Barn environment intelligent monitoring method and system based on internet of things
By acquiring and analyzing environmental data within the cattle shed, and calculating characteristics and comprehensive impact indicators, intelligent monitoring and real-time control of the cattle shed environment have been achieved. This has solved the problem of uneven temperature and humidity, improved monitoring accuracy and stability, and ensured the health of the cattle and production efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HUNAN LINGMAO ANIMAL HUSBANDRY CO LTD
- Filing Date
- 2026-04-22
- Publication Date
- 2026-05-29
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure CN122108272A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of IoT-based smart cattle farming technology, specifically to an IoT-based intelligent monitoring method and system for cattle shed environment. Background Technology
[0002] In contemporary society, with the rapid development of standardization and large-scale operations in the livestock and poultry industry, high-yield breeds in large-scale farms are particularly sensitive to changes in the breeding environment. For cattle farming, intelligent monitoring of the cattle shed environment is a core element in promoting the transformation and upgrading of animal husbandry towards precision and intelligence, playing a crucial role in ensuring cattle health, improving production efficiency, and achieving sustainable development in livestock farming. During the monitoring process, temperature and humidity are the core factors affecting cattle health: abnormal temperature directly leads to slowed growth and reduced feed conversion rates, while humidity imbalances may exacerbate the risk of pathogenic microorganism transmission. Therefore, controlling the temperature and humidity in cattle sheds is key to ensuring a stable environment.
[0003] Currently, intelligent monitoring of cattle shed environments primarily relies on the integration of IoT sensors, wireless transmission networks, and temperature and humidity control systems, providing real-time feedback through visual displays. In cattle sheds, cattle produce carbon dioxide and moisture through respiration and heat dissipation, causing continuous fluctuations in temperature and humidity. Abnormal temperatures and humidity can trigger stress responses in cattle, impacting their health. Therefore, regulating equipment is needed for real-time adjustments.
[0004] Although temperature and humidity control instruments can enable real-time monitoring and regulation of the environment, differences in cattle density in different areas of the barn can lead to uneven changes in temperature and humidity. These localized differences can cause abnormal fluctuations in temperature and humidity during adjustments, thus reducing the accuracy of monitoring the barn's environmental conditions. Summary of the Invention
[0005] In view of the above, it is necessary to provide an intelligent monitoring method and system for cattle shed environment based on the Internet of Things to solve the above problems.
[0006] The first aspect of this application provides a method for intelligent monitoring of cattle shed environment based on the Internet of Things, the method comprising: Obtain environmental data for each area of the cattle shed at each sampling time, including temperature and humidity data; The correlation between temperature and humidity in each region at each sampling time within a preset time period is obtained. Combined with the degree of disorder and overall distribution of environmental data changes within the preset time period, the characteristic indicators of each region at each sampling time are obtained. The operation interval for adjusting preset parameters is determined by the distribution characteristics of characteristic indicators of all areas between each area and the vent in the preset time period at each operation time, as well as the distance distribution characteristics between areas, to determine the comprehensive impact index of each area at each operation time; based on the characteristic indicators, comprehensive impact index, and the distribution characteristics of the correlation of each area in the preset time period at each operation time, the characteristic value of each area in each operation time is determined. Based on the proportion of the characteristic values of each region at each operation time to the values of all regions, and the measured environmental data at each operation time, comprehensive environmental data for each operation time is obtained, enabling intelligent monitoring of the cattle shed environment.
[0007] The specific process for obtaining the feature indicators of each region at each sampling time is as follows: Based on the degree of disorder of environmental changes between adjacent times within a preset time period at each sampling time in each region, and combined with the overall distribution, the environmental fluctuation characteristic value of each region at each sampling time is obtained. Based on the correlation between temperature and humidity in each region within a preset time period at each sampling time, and the environmental fluctuation characteristic value, a characteristic index is calculated. The characteristic index is negatively correlated with the environmental fluctuation characteristic value and positively correlated with the correlation.
[0008] Specifically, obtaining the environmental fluctuation characteristic values of each region at each sampling time is as follows: The degree of disorder of environmental differences in each region at all adjacent times within a preset time period at each sampling time is obtained, and the negative correlation mapping result with the normalized environmental mean within the same preset time period is positively fused to obtain the environmental fluctuation characteristic value of each region at each sampling time.
[0009] Specifically, determining the comprehensive impact index of each region at each operation time involves: The distribution similarity of characteristic indicators of each region and each region between it and the ventilation opening is analyzed at all sampling times within a preset time period at each operation time. Combined with the distance between regions, the regional influence indicators of each region at each operation time are obtained. The characteristic indicators of each area between each zone and the vent at each operating moment are used as the weights of the corresponding area's influence indicators. The weighted average of all areas between each zone and the vent is then calculated to obtain the comprehensive influence indicator of each area at each operating moment.
[0010] Specifically, obtaining the regional impact index of each region at each operation time involves: recording each region between each region and the vent as its corresponding intermediate region, and positively fusing the negative correlation mapping result of the distance between each region and its intermediate regions with the distribution similarity obtained at each operation time to obtain the regional impact index of each region at each operation time.
[0011] Specifically, the distribution characteristics of the correlation are the coefficients of variation of the correlation obtained from all sampling times within a preset time period for each operation time.
[0012] Specifically, the feature value is calculated by multiplying the sum of the feature index and the comprehensive influence index of each region at each operation time with the negative correlation mapping result of the coefficient of variation to obtain the feature value of each region at each operation time.
[0013] Specifically, obtaining the comprehensive environmental data at each operation moment includes: The proportion of the characteristic value of each region at each operation time to the total value of all regions is used as the weight of the measured environmental data at each operation time. The measured environmental data of all regions at each operation time are weighted and summed to obtain the comprehensive environmental data at each operation time.
[0014] Specifically, the intelligent monitoring of the cattle shed environment involves using the comprehensive environmental data of the cattle shed at each operating moment and the preset environmental range as input to the PID algorithm, outputting a control signal to adjust the cattle shed environment, and visually displaying the adjusted environment.
[0015] Secondly, embodiments of this application also provide an intelligent monitoring system for cattle shed environment based on the Internet of Things, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.
[0016] This application has at least the following beneficial effects: This application allows for a comprehensive understanding of the environmental conditions in various areas of the cattle shed by regularly collecting temperature and humidity data in different zones. This helps identify abnormal changes in temperature and humidity, enabling timely intervention to ensure the comfort and health of the cattle.
[0017] Secondly, based on the degree of disorder and overall distribution of environmental data, and combined with the correlation between temperature and humidity, characteristic indicators can be generated. These indicators can reflect the environmental stability and suitability of each region, providing a basis for subsequent environmental regulation.
[0018] By analyzing the distance and characteristic indicators of each zone and its area relative to the vents, a comprehensive impact index can be derived. This process helps to understand the differences in ventilation and heat distribution among different zones, providing data support for optimizing ventilation systems and thermal management strategies. Based on the comprehensive impact index and characteristic indicators, characteristic values for each zone are determined. This index reflects the environmental changes in each zone at different operating times, helping to track and predict environmental trends within the cattle shed.
[0019] Finally, by combining the characteristic values of each area with the measured environmental data, comprehensive environmental data is calculated. This indicator can provide accurate data support for the overall environmental monitoring of cattle sheds, which helps to identify problems in a timely manner and make corresponding adjustments. When controlling the temperature and humidity in cattle sheds, the feedback signals of real-time adjustment are used to regulate the cattle shed environment, which improves the stability of the cattle shed environment and avoids frequent abnormal situations in the intelligent monitoring of cattle shed environment based on the Internet of Things. Attached Figure Description
[0020] Figure 1 A flowchart illustrating the steps of an IoT-based intelligent monitoring method for cattle shed environment according to an embodiment of this application; Figure 2 This is a schematic diagram illustrating the acquisition of comprehensive environmental data according to one embodiment of this application. Detailed Implementation
[0021] In the description of the embodiments in this application, the words "exemplary," "or," and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary," "or," and "for example" is intended to present the relevant concepts in a specific manner.
[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in this application's specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
[0023] It should also be noted that the terms "first" and "second" in this application and its accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The methods disclosed in the embodiments of this application or the methods shown in the flowcharts include one or more steps for implementing the method. Without departing from the scope of protection of this application, the execution order of multiple steps can be interchanged, and some steps can also be deleted.
[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.
[0025] The following description, in conjunction with the accompanying drawings, details the specific scheme of the IoT-based intelligent monitoring method and system for cattle shed environment provided in this application.
[0026] Please see Figure 1 The diagram illustrates a flowchart of an IoT-based intelligent monitoring method for cattle shed environment according to an embodiment of this application. The method includes the following steps: The first step: Obtain environmental data for each area of the cattle shed at each sampling time, including temperature and humidity data.
[0027] To achieve intelligent monitoring of the cattle shed environment based on the Internet of Things (IoT), this application considers dividing the cattle shed into n equally spaced areas, starting from the entrance. The value of n can be set according to specific circumstances; in this embodiment, n is set to 10. While avoiding facilities such as fans, sprinklers, misting systems, and water curtains, temperature and humidity sensors are used on the guardrails of the walkways within each area, 1.5 meters above the ground, to acquire temperature and humidity signals for that area. The temperature and humidity sensors used are high-precision industrial-grade sensors to ensure real-time acquisition of high-precision data. When deploying sensors according to the specific implementation scenario, the deployment interval of the same type of sensor is kept as consistent as possible, and the sampling frequency is uniformly set to 1Hz. Furthermore, the acquired data is uniformly calibrated using the UTC+8 time standard to avoid time errors affecting subsequent calculations.
[0028] The second step is to obtain the correlation between temperature and humidity in each region at each sampling time within a preset time period. Combined with the degree of disorder and overall distribution of environmental data changes within the preset time period, the characteristic indicators of each region at each sampling time are obtained.
[0029] The acquired data was analyzed. Considering that in a cattle shed setting, cattle continuously release a large amount of water vapor into the environment through normal physiological processes such as respiration and skin evaporation, when ventilation is insufficient, temperature and humidity will rise synchronously with the enclosure of the shed, showing a high correlation. However, when cattle are dispersed or move frequently, local areas have sufficient space and better ventilation, typically resulting in continuous air exchange. Because temperature and humidity changes randomly during gas exchange, this exchange process usually disrupts the synergy between temperature and humidity, leading to a relatively low correlation between them.
[0030] Based on the above analysis, the steady-state conditions of temperature and humidity within a local time period are obtained to control the temperature and humidity of the cattle shed. Each sampling moment and the preceding v minutes are defined as the sampling period for that sampling moment, and all sampled data within that period are used as the sample set for that sampling moment. The value of v can be adjusted by the implementer according to the actual situation. In this embodiment, v is set to 2. When the data obtained at the moments preceding the sampling moment is insufficient to form a sample set, the corresponding number of sampled data is used as the corresponding sample set.
[0031] Furthermore, analysis of the sampling sets corresponding to each sampling time revealed that in cattle shed environments, due to the cattle's typically unrestricted movement, densely packed areas can experience abnormally high local temperatures and humidity levels due to their continuous metabolism, thus exacerbating heat stress in the cattle. On the other hand, excessive ventilation in certain areas may lead to relatively low temperatures and humidity in those areas. When cattle move to these low-temperature, low-humidity areas, they may experience cold stress, negatively impacting livestock farming.
[0032] Based on the above analysis, when a local area has insufficient ventilation due to dense cattle populations, temperature and humidity will rise synchronously due to the cattle's metabolism, exhibiting a high degree of consistency between temperature and humidity. However, when a local area receives effective ventilation and temperature and humidity control, air circulation occurs, and this exchange process usually disrupts the synergy between temperature and humidity, resulting in a relatively low correlation between temperature and humidity. Therefore, this embodiment obtains the correlation between all temperature and humidity data in the sampling set at each sampling time. The maximum information coefficient method is used in this embodiment. The acquisition of the maximum information coefficient is a well-known technique and will not be elaborated upon here. Taking sampling time i of region a as an example, the correlation between the temperature and humidity data of region a at sampling time i is denoted as... In this embodiment, the correlation is calculated using the maximum information coefficient. When insufficient ventilation occurs in a localized area due to overcrowding of cattle, the temperature and humidity in the cattle shed rise synchronously with respiration and skin moisture evaporation, exhibiting a high degree of positive correlation. The value is relatively high; when the area is ideally ventilated, the temperature and humidity during ventilation will change with the air exchange, and the correlation between temperature and humidity is relatively low, meaning the obtained value is relatively low. The value is low.
[0033] In cattle sheds, areas with a high density of cattle continuously generate heat. The cattle's bodies also create physical barriers, disrupting and obstructing airflow, resulting in narrower and more tortuous airflow channels. Temperature and humidity in these areas typically change slowly, exhibiting smooth temperature and humidity curves, and are generally at higher levels compared to other areas. In contrast, areas with sparse or frequently moving cattle experience fluctuating temperatures and humidity levels, as the number of cattle changes constantly. The total amount of heat and moisture generated also varies with the number of cattle. These areas are primarily influenced by air from the ventilation system and other areas, resulting in better overall air circulation and relatively lower temperatures and humidity. Temperature and humidity fluctuations are rapid due to the effects of air exchange, and the movement of cattle adds further randomness to these fluctuations, resulting in wave-like temperature and humidity curves of varying sizes.
[0034] Based on the above analysis, temperature and humidity data at different locations in the cattle shed are acquired. Taking temperature data from the environmental data as an example, this application obtains the temperature difference between adjacent sampling times at each sampling point in each region, based on the sampling set at each sampling time. The disorder level of all temperature differences in the sampling set is then obtained. The temperature difference is calculated using the absolute value of the temperature difference; the disorder level is calculated using permutation entropy, a well-known technique, which will not be elaborated further. The embedding dimension of the permutation entropy is set to 3, and the delay time is set to 1. The disorder level obtained in the a-th region at sampling time i is denoted as... The negative correlation mapping results with the normalized temperature mean in the sampling set are positively fused to obtain the temperature fluctuation feature value. In this embodiment, the forward fusion of variables uses a multiplication method, and the specific calculation formula is as follows: ; This represents the normalized value of the mean temperature in the sampling set of the a-th region at sampling time i, used to reflect the overall distribution of temperature data; The value is a very small positive number to ensure that the denominator is not 0. In this embodiment, the value is 0.01, and the normalization method adopts the maximum and minimum value normalization method. The negative correlation mapping result represents the normalized temperature mean. In other embodiments, the inverse of the temperature mean can also be obtained, and the inverse can be used as the exponent of an exponential function with the natural constant as the base, and the result of the exponential function can be used as the negative correlation mapping result.
[0035] It should be understood that in the areas where cattle are concentrated in the cattle shed, the overall temperature is higher and fluctuates less, resulting in smaller temperature fluctuation characteristic values. In the areas of the cattle shed where cattle are dispersed and move frequently, the overall temperature is lower due to better air circulation. Furthermore, the temperature fluctuates frequently and randomly as air circulates and cattle move within the area. The overall temperature change rate at sampling points fluctuates frequently, leading to greater disorder in the data, a smaller average temperature, and larger overall temperature fluctuation characteristic values.
[0036] Furthermore, based on the correlation and temperature fluctuation characteristic values obtained for each region at each sampling time, a characteristic index is calculated. The characteristic index is negatively correlated with the temperature fluctuation characteristic value and positively correlated with the correlation.
[0037] In this embodiment, taking temperature as an example, the corresponding feature index is obtained for sampling time i of the a-th region. Its formula is: in, This represents the correlation of the a-th region at sampling time i; This represents the temperature characteristic fluctuation value of the a-th region at sampling time i; the characteristic index is used to characterize the temperature characteristics within the sampling set corresponding to the target time of region a. The value is a very small positive number to ensure the denominator is not zero; in this embodiment, it is set to 0.01. In the cattle shed, when cattle congregate in one area for a long time, the temperature and humidity in that area will continuously and steadily change due to the cattle's metabolism. This results in a higher correlation between temperature and humidity, and the overall temperature remains smooth, leading to a larger characteristic index. Conversely, when there are areas in the cattle shed where cattle move or there are fewer cattle, the overall ventilation is better, resulting in a lower correlation between the temperature and humidity in those local areas, and a smaller characteristic index.
[0038] The third step: the operation interval for preset parameter adjustment, by using the distribution characteristics of characteristic indicators of all areas between each area and the vent in the preset time period corresponding to each operation time, and the distance distribution characteristics between areas, to determine the comprehensive impact index of each area at each operation time; based on the characteristic indicators, comprehensive impact index, and the distribution characteristics of the correlation of each area in the preset time period of each operation time, to determine the characteristic value of each area in each operation time.
[0039] Considering the varying density of cattle in different areas of a cattle shed, and the varying cattle density between each area and the ventilation openings, the impact on the ventilation effect of the target area also differs. When there is a highly dense area of cattle between a target area and the ventilation opening, the ventilation effect in that area will be relatively poor, as the target area is blocked by this high-density area, resulting in insufficient ventilation and temperature and humidity changes similar to those in the high-density area. Conversely, the better the ventilation effect between the target area and the ventilation opening, the smaller the impact of these areas on the target area.
[0040] In this embodiment, the equipment is set to be adjusted once every sampling period to regulate the temperature and humidity in the cattle shed. The time of each adjustment operation is called the operation time.
[0041] Based on the above analysis, taking temperature data as an example, and specifically the operation time t of the a-th region as an example, the maximum information coefficient is calculated by using the feature indicators corresponding to all sampling times in the sampling set at that time, and comparing them with the feature indicators corresponding to all sampling times in the sampling set of the region near the vent at the same time. , where j represents the region j between the a-th region and the vent, and is denoted as the j-th intermediate region corresponding to the a-th region.
[0042] Furthermore, an area impact index is constructed for the a-th region and the region j between it and the vent at operation time t. The specific formula is as follows: ,in, The normalized value of the Euclidean distance between the a-th region and its corresponding intermediate region j is determined by using the straight-line distance between the two regions using the same sampling device. The normalized value of the Euclidean distance is determined by the maximum-minimum normalization method. It is an exponential function with the natural constant as its base; This represents the maximum information coefficient obtained from the sampling set of temperature data of region a and its corresponding intermediate region j at operation time t; It is a very small positive number, ensuring that the denominator is not 0. In this embodiment, the value is 0.01.
[0043] The closer the area between the target area and the vent is to the target area, the more significant its influence. A higher correlation in temperature characteristics indicates a dense herd of cattle on one side of the vent, resulting in similar temperature characteristics and a greater impact on the target area. Conversely, the farther the area between the target area and the vent is from the target area, the weaker its influence. Furthermore, when cattle are more dispersed within the area between the target area and the vent, the correlation between the temperature characteristics of these areas and the target area is lower due to air circulation, resulting in a smaller overall impact.
[0044] Furthermore, a comprehensive impact index is obtained by combining all areas on one side of the target area's ventilation opening. The formula is as follows: This is used to represent the overall intensity of the influence of the area on one side of the ventilation opening of the target area on the target area, where, This represents the comprehensive impact index of region a at operation time t; M represents the total number of regions between region a and the vent. The characteristic index of the intermediate region j between the a-th region and the vent at operation time t.
[0045] Furthermore, considering that when cattle move around in the barn, they generate a lot of heat and moisture through metabolism during the movement. Each cow is a constantly moving heat and moisture source that affects the temperature and humidity inside the barn. Therefore, the temperature and humidity in different areas of the barn will change in real time as the cattle move. When temperature control is implemented, if the movement of cattle causes frequent changes in the density of cattle in a certain area, the stability of the temperature and humidity in that area will be relatively poor, and the temperature reference value of these areas with poor stability will be relatively small.
[0046] Based on the above analysis, temperature and humidity data at different locations in the cattle shed were acquired. Taking temperature data as an example, in each region, the dispersion of the correlation of all sampling times in the sampling set corresponding to operation time t was obtained. In this embodiment, the dispersion of multiple variables was calculated using the coefficient of variation. The feature value of the target operation time was obtained. ;in, This represents the characteristic value of the a-th region at operation time t; This represents the characteristic index of the a-th region at operation time t; This represents the comprehensive impact index of the a-th region at operation time t. This represents the coefficient of variation for the a-th region at operation time t; The value is a very small positive number to ensure the denominator is not zero; in this embodiment, it is set to 0.01. When the target area is a cattle-concentrated area with little movement, the temperature in that area has a high correlation. The higher the density of cattle on the side of the ventilation opening, the better the temperature obtained. The higher the value, and the higher the temperature stability due to the dense gathering of cattle, the better the obtained... The smaller the value, the lower the yield. The larger the value, the more likely the temperature and humidity will change randomly within the target area when cattle move frequently. This leads to significant changes in the correlation between the values and the obtained data. The value is relatively small.
[0047] The fourth step: Based on the proportion of the characteristic values of each region at each operation time to the values of all regions, and the measured environmental data at each operation time, comprehensive environmental data for each operation time is obtained, and the cattle shed environment is intelligently monitored.
[0048] Furthermore, considering the need to regulate temperature in cattle sheds to ensure the health of the cattle, high-density areas are prone to high temperature and humidity when cattle are densely gathered in one area with little movement, which is detrimental to the healthy breeding of cattle. Therefore, the temperature and humidity of such areas should be used as an important reference for control. In contrast, in areas where cattle are scattered or in open areas, the temperature and humidity usually do not show abnormalities, and the reference weight for temperature and humidity control should be relatively small.
[0049] Based on the above analysis, real-time temperature and humidity weights are calculated for each region. Taking the temperature weight calculation at time i in region a as an example, the temperature weight at the target time is obtained. ,in, This indicates the total number of areas in the cowshed; This represents the temperature weight of the a-th region at operation time t; , These represent the feature values of the a-th region and the k-th region at operation time t, respectively; the humidity weight of each region at operation time t is obtained using the same calculation method based on the humidity data.
[0050] The temperature and humidity weights of each region are obtained in real time using the above calculation method. Based on the obtained temperature and humidity weights of each region, the temperature and humidity are weighted and accumulated separately. Taking the i-th time as an example, the final comprehensive temperature is obtained as follows: ,in, This represents the overall temperature of the cowshed at time i. This represents the measured temperature of the z-th region at the i-th time. This indicates the total number of areas in the cowshed. This represents the temperature weight of the z-th region at time i. Similarly, the comprehensive humidity of the cattle shed at the corresponding time is calculated in the same way. The calculated comprehensive temperature data and comprehensive humidity data are used as feedback temperature and feedback humidity, respectively, for subsequent control operations on the temperature and humidity of the cattle shed. Both the comprehensive temperature data and comprehensive humidity data are comprehensive environmental data. A schematic diagram of the acquisition of comprehensive environmental data is shown below. Figure 2 As shown.
[0051] To achieve real-time temperature control in the cattle shed, the current feedback temperature and preset temperature range are input into a PID control algorithm. The PID algorithm calculates and outputs a control signal to adjust the cattle shed temperature. Similarly, the feedback humidity and preset humidity range are input into the PID control algorithm, which outputs a control signal to adjust the cattle shed humidity. These temperature and humidity control signals are transmitted to the temperature and humidity control modules of an integrated temperature and humidity control system, respectively. The temperature control module of the integrated system controls the temperature inside the cattle shed, while its humidity control module controls the humidity. The temperature range is set to the optimal breeding temperature for cattle (10℃~24℃), and the humidity is set to 60%~70%. Furthermore, the real-time temperature and humidity data, along with the cattle shed's environmental temperature and humidity index, are visualized and transmitted to mobile devices. Relevant personnel can use these mobile devices to obtain real-time information about the cattle shed's environmental status, achieving intelligent monitoring of the cattle shed environment based on the Internet of Things (IoT).
[0052] Based on the same inventive concept as the above methods, this application also provides an IoT-based intelligent monitoring system for cattle shed environment, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-described IoT-based intelligent monitoring methods for cattle shed environment.
[0053] In the attached diagram Figure 1 and Figure 2 The architecture, functionality, and operation of possible implementations of the system, method, and computer program product according to embodiments of this application are illustrated. In this respect, Figure 1 or Figure 2 Each box in the figures may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the boxes may occur in a different order than shown in the figures. For example, two consecutive boxes may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the figures... Figure 1 and Figure 2 In the corresponding descriptions, the operations or steps corresponding to different boxes may occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed in essentially parallel, or they can sometimes be executed in reverse order, depending on the functions involved. Figure 1 and / or Figure 2 Each box in, and Figure 1 and / or Figure 2 The combination of boxes in the diagram can be implemented using a dedicated hardware-based system that performs the specified function or action, or it can be implemented using a combination of dedicated hardware and computer instructions.
[0054] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from its essential characteristics. Therefore, the embodiments described above should be considered exemplary and non-limiting in all respects; modifications to the technical solutions described in the foregoing embodiments, or equivalent substitutions of some technical features, without causing the essence of the corresponding technical solutions to deviate from the scope of the technical solutions in the embodiments of this application, should all be included within the protection scope of this application.
Claims
1. A method for intelligent monitoring of cattle shed environment based on the Internet of Things, characterized in that, The method includes the following steps: Obtain environmental data for each area of the cattle shed at each sampling time, including temperature and humidity data; The correlation between temperature and humidity in each region at each sampling time within a preset time period is obtained. Combined with the degree of disorder and overall distribution of environmental data changes within the preset time period, the characteristic indicators of each region at each sampling time are obtained. The operation interval for adjusting preset parameters is determined by the distribution characteristics of characteristic indicators of all areas between each area and the vent in the preset time period at each operation time, as well as the distance distribution characteristics between areas, to determine the comprehensive impact index of each area at each operation time; based on the characteristic indicators, comprehensive impact index, and the distribution characteristics of the correlation of each area in the preset time period at each operation time, the characteristic value of each area in each operation time is determined. Based on the proportion of the characteristic values of each region at each operation time to the values of all regions, and the measured environmental data at each operation time, comprehensive environmental data for each operation time is obtained, enabling intelligent monitoring of the cattle shed environment.
2. The intelligent monitoring method for cattle shed environment based on the Internet of Things as described in claim 1, characterized in that, The process of obtaining the feature indicators of each region at each sampling time is as follows: Based on the degree of disorder of environmental changes between adjacent times within a preset time period at each sampling time in each region, and combined with the overall distribution, the environmental fluctuation characteristic value of each region at each sampling time is obtained. Based on the correlation between temperature and humidity in each region within a preset time period at each sampling time, and the environmental fluctuation characteristic value, a characteristic index is calculated. The characteristic index is negatively correlated with the environmental fluctuation characteristic value and positively correlated with the correlation.
3. The intelligent monitoring method for cattle shed environment based on the Internet of Things as described in claim 2, characterized in that, The environmental fluctuation characteristic values of each region at each sampling time are obtained as follows: The degree of disorder of environmental differences in each region at all adjacent times within a preset time period at each sampling time is obtained, and the negative correlation mapping result with the normalized environmental mean within the same preset time period is positively fused to obtain the environmental fluctuation characteristic value of each region at each sampling time.
4. The intelligent monitoring method for cattle shed environment based on the Internet of Things as described in claim 1, characterized in that, The determination of the comprehensive impact index of each region at each operation time is specifically as follows: The distribution similarity of characteristic indicators of each region and each region between it and the ventilation opening is analyzed at all sampling times within a preset time period at each operation time. Combined with the distance between regions, the regional influence indicators of each region at each operation time are obtained. The characteristic indicators of each area between each zone and the vent at each operating moment are used as the weights of the corresponding area's influence indicators. The weighted average of all areas between each zone and the vent is then calculated to obtain the comprehensive influence indicator of each area at each operating moment.
5. The intelligent monitoring method for cattle shed environment based on the Internet of Things as described in claim 4, characterized in that, The method for obtaining the regional impact index of each region at each operation time is as follows: each region between each region and the vent is recorded as an intermediate region corresponding to each region, and the negative correlation mapping result of the distance between each region and its intermediate regions is positively fused with the distribution similarity obtained at each operation time to obtain the regional impact index of each region at each operation time.
6. The intelligent monitoring method for cattle shed environment based on the Internet of Things as described in claim 1, characterized in that, The distribution characteristics of the correlation are specifically the coefficient of variation of the correlation obtained from all sampling times within a preset time period for each operation time.
7. The intelligent monitoring method for cattle shed environment based on the Internet of Things as described in claim 6, characterized in that, The specific feature value is calculated by multiplying the sum of the feature index and the comprehensive influence index of each region at each operation time with the negative correlation mapping result of the coefficient of variation to obtain the feature value of each region at each operation time.
8. The intelligent monitoring method for cattle shed environment based on the Internet of Things as described in claim 1, characterized in that, The comprehensive environmental data obtained at each operation moment is specifically as follows: The proportion of the characteristic value of each region at each operation time to the total value of all regions is used as the weight of the measured environmental data at each operation time. The measured environmental data of all regions at each operation time are weighted and summed to obtain the comprehensive environmental data at each operation time.
9. The intelligent monitoring method for cattle shed environment based on the Internet of Things as described in claim 1, characterized in that, The intelligent monitoring of the cattle shed environment specifically involves using the comprehensive environmental data of the cattle shed at each operating moment and the preset environmental range as input to the PID algorithm, outputting a control signal to adjust the cattle shed environment, and visually displaying the adjusted environment.
10. An intelligent monitoring system for cattle shed environment based on the Internet of Things, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-9.