optimization of the genetic algorithm, the optimal environmental parameter combination can be found for different ages of laying hens in a short time, realizing the automation and intelligence of breeding environment regulation, significantly improving the calculation efficiency, accuracy, and practicability, and being applicable to large-scale breeding scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0042] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to specific embodiments.

[0043] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those of ordinary skill in the field to which the present invention pertains. The "first", "second" and similar terms used in the present invention do not denote any order, quantity or importance, but are only used to distinguish the components. The terms such as "comprising" or "including" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. The terms such as "connected" or "linked" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left" and "right" are only used to represent relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0044] Embodiment:

[0045] Please refer to Figure 1 , the present invention provides a technical solution:

[0046] An optimization method for the breeding environment parameters of laying hens based on big data, the specific steps include:

[0047] Step 1: Preset multiple time periods in advance, group laying hens of each age group into young laying hens, middle-aged laying hens and old laying hens, and construct a quality comprehensive score model by weighted summation based on the egg production rate and feed conversion rate within the same time period to obtain the quality comprehensive score;

[0048] Preset the time period T s to be 7 days. Some physiological changes and production performance of laying hens have certain periodicities. The 7-day time period can better capture these changes. For example, the egg production cycle of laying hens usually has certain rules. Within a relatively short cycle, indicators such as the egg production rate and the quality of eggs may fluctuate significantly. The 7-day time length is neither too long to ignore short-term changes nor too short to make the data too scattered to analyze, and can relatively completely record the production situation of laying hens within a small cycle.

[0049] Laying hens aged 20 - 30 weeks are classified as young laying hens. At this stage, the laying hens are in the stage of sexual maturity and the initial stage of egg production. Their bodies are still growing and developing, their bones and muscles are gradually maturing, and their reproductive systems begin to develop rapidly and gradually reach the egg production peak.

[0050] Laying hens aged 31 - 50 weeks are classified as middle-aged laying hens. At this time, the laying hens have entered the peak egg production period and maintain a relatively stable egg production level. Their body functions are in a relatively mature and stable state, and their adaptability to the environment is relatively strong.

[0051] Laying hens aged 51 - 70 weeks are classified as old - age laying hens. As they age, the physical functions of laying hens gradually decline, making them more sensitive to environmental changes, and generally the egg production rate also begins to decrease.

[0052] The egg production rate is an important indicator to measure the quality of laying - hen breeds. By statistically analyzing the egg production rates of laying hens at different ages, and then adjusting the breeding environment to increase breeding benefits. In the same time period T s For young laying hens, middle - aged laying hens, and old - age laying hens, respectively, count the total number of laying hens and the total number of eggs produced, and calculate the egg production rate:

[0053]

[0054] In the formula, R ij represents the egg production rate of the i - th group of laying hens at the j - th time period, N ij represents the total number of the i - th group of laying hens at the j - th time period, E ij represents the total number of eggs produced by the i - th group of laying hens at the j - th time period. i = 1, 2, 3 represent young laying hens, middle - aged laying hens, and old - age laying hens respectively;

[0055] By optimizing environmental parameters and improving feed conversion rate, laying hens can utilize nutrients in feed more effectively, reduce feed waste, record the feed consumption and the total weight of eggs produced by the i - th group of laying hens at the j - th time period, and calculate the feed conversion rate:

[0056]

[0057] In the formula, F ij represents the feed conversion rate of the i - th group of laying hens at the j - th time period, M ij represents the total weight of feed consumed by the i - th group of laying hens at the j - th time period, E ij represents the total weight of eggs produced by the i - th group of laying hens at the j - th time period. Paying attention to this indicator means that breeders can reduce the amount of feed fed while ensuring the production performance of laying hens, thereby reducing feed costs. For example, under suitable environmental conditions, if the feed conversion rate is increased by 10%, calculated based on an annual feed consumption of 100 tons, 10 tons of feed can be saved, reducing the breeding cost;

[0058] The egg production rate and the feed conversion rate are two key indicators to measure the breeding efficiency of laying hens. The egg production rate directly reflects the egg - laying ability of laying hens, while the feed conversion rate reflects the feed utilization efficiency. Combining the two can more comprehensively evaluate the production performance of laying hens under specific environmental parameters and time periods. Based on the egg production rate and the feed conversion rate of the i - th group of laying hens at the j - th time period, construct a comprehensive quality score model through weighted summation:

[0059]

[0060] In the formula, Q ij It is expressed as the construction quality comprehensive score model of the i-th group of laying hens in the j-th time period, β is expressed as a weight coefficient. The egg production rate is directly related to the breeding income. The higher the egg production rate, the more eggs are produced under the same breeding scale, and the higher the sales income. The feed conversion rate reflects the efficiency of feed cost utilization. The lower the feed conversion rate, the more feed is consumed to produce a unit weight of eggs, and the higher the cost. Using subtraction to construct a model can reflect the pursuit of income while subtracting the data reflecting the cost, thereby intuitively reflecting the breeding benefits.

[0061] At the same time, the egg market demand is strong, the price is high, and the feed cost is relatively stable. Farmers pay more attention to the egg production rate of laying hens, because a higher egg production rate can directly lead to more egg production, thereby increasing sales revenue. Therefore, the weight coefficient And it can be adjusted according to actual conditions. Farmers can flexibly set the weights according to their own emphasis on egg production rate and feed conversion rate to adapt to different breeding goals and market demands. For example, when the market price of eggs is high, the weight of egg production rate can be appropriately increased, and when feed costs are high, the weight of feed conversion rate can be increased.

[0062] Step 2: Count the environmental parameters in each time period, and map them with the quality comprehensive scores of laying hens of different ages in the same time period to construct an environmental parameter data set for each period, wherein the environmental parameters include temperature, stocking density and carbon dioxide concentration;

[0063] Temperature directly affects the thermoregulation and metabolism of laying hens. The suitable temperature range for laying hens is relatively narrow. Too high or too low a temperature will affect their feed intake, egg production rate and feed conversion rate. Stocking density is related to the activity space, feeding and rest of laying hens. Too high a stocking density can easily cause stress in laying hens, affecting their growth and egg production. The carbon dioxide concentration reflects the air quality in the chicken house. Too high a density can cause hypoxia in laying hens, affecting their breathing and health, and thus affecting their egg production performance. In actual breeding, the temperature can be adjusted through temperature control equipment (such as air conditioners, heaters, etc.), the stocking density can be controlled by adjusting the layout of the chicken house and the number of chickens raised, and the carbon dioxide concentration can be adjusted through ventilation equipment. Therefore, different optimization measures can be taken according to the changes in different parameters.

[0064] In the same cycle T s The quality comprehensive score Q of laying hens of different ages under different environmental parameters is calculated within 7 days. ij, in the record of the environmental parameters including temperature, breeding density, and carbon dioxide concentration, the method for obtaining the temperature value is as follows: from 8:00 am to 5:00 pm every day within each time period, the temperature of the breeding environment is measured every hour. The period from 8:00 am to 5:00 pm is usually when laying hens are more active, with concentrated feeding and egg production. Measuring the temperature during this period can more accurately reflect the actual thermal environment in which laying hens are in an active state. Since the sensitivity and demand for temperature of laying hens are different when they are active and when they are resting, measuring once every hour can capture the temperature fluctuations during the day in a more detailed manner, which helps to accurately grasp the thermal comfort requirements of laying hens. Record the measured temperature as T a , a represents the serial number for recording each temperature measurement. It is measured 10 times a day (from 8:00 am to 5:00 pm, at one-hour intervals), and a total of 70 times in 7 days. Therefore, a = 1, 2, …, 70. Calculate the temperature of the j-th time period:

[0065]

[0066] In the formula, T j represents the temperature of the j-th time period;

[0067] The method for obtaining the breeding density value is to record the number of laying hens and the area of the breeding area within each time period. During one time period, the number of laying hens and the area of the breeding area are relatively stable, and only one statistical count is required at the end of the period. Data can be obtained through simple counting and measurement, and then the breeding density can be calculated using the formula. The breeding density of the j-th time period is:

[0068]

[0069] In the formula, D j represents the breeding density of the j-th time period, and S ad represents the area of the breeding area;

[0070] The method for obtaining the carbon dioxide concentration value is to measure the carbon dioxide concentration of the breeding environment every 2 hours from 8:00 am to 6:00 pm every day within each time period. Among them, measuring once every 2 hours not only ensures obtaining enough data points during the main activity period of laying hens to comprehensively present the changing trend of carbon dioxide concentration, but also does not increase excessive labor and material costs due to overly frequent measurement. Record the measured carbon dioxide concentration as C b , b represents the serial number for recording the carbon dioxide concentration of each environment measurement. It is measured 6 times a day (from 8:00 am to 6:00 pm, at two-hour intervals), and a total of 42 times in 7 days. Therefore, b = 1, 2, …, 42. Calculate the carbon dioxide concentration of the j-th time period:

[0071]

[0072] where C j represents the carbon dioxide concentration over j time periods.

[0073] Step 3: Preset the constraint conditions of environmental parameters, and based on the constraint conditions, use the genetic algorithm to output the optimal temperature, feeding density, and carbon dioxide concentration corresponding to laying hens of different ages;

[0074] The physiological characteristics, production performance, and environmental requirements of laying hens at different ages vary significantly. For example, young laying hens are in the growth and development stage and may be more sensitive to changes in temperature and feeding density; middle-aged laying hens have strong egg-laying performance, and environmental parameters have a greater impact on the quality and quantity of their eggs; old laying hens have relatively low immunity and are more susceptible to environmental factors such as carbon dioxide concentration. Constructing datasets separately can accurately capture the relationship between laying hens at each stage and environmental parameters, and the datasets for laying hens of different ages can provide references for accurately changing environmental parameters.

[0075] Based on the collected environmental parameters, calculate the corresponding quality comprehensive score model. For young laying hens, construct the dataset ε j1 , where each sample is (T j , D j , C j , Q 1j ). For middle-aged laying hens, construct the dataset ε j2 , where each sample is (T j , D j , C j , Q 2j ). For old laying hens, construct the dataset ε j3 , where each sample is (T j , D j , C j , Q 3j ).

[0076] The constraint conditions for the set temperature are: 18 ≤ T ≤ 24. The constraint conditions for the set breeding density are: 5 ≤ D ≤ 10. The constraint conditions for the set carbon dioxide concentration are: 1500 ≤ C ≤ 3000. Generally speaking, when the environmental temperature is lower than 18 °C, laying hens need to consume more energy to maintain their body temperature, which may lead to a slowdown in growth rate and a decline in egg-laying performance. When the temperature is higher than 24 °C, laying hens are prone to heat stress reactions, with increased breathing rate and reduced feed intake, which will also affect their production performance and health. When the carbon dioxide concentration in the chicken house is too high (exceeding 3000 ppm), it will lead to a relatively insufficient oxygen content, and laying hens will show symptoms such as dyspnea and listlessness, seriously affecting their health and production performance. When the carbon dioxide concentration is too low (below 1500 ppm), it may mean excessive ventilation in the chicken house, which will cause large fluctuations in the temperature inside the house and is also not conducive to the growth and production of laying hens. Laying hens generate heat during metabolism. Too high a breeding density will make it difficult for the chicken flock to dissipate heat, causing the local temperature in the chicken house to rise and increasing the risk of heat stress. When 5 - 10 laying hens are raised per square meter, there is enough space between chickens, which is conducive to air circulation and heat dissipation, helping laying hens maintain an appropriate body temperature. Research shows that when there are more than 10 chickens, it may interfere with feeding and drinking.

[0077] For laying hens of each age group, the environmental parameters temperature T, breeding density D, and carbon dioxide concentration C are respectively encoded as an individual: [T, D, C], and they meet the set constraint conditions. The population size N is set to 100, that is, 100 different combinations of temperature, breeding density, and carbon dioxide concentration participate in the subsequent genetic operations. The random number generation function is used to generate temperature values in the range of 18 ≤ T ≤ 24, breeding density values in the range of 5 ≤ D ≤ 10, and carbon dioxide concentration values in the range of 1500 ≤ C ≤ 3000.

[0078] For the i - th age group of laying hens, the matching value of the quality comprehensive score Q ij is used as the fitness value, that is, to find the Q i value of the data point in the dataset ε ij that is closest to [T, D, C]. For each individual [T, D, C] in the population, based on the Euclidean distance, find the data point in ε i that is closest to the combination of the individual's environmental parameters. Suppose the combination of the individual's environmental parameters is [T1, d1, C1], and the environmental parameters of a data point in the dataset are [T2, D2, C2]. Then the formula for calculating their Euclidean distance is:

[0079]

[0080] Wherein, d represents the Euclidean distance between them. To find the closest data point, it is necessary to calculate the Euclidean distance between each data point in the data set and the individual, and then select the data point with the smallest distance.

[0081] Each time, randomly select 3 individuals from the population and compare their fitness values, that is, find the data point Q i in the data set ε ij that is closest to the combination of the individual's environmental parameters. The method of randomly selecting 3 individuals for competition avoids the problem of the rapid loss of population diversity caused by only selecting a few individuals with the highest fitness. Select the individual with the highest fitness as the parent generation, so as to find the optimal solution. Repeat this process until 100 parent generation individuals are selected. Set the crossover probability P c = 0.7. Pair the 100 selected parent generation individuals in pairs. For each pair of parent generation individuals, generate a random number r between 0 and 1. If r < P c , then perform a single-point crossover operation, exchange the parts before and after the crossover point of the two parent generation individuals, and generate two offspring individuals. If r ≥ P c , then this pair of parent generation individuals directly serve as offspring individuals without performing a crossover operation;

[0082] Set the mutation probability P m = 0.2. Use the uniform mutation method to determine whether the parameters (T, D, C) in the individual mutate, that is, for each offspring individual, generate a random number r' between 0 and 1. If r' < P m , then perform a uniform mutation operation on each offspring individual, randomly select one or more parameters (T, D, C) in the individual, and regenerate a value within the constraint range of the parameter. If r' ≥ P m , then the offspring individual remains unchanged;

[0083] Set the maximum number of iterations G = 50. After each iteration ends, replace the current population with the newly generated offspring individuals. After the algorithm terminates, finally select the individuals with the highest fitness from the populations corresponding to the young, middle-aged, and old age groups respectively. The corresponding [T, D, C] is the optimal combination of environmental parameters (temperature, feeding density, and carbon dioxide concentration) for laying hens of young, middle-aged, and old age groups.

[0084] Step 4: After adjusting the environmental parameters according to the results output by the genetic algorithm, record the comprehensive quality scores of laying hens of each age group and update the environmental parameter data set to optimize the genetic algorithm in real time;

[0085] By updating the dataset in real time and optimizing the genetic algorithm, the environmental parameters of laying hen farming can be continuously adjusted to better meet the needs of different growth stages of laying hens. For example, during the peak egg production period of laying hens, finding the optimal combination of temperature, feeding density, and carbon dioxide concentration can increase the egg production rate and egg quality, thereby increasing the farming income.

[0086] After the genetic algorithm iterates, it will output the optimal environmental parameter combination [T, D, C] for laying hens of different ages. According to these optimal parameter combinations, the laying hen farming environment is adjusted accordingly. For example, if the genetic algorithm gives the optimal temperature for young laying hens as 22°C and the current chicken house temperature is 20°C, the temperature is increased to 22°C through the temperature control device; if the optimal feeding density is 8 hens per square meter and the current density is 10 hens per square meter, the number of hens is appropriately reduced or the farming space is expanded; if the optimal carbon dioxide concentration is 2000 ppm and the current concentration is 2500 ppm, ventilation is strengthened to reduce the concentration. After adjusting the environmental parameters, the comprehensive quality score is calculated, and the adjusted environmental parameters and the corresponding comprehensive quality score are combined into a new data point, which is added to the corresponding environmental parameter dataset ε. i The growth environment and the state of laying hens change continuously over time. The real-time optimization of the genetic algorithm can adjust the environmental parameters in a timely manner according to these changes, ensuring that laying hens are always in the best growth and production environment. For example, when the immunity of old laying hens declines and most of the laying hens in the farm are old, the present invention can create an environment conducive to maintaining their health and extend the effective egg production period.

[0087] After that, using the updated dataset, the population of the genetic algorithm is reinitialized. The individuals in the new population are still randomly generated within the constraints of the environmental parameters. However, due to the update of the dataset, the fitness calculation of the individuals will more accurately reflect the relationship between the environmental parameters and the comprehensive quality score. Reinitializing the population can introduce new individuals, which have greater randomness and diversity in the values of the environmental parameters, thus increasing the diversity of the population. For example, in the problem of finding the optimal environmental parameter combination for laying hens, the newly initialized population may contain combinations of temperature, feeding density, and carbon dioxide concentration that have not been explored before, providing more search directions for the algorithm and avoiding the algorithm falling into a local optimum and being unable to find the true optimal solution.

[0088] The above formulas are all calculated by taking the numerical values after dimensionless. The formula is obtained by collecting a large amount of data and performing software simulation to get a formula closest to the real situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0089] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art will appreciate that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0090] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units. They may be located in one place or distributed over multiple network units. Some or all of the units can be selected according to actual needs to achieve the objectives of the solution of this embodiment.

[0091] As described above, the above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all of them should be covered by the protection scope of this application.

Claims

1. A method for optimizing laying hen breeding environment parameters based on big data, characterized in that: The specific steps include: Step 1: Pre-set multiple time periods, group laying hens of different ages into young laying hens, middle-aged laying hens and old laying hens, and construct a quality comprehensive score model through weighted summation based on egg production rate and feed conversion rate in the same time period to obtain a quality comprehensive score; Step 2: Count the environmental parameters in each time period, and map them with the quality comprehensive scores of laying hens of different ages in the same time period to construct an environmental parameter data set for each period, wherein the environmental parameters include temperature, stocking density and carbon dioxide concentration; Step 3: Preset the constraints of environmental parameters, and use genetic algorithms to output the optimal temperature, stocking density and carbon dioxide concentration corresponding to laying hens of different ages based on the constraints; Step 4: After adjusting the environmental parameters according to the results output by the genetic algorithm, the comprehensive quality scores of laying hens of each age group are recorded and the environmental parameter data set is updated to optimize the genetic algorithm in real time.

2. The method for optimizing laying hen breeding environment parameters based on big data according to claim 1, characterized in that: Preset the time period T in multiple time periods s The length is 7 days.

3. The method for optimizing laying hen breeding environment parameters based on big data according to claim 1, characterized in that: Grouping laying hens of different ages into young laying hens, middle-aged laying hens and old laying hens involves the following steps: Laying hens aged 20-30 weeks are classified as young laying hens, laying hens aged 31-50 weeks are classified as middle-aged laying hens, and laying hens aged 51-70 weeks are classified as old laying hens.

4. The method for optimizing laying hen breeding environment parameters based on big data according to claim 2, characterized in that: The method for constructing a comprehensive quality score model is: In the same time period T s For young laying hens, middle-aged laying hens and old laying hens, the total number of laying hens, the total number of eggs laid, and the egg production rate were calculated: In the formula, R ij It is expressed as the egg production rate of the i-th age laying hens in the j-th time period, N ij represents the total number of laying hens of age group i in the jth time period, E ij It is represented by the total number of eggs laid by the i-th age laying hens in the j-th time period, where i=1, 2, and 3 represent young laying hens, middle-aged laying hens, and old laying hens, respectively; Record the feed consumption and total weight of eggs produced by the i-th group of laying hens in the j-th time period, and calculate the feed conversion rate: In the formula, F ij It is expressed as the feed conversion rate of the i-th age laying hens in the j-th time period, M ij It is expressed as the total weight of feed consumed by the laying hens in the i-th group in the j-th time period, E ij It is expressed as the total weight of eggs produced by laying hens of age group i in the jth time period; According to the egg production rate and feed conversion rate of the i-th group of laying hens in the j-th time period, a quality comprehensive score model is constructed by weighted summation: In the formula, Q ij It is expressed as the comprehensive quality score of the i-th group of laying hens in the j-th time period, β is the weight coefficient, and 5. The method for optimizing laying hen breeding environment parameters based on big data according to claim 1, characterized in that: Among the environmental parameters, the temperature value is measured every hour from 8:00 a.m. to 17:00 p.m. every day in each time period, and the measured temperature is recorded as T a , a represents the number of each temperature record, a = 1, 2, ..., 70, calculate the temperature of the jth time period: Where, T j Expressed as the temperature of j time periods; The method for obtaining the stocking density is to record the number of laying hens in the breeding area and the area of ​​the breeding area in each time period, and calculate the stocking density in the jth time period: Where D j Expressed as the stocking density in the jth time period, S ad It is expressed as the area of ​​the breeding area; The method for obtaining the carbon dioxide concentration is to measure the carbon dioxide concentration in the breeding environment every 2 hours from 8:00 a.m. to 18:00 p.m. every day in each time period, and record the measured carbon dioxide concentration as C b , b represents the number of recording the carbon dioxide concentration of each environment, b = 1, 2, ..., 42, calculate the carbon dioxide concentration of the jth time period: In the formula, C j Expressed as the carbon dioxide concentration in j time periods.

6. The method for optimizing laying hen breeding environment parameters based on big data according to claim 2, characterized in that: Each environmental parameter dataset constructed includes ε j1 , ε j2 and ε j3 , ε j1 , ε j2 and ε j3 are the data sets of young laying hens, middle-aged laying hens and old laying hens in the jth cycle, respectively, where: For young laying hens, construct a dataset ε j1 , where each sample is (T j , D j , C j , F 1j , Q 1j ), for middle-aged laying hens, construct the data set ε j2 , where each sample is (T j , D j , C j , F 2j , Q 2j ), for old laying hens, construct the data set ε j3 , where each sample is (T j , D j , C j , F 3j , Q 3j ).

7. The method for optimizing laying hen breeding environment parameters based on big data according to claim 1, characterized in that: The constraints of the pre-set environmental parameters include: The temperature constraint is set as: 18≤T≤24, the stocking density constraint is set as: 5≤D≤10, and the carbon dioxide concentration constraint is set as: 1500≤C≤3000.

8. The method for optimizing laying hen breeding environment parameters based on big data according to claim 7, characterized in that: The method of using genetic algorithm to output the optimal temperature, stocking density and carbon dioxide concentration corresponding to laying hens of different ages based on constraints is as follows: For laying hens of each age group, the environmental parameters temperature T, stocking density D and carbon dioxide concentration C are encoded as an individual: [T, D, C], and the set constraints are met. The population size N is set, and the random number generation function is used to generate temperature values ​​in the range of 18≤T≤24, stocking density values ​​in the range of 5≤D≤10, and carbon dioxide concentration values ​​in the range of 1500≤C≤3000. For the i-th group of laying hens, the quality comprehensive score Q ij The matching value of is taken as the fitness value, that is, from the data set ε ji Find the data point Q that is closest to [T, D, C] ij For each individual [T, D, C] in the population, the Euclidean distance is calculated in ε ji Find the data point closest to the individual environmental parameter combination in the population, randomly select 3 individuals from the population each time, compare their fitness values, select the individual with the highest fitness as the parent, repeat this process until 100 parent individuals are selected, and set the crossover probability P c =0.7, select the single-point crossover method, exchange the parts of the two parent individuals before and after the crossover point, generate two offspring individuals, and set the mutation probability P m =0.2, the uniform mutation method is used to determine whether the parameters (T, D, C) in the individual vary, and the maximum number of iterations G is set to 50. After the algorithm terminates, the individuals with the highest fitness are finally selected from the populations corresponding to young, middle-aged, and old hens, respectively. The corresponding [T, D, C] are the optimal environmental parameter combinations for young, middle-aged, and old laying hens.

9. The method for optimizing laying hen breeding environment parameters based on big data according to claim 1, characterized in that: Real-time optimization of genetic algorithms includes the following steps: Continue to collect environmental parameters of laying hens of all ages in each cycle, and record the results calculated based on the quality comprehensive score model. Add the newly collected environmental parameters and the corresponding results of the quality comprehensive score model to the environmental parameter dataset ε for laying hens of all ages. ji , using the updated environmental parameter data set, restart the genetic algorithm for iterative calculation.

Images