Intelligent rationing system for pig house feed supply

Abstract

The invention relates to the technical field of artificial intelligence, and discloses an intelligent rationing system for pig house feed supply, which comprises the following steps: performing identity recognition on pigs in a feeding area through radio frequency identification tags, and extracting weight, growth cycle and behavior characteristics; based on historical ingestion records, health data and environmental factors, a dynamic nutritional requirement model of the pigs is constructed, and the current feed requirement is predicted in combination with a multi-factor regression algorithm; according to the feed demand result, the feeding amount and the feeding frequency of the corresponding trough are adjusted in real time; dynamically adjusting the power of a conveying motor and the pressure difference of a pipeline section by utilizing a variable-frequency driving control technology; and collecting the ingestion response and the feeding execution state of the pigs, and outputting an updated pig allocation result in combination with online feedback and historical data differences. The feeding device has the advantage that the feeding stability is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an intelligent feed distribution system for pig houses. Background Art

[0002] In existing automatic feeding systems for pig houses, fixed time intervals are often used to control the opening of feeding valves to achieve timed feeding. Although some systems have the ability to distribute feed by age or stage, in actual operation, uneven feeding at the end of the feed delivery pipeline often occurs. Due to differences in the length and pressure of the delivery pipeline, the feeding port close to the main feed bin gets the feed first, while the feeding port at the end has a delay in feeding or even temporarily no feed, resulting in the pigs in the end pens being unable to eat synchronously at the beginning of each feeding. This persistent imbalance will accumulate into differences in pig weight over a long feeding cycle, affecting the consistency of slaughter and increasing the difficulty of breeding and management. Therefore, it is necessary to design an intelligent feed distribution system for pig houses that improves feeding stability. Summary of the Invention

[0003] In response to the deficiencies in the prior art, the present invention provides an intelligent feed distribution system for pig houses, which has the advantage of improving feeding stability and solves the problems in the above-mentioned background technology.

[0004] To achieve the above-mentioned purpose of improving feeding stability, the present invention provides the following technical solution: an intelligent feed distribution system for piggeries, comprising: Pig identification module: Uses radio frequency identification tags to identify pigs in the feeding area, extracts weight, growth cycle and behavioral characteristics, and determines whether the pigs need to be fed. If so, it enters the feeding parameter modeling module; Feeding parameter modeling module: Based on historical feeding records, health data and environmental factors, it builds a dynamic nutritional requirement model for pigs, and combines a multi-factor regression algorithm to predict current feed demand and determine whether there is any abnormality in feed demand. If so, it enters the feeding control module; Feeding control module: According to the feed demand results, the feeding amount and feeding frequency of the corresponding feed trough are adjusted in real time, and a multi-point pressure monitoring device is used to determine whether there is flow abnormality at the end of the feeding pipeline. If so, the module enters the pipeline balancing control module; Pipeline balancing control module: Utilizes variable frequency drive control technology to dynamically adjust the conveying motor power and the pressure difference in the pipeline section. Based on the operating data of the conveying motor and the feeding pipeline after each feeding, it determines whether the operating data needs to be optimized. If so, it enters the data adaptive optimization module; Data adaptive optimization module: collects pigs' feeding response and feeding execution status, combines online feedback with historical data differences, dynamically modifies feeding strategy parameters through adaptive learning algorithms, and outputs updated pig ration results.

[0005] Preferably, the process of determining whether the pigs need to be fed is: Read the pigs’ RFID tag information and match it with their health records; Collect the pigs' eating behavior characteristic data in the current time period, including eating frequency, eating duration and eating posture changes; Combining the pig's current weight, growth cycle stage and historical feeding records, the pig's feeding probability value is calculated through a behavioral pattern analysis model; When the pig feeding probability value is higher than the set behavioral response threshold and the current time interval exceeds the minimum feeding interval threshold, it is determined that the pig needs to enter the feeding process.

[0006] Preferably, the process of constructing a dynamic nutritional requirement model for pigs based on historical feeding records, health data, and environmental factors is as follows: Collect the physiological and behavioral characteristics of pigs at each growth stage, including phased feed intake, weight change trends, physiological development indicators and daily behavioral activity; Based on the time series recording method, the physiological and behavioral characteristics are structured and organized into the nutritional intake history samples of individual pigs, forming a time characteristic sequence for constructing a dynamic nutritional demand model; Collect environmental monitoring data in the pig house and calculate the influence coefficient of environmental monitoring data on pigs' feeding behavior and nutrient absorption efficiency through statistical regression; A multivariate regression algorithm was used to construct a dynamic nutritional requirement model that dynamically adapts to changes in pig status.

[0007] Preferably, the process of predicting current feed demand by combining a multi-factor regression algorithm is as follows: Collect the current pig's weight, growth cycle and key physiological health indicators as basic input factors for individual status; The environmental monitoring data and pig house operation data are input into the dynamic nutritional demand model. The internal weight mechanism of the dynamic nutritional demand model is used to differentiate the basic input factors, and the interference of redundant variables is suppressed through regularization. Finally, the feed requirement corresponding to the pigs at the current moment is output.

[0008] Preferably, the process of determining whether there is an abnormality in feed demand is: Taking the current physiological and behavioral characteristics of pigs and environmental parameters as input, the dynamic nutritional requirement model outputs the current predicted feed requirement value; Extract measured feed supply data from the pigs' historical feeding records and calculate the pigs' average feed requirement and standard deviation of feed requirement; Compare the current predicted feed requirement with the average feed requirement of the pigs, calculate the relative deviation ratio, and use the standard deviation of feed requirement as the normalization scale to obtain the abnormal deviation score; Combine the pig's current health status indicator and activity status, correct the abnormal deviation score, and obtain the abnormal confidence factor; If the abnormal confidence factor is greater than the set tolerance threshold, it is determined that the current feed demand is abnormal; If the abnormal confidence factor is less than or equal to the set tolerance threshold, it is determined that there is no abnormality in the current feed demand.

[0009] Preferably, the process of determining whether there is flow abnormality at the end of the feed pipe is as follows: By deploying multiple micro-pressure sensing nodes at the end of the feeding pipeline, real-time data on pressure changes over time during the feeding process is collected; According to the target pressure variation range preset when designing the feeding system, combined with the actual pressure data collected by the current micro-pressure sensor, a pressure difference index is constructed, and the flow rate fluctuation rate per unit time is calculated; When the flow rate fluctuation rate is greater than the set time threshold, it is determined that there is a flow abnormality at the feeding end; When the flow rate fluctuation rate is less than or equal to the set time threshold, it is determined that there is no flow abnormality at the feeding end.

[0010] Preferably, the process of dynamically adjusting the conveying motor power and the pressure difference of the pipeline section is: Real-time data collection of feed end pressure, pressure difference in each middle section, and end flow rate data is generated to generate a multi-dimensional parameter set reflecting the dynamic state of feed, forming the feed state parameters of the current round, and judging whether the pressure difference of the pipeline section is within the target stable range. If not, the adjustment instruction is triggered; The regulation instructions are executed through variable frequency drive control technology, which adjusts the operating frequency of the conveying motor in real time and regulates the motor output power and speed; After each round of feeding, the duration of each feeding section, the motor power change curve and the pressure difference fluctuation amplitude are recorded as the feeding response data of this round, and the data are summarized to form a feeding response database; A control strategy is built based on a feeding response database. A self-learning gain adjustment algorithm is introduced into the control strategy. The feeding state parameters, motor output, and pressure difference change data of historical high-efficiency rounds are extracted from the feeding response database. Combined with the current round parameters, the key adjustment coefficients in the control strategy are dynamically corrected. Compare the motor power consumption, feeding time and pressure difference stability indicators under the same feeding conditions before and after adjustment, and calculate the feeding process stability score.

[0011] Preferably, the process of determining whether the operating data needs to be optimized is: After each feeding task is completed, key operating data of the feeding process is recorded, including the power change curve of the conveying motor, the duration of each feeding section, the pipeline pressure fluctuation amplitude and the real-time feeding volume fed back by the end flow sensor; Collect behavioral response information of the current batch of pigs being fed and calculate the matching degree of feeding behavior response; Perform difference analysis on the feeding parameter samples of this round of feeding operation data and the feeding parameter samples with high stability and high feeding behavior response matching in the historical records, and calculate the performance deviation factor; When the performance deviation factor exceeds the preset threshold, it is determined that there is room for optimization of the current feeding control parameters, and the feeding control parameters are sent to the data adaptive optimization module.

[0012] Preferably, the process of outputting the updated pig rationing result is: Based on the key operating data recorded during the feeding process, the implementation effect of the current feeding strategy is evaluated to form a feeding feedback data set; Compare the recommended feed supply parameters output by the dynamic nutrient requirement model with the actual feeding performance of each pig in the feeding feedback data set after the current feeding round to identify the deviation between the recommended feed supply parameters and actual performance; Based on the deviation results of the recommended feed supply parameters, the built-in online learning mechanism is used to fine-tune the pig characteristic weights and environmental adaptation parameters in the dynamic nutritional requirement model; The output includes pig number, recommended feed type, recommended feeding amount and feeding period.

[0013] Compared with the existing technology, the present invention provides an intelligent pig house feed distribution system with the following beneficial effects: 1. Rapid and accurate identification of pigs in the feeding area can be achieved through radio frequency identification technology. This not only allows efficient acquisition of key data such as individual weight, growth cycle, and behavioral characteristics, but also allows for dynamic assessment of whether pigs have the current feeding needs in combination with a real-time behavioral judgment mechanism, thereby avoiding overfeeding or missed feeding and improving feed utilization efficiency and pig herd health.

[0014] 2. By integrating historical feeding data, physiological health information and environmental change factors, a refined individual dynamic nutritional demand model is constructed, and a multi-factor regression method is introduced to improve the accuracy of feed demand prediction and personalized response capabilities. Potential abnormal feeding needs can be identified in a timely manner, improving the scientific nature and adaptability of feeding decisions.

[0015] 3. By adjusting the feeding parameters of the trough in real time, accurate feeding can be achieved on demand. At the same time, with the help of multi-point pressure monitoring devices, the flow status at the end of the feeding pipeline can be sensed to detect potential feeding anomalies in time, effectively ensuring the stability and continuity of the feeding process.

[0016] 4. Through variable frequency drive and dynamic feedback control mechanism, the conveying motor power and the pressure difference of each section of the pipeline are intelligently adjusted to make the feeding process more energy-efficient and efficient. At the same time, the system operating status is evaluated based on the operating data after the feeding is completed to ensure that the system maintains good stability and adjustment sensitivity under different workloads.

[0017] 5. By integrating individual feeding behavior feedback and pipeline feeding execution data, and using online learning algorithms to continuously optimize feeding strategies, the system dynamically outputs individualized feed type, feeding amount, and feeding period adjustment results, enabling iterative upgrades of the intelligent system and improving long-term operation accuracy and resource utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a structural schematic diagram of the present invention. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0020] Example 1: Please refer to Figure 1 As shown, an intelligent pig house feed distribution system according to an embodiment of the present invention includes: Pig identification module: Identify the pigs in the feeding area through radio frequency identification tags, extract weight, growth cycle and behavioral characteristics, and determine whether the pigs need to be fed. If so, enter the feeding parameter modeling module.

[0021] The process of judging whether a pig needs to be fed in the pig identification module is as follows: Read the pig's radio frequency identification tag information and match it with the pig's health record. A high-frequency RFID reader installed at the entrance to the feeding area automatically obtains the electronic ear tag identification code of the pig entering the area. The identification code is quickly compared with the health record in the local database to extract the corresponding pig file data, including birth date, vaccination history, disease records, growth curve, and feeding abnormality history. Collects characteristic data on the pigs' eating behavior during the current time period, including eating frequency, duration, and changes in eating posture; records the pigs' residence time in front of the feed trough, head movement trajectory, and changes in eating posture in real time; uses image recognition technology to analyze eating action patterns, and combines pressure change data to identify the start and end times of eating, and then calculates the frequency and duration of eating; Combining the pig's current weight, growth cycle stage, and historical feeding records, the behavioral pattern analysis model calculates the pig's feeding probability value. Real-time weight data is obtained and the pig's current stage of lactation, nursing, fattening, or rearing is determined. Historical feeding records and reference feeding models for corresponding growth stages are called and combined with current behavioral characteristics. These are input into a behavioral pattern analysis model built based on a deep decision tree or lightweight neural network. The current feeding probability value is output, reflecting the degree of match between the pig's feed demand willingness and physiological needs. When the pig's feeding probability value is higher than the set behavioral response threshold and the current time interval exceeds the minimum feeding interval threshold, it is determined that the pig needs to enter the feeding process; two threshold control variables are set: the behavioral response threshold and the minimum feeding interval threshold; when the feeding probability value output by the behavioral model is higher than the set threshold and the time from the last feeding exceeds the minimum interval, it is determined that the pig has generated an effective feeding demand.

[0022] Feeding parameter modeling module: Based on historical feeding records, health data and environmental factors, a dynamic nutritional requirement model for pigs is constructed, and a multi-factor regression algorithm is used to predict current feed demand and determine whether there is any abnormality in feed demand. If so, the feeding control module is entered.

[0023] The process of constructing a dynamic nutritional requirement model for pigs based on historical feeding records, health data, and environmental factors is as follows: The physiological and behavioral characteristics of pigs at various growth stages are collected, including phased feed intake, weight change trends, physiological development indicators, and daily behavioral activity. The collected objects include the pigs' phased feed intake, weight change trends, and physiological development indicators. Behavioral activity data is obtained through a visual monitoring system or inertial sensors, including standing time, activity path, and feeding frequency. Each data point is bound to a timestamp and a unique pig number to form a set of physiological and behavioral characteristics of the pigs at a specific growth stage. Based on a time series recording method, physiological and behavioral characteristics are structured and organized into historical samples of individual pig nutrition intake, forming a time feature sequence for constructing a dynamic nutrition requirement model. A fixed time window is used to aggregate the data to construct continuous time series samples. Each time point sample contains structured features such as feed intake, weight change, and behavioral indicators. This creates a chronologically arranged two-dimensional sample matrix, which is used to explore the correlation trends between pig nutrition intake and physiological and behavioral changes. Environmental monitoring data from the piggery was collected and the impact coefficient of this data on pigs' feeding behavior and nutrient absorption efficiency was calculated using statistical regression. Daily temperature, humidity, ammonia concentration, light intensity, and pen density information were obtained from environmental sensors within the pen. The sensitivity score of environmental factors to feeding behavior was derived by calculating the correlation between environmental indicators and historical changes in feed intake. A multivariate regression algorithm is used to construct a dynamic nutritional requirement model that dynamically adapts to changes in pig status; an input variable matrix is ​​established, including the physiological characteristics and environmental indicators of pigs at the current time point; historical feeding data is used as the target variable, and modeling is carried out through methods such as multivariate linear regression or ridge regression to output the estimated nutritional requirement value at the current time point.

[0024] The process of predicting current feed demand in the feeding parameter modeling module by combining the multi-factor regression algorithm is as follows: The current pig weight, growth cycle, and key physiological health indicators are collected as basic input factors for the individual status. The pig identification module obtains the pig's identity information and calls the real-time weighing device or historical weight database to obtain the current weight. The pig's growth cycle information is read to reflect the pig's development stage. Key physiological health indicators are obtained and collected in real time through physiological sensing equipment or health monitoring systems. The above data are aggregated and formatted to form a multi-dimensional input vector of the pig's individual status. Environmental monitoring data and pig house operation data are input into the dynamic nutritional demand model, and the internal weight mechanism of the dynamic nutritional demand model is used to differentiate the basic input factors, and the interference of redundant variables is suppressed through regularization, and the feed requirement corresponding to the pigs at the current moment is finally output; environmental monitoring data and pig house operation data are collected; environmental parameters and individual state inputs are combined to form a complete set of input variables, which are sent to the multi-factor regression model; the model assigns different importance weights to different input variables based on the weight coefficients obtained through training, highlights the role of key factors, and finally outputs the feed requirement corresponding to the pigs at the current moment; after the model calculation, the feed demand forecast value of the pigs at the current time point is generated, indicating the reasonable feeding amount; the predicted value is used as a reference standard for the subsequent feeding control module to dynamically adjust the feeding amount and feeding frequency.

[0025] The process of judging whether there is an abnormality in the feeding parameter modeling module is as follows: The dynamic nutritional requirement model uses the pig's current physiological and behavioral characteristics and environmental parameters as input to output the current predicted feed requirement value. The dynamic nutritional requirement model uses the pig's current weight, growth cycle, physiological health indicators, and data such as temperature, humidity, and ammonia concentration collected by environmental sensors to input data. After the model is calculated, the predicted theoretical feed requirement value of the pig at the current time point is output, reflecting the reasonable feeding standard. Extract measured feed supply data from the pigs' historical feeding records and calculate the pigs' average feed requirement and standard deviation of feed requirement. Query the pigs' historical feeding database and select feeding records of pigs at similar growth stages and with similar health indicators. Perform statistical analysis on the selected historical data and calculate the average feed requirement and standard deviation of the requirement, which serve as a reference for the normal feed requirement range for the pigs. Compare the current forecasted feed requirement with the average feed requirement of the pigs, calculate the relative deviation ratio, and use the standard deviation of feed requirement as the normal scale to obtain an abnormal deviation score. Calculate the difference between the current forecasted feed requirement and the historical average: Deviation = Current Forecast Value - Historical Average. Divide the deviation by the historical standard deviation to obtain a standardized deviation score, which reflects the degree to which the current demand deviates from the normal level. The larger the score, the more the current forecasted demand deviates from the historical normal range, and the higher the potential abnormality. Combine the pig's current health status and activity status to correct the abnormal deviation score and obtain the abnormal confidence factor; obtain the pig's real-time health status and behavioral activity index; make weighted adjustments to the abnormal deviation score based on health and behavioral status, for example, increase the confidence level of the abnormal score when health is abnormal; and finally output the corrected abnormal confidence factor as a reference for determining feed demand abnormality. If the abnormal confidence factor is greater than the set tolerance threshold, it is determined that the current feed demand is abnormal; If the abnormal confidence factor is less than or equal to the set tolerance threshold, it is determined that there is no abnormality in the current feed demand.

[0026] Feeding control module: According to the feed demand results, the feeding amount and feeding frequency of the corresponding feed trough are adjusted in real time, and the multi-point pressure monitoring device is used to determine whether there is flow abnormality at the end of the feeding pipeline. If so, the pipeline balance control module is entered.

[0027] The process of judging whether there is flow abnormality at the end of the feeding pipeline in the feeding control module is as follows: By deploying multiple micro-pressure sensing nodes at the end of the feeding pipeline, real-time data on pressure changes over time during the feeding process is collected. Multiple micro-pressure sensors are evenly installed at the end of the feeding pipeline to ensure coverage of key monitoring points. The sensors collect real-time pressure values ​​in the pipeline during the feeding process, and the sampling frequency meets the requirements for dynamic change detection. Based on the target pressure variation range preset during the design of the feeding system and the actual pressure data collected by the current micro-pressure sensor, a pressure difference index is constructed, and the flow rate fluctuation rate per unit time is calculated. According to the design specifications of the feeding system, a target pressure variation range is set as a reference range for the pressure during normal operation. The actual pressure data collected in real time is compared with the target pressure range, and the pressure difference at each time point is calculated to form a pressure difference index. The variation range of the pressure difference per unit time is statistically calculated and converted into a flow rate fluctuation index to evaluate the stability of the feeding flow rate. When the flow rate fluctuation rate is greater than the set time threshold, it is determined that there is a flow abnormality at the feeding end; When the flow rate fluctuation rate is less than or equal to the set time threshold, it is determined that there is no flow abnormality at the feeding end.

[0028] It is understandable that the function of judging whether there is flow abnormality at the end of the feed pipe is as follows: Function 1: Timely detect abnormal conditions such as blockage, leakage or air blockage during the feeding process, ensure that the feed can be smoothly delivered to the terminal feed trough according to the set flow rate, and ensure continuous and stable feeding of pigs; Function 2: Provide data support for the dynamic regulation of the feeding system, so that the system can quickly switch to the pipeline balancing control module after detecting an abnormality, adjust the motor power and valve opening, and thus maintain the overall pressure balance and energy efficiency optimization of the feeding system.

[0029] The technical solution of this embodiment is: through dynamic modeling of pigs' feeding behavior, weight changes and nutritional needs, the feeding amount and feeding frequency of the corresponding feed trough are adjusted in real time. At the same time, the multi-point pressure monitoring device arranged at the end of the feeding pipeline can collect pressure change data in real time to determine whether there is flow abnormality. If an abnormality is detected, the system automatically switches to the pipeline balancing control module to perform closed-loop adjustment of the conveying motor power and pipeline valve opening. Accurate and efficient feeding management of pigs is achieved, significantly improving feed utilization and the health level of the pig herd; at the same time, through multi-point pressure monitoring and adaptive flow control, problems such as feeding blockage and flow rate imbalance are effectively prevented, ensuring the continuity and stability of the feeding process, thereby improving the energy efficiency and reliability of the entire intelligent feeding system.

[0030] Example 2: Figure 1 As shown, an intelligent feed distribution system for pig houses also includes the following modules: Pipeline balancing control module: Utilizes variable frequency drive control technology to dynamically adjust the conveying motor power and the pressure difference of the pipeline section. Based on the operating data of the conveying motor and the feeding pipeline after each feeding, it is determined whether the operating data needs to be optimized. If so, the module enters the data adaptive optimization module.

[0031] The process of dynamically adjusting the power of the conveying motor and the pressure difference of the pipeline section in the pipeline balancing control module is as follows: Real-time data collection of feed end pressure, pressure differentials in each mid-section, and end flow rate data is generated to generate a multi-dimensional parameter set reflecting the dynamic state of feeding, forming the feeding state parameters of the current round. It determines whether the pressure differential of the pipeline section is within the target stable range. If not, an adjustment instruction is triggered. Using an embedded sensor network, data from the feed end pressure sensor, data from the pressure differential sensors in each mid-section of the pipeline, and the output of the end flow meter are collected in real time during the feeding process. The data collected by each sensor is synchronously integrated and marked with timestamps to form continuous multi-dimensional data points. After filtering the collected data and removing outliers, a multi-dimensional feeding state parameter set for the current feeding task is constructed in time series. The regulation instructions are executed through variable frequency drive control technology, which adjusts the operating frequency of the conveying motor in real time, regulating the motor's output power and speed. During the feeding execution phase, the variable frequency drive control module is called to dynamically adjust the operating frequency of the conveying motor based on the current round of feeding status parameters. The motor frequency is adjusted in real time to synchronously control its speed and output power, ensuring that the feeding speed matches the target flow rate. The actuator unit in the parallel control valve module synchronously adjusts the valve opening of the pipe section according to the pressure difference change trend of each mid-section. After each feeding round, the duration of each feeding segment, the motor power change curve, and the pressure difference fluctuation amplitude are recorded as the feeding response data of this round, and the data are summarized to form a feeding response database. After each feeding round, the key regulation indicators of this round are automatically recorded, including the duration of each feeding segment, the power change curve of the conveying motor, and the pressure difference fluctuation amplitude of each mid-segment. The feeding response efficiency of this round is compared with the regulation effect samples of historical high-efficiency rounds, and feature classification is performed based on the statistical learning method. A regulation response database containing the triple of input state, control action, and feedback effect is constructed. A control strategy is constructed based on a feeding response database. A self-learning gain adjustment algorithm is introduced into the control strategy. Feeding state parameters, motor output, and pressure difference change data of historical high-efficiency rounds are extracted from the feeding response database. Combined with the current round parameters, the key adjustment coefficients in the control strategy are dynamically corrected. A self-learning mechanism is introduced to compare the deviation degree of the current round feeding response with the historical best response in the database. The gain adjustment algorithm is used to automatically fine-tune key parameters in the control strategy, such as the gain coefficient in the motor power adjustment function and the adjustment ratio corresponding to the valve execution speed. Through continuous iteration and feedback correction, the motor power output response accuracy and valve linkage stability are improved, and the dynamic adaptability of the overall feeding process is optimized. Compare the motor power consumption, feeding time and pressure difference stability indicators under the same feeding conditions before and after adjustment, and calculate the feeding process stability score.

[0032] The process of determining whether the operating data needs to be optimized in the pipeline balancing module is as follows: After each feeding task is completed, key operating data of the feeding process is recorded, including the power change curve of the conveying motor, the duration of each feeding section, the pipeline pressure fluctuation amplitude, and the real-time feeding volume fed by the terminal flow sensor. The power change of the conveying motor during the entire feeding process is monitored and recorded in real time to form a power change curve. The feeding duration of each pipeline section is recorded to reflect the time distribution of material transportation. The pressure fluctuation data of each node in the pipeline is collected, the pressure fluctuation amplitude is calculated, and the pressure stability during the transportation process is evaluated. The real-time feeding volume feedback is obtained through the terminal flow sensor to verify whether the actual feeding reaches the expected target. Collect behavioral response information from the current batch of pigs being fed and calculate the matching degree of feeding behavior response; use the pig behavior monitoring system to collect indicators such as the pigs' feeding time, feeding frequency, and behavioral activity after feeding; analyze the collected behavioral data to evaluate the pigs' acceptance and response effect of this feeding; compare the behavioral response indicators with the expected feeding model to calculate the matching degree of behavioral response, reflecting the suitability and effect of feeding; Perform a differential analysis between the current round of feeding operation data and feeding parameter samples in historical records that demonstrate high stability and high matching of feeding behavior responses, and calculate the performance deviation factor. Select typical sample data from the historical database that demonstrate excellent feeding parameter performance, stable system operation, and high matching of behavior responses. Compare key indicators such as the current round's feeding power curve, feeding duration, pressure fluctuation, and flow rate feedback with those of the typical samples. Statistical analysis methods are used to calculate the deviation between the current data and historical samples, deriving a comprehensive performance deviation factor to quantify the degree of deviation of the current feeding parameters. When the performance deviation factor exceeds the preset threshold, it is determined that there is room for optimization of the current feeding control parameters, and the feeding control parameters are sent to the data adaptive optimization module.

[0033] Data adaptive optimization module: collects pigs' feeding response and feeding execution status, combines online feedback with historical data differences, and outputs updated pig ration results.

[0034] The process of outputting the updated pig ration results in the data adaptive optimization module is as follows: Based on the key operating indicators recorded during the feeding process, the system evaluates the effectiveness of the current feeding strategy and forms a feeding feedback data set. It also automatically collects the key operating indicators of the current feeding cycle, including feeding time, feed volume, and conveying efficiency. Compare the recommended feed supply parameters output by the dynamic nutritional requirement model with the actual feeding performance of each pig in the feeding feedback data set after the current feeding round to identify the deviation between the recommended feed supply parameters and the actual performance; retrieve the feed requirement value predicted by the dynamic nutritional requirement model for the corresponding pig; compare the difference between the actual feeding performance and the value predicted by the dynamic nutritional requirement model; evaluate the matching degree of feeding parameters to determine whether there is insufficient or excessive deviation; Based on the deviation results of the recommended feed supply parameters, the built-in online learning mechanism is used to fine-tune the pig characteristic weights and environmental adaptation parameters in the dynamic nutritional requirement model. The model parameters are adjusted using the incremental learning algorithm based on the feedback data and deviation results. The individual pig characteristic weights and environmental impact parameters are refined and updated. Output pig ration results including pig number, recommended feed type, recommended feeding amount and feeding period; The output information includes: Pig number: uniquely identifies each pig; Recommended feed type: feed category determined based on nutritional requirements and feed ratio; Recommended feed amount: The precise feed weight or volume determined for the pig’s current needs; Feeding period: recommended start and end times for feeding to ensure optimal matching of feed delivery and feeding behavior; The rationing results are sent to the automatic feeding equipment or breeders through the system to achieve precise feeding.

[0035] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0036] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent feed distribution system for piggeries, characterized in that: include: Pig identification module: Uses radio frequency identification tags to identify pigs in the feeding area, extracts weight, growth cycle and behavioral characteristics, and determines whether the pigs need to be fed. If so, it enters the feeding parameter modeling module; Feeding parameter modeling module: Based on historical feeding records, health data and environmental factors, it builds a dynamic nutritional requirement model for pigs, and combines a multi-factor regression algorithm to predict current feed demand and determine whether there is any abnormality in feed demand. If so, it enters the feeding control module; Feeding control module: According to the feed demand results, the feeding amount and feeding frequency of the corresponding feed trough are adjusted in real time, and a multi-point pressure monitoring device is used to determine whether there is flow abnormality at the end of the feeding pipeline. If so, the module enters the pipeline balancing control module; Pipeline balancing control module: Utilizes variable frequency drive control technology to dynamically adjust the conveying motor power and the pressure difference in the pipeline section. Based on the operating data of the conveying motor and the feeding pipeline after each feeding, it determines whether the operating data needs to be optimized. If so, it enters the data adaptive optimization module; Data adaptive optimization module: collects pigs' feeding response and feeding execution status, combines online feedback with historical data differences, and outputs updated pig ration results.

2. The intelligent pig house feed distribution system according to claim 1, characterized in that: The process of determining whether a pig needs to be fed is as follows: Read the pigs’ RFID tag information and match it with their health records; Collect the pigs' eating behavior characteristic data in the current time period, including eating frequency, eating duration and eating posture changes; Combining the pig's current weight, growth cycle stage and historical feeding records, the pig's feeding probability value is calculated through a behavioral pattern analysis model; When the pig feeding probability value is higher than the set behavioral response threshold and the current time interval exceeds the minimum feeding interval threshold, it is determined that the pig needs to enter the feeding process.

3. The intelligent pig house feed distribution system according to claim 2, characterized in that: The process of building a dynamic nutritional requirement model for pigs based on historical feeding records, health data, and environmental factors is as follows: Collect the physiological and behavioral characteristics of pigs at each growth stage, including phased feed intake, weight change trends, physiological development indicators and daily behavioral activity; Based on the time series recording method, the physiological and behavioral characteristics are structured and organized into the nutritional intake history samples of individual pigs, forming a time characteristic sequence for constructing a dynamic nutritional demand model; Collect environmental monitoring data in the pig house and calculate the influence coefficient of environmental monitoring data on pigs' feeding behavior and nutrient absorption efficiency through statistical regression; A multivariate regression algorithm was used to construct a dynamic nutritional requirement model that dynamically adapts to changes in pig status.

4. The intelligent pig house feed distribution system according to claim 3, characterized in that: The process of predicting current feed demand by combining the multi-factor regression algorithm is as follows: Collect the current pig's weight, growth cycle and key physiological health indicators as basic input factors for individual status; The environmental monitoring data and pig house operation data are input into the dynamic nutritional demand model. The internal weight mechanism of the dynamic nutritional demand model is used to differentiate the basic input factors, and the interference of redundant variables is suppressed through regularization. Finally, the feed requirement corresponding to the pigs at the current moment is output.

5. The intelligent pig house feed distribution system according to claim 4, characterized in that: The process of determining whether there is an abnormality in feed demand is as follows: Taking the current physiological and behavioral characteristics of pigs and environmental parameters as input, the dynamic nutritional requirement model outputs the current predicted feed requirement value; Extract measured feed supply data from the pigs' historical feeding records and calculate the pigs' average feed requirement and standard deviation of feed requirement; Compare the current predicted feed requirement with the average feed requirement of the pigs, calculate the relative deviation ratio, and use the standard deviation of feed requirement as the normalization scale to obtain the abnormal deviation score; Combine the pig's current health status indicator and activity status, correct the abnormal deviation score, and obtain the abnormal confidence factor; If the abnormal confidence factor is greater than the set tolerance threshold, it is determined that the current feed demand is abnormal; If the abnormal confidence factor is less than or equal to the set tolerance threshold, it is determined that there is no abnormality in the current feed demand.

6. The intelligent pig house feed distribution system according to claim 5, characterized in that: The process of determining whether there is flow abnormality at the end of the feed pipe is as follows: By deploying multiple micro-pressure sensing nodes at the end of the feeding pipeline, real-time data on pressure changes over time during the feeding process is collected; According to the target pressure variation range preset when designing the feeding system, combined with the actual pressure data collected by the current micro-pressure sensor, a pressure difference index is constructed, and the flow rate fluctuation rate per unit time is calculated; When the flow rate fluctuation rate is greater than the set time threshold, it is determined that there is a flow abnormality at the feeding end; When the flow rate fluctuation rate is less than or equal to the set time threshold, it is determined that there is no flow abnormality at the feeding end.

7. The intelligent pig house feed distribution system according to claim 6, characterized in that: The process of dynamically adjusting the conveying motor power and the pressure difference of the pipeline section is as follows: Real-time data collection of feed end pressure, pressure difference in each middle section, and end flow rate data is generated to generate a multi-dimensional parameter set reflecting the dynamic state of feed, forming the feed state parameters of the current round, and judging whether the pressure difference of the pipeline section is within the target stable range. If not, the adjustment instruction is triggered; The regulation instructions are executed through variable frequency drive control technology, which adjusts the operating frequency of the conveying motor in real time and regulates the motor output power and speed; After each round of feeding, the duration of each feeding section, the motor power change curve and the pressure difference fluctuation amplitude are recorded as the feeding response data of this round, and the data are summarized to form a feeding response database; A control strategy is built based on a feeding response database. A self-learning gain adjustment algorithm is introduced into the control strategy. The feeding state parameters, motor output, and pressure difference change data of historical high-efficiency rounds are extracted from the feeding response database. Combined with the current round parameters, the key adjustment coefficients in the control strategy are dynamically corrected. Compare the motor power consumption, feeding time and pressure difference stability indicators under the same feeding conditions before and after adjustment, and calculate the feeding process stability score.

8. The intelligent pig house feed distribution system according to claim 7, characterized in that: The process of determining whether the operating data needs to be optimized is as follows: After each feeding task is completed, key operating data of the feeding process is recorded, including the power change curve of the conveying motor, the duration of each feeding section, the pipeline pressure fluctuation amplitude and the real-time feeding volume fed back by the end flow sensor; Collect behavioral response information of the current batch of pigs being fed and calculate the matching degree of feeding behavior response; Perform difference analysis on the feeding parameter samples of this round of feeding operation data and the feeding parameter samples with high stability and high feeding behavior response matching in the historical records, and calculate the performance deviation factor; When the performance deviation factor exceeds the preset threshold, it is determined that there is room for optimization in the current feeding operation data, and the feeding operation data is sent to the data adaptive optimization module.

9. The intelligent pig house feed distribution system according to claim 8, characterized in that: The process of outputting the updated pig ration results is: Based on the key operating data recorded during the feeding process, the implementation effect of the current feeding strategy is evaluated to form a feeding feedback data set; Compare the recommended feed supply parameters output by the dynamic nutrient requirement model with the actual feeding performance of each pig in the feeding feedback data set after the current feeding round to identify the deviation between the recommended feed supply parameters and actual performance; Based on the deviation results of the recommended feed supply parameters, the built-in online learning mechanism is used to fine-tune the pig characteristic weights and environmental adaptation parameters in the dynamic nutritional requirement model; The output includes pig number, recommended feed type, recommended feeding amount and feeding period.

Images