Intelligent control system for sow feeding

Abstract

The present application relates to the technical field of feeding control, and particularly relates to a sow feeding intelligent control system, which comprises: a feeding module connected with a feed warehouse and used for storing feed; a conveying module connected with the feeding module and used for conveying the feed output by the feeding module; a discharging module connected with the conveying module and comprising a discharging port arranged above a trough and used for spreading the feed output by the conveying module into the trough; a detection module connected with the discharging module and used for detecting the current feed height of the trough and the current backfat thickness of the sow, the detection module comprising a height sensor arranged on the inner wall of the trough and used for detecting the feed height in the trough and a backfat thickness detector arranged above the trough and used for detecting the backfat thickness of the sow when the sow is eating; and a central control module used for adjusting and reducing the discharging height to a first corresponding discharging height according to the difference between the feed height and a preset feed height, so that the feeding accuracy is improved.

Description

Technical Field

[0001] This invention relates to the field of feeding control technology, and in particular to an intelligent control system for feeding sows. Background Technology

[0002] Pig farming, as an important component of agriculture, plays a vital role in agricultural development. In the past decade or so, my country's pig farming industry has developed steadily, with its overall scale consistently ranking first in the world. Currently, my country's pig farming industry is transforming from traditional to modern, with significant changes occurring in farming models, regional layout, production methods, and production capacity. Sow reproductive performance is one of the important economic indicators for measuring pig production, and fully utilizing sow reproductive performance is a fundamental means to improve the economic benefits of pig farms. The nutritional status of sows directly affects their reproductive performance; therefore, the nutritional status of sows at different reproductive stages has become a key focus of research for pig producers. Since the nutritional status of sows is difficult to directly determine, backfat thickness, which is highly correlated with it, becomes an important indicator for measuring sow nutritional status. Therefore, we focus on a systematic research and analysis integrating backfat thickness, feed intake data, water consumption data, and the sow's stage of development. This lays the foundation for precise feeding and management of sows.

[0003] Chinese Patent Publication No. CN112154931A discloses a method for precise feeding control of farrowing sows. The method includes the following steps: pre-binding the information of sows about to farrow with the information of the feeding controller corresponding to the sow's pen, and feeding the binding information back to the cloud; real-time monitoring of the sow's status from the pre-partum stage to the farrowing stage and feeding it back to the cloud; the cloud searching for the corresponding feeding curve based on the sow's current status; the cloud calling the feeding program corresponding to the found feeding curve, and controlling the feeder to feed the sow in the corresponding pen based on the feeding program. Therefore, the precise feeding control method for farrowing sows described in the above technical solution has the following problems: it can only feed sows from the pre-partum stage to the farrowing stage, and cannot provide precise feeding for each stage of the sow's life. Furthermore, during the feeding process, only the period before farrowing is precisely fed, and other stages are not precisely fed, which is detrimental to the growth and development of the piglets. Summary of the Invention

[0004] To address this issue, the present invention provides a method for precise feeding curves of sows based on machine learning and multi-feature fusion, in order to overcome the problem that existing technologies do not provide precise feeding for sows at various stages.

[0005] To achieve the above objectives, in one aspect, the present invention provides an intelligent control system for sow feeding, comprising:

[0006] The feeding module, which is connected to the feed warehouse, is used to store feed;

[0007] A conveying module, which is connected to the feeding module, is used to convey the feed output by the feeding module;

[0008] The feeding module is connected to the conveying module and includes an outlet located above the feed trough for distributing the feed output from the conveying module into the feed trough.

[0009] The detection module, which is connected to the feeding module, is used to detect the current feed height in the feed trough and the current backfat thickness of the sow. It includes a height sensor installed on the inner wall of the feed trough to detect the feed height in the feed trough and a backfat thickness detector installed above the feed trough to detect the backfat thickness of the sow when the sow is feeding.

[0010] The central control module, which is connected to the feeding module, the conveying module, the discharging module, and the detection module, is used to adjust the discharging height to a first corresponding discharging height based on the difference between the feed height and the preset feed height; adjust the discharging port diameter to a corresponding diameter based on the discharging time; adjust the discharging height to a second corresponding discharging height based on the average delay time of feeding multiple sows; and adjust the feeding amount per unit time to a corresponding value based on the fat gain of pigs in historical data.

[0011] Furthermore, the central control module determines whether the stability of the feeding process is within the allowable range based on the average height of the feed in the trough using three different methods.

[0012] The area of ​​the material trough is S, the unloading volume of the unloading module in a single measurement cycle is V, and the average height is... The calculation formula is: The average height of the feed in the trough before feeding, as measured by the detection module;

[0013] The first type of determination method is that the central control module determines that the stability of the feeding process is lower than the allowable range under the preset first height condition, initially determines that the continuity of feed feeding is lower than the allowable range, and makes a second determination on whether the continuity of feeding is lower than the allowable range based on the feeding time required to reach the standard feed height.

[0014] The second type of determination method is that the central control module determines that the stability of the feeding process is lower than the allowable range under the preset second height condition, and adjusts the feeding height to the first feeding height by calculating the difference between the current feed height in the trough and the preset first height.

[0015] The third type of determination method is that the central control module determines that the stability of the feeding process is within the allowable range under the preset third height condition;

[0016] Wherein, the first height condition is that the feed height is less than the first preset height; the second height condition is that the feed height is greater than or equal to the first preset height and less than or equal to the second preset height; the third height condition is that the feed height is greater than the second preset height; and the first preset height is less than the second preset height.

[0017] Furthermore, under the preset second height condition, the central control module determines three adjustment methods for the feeding height based on the difference between the current feed height in the trough and the preset first height.

[0018] The first type of adjustment method is that the central control module adjusts the material feeding height to the preset material feeding height under the condition of a preset first height difference;

[0019] The second type of adjustment method is that the central control module adjusts the material discharge height to the first material discharge height using a preset second material discharge height adjustment coefficient under the preset second height difference condition;

[0020] The third type of adjustment method is that the central control module adjusts the material discharge height to the second material discharge height using a preset first material discharge height adjustment coefficient under the preset third height difference condition;

[0021] Wherein, the first height difference condition is that the difference between the current feed height in the trough and the preset first height is less than or equal to the first preset height difference; the second height difference condition is that the difference between the current feed height in the trough and the preset first height is greater than the first preset height difference and less than or equal to the second preset height difference; the third height difference condition is that the difference between the current feed height in the trough and the preset first height is greater than the second preset height difference; the first preset height difference is less than the second preset height difference, and the preset first feeding height adjustment coefficient is less than the preset second feeding height adjustment coefficient.

[0022] Furthermore, under the first height condition, the central control module determines whether the feeding continuity is below the allowable range based on two secondary judgment methods: the feeding time required to reach the standard feed height range, and the feeding continuity is below the allowable range.

[0023] The first type of continuity secondary determination method is that the central control module determines the continuity of material feeding within the allowable range under the condition of a preset first material feeding time.

[0024] The first type of continuity secondary determination method is that the central control module determines that the feeding continuity is lower than the allowable range under the preset second feeding time condition, and adjusts the feeding port diameter to the first feeding port diameter by calculating the difference between the feeding time required to reach the standard feed height range and the preset feeding time.

[0025] The first preset feeding time condition is that the feeding time required to reach the standard feed height range is less than or equal to the preset feeding time; the second preset feeding time condition is that the feeding time required to reach the standard feed height range is greater than the preset feeding time.

[0026] Furthermore, under the preset second feeding time condition, the central control module determines two adjustment methods for the feeding port diameter based on the difference between the feeding time required to reach the standard feed height range and the preset feeding time.

[0027] The first type of diameter adjustment method is that the central control module feeds material according to the preset feeding port diameter under the condition of a preset first feeding time difference;

[0028] The second type of diameter adjustment method is that the central control module adjusts the diameter of the discharge port to the first discharge diameter using a preset first diameter adjustment coefficient under the condition of a preset second material feeding time difference.

[0029] The first preset feeding time difference condition is that the difference between the feeding time required to reach the standard feed height range and the preset feeding time is less than or equal to the preset feeding time difference; the second preset feeding time difference condition is that the difference between the feeding time required to reach the standard feed height range and the preset feeding time is greater than the preset feeding time difference; and the first preset diameter adjustment coefficient is always greater than 1.

[0030] Furthermore, the central control module determines whether the overall conveying speed from the conveying section to the unloading section is within the allowable range based on two methods, according to the average delay time of feeding several sows.

[0031] The first type of determination method is that the central control module determines that the overall conveying speed is within the allowable range under a preset first delay time condition;

[0032] The second type of determination method is that the central control module determines that the overall conveying speed is lower than the allowable range under the preset second delay time condition, and adjusts the feeding height to the third feeding height by calculating the difference between the current average feeding delay time and the preset first delay time.

[0033] The preset first delay duration condition is that the current average delay duration is less than or equal to the first average delay duration; the second delay duration condition is that the current average delay duration is greater than the first average delay duration.

[0034] Furthermore, under a preset second delay duration, the central control module determines two adjustment methods for the feeding height based on the time difference between the current average feeding delay duration and the preset first delay duration.

[0035] The first feeding height adjustment method is that the central control module delivers feed according to preset parameters under the preset average delay time condition for feeding the first sow, and continues to record relevant values ​​of the sow;

[0036] The second feeding height adjustment method is that the central control module adjusts the feeding height to the third feeding height using a third feeding height adjustment coefficient under the condition of the preset average delay time of feeding the second sow;

[0037] The third feeding height adjustment coefficient is greater than 0 and less than 1.

[0038] Furthermore, the central control module determines whether the sow's growth rate is within the normal range based on two methods, according to the currently measured backfat thickness.

[0039] The first method for determining growth rate is that the central control module determines that the growth rate of the sow is within the allowable range when the current backfat thickness of the sow is within the preset first backfat thickness condition;

[0040] The second growth rate determination method is that when the current backfat thickness of the sow is within the preset second backfat thickness condition, the central control module determines that the growth rate of the sow is lower than the allowable range, and adjusts the daily feed amount to the corresponding value by calculating the difference between the current backfat thickness of the sow and the preset first backfat thickness.

[0041] The backfat thickness of sows varies at different production stages. The preset first backfat thickness condition is that the current backfat thickness of the sow is greater than or equal to the first backfat thickness, and the preset second backfat thickness condition is that the current backfat thickness of the sow is less than the first backfat thickness.

[0042] Furthermore, under the preset second backfat thickness condition, the central control module determines two adjustment methods for the subsequent feed dispensing amount based on the difference between the current backfat thickness and the first backfat thickness.

[0043] The first type of feed quantity adjustment method is that the central control module feeds the animal according to the current daily feed quantity under the condition of a preset first backfat thickness difference;

[0044] The second type of material feeding adjustment method is that, under the condition of a preset second back fat thickness difference, the central control module uses the first adjustment coefficient of the daily material feeding to increase the daily material feeding to the first preset daily material feeding.

[0045] Furthermore, the first backfat thickness difference condition is that the difference between the current backfat thickness and the first backfat thickness is positive, the second backfat thickness difference condition is that the difference between the current backfat thickness and the first backfat thickness is negative, and the first daily feed rate adjustment coefficient is greater than 1.

[0046] Compared with the prior art, the beneficial effects of the present invention are as follows: The control system of the present invention, through the setting of a feeding module, a conveying module, a discharging module, a detection module, and a central control module, adjusts the discharging height to a first corresponding discharging height based on the difference between the feed height and the preset feed height, thereby reducing the impact of the discharging height on the degree of feed scattering. At the same time, it can also eliminate the problem of insufficient feed for sows due to machine problems. By adjusting the diameter of the discharging port to a corresponding diameter based on the discharging time, it reduces the impact of inaccurate adjustment of the discharging port diameter on the feeding accuracy. By adjusting the discharging height to a second corresponding discharging height based on the average delay time of feeding multiple sows, it reduces the impact of inaccurate adjustment of the discharging height on the feeding speed, thereby improving the feeding accuracy.

[0047] Furthermore, three judgment conditions are set for feeding stability to determine why the feed height is not within the standard height range. Based on different feed heights, the causes of different heights are determined, and the feeding module is adjusted to reduce the impact of other factors on the feeding speed, thereby further improving feeding accuracy.

[0048] Furthermore, different methods of adjusting the feeding height make the adjustment process simpler and further improve the accuracy of feeding.

[0049] Furthermore, the purpose of determining the continuity of feeding time is to further eliminate whether it is interference from the feeding module, and to measure the feeding status of sows in subsequent monitoring, thereby further improving the accuracy of feeding.

[0050] Furthermore, the diameter of the feed inlet of the feeding module was adjusted to eliminate its influence, and the feeding status of the sows was measured as a basis for subsequent adjustment of the feeding amount, thereby further improving the accuracy of feeding.

[0051] Furthermore, the extended feeding time for multiple sows was statistically analyzed to determine whether the feeding module's conveying speed was within the allowable range. The feeding height was then adjusted a second time to avoid the impact of adjustment errors on subsequent intelligent feeding, thereby further improving feeding accuracy.

[0052] Furthermore, by adjusting the feeding height a second time when the conveying speed is below the allowable range, the feed conveying speed can be optimized, thus avoiding feed waste and further improving feeding accuracy.

[0053] Furthermore, real-time measurement of backfat in sows can directly provide current body indicators. Different backfat conditions can be categorized, allowing for adjustments to daily feed amounts to achieve optimal feeding results and ensure the sow's health, thus further improving feeding precision.

[0054] Furthermore, by increasing feed or maintaining the current feeding situation for sows with different backfat conditions, precise feeding of sows at various stages can be achieved, further improving the accuracy of feeding. Attached Figure Description

[0055] Figure 1 This is an overall structural block diagram of an intelligent control system for sow feeding according to an embodiment of the present invention;

[0056] Figure 2 This is a flowchart illustrating a machine learning method involved in an intelligent control system for sow feeding according to an embodiment of the present invention.

[0057] Figure 3 This is a standard diagram of backfat thickness of sows collected at various stages during the testing process of an intelligent control system for sow feeding, according to an embodiment of the present invention.

[0058] Figure 4 This is a chart showing the daily feeding standards for sows collected during the testing process of an intelligent control system for sow feeding, as described in an embodiment of the present invention. Detailed Implementation

[0059] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0060] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0061] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0062] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0063] Please see Figure 1 , Figure 2 , Figure 3 as well as Figure 4 The diagrams shown above represent the overall structural block diagram of an intelligent sow feeding control system according to an embodiment of the present invention, a flowchart of the machine learning method involved in the system, standard diagrams of sow backfat thickness collected at various stages during the system's testing process, and standard diagrams of sow daily feed collected during the system's testing process. The intelligent sow feeding control system of the present invention includes:

[0064] The feeding module, which is connected to the feed warehouse, is used to store feed;

[0065] A conveying module, which is connected to the feeding module, is used to convey the feed output by the feeding module;

[0066] The feeding module is connected to the conveying module and includes an outlet located above the feed trough for distributing the feed output from the conveying module into the feed trough.

[0067] The detection module, which is connected to the feeding module, is used to detect the current feed height in the feed trough and the current backfat thickness of the sow. It includes a height sensor installed on the inner wall of the feed trough to detect the feed height in the feed trough and a backfat thickness detector installed above the feed trough to detect the backfat thickness of the sow when the sow is feeding.

[0068] The central control module is connected to the feeding module, the conveying module, the discharging module, and the detection module, respectively. It is used to adjust the discharging height to a first corresponding discharging height according to the difference between the feed height and the preset feed height, adjust the discharging port diameter to a corresponding diameter according to the discharging time, adjust the discharging height to a second corresponding discharging height according to the average delay time of feeding multiple sows, and adjust the feeding amount per unit time to a corresponding value according to the fat gain of pigs in historical data.

[0069] Compared with the prior art, the beneficial effects of the present invention are as follows: The control system of the present invention, through the setting of a feeding module, a conveying module, a discharging module, a detection module, and a central control module, adjusts the discharging height to a first corresponding discharging height based on the difference between the feed height and the preset feed height, thereby reducing the impact of the discharging height on the degree of feed scattering. At the same time, it can also eliminate the problem of insufficient feed for sows due to machine problems. By adjusting the diameter of the discharging port to a corresponding diameter based on the discharging time, it reduces the impact of inaccurate adjustment of the discharging port diameter on the feeding accuracy. By adjusting the discharging height to a second corresponding discharging height based on the average delay time of feeding multiple sows, it reduces the impact of inaccurate adjustment of the discharging height on the feeding speed, thereby improving the feeding accuracy.

[0070] Specifically, the central control module determines whether the stability of the feeding process is within the allowable range based on three methods according to the average height of the feed in the trough.

[0071] The area of ​​the material trough is S, the unloading volume of the unloading module in a single measurement cycle is V, and the average height is... The calculation formula is: The average height of the feed in the trough before feeding, as measured by the detection module;

[0072] The first type of determination method is that the central control module determines that the stability of the feeding process is lower than the allowable range under the preset first height condition, initially determines that the continuity of feed feeding is lower than the allowable range, and makes a second determination on whether the continuity of feeding is lower than the allowable range based on the feeding time required to reach the standard feed height.

[0073] The second type of determination method is that the central control module determines that the stability of the feeding process is lower than the allowable range under the preset second height condition, and adjusts the feeding height to the first feeding height by calculating the difference between the current feed height in the trough and the preset first height.

[0074] The third type of determination method is that the central control module determines that the stability of the feeding process is within the allowable range under the preset third height condition;

[0075] Let the feed height be h, the first preset height be h1, and the second preset height be h2, then we have:

[0076] The first height condition is h < h1;

[0077] The second height condition is h1≤h≤h2;

[0078] The third height condition is h2 < h;

[0079] Furthermore, three judgment conditions are set for feeding stability to determine why the feed height is not within the standard height range. Based on different feed heights, the causes of different heights are determined, and the feeding module is adjusted to reduce the impact of other factors on the feeding speed, thereby further improving feeding accuracy.

[0080] Specifically, under a preset second height condition, the central control module determines three adjustment methods for the feeding height based on the difference between the current feed height in the trough and the preset first height.

[0081] The first type of adjustment method is that the central control module adjusts the material feeding height to the preset material feeding height under the condition of a preset first height difference;

[0082] The second type of adjustment method is that the central control module adjusts the material discharge height to the first material discharge height using a preset second material discharge height adjustment coefficient under the preset second height difference condition;

[0083] The third type of adjustment method is that the central control module adjusts the material discharge height to the second material discharge height using a preset first material discharge height adjustment coefficient under the preset third height difference condition;

[0084] Let Δh be the difference between the feed height in the preset trough and the preset first height, Δh1 be the first preset height difference, Δh2 be the second preset height difference, α1 be the first feeding height adjustment coefficient, and α2 be the second feeding height adjustment coefficient. Then:

[0085] The first height difference condition is Δh≤Δh1;

[0086] The second height difference condition is Δh1<Δh≤Δh2;

[0087] The third height difference condition is Δh2 < Δh;

[0088] The preset first material feeding height adjustment coefficient is less than the preset second material feeding height adjustment coefficient 1 < α1 < α2;

[0089] Furthermore, different methods of adjusting the feeding height make the adjustment process simpler and further improve the accuracy of feeding.

[0090] Specifically, the central control module uses two secondary determination methods to assess whether the feeding continuity is below the allowable range based on the feeding time required to reach the standard feed height under the first height condition.

[0091] The first type of continuity secondary determination method is that the central control module determines the continuity of material feeding within the allowable range under the condition of a preset first material feeding time.

[0092] The first type of continuity secondary determination method is that the central control module determines that the feeding continuity is lower than the allowable range under the preset second feeding time condition, and adjusts the feeding port diameter to the first feeding port diameter by calculating the difference between the feeding time required to reach the standard feed height range and the preset feeding time.

[0093] Let t be the feeding time required to reach the standard feed height range, and t1 be the preset feeding time. Then:

[0094] The preset first feeding time condition is t≤t1;

[0095] The preset second feeding time condition is t1 < t;

[0096] Furthermore, the purpose of determining the continuity of the feeding time is to further eliminate interference from the feeding module and to measure the sow's feeding status in subsequent monitoring, thereby further improving feeding accuracy. Specifically, under the preset second feeding time condition, the central control module determines two adjustment methods for the feeding inlet diameter based on the difference between the feeding time required to reach the standard feed height range and the preset feeding time.

[0097] The first type of diameter adjustment method is that the central control module feeds material according to the preset feeding port diameter under the condition of a preset first feeding time difference;

[0098] The second type of diameter adjustment method is that the central control module adjusts the diameter of the discharge port to the first discharge diameter using a preset first diameter adjustment coefficient under the condition of a preset second material feeding time difference.

[0099] Let Δt be the difference between the feeding time required to reach the standard feed height range and the preset feeding time, Δt be the preset feeding time difference, and β1 be the preset first diameter adjustment coefficient. Then:

[0100] The preset first material feeding time difference condition is Δt≤Δt1;

[0101] The preset second feeding time difference condition is Δt1 < Δt;

[0102] The preset first diameter adjustment coefficient β1 > 1;

[0103] Furthermore, the feed inlet diameter of the feeding module was adjusted to eliminate its influence, and the feeding status of the sows was measured as a basis for subsequent feed amount adjustments, further improving feeding accuracy. Specifically, the central control module determines whether the overall conveying speed from the conveyor section to the feeding section is within the allowable range based on two methods: the average delay time of feeding several sows, and...

[0104] The first type of determination method is that the central control module determines that the overall conveying speed is within the allowable range under a preset first delay time condition;

[0105] The second type of determination method is that the central control module determines that the overall conveying speed is lower than the allowable range under the preset second delay time condition, and adjusts the feeding height to the third feeding height by calculating the difference between the current average feeding delay time and the preset first delay time.

[0106] Let the current average latency be T, and the first average latency be T1, then we have:

[0107] The preset first delay duration condition is T≤T1;

[0108] The preset second delay duration condition is T1 < T;

[0109] Furthermore, the extended feeding time for multiple sows was statistically analyzed to determine whether the feeding module's conveying speed was within the allowable range. The feeding height was then adjusted a second time to avoid the impact of adjustment errors on subsequent intelligent feeding, thereby further improving feeding accuracy.

[0110] Specifically, under a preset second delay duration, the central control module determines two adjustment methods for the feeding height based on the time difference between the current average feeding delay duration and the preset first delay duration.

[0111] The first feeding height adjustment method is that the central control module delivers feed according to preset parameters under the preset average delay time condition for feeding the first sow, and continues to record relevant values ​​of the sow;

[0112] The second feeding height adjustment method is that the central control module adjusts the feeding height to the third feeding height using a third feeding height adjustment coefficient under the condition of the preset average delay time of feeding the second sow;

[0113] If the third feeding height adjustment coefficient is set to γ1, then:

[0114] The third feeding height adjustment coefficient is 0 < γ1 < 1;

[0115] Furthermore, by adjusting the feeding height a second time when the conveying speed is below the allowable range, the feed conveying speed can be optimized, thus avoiding feed waste and further improving feeding accuracy.

[0116] Specifically, the central control module determines whether the sow's growth rate is within the normal range based on two methods, using the currently measured backfat thickness.

[0117] The first method for determining growth rate is that the central control module determines that the growth rate of the sow is within the allowable range when the current backfat thickness of the sow is within the preset first backfat thickness condition;

[0118] The second growth rate determination method is that when the current backfat thickness of the sow is within the preset second backfat thickness condition, the central control module determines that the growth rate of the sow is lower than the allowable range, and adjusts the daily feed amount to the corresponding value by calculating the difference between the current backfat thickness of the sow and the preset first backfat thickness.

[0119] Since the backfat thickness of sows varies at different production stages, let the current backfat thickness of the sow be H, and the first backfat thickness be H1, then we have:

[0120] The preset first backfat thickness condition is H1≤H;

[0121] The preset second backfat thickness condition is H < H1;

[0122] Furthermore, real-time measurement of backfat in sows can directly provide current body indicators. Different backfat conditions can be categorized, allowing for adjustments to daily feed amounts to achieve optimal feeding results and ensure the sow's health, thus further improving feeding precision.

[0123] Specifically, the central control module, under a preset second backfat thickness condition, determines two adjustment methods for the subsequent feed dispensing amount based on the difference between the current backfat thickness and the first backfat thickness.

[0124] The first type of feed quantity adjustment method is that the central control module feeds the animal according to the current daily feed quantity under the condition of a preset first backfat thickness difference;

[0125] The second type of material feeding adjustment method is that, under the condition of a preset second back fat thickness difference, the central control module uses the first adjustment coefficient of the daily material feeding to increase the daily material feeding to the first preset daily material feeding.

[0126] Let ΔH be the difference between the current backfat thickness and the first backfat thickness, and δ1 be the adjustment coefficient for the first day's feed rate. Then:

[0127] The first backfat thickness difference condition is 0 < ΔH;

[0128] The second backfat thickness difference condition is 0 > ΔH;

[0129] The material feeding adjustment coefficient δ1 > 1 on the first day;

[0130] Furthermore, by increasing feed or maintaining the current feeding situation for sows with different backfat conditions, precise feeding of sows at various stages can be achieved, further improving the accuracy of feeding.

[0131] Specifically, the machine learning methods involved in the central control module are as follows:

[0132] Step S1: Collect the sow's production data set and simultaneously collect the sow's daily feed and water intake information;

[0133] Step S2: Measure the backfat of each sow at different stages of gestation, based on the sow's current gestation time.

[0134] Step S3: Collect the backfat standards of sows at different stages, and the corresponding daily feed intake standards for sows at the corresponding stages;

[0135] Step S4: Use the various information features collected in steps S1 to S3 to perform data modeling to obtain a dataset;

[0136] Step S5: Apply the dataset to machine learning to construct the precision feeding curve for sows;

[0137] Step S6: Construct a classification model of the sow feeding curve and conduct visual analysis to explore the relevant factors affecting sow feed intake;

[0138] Step S7: Based on the analyzed factors, the machine adjusts the daily feed amount for the sows to provide precise feeding.

[0139] In step S7, the view analysis includes visualization analysis and data visualization. Through view analysis, the visualization analysis includes descriptive analysis, normative analysis and predictive analysis, to find the factors that affect the backfat of sows, and then to accurately regulate the feeding of sows.

[0140] Visual analysis involves visualization and data visualization. Visual analysis describes the relationship between sow production datasets, cognitive information, and backfat, and identifies the root causes. Rule analysis can learn from the current backfat status of sows and formulate precise feeding plans. Predictive analysis can identify and suggest future situations, predict trends, and make adjustments to achieve precise feeding of sows.

[0141] Machine learning is used to obtain the curve of precise feeding of sows, so as to achieve the purpose of precise feeding of sows under different factors at different times;

[0142] The central control module uses machine learning to achieve intelligent operation. It employs a dataset formed by the fusion of multiple features, uses a small amount of labeled data and a large amount of unlabeled data for semi-supervised learning, and makes predictions based on expected data. The model organizes the data through the learning structure to make predictions, thereby achieving classification and regression of sow production datasets and feeding information. The machine learning algorithms used include instance-based learning algorithms, dimensionality reduction algorithms, association rule learning, and model fusion algorithms.

[0143] In machine learning, instance-based learning algorithms model production datasets and feeding information to obtain a sample database. By comparing new information with these databases, predictions can be made. Dimensionality reduction algorithms simplify various types of data while also summarizing and describing them. They can classify and regress production datasets and feeding information. Association rule learning can identify the relationships between various data and describe them using appropriate rules, thus providing data support for subsequent curve construction. Model fusion algorithms can combine the above algorithms into a single prediction, providing accurate data references for feeding regulation.

[0144] Among them, the instance-based learning algorithm uses K-nearest neighbors (KNN). The entire training dataset represents the prediction of new data points by searching for the K most similar instances in the entire training set and summarizing the output variables of these K instances.

[0145] The dimensionality reduction algorithm used is Logistic Linear Discriminant Analysis (LDA), which consists of statistical attributes of the data and is calculated for each class. For a single input variable, these include: the mean of each class and the variance calculated across all classes. LDA works by calculating the discriminant value for each class and predicting the class with the maximum value.

[0146] Association rule learning observes associations between different variables in the data. The algorithm's task is to find the rules that best describe these relationships, which means acquiring knowledge about the dependencies or associations between an event and other events. Commonly used association rule algorithms include the Apriori algorithm and the Eclat algorithm.

[0147] Model fusion algorithms combine multiple simple, separately trained weak machine learning algorithms, integrating their predictions into a single prediction. Typically, this integrated prediction is more accurate than the prediction of any single algorithm. Common model fusion enhancement methods include: Boosting, Bagging, AdaBoost, stacked generalization, GBM algorithm, GBRT algorithm, and Random Forest.

[0148] It is understood that the machine learning algorithms used in this invention are not limited to the types mentioned above, as long as they can fulfill the required machine learning requirements, and no specific limitations are made here.

[0149] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0150] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A sow feeding intelligent control system, characterized in that, The application relates to a pig feeding device, which comprises the following modules: a feeding module connected with a feed warehouse for storing feed; a conveying module connected with the feeding module for conveying the feed output by the feeding module; a discharging module connected with the conveying module and comprising a discharging port arranged above a trough for spreading the feed output by the conveying module into the trough; a detecting module connected with the discharging module for detecting the current feed height in the trough and the current backfat thickness of a sow, which comprises a height sensor arranged on the inner wall of the trough for detecting the feed height in the trough and a backfat thickness detector arranged above the trough for detecting the backfat thickness of the sow when the sow is eating; a central control module connected with the feeding module, the conveying module, the discharging module and the detecting module for determining whether the stability of the discharging process is within the allowable range according to the average height of the feed in the trough, wherein The area of the trough is S, the discharging volume of the discharging module in a single measurement period is V, and the average height The calculation formula is: , is the average height of the feed in the trough before discharging measured by the detection module. a first type of determination mode is that the central control module determines that the stability of the discharging process is lower than the allowable range under a preset first height condition, preliminarily determines that the continuity of the feed discharging is lower than the allowable range, and secondarily determines whether the continuity of the discharging is lower than the allowable range according to the discharging time length required for reaching the standard feed height; a second type of determination mode is that the central control module determines that the stability of the discharging process is lower than the allowable range under a preset second height condition, and adjusts the discharging height to a first discharging height by calculating the difference between the current feed height in the trough and the preset first height; a third type of determination mode is that the central control module determines that the stability of the discharging process is within the allowable range under a preset third height condition; wherein the first height condition is that the feed height is less than a first preset height, the second height condition is that the feed height is greater than or equal to the first preset height and less than or equal to a second preset height, and the third height condition is that the feed height is greater than the second preset height; the first preset height is less than the second preset height; three types of adjustment modes for the discharging height are determined according to the difference between the current feed height in the trough and the preset first height under the preset second height condition, wherein a first type of adjustment mode is that the central control module adjusts the discharging height to a preset discharging height under a preset first height difference condition; a second type of adjustment mode is that the central control module adjusts the discharging height to a first discharging height by using a preset second discharging height adjustment coefficient under a preset second height difference condition; a third type of adjustment mode is that the central control module adjusts the discharging height to a second discharging height by using a preset first discharging height adjustment coefficient under a preset third height difference condition. The first height difference value condition is that the difference between the current feed height in the trough and the preset first height is less than or equal to a first preset height difference value; the second height difference value condition is that the difference between the current feed height in the trough and the preset first height is greater than the first preset height difference value and less than or equal to a second preset height difference value; the third height difference value condition is that the difference between the current feed height in the trough and the preset first height is greater than the second preset height difference value; the first preset height difference value is less than the second preset height difference value, and the preset first discharge height adjustment coefficient is less than the preset second discharge height adjustment coefficient; The two types of secondary determination methods for determining whether the discharge continuity is lower than the allowable range according to the required discharge time length to reach the standard feed height range under the first height condition, wherein The first type of continuity secondary determination method is that the central control module secondarily determines whether the discharge continuity is within the allowable range under a preset first discharge time length condition; The first type of continuity secondary determination method is that the central control module secondarily determines whether the discharge continuity is lower than the allowable range under a preset second discharge time length condition, and adjusts the discharge port diameter to the first discharge port diameter by calculating the difference between the required discharge time length to reach the standard feed height range and the preset discharge time length; The preset first discharge time length condition is that the required discharge time length to reach the standard feed height range is less than or equal to the preset discharge time length; and the preset second discharge time length condition is that the required discharge time length to reach the standard feed height range is greater than the preset discharge time length; The two types of adjustment methods for the discharge port diameter are determined according to the difference between the required discharge time length to reach the standard feed height range and the preset discharge time length under the preset second discharge time length condition, wherein The first type of diameter adjustment method is that the central control module discharges according to the preset discharge port diameter under a preset first discharge time length difference condition; The second type of diameter adjustment method is that the central control module adjusts the discharge port diameter to the first discharge diameter using a preset first diameter adjustment coefficient under a preset second discharge time length difference condition; The preset first discharge time length difference condition is that the difference between the required discharge time length to reach the standard feed height range and the preset discharge time length is less than or equal to a preset discharge time length difference value; the preset second discharge time length difference condition is that the difference between the required discharge time length to reach the standard feed height range and the preset discharge time length is greater than the preset discharge time length difference value; and the preset first diameter adjustment coefficient is greater than 1; The central control module is also used to secondarily adjust the discharge height to a second corresponding discharge height according to the average delay time length of the multiple sows, and adjust the feeding amount per unit time to a corresponding value according to the growth amount of the pig fat in the historical data.

2. The sow feeding intelligent control system according to claim 1, characterized in that, The two types of determination methods for determining whether the overall conveying speed of the conveying part to the discharging part is within the allowable range according to the average delay time length of the multiple sows, wherein The first type of determination method is that the central control module determines whether the overall conveying speed is within the allowable range under a preset first delay time length condition; The second type of determination mode is that the central control module determines that the overall feeding speed is lower than the allowable range under a preset second delay time condition, and adjusts the discharging height to a third discharging height by calculating the difference between the average delay time of the current feeding and the preset first delay time. The preset first delay time condition is that the current average delay time is less than or equal to the first average delay time, and the second delay time condition is that the current average delay time is greater than the first average delay time.

3. The sow feeding intelligent control system according to claim 2, characterized in that, The central control module determines two types of adjustment modes for the discharging height according to the time difference between the average delay time of the current feeding and the preset first delay time under a preset second delay time condition, wherein The first discharging height adjustment mode is that the central control module feeds the feed according to the preset parameters under the preset first average delay time condition of the sow feeding, and continues to record the sow-related values. The second discharging height adjustment mode is that the central control module adjusts the discharging height to the third discharging height using a third discharging height adjustment coefficient under a preset second average delay time condition of the sow feeding. The third discharging height adjustment coefficient is greater than 0 and less than 1.

4. The sow feeding intelligent control system according to claim 3, characterized in that, The central control module determines two types of determination modes for whether the growth speed of the sow is within the normal range according to the currently measured backfat thickness of the sow, wherein The first type of growth speed determination mode is that the central control module determines that the growth speed of the sow is within the allowable range when the current backfat thickness of the sow is under a preset first backfat thickness condition. The second type of growth speed determination mode is that the central control module determines that the growth speed of the sow is lower than the allowable range when the current backfat thickness of the sow is under a preset second backfat thickness condition, and adjusts the daily discharging amount to a corresponding value by calculating the difference between the current backfat thickness of the sow and the preset first backfat thickness. The backfat thickness of the sow in each production stage is different, the preset first backfat thickness condition is that the current backfat thickness of the sow is greater than or equal to the first backfat thickness, and the preset second backfat thickness condition is that the current backfat thickness of the sow is less than the first backfat thickness.

5. The sow feeding intelligent control system according to claim 4, characterized in that, The central control module determines two types of adjustment modes for the subsequent feed discharging amount according to the difference between the current backfat thickness and the first backfat thickness under a preset second backfat thickness condition, wherein The first type of discharging amount adjustment mode is that the central control module feeds according to the current daily discharging amount under a preset first backfat thickness difference condition. The second type of discharging amount adjustment mode is that the central control module uses a daily discharging amount first adjustment coefficient to increase the daily discharging amount to a first preset daily discharging amount under a preset second backfat thickness difference condition.

6. The sow feeding intelligent control system according to claim 5, characterized in that, The first backfat thickness difference condition is that the difference between the current backfat thickness and the first backfat thickness is positive, and the second backfat thickness difference condition is that the difference between the current backfat thickness and the first backfat thickness is negative. The first daily discharging amount adjustment coefficient is greater than 1.

Images