Sheep body temperature monitoring device and heat stress management method

Abstract

The invention provides a sheep body temperature monitoring device and a heat stress management method, and the method comprises the steps: obtaining a real-time body temperature signal based on the sheep body temperature monitoring device, obtaining real-time environment information based on an environment collection device, building a temperature compensation model according to the real-time body temperature signal and the environment information, and obtaining a real-time temperature change curve, the method comprises the following steps: acquiring a real-time temperature change curve, acquiring signal characteristics according to the real-time temperature change curve, comparing the signal characteristics with a preset reference value, calculating a real-time temperature change rate, constructing a heat stress evaluation model according to the signal characteristics and the temperature change rate, judging the heat stress state of a tested individual, and implementing heat management measures according to the heat stress state. The environment comfort level of animals in a farm can be improved, high-temperature stress generation and energy waste can be reduced, animal welfare guarantee can be provided for individual sheep in a high-temperature environment, and heat stress events can be effectively prevented and managed.

Description

Technical Field

[0001] The present invention relates to the field of smart breeding technology, and in particular to a sheep body temperature monitoring device and a heat stress management method. Background Art

[0002] At present, intensive farms refer to farms that carry out large-scale animal breeding in a highly organized and mechanized manner within a limited space. This breeding method can improve production efficiency, but it also brings animal welfare and health problems, especially putting higher requirements on the body temperature management of ruminants such as sheep. Traditional body temperature monitoring methods mainly rely on manual measurement, which is not only inefficient but also difficult to achieve continuous monitoring. The body temperature of sheep is an important indicator of their health status. Abnormal body temperature may be a sign of disease, stress or other health problems. In intensive breeding environments, if abnormal body temperature is not detected and handled in time, it may lead to the spread of diseases and affect the health of the entire flock. In addition to monitoring body temperature, effective thermal management is equally important for maintaining the comfort and health of sheep. Excessively high or low ambient temperatures will have adverse effects on sheep. However, existing thermal management methods often lack pertinence and real-time performance, and it is difficult to meet the needs of precise control in intensive breeding environments. For sheep, studying the sheep body temperature monitoring device for real-time adjustment of thermal management measures in intensive breeding environments has great research and practical value. Therefore, it is very necessary to design a sheep body temperature monitoring device and a heat stress management method. Summary of the invention

[0003] In order to overcome the deficiencies of the prior art, the object of the present invention is to provide a sheep body temperature monitoring device and a heat stress management method.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] The invention provides a sheep body temperature monitoring device, comprising: a graphene-based sensor, a signal processing circuit and a skin contact interface, wherein the sheep body temperature monitoring device is arranged on a tested sheep through an elastic band; the graphene-based sensor comprises a copper-clad polyimide film and a reduced graphene oxide layer, the side of the copper-clad polyimide film away from the sheep is the B side, and the side close to the sheep is the A side, the reduced graphene oxide layer is arranged on the A side of the copper-clad polyimide film, the signal processing circuit is arranged on the B side of the copper-clad polyimide film, and the skin contact interface is arranged on the outer side of the reduced graphene oxide layer; the signal processing circuit comprises an operational amplifier, an analog-to-digital converter, a microcontroller and a signal transmitter; and the skin contact interface is a hydrogel interface.

[0006] Preferably, the preparation method of the graphene-based sensor is:

[0007] A quantitative amount of graphene oxide solution is collected by a pipette and dropped on the A surface of the copper-clad polyimide film. After the solution dries, it is scanned and reduced by a laser marking machine under optimal laser parameters to obtain a reduced graphene oxide layer bonded to the copper-clad polyimide film.

[0008] Preferably, the signal processing circuit is prepared by:

[0009] The B surface of the copper-clad polyimide film is etched by a laser marking machine, and after multiple etchings, it is cleaned and dried to finally form the signal processing circuit.

[0010] Preferably, the preparation method of the hydrogel interface is:

[0011] Polyacrylamide and sodium alginate are mixed in proportion to form a solution with an interpenetrating network structure, and then vinyl-functionalized boron nitride nanosheets (v-BNNS) are mixed in, and the mixed solution is evenly coated on a mold by a cold lamination method to form a film, and the film is placed under suitable conditions for curing to form a hydrogel with high thermal conductivity, which is cut into a suitable size as needed and placed between the sheep and the graphene-based sensor;

[0012] The preparation process of the hydrogel is carried out under sterile conditions.

[0013] The present invention also provides a method for managing heat stress in sheep, comprising:

[0014] Based on the sheep body temperature monitoring device, real-time body temperature signals are obtained, and based on the environment collection device, real-time environmental information is obtained;

[0015] According to the real-time body temperature signal and environmental information, a temperature compensation model is constructed and a real-time temperature change curve is obtained;

[0016] Acquire signal characteristics according to the real-time temperature change curve, compare it with a preset reference value, and calculate the real-time temperature change rate;

[0017] Constructing a heat stress assessment model according to the signal characteristics and the temperature change rate to determine the heat stress state of the tested individual;

[0018] Thermal management measures are implemented according to the heat stress state.

[0019] Preferably, based on the sheep body temperature monitoring device, real-time body temperature signals are obtained and based on the environment acquisition device, real-time environmental information is obtained, specifically:

[0020] Determine the contact part between the sheep body temperature monitoring device and the tested sheep, shave the contact part, initialize the sheep body temperature monitoring device, and wear it to the contact part using an elastic band;

[0021] The environment collection device is arranged inside the sheep house, wherein the environment collection device includes a temperature and humidity sensor, an ammonia sensor and a sulfur dioxide sensor. When setting, the temperature and humidity sensor, the ammonia sensor and the sulfur dioxide sensor are integrated into a group in an array manner, and the sheep house area is divided into grids in the length direction, the width direction and the height direction. The number of array groups is determined according to the sheep house grid, and the calculation formula is:

[0022]

[0023] N|≤abc max

[0024] Where N is the number of array groups, d is the length of the sheep house, h is the width of the sheep house, l is the height of the sheep house, α is the number of grids in the length direction of the sensor array, β is the number of grids in the width direction of the sensor array, χ is the number of grids in the height direction of the sensor array, θ is the optimization coefficient, [] means rounding up the function to ensure that the number of sensors meets or exceeds the calculated value to ensure that each area in the sheep house can be effectively monitored, n is the number of sensor groups in the length direction of the sheep house, m is the number of sensor groups in the width direction of the sheep house, p is the number of sensor groups in the height direction of the sheep house, and the number of array groups does not exceed the maximum number of grids abc max ;

[0025] Establish a sensor matrix expression, then determine the influence of the overlapping area in the sensor coverage, associate the sensor matrix expression with the influence of the overlapping area, and finally optimize the layout points, thereby completing the optimal layout of the sensor array;

[0026] Among them, the sensor matrix expression is:

[0027] Matrix={(x i ,y j ,z k )|1≤i≤m,1≤j≤n,1≤k≤p}

[0028] In the formula, x i ,y j 、z k They are the points in the three directions of length, width and height;

[0029] The calculation formula for the overlapping area of ​​sensor coverage is:

[0030]

[0031] In the formula, V represents the coverage volume, C represents x i With y j , ∩ is the intersection of the coverage ranges, and ∪ is the union of the coverage ranges;

[0032] The calculation formula for associating the sensor matrix expression with the influence degree of the overlapping area is:

[0033]

[0034] Preferably, according to the real-time body temperature signal and environmental information, a temperature compensation model is constructed and a real-time temperature change curve is obtained, specifically:

[0035] The environmental information and sensor resistance signal are extracted as input, the input data is normalized and outliers are eliminated, and then input into the calibration formula to obtain the compensated temperature value. In addition, the monitoring time is used as the x-axis and the temperature value is used as the y-axis to obtain the real-time temperature change curve;

[0036] The calibration formula is:

[0037]

[0038] In the formula, q is the number of input data, x (i) is the sensor resistance signal, y (i) is the environmental information, p is the number of data categories, λ is the regularization coefficient, γ j is the compensation parameter vector, and the calculation formula is:

[0039]

[0040] Where β is the feedback ratio, is the partial derivative with respect to the jth data.

[0041] Preferably, the signal characteristics are obtained according to the real-time temperature change curve, and compared with a preset reference value to calculate the real-time temperature change rate, specifically:

[0042] According to the real-time temperature change curve, the real-time temperature value is extracted at fixed time intervals, the local maximum and minimum points of the temperature change curve are determined, the amplitude and frequency of the temperature fluctuation are calculated, the standard deviation and the root mean square value are calculated to quantify the discrete degree and fluctuation intensity of the temperature change, and the average temperature within a fixed time is used as a preset reference value to calculate the real-time temperature change rate;

[0043] Among them, the signal characteristics include T max , T min , Range, σ, RMS, the specific calculation formulas are as follows:

[0044] T max =max(T(t))

[0045] T min =min(T(t))

[0046] Range=T max -T min

[0047]

[0048] Where T(t) is the temperature value that changes with time;

[0049] The calculation formula of the temperature change rate is:

[0050]

[0051] Where ΔT is the temperature change within the Δt time range, Δt is the time change, T1 and T2 are the temperature values ​​at two different times, and t1 and t2 are the corresponding time values.

[0052] Preferably, a heat stress assessment model is constructed according to the signal characteristics and the temperature change rate to determine the heat stress state of the tested individual, specifically:

[0053] The signal characteristics and the temperature change rate are used as independent variables, and the heat stress state of the individual is used as the dependent variable. The association between the independent variable and the heat stress state is established through the Y function, and a coefficient correction method is set to prevent overfitting. The first-level decision threshold is dynamically adjusted according to the real-time monitoring data to adapt to the physiological changes of the individual and the fluctuations of environmental conditions. When the heat stress probability predicted by the model exceeds the set threshold, the system will determine that the individual is in a heat stress state. By setting different second-level decision thresholds, the heat stress assessment can identify different state levels with different sensitivities;

[0054] The calculation formula of the Y function is:

[0055] Y=U+S×Range+Equation(a)+Equation(b)+Equation(c)

[0056] In the formula, the calculation formulas of Equation (a), Equation (b), and Equation (c) are: Equation (a) = e (0.00182×RH+1.8×Am-5×RT×RH) ×(0.0054×T max 2 +0.00192×T min -0.0285)×(RH-30)

[0057]

[0058] Equation (c) = 0.0076 × T max -0.02×RMS×T min+0.5×Range 2 ×0.1×Sd-2

[0059] In the formula, U is the coefficient term, Y is the dependent variable vector of heat stress state, RT is the ambient temperature, RH is the ambient humidity, Am is the ammonia concentration, and Sd is the sulfur dioxide concentration;

[0060] The dynamically adjusting the first-level decision threshold according to the real-time monitoring data specifically includes:

[0061] P new =P old +K p ·(P base -P measured )

[0062] Where P new is the updated first-level decision threshold, P old is the first-level decision threshold before updating, K p is the decision gain, P base is the benchmark decision threshold, P measured Real-time monitoring data;

[0063] P base The calculation formula is:

[0064]

[0065] By setting different secondary decision thresholds, heat stress assessment can identify different status levels with different sensitivities, including: according to the primary decision threshold, the secondary decision threshold is set with a fluctuation of 10% up and down;

[0066] The secondary decision threshold is divided into two categories, namely the first threshold and the second threshold.

[0067] Preferably, thermal management measures are implemented according to the heat stress state, specifically:

[0068] When the heat stress assessment model determines that the tested sheep are in a state of heat stress, the corresponding heat stress management measures are automatically triggered according to the level of heat stress. Among them, the preset feedback mechanism dynamically adjusts the intensity of heat stress management measures according to the real-time physiological parameter monitoring results of the tested sheep.

[0069] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0070] The present invention provides a sheep temperature monitoring device and a heat stress management method, the device includes: a graphene-based sensor, a signal processing circuit and a skin contact interface; the method includes obtaining a real-time body temperature signal based on the sheep temperature monitoring device and obtaining real-time environmental information based on an environment acquisition device, constructing a temperature compensation model and obtaining a real-time temperature change curve based on the real-time body temperature signal and environmental information, obtaining signal characteristics based on the real-time temperature change curve, and comparing it with a preset reference value, calculating the real-time temperature change rate, constructing a heat stress assessment model based on the signal characteristics and the temperature change rate, for judging the heat stress state of the tested individual, and implementing heat management measures according to the heat stress state. The present invention can improve the environmental comfort level of animals in farms, reduce the generation of high temperature stress and energy waste, provide animal welfare protection for sheep individuals in high temperature environments, and effectively prevent and manage heat stress events. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0072] Figure 1 A schematic diagram of a process flow of a method for managing heat stress in sheep provided by an embodiment of the present invention;

[0073] Figure 2 A schematic diagram of the structure of a sheep body temperature monitoring device provided by an embodiment of the present invention;

[0074] Figure 3 A schematic diagram of the preparation process of the sheep body temperature monitoring device in the embodiment provided by the present invention;

[0075] Figure 4 A detailed schematic diagram of the sheep heat stress management method in the embodiment provided by the present invention.

[0076] Figure numerals: 1. Sheep body temperature monitoring device; 2. Elastic strap; 3. Sheep under test; 11. Graphene-based sensor; 12. Signal processing circuit. DETAILED DESCRIPTION

[0077] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0078] The purpose of the present invention is to provide a body temperature monitoring device for sheep, which has little interference to the tested individual, has high tolerance to the tested individual, is easy to wear and has high test accuracy. Another purpose of the present invention is to provide a method for managing heat stress in sheep, which processes the body temperature signal data and the ambient temperature and humidity information of the sheep, further monitors the stress status of the sheep, and thus better judges and implements the heat management control method, and finally better protects the animal welfare of the sheep and improves the productivity and economic benefits of the farm.

[0079] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0080] Figure 2 The device structure diagram provided by the embodiment of the present invention is as follows: Figure 2 As shown, the present invention provides a sheep body temperature monitoring device 1, comprising:

[0081] Graphene-based sensor 11, signal processing circuit 12 and skin contact interface, the sheep temperature monitoring device 1 is set on the tested sheep 3 through an elastic band 2;

[0082] The graphene-based sensor 1 comprises a copper-clad polyimide film and a reduced graphene oxide layer, wherein the side of the copper-clad polyimide film away from the sheep is the B side, and the side close to the sheep is the A side, the reduced graphene oxide layer is arranged on the A side of the copper-clad polyimide film, the signal processing circuit is arranged on the B side of the copper-clad polyimide film, and the skin contact interface is arranged on the outer side of the reduced graphene oxide layer;

[0083] The signal processing circuit includes an operational amplifier, an analog-to-digital converter, a microcontroller and a signal transmitter;

[0084] The skin contact interface is a hydrogel interface, which provides good contact between the skin surface of the tested sheep 3 and the graphene-based sensor 11 .

[0085] like Figure 3 As shown, the preparation method of the graphene-based sensor 11 is:

[0086] A quantitative amount of graphene oxide solution is collected by a pipette and dropped on the A surface of the copper-clad polyimide film. After the solution dries, it is scanned and reduced by a laser marking machine under optimal laser parameters to obtain a reduced graphene oxide layer bonded to the copper-clad polyimide film.

[0087] The present invention provides a specific embodiment, the collected graphene oxide solution is 5 ml, the drying time at room temperature is 10 minutes, and the optimal laser parameters of the laser marking machine are scanning speed 120 mm / s, laser power 8 kW, laser height 10 mm, and scanning spacing 1 mm.

[0088] The preparation method of the signal processing circuit is as follows:

[0089] Etching the B surface of the copper-clad polyimide film by a laser marking machine, cleaning and drying after multiple etchings, and finally forming the signal processing circuit;

[0090] The cleaning and drying specifically includes cleaning with deionized water and drying at room temperature;

[0091] The operational amplifier is used to convert the detected small resistance changes into measurable voltage signals, and filter and amplify these signals to facilitate subsequent analog-to-digital conversion;

[0092] The analog-to-digital converter is used to convert the voltage signal processed by the operational amplifier into a digital form, providing the microcontroller with data that can be directly read and analyzed;

[0093] The microcontroller is used to receive digital signals from the analog-to-digital converter and process the data according to a preset algorithm or program to monitor and analyze physiological parameters. It is also responsible for controlling other parts of the signal processing circuit, such as adjusting the gain of the operational amplifier, managing the sampling rate of the analog-to-digital converter, and triggering an alarm or performing other preset actions based on the monitoring results.

[0094] The signal transmitter is used to transmit the data processed by the microcontroller to a remote device or a display terminal.

[0095] like Figure 3 As shown, the preparation method of the hydrogel interface is:

[0096] Polyacrylamide (PAAm) and sodium alginate (alginate) are mixed in proportion to form a solution of an interpenetrating network structure, and then vinyl-functionalized boron nitride nanosheets (v-BNNS) are mixed, and the mixed solution is evenly coated on a mold by a cold lamination method to form a film, and the film is placed under suitable conditions for curing to form a hydrogel with good biocompatibility, high air permeability, excellent mechanical properties and adhesion properties and high thermal conductivity, and the hydrogel is cut into a suitable size as needed, and is set between the sheep and the graphene-based sensor 1;

[0097] The mixing includes using a power-enhancing electric stirrer at room temperature for 20 minutes;

[0098] The coating includes using an automatic cold laminator at a speed of 100 mm / s and a pressure of 10 Pa for 10 minutes to ensure the uniformity of the solution coating and the thickness of the film;

[0099] The curing includes using ultraviolet curing equipment at 365nm long-wave ultraviolet light for 20 minutes; the preparation process of the hydrogel is carried out under sterile conditions to ensure the safety and effectiveness of the hydrogel.

[0100] The sheep body temperature monitoring device realizes the manufacturing of sensors and signal processing circuits on the same copper-clad polyimide film at the same time. This highly integrated design is one of the important features of the present invention.

[0101] like Figure 1 As shown, the present invention also provides a sheep heat stress management method based on the sheep body temperature monitoring device, comprising:

[0102] S1: Based on the sheep body temperature monitoring device, obtain the real-time body temperature signal and based on the environment collection device, obtain the real-time environment information;

[0103] S2: constructing a temperature compensation model and obtaining a real-time temperature change curve according to the real-time body temperature signal and environmental information;

[0104] S3: acquiring signal characteristics according to the real-time temperature change curve, and comparing the signal characteristics with a preset reference value to calculate the real-time temperature change rate;

[0105] S4: constructing a heat stress assessment model according to the signal characteristics and the temperature change rate to determine the heat stress state of the tested individual;

[0106] S5: Implementing heat management measures according to the heat stress state.

[0107] In S1, based on the sheep body temperature monitoring device, real-time body temperature signals are obtained and based on the environment collection device, real-time environmental information is obtained, specifically:

[0108] The method of obtaining real-time body temperature signals based on the sheep body temperature monitoring device and obtaining real-time environmental information based on the environment acquisition device specifically includes: first determining the contact site between the sheep body temperature monitoring device and the individual under test; shaving the contact site in order to better contact the sheep's skin and obtain a real-time signal that is more representative of the core temperature. Then the device is initialized, the sheep body temperature monitoring device is worn on the site, and an elastic band is used to reinforce it to prevent the body temperature monitoring device from falling off. Due to the small size, light weight and excellent interface characteristics brought about by the highly integrated sheep body temperature monitoring device, real-time signals can be reliably acquired. In addition, the environment acquisition device is arranged inside the sheep house to obtain real-time environmental information;

[0109] The environment collection device is arranged inside the sheep house and is used to obtain real-time environmental information, specifically including: the environment collection device is an environmental sensor node arranged at a fixed point in the sheep house, including a temperature and humidity sensor, an ammonia sensor and a sulfur dioxide sensor; the temperature and humidity sensor, the ammonia sensor and the sulfur dioxide sensor are used to collect the real-time environmental information, including real-time temperature and humidity, ammonia content and sulfur dioxide content;

[0110] As a specific embodiment, the real-time body temperature signal and the real-time environmental information are both presented in the form of a data set;

[0111] The method for arranging the environment collection device at a fixed point in the sheep house specifically includes:

[0112] The temperature and humidity sensor, the ammonia sensor and the sulfur dioxide sensor are integrated into one group in an array manner, the sheep house area is divided into grids in the length direction, the width direction and the height direction, and the number of array groups is determined according to the sheep house grid; all groups of sensor arrays are arranged according to the points after multi-objective optimization;

[0113] The number of array groups is determined according to the sheep house grid, and the calculation formula is:

[0114]

[0115] N|≤abc max

[0116] Where N is the number of array groups, d is the length of the sheep house, h is the width of the sheep house, l is the height of the sheep house, α is the number of grids of the sensor array in the length direction, β is the number of grids of the sensor array in the width direction, χ is the number of grids of the sensor array in the height direction, θ is the optimization coefficient, [] means rounding up the function to ensure that the number of sensors meets or exceeds the calculated value to ensure that each area in the sheep house can be effectively monitored, n is the number of sensor groups in the length direction of the sheep house, m is the number of sensor groups in the width direction of the sheep house, and p is the number of sensor groups in the height direction of the sheep house. In addition, in order to control costs, the number of array groups does not exceed the maximum number of grids abc max ;

[0117] All sensor arrays are placed according to the points optimized by multiple objectives, including:

[0118] Establish a sensor matrix expression, then determine the influence of the overlapping area in the sensor coverage, associate the sensor matrix expression with the influence of the overlapping area, and finally optimize the layout points, thereby completing the optimal layout of the sensor array;

[0119] Among them, the sensor matrix expression is:

[0120] Matrix={(xi ,y j ,z k )|1≤i≤m,1≤j≤n,1≤k≤p}

[0121] In the formula, x i ,y j 、z k They are the points in the three directions of length, width and height;

[0122] The calculation formula for the overlapping area of ​​sensor coverage is:

[0123]

[0124] In the formula, V represents the coverage volume, C represents x i With y j , ∩ is the intersection of the coverage ranges, and ∪ is the union of the coverage ranges;

[0125] The calculation formula for associating the sensor matrix expression with the influence degree of the overlapping area is:

[0126]

[0127] In S2, a temperature compensation model is constructed according to the real-time body temperature signal and environmental information, and a real-time temperature change curve is obtained, specifically:

[0128] The environmental information and sensor resistance signal are extracted as input, the input data is normalized and outliers are eliminated, and then input into the calibration formula to obtain the compensated temperature value. In addition, the monitoring time is used as the x-axis and the temperature value is used as the y-axis to obtain the real-time temperature change curve;

[0129] The calibration formula is:

[0130]

[0131] In the formula, q is the number of input data, x (i) is the sensor resistance signal, y (i) is the environmental information, p is the number of data categories, λ is the regularization coefficient, γ j is the compensation parameter vector, and the calculation formula is:

[0132]

[0133] Where α is the feedback ratio, is the partial derivative with respect to the jth data.

[0134] In S3, the signal characteristics are obtained according to the real-time temperature change curve, and compared with the preset reference value to calculate the real-time temperature change rate, specifically:

[0135] According to the real-time temperature change curve, the real-time temperature value is extracted at fixed time intervals, the local maximum and minimum points of the temperature change curve are determined, the amplitude and frequency of the temperature fluctuation are calculated, the standard deviation and the root mean square value are calculated to quantify the discrete degree and fluctuation intensity of the temperature change, and the average temperature within a fixed time is used as a preset reference value to calculate the real-time temperature change rate;

[0136] Among them, the signal characteristics include T max , T min , Range, σ, RMS, the specific calculation formulas are as follows:

[0137] T max =max(T(t))

[0138] T min =min(T(t))

[0139] Range=T max -T min

[0140]

[0141] Wherein, T(t) is the temperature value that changes with time; the calculation formula of the temperature change rate is:

[0142]

[0143] Where ΔT is the temperature change within the Δt time range, Δt is the time change, T1 and T2 are the temperature values ​​at two different times, and t1 and t2 are the corresponding time values.

[0144] In S4, a heat stress assessment model is constructed according to the signal characteristics and the temperature change rate to determine the heat stress state of the tested individual, specifically:

[0145] The signal characteristics and temperature change rate are used as independent variables, and the individual's heat stress state is used as the dependent variable. The Y function is used to establish the association between the independent variable and the heat stress state, and a coefficient correction method is set to prevent overfitting. The first-level decision threshold is dynamically adjusted according to real-time monitoring data to adapt to individual physiological changes and fluctuations in environmental conditions. When the heat stress probability predicted by the model exceeds the set threshold, the system will determine that the individual is in a heat stress state; by setting different second-level decision thresholds, heat stress assessment can identify different state levels with different sensitivities;

[0146] Preferably, the calculation formula of the Y function is:

[0147] Y=U+S×Range+Equation(a)+Equation(b)+Equation(c)

[0148] Among them, the calculation formulas of Equation (a), Equation (b), and Equation (c) are:

[0149] Equation (a) = e (0.00182×RH+1.8×Am-5×RT×RH) ×(0.0054×T max 2 +0.00192×T min -0.0285)×(RH-30)

[0150]

[0151] Equation (c) = 0.0076 × T max -0.02×RMS×T min +0.5×Range 2 ×0.1×Sd-2

[0152] Among them, U is the coefficient term, Y is the dependent variable vector of heat stress state, RT is the ambient temperature, RH is the ambient humidity, Am is the ammonia concentration, and Sd is the sulfur dioxide concentration.

[0153] Preferably, the dynamically adjusting the first-level decision threshold according to the real-time monitoring data specifically includes:

[0154] P new =P old +K p ·(P base -P measured )

[0155] Among them, P new is the updated first-level decision threshold, P old is the first-level decision threshold before updating, K p is the decision gain, P base is the benchmark decision threshold, P measured Real-time monitoring data.

[0156] P base The calculation formula is:

[0157]

[0158] Preferably, by setting different secondary decision thresholds, the heat stress assessment can identify different state levels with different sensitivities, specifically including: according to the primary decision threshold, the secondary decision threshold is set with a floating ratio of 10% up and down. The floating ratio can be adjusted according to the actual situation to achieve the recognition of stress state levels under different sensitivity conditions.

[0159] Wherein, the secondary decision threshold is divided into two categories, namely the first threshold and the second threshold;

[0160] The setting of different decision thresholds includes a first threshold and a second threshold;

[0161] like Figure 4 As shown, the heat stress threshold determined by the signal characteristics is used to set the first threshold and the second threshold, specifically including: inputting the heat stress assessment result into the judgement device, if the heat stress assessment result is greater than or equal to the heat stress threshold, setting the second threshold, if the heat stress assessment result is less than the heat stress threshold, setting the first threshold;

[0162] The heat stress state is divided into three levels: mild heat stress, moderate heat stress and severe heat stress;

[0163] The mild heat stress, moderate heat stress and severe heat stress are determined according to the heat stress threshold, specifically:

[0164] If it is less than the first threshold, it is mild heat stress;

[0165] If it is greater than the first threshold but less than the second threshold, it is moderate heat stress;

[0166] If it is greater than the second threshold, it is severe heat stress.

[0167] In S5, thermal management measures are implemented according to the heat stress state, specifically:

[0168] When the heat stress assessment model determines that the tested sheep is in a heat stress state, corresponding heat stress management measures are automatically triggered according to the heat stress state level, such as adjusting the ventilation size and providing external cooling, so as to reduce the potential impact of heat stress on the health of individual sheep. The present invention provides an embodiment as follows:

[0169] If the sheep is not in a stressful state, the stress threshold is updated;

[0170] If the sheep are in a state of mild heat stress, implement ventilation adjustment measures;

[0171] If the sheep are in a state of moderate heat stress, implement regulated cooling measures;

[0172] If the sheep are in a state of severe heat stress, implement cooling, increase ventilation and sound the alarm;

[0173] The present invention also provides an additional feedback mechanism that can dynamically adjust the intensity of heat stress management measures based on the real-time physiological parameter monitoring results of the tested individual. For example, when the individual's stress level is detected to be elevated, the system will automatically increase the intensity of management measures, such as increasing the fan speed or increasing the cooling intensity, to ensure that the individual's heat stress state is effectively controlled.

[0174] Through the above device and method, the heat stress state of sheep can be quantified, and ventilation and cooling measures can be automatically adjusted according to the state to reduce the potential impact of heat stress on the health of individual sheep, and the probability of heat stress in sheep can be effectively reduced. Table 1 is a comparison chart of the results of the method in the embodiment provided by the present invention and other methods. Therefore, it can be explained that the sheep body temperature monitoring device and heat stress management method proposed by the present invention have obvious advantages over simple machine learning methods.

[0175] Table 1 Performance comparison of the sheep heat stress management method of the present invention and other methods

[0176]

[0177]

[0178] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0179] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A sheep body temperature monitoring device, characterized in that: include: A graphene-based sensor, a signal processing circuit and a skin contact interface, wherein the sheep temperature monitoring device is arranged on the sheep to be tested via an elastic strap; The graphene-based sensor comprises a copper-clad polyimide film and a reduced graphene oxide layer, wherein the side of the copper-clad polyimide film away from the sheep is the B side, and the side close to the sheep is the A side, the reduced graphene oxide layer is arranged on the A side of the copper-clad polyimide film, the signal processing circuit is arranged on the B side of the copper-clad polyimide film, and the skin contact interface is arranged on the outer side of the reduced graphene oxide layer; The signal processing circuit includes an operational amplifier, an analog-to-digital converter, a microcontroller and a signal transmitter; the skin contact interface is a hydrogel interface.

2. The sheep body temperature monitoring device according to claim 1, characterized in that: The preparation method of the graphene-based sensor is: A quantitative amount of graphene oxide solution is collected by a pipette and dropped on the A surface of the copper-clad polyimide film. After the solution dries, it is scanned and reduced by a laser marking machine under optimal laser parameters to obtain a reduced graphene oxide layer bonded to the copper-clad polyimide film.

3. The sheep body temperature monitoring device according to claim 1, characterized in that: The preparation method of the signal processing circuit is as follows: The B surface of the copper-clad polyimide film is etched by a laser marking machine, and after multiple etchings, it is cleaned and dried to finally form the signal processing circuit.

4. The sheep body temperature monitoring device according to claim 1, characterized in that: The preparation method of the hydrogel interface is: Polyacrylamide and sodium alginate are mixed in proportion to form a solution with an interpenetrating network structure, and then vinyl-functionalized boron nitride nanosheets are mixed in, and the mixed solution is evenly coated on a mold by a cold lamination method to form a film, and the film is placed under suitable conditions for curing to form a hydrogel with high thermal conductivity, which is cut into a suitable size as needed and placed between the sheep and the graphene-based sensor; The preparation process of the hydrogel is carried out under sterile conditions.

5. A method for managing heat stress in sheep, characterized in that: include: Based on the sheep body temperature monitoring device, real-time body temperature signals are obtained, and based on the environment collection device, real-time environmental information is obtained; According to the real-time body temperature signal and environmental information, a temperature compensation model is constructed and a real-time temperature change curve is obtained; Acquire signal characteristics according to the real-time temperature change curve, compare it with a preset reference value, and calculate the real-time temperature change rate; Constructing a heat stress assessment model according to the signal characteristics and the temperature change rate to determine the heat stress state of the tested individual; Thermal management measures are implemented according to the heat stress state.

6. The sheep heat stress management method according to claim 5, characterized in that: Based on the sheep body temperature monitoring device, real-time body temperature signals are obtained, and based on the environment collection device, real-time environmental information is obtained, specifically: Determine the contact part between the sheep body temperature monitoring device and the tested sheep, shave the contact part, initialize the sheep body temperature monitoring device, and wear it to the contact part using an elastic band; The environment collection device is arranged inside the sheep house, wherein the environment collection device includes a temperature and humidity sensor, an ammonia sensor and a sulfur dioxide sensor. When setting, the temperature and humidity sensor, the ammonia sensor and the sulfur dioxide sensor are integrated into a group in an array manner, and the sheep house area is divided into grids in the length direction, the width direction and the height direction. The number of array groups is determined according to the sheep house grid, and the calculation formula is: |N|≤abc max Where N is the number of array groups, d is the length of the sheep house, h is the width of the sheep house, l is the height of the sheep house, α is the number of grids in the length direction of the sensor array, β is the number of grids in the width direction of the sensor array, χ is the number of grids in the height direction of the sensor array, θ is the optimization coefficient, [] means rounding up the function to ensure that the number of sensors meets or exceeds the calculated value to ensure that each area in the sheep house can be effectively monitored, n is the number of sensor groups in the length direction of the sheep house, m is the number of sensor groups in the width direction of the sheep house, p is the number of sensor groups in the height direction of the sheep house, and the number of array groups does not exceed the maximum number of grids abc max ; Establish a sensor matrix expression, then determine the influence of the overlapping area in the sensor coverage, associate the sensor matrix expression with the influence of the overlapping area, and finally optimize the layout points, thereby completing the optimal layout of the sensor array; Among them, the sensor matrix expression is: Matrix={(x i ,y j ,z k )|1≤i≤m,1≤j≤n,1≤k≤p} In the formula, x i ,y j 、z k They are the points in the three directions of length, width and height; The calculation formula for the overlapping area of ​​sensor coverage is: In the formula, V represents the coverage volume, C represents x i With y j , ∩ is the intersection of the coverage ranges, and ∪ is the union of the coverage ranges; The calculation formula for associating the sensor matrix expression with the influence degree of the overlapping area is:

7. The method for managing heat stress in sheep according to claim 5, characterized in that: According to the real-time body temperature signal and environmental information, a temperature compensation model is constructed and a real-time temperature change curve is obtained, specifically: The environmental information and sensor resistance signal are extracted as input, the input data is normalized and outliers are eliminated, and then input into the calibration formula to obtain the compensated temperature value. In addition, the monitoring time is used as the x-axis and the temperature value is used as the y-axis to obtain the real-time temperature change curve; The calibration formula is: In the formula, q is the number of input data, x (i) is the sensor resistance signal, y (i) is the environmental information, p is the number of data categories, λ is the regularization coefficient, γ j is the compensation parameter vector, and the calculation formula is: Where α is the feedback ratio, is the partial derivative with respect to the jth data.

8. The method for managing heat stress in sheep according to claim 5, characterized in that: The signal characteristics are obtained according to the real-time temperature change curve, and compared with the preset reference value to calculate the real-time temperature change rate, specifically: According to the real-time temperature change curve, the real-time temperature value is extracted at fixed time intervals, the local maximum and minimum points of the temperature change curve are determined, the amplitude and frequency of the temperature fluctuation are calculated, the standard deviation and the root mean square value are calculated to quantify the discrete degree and fluctuation intensity of the temperature change, and the average temperature within a fixed time is used as a preset reference value to calculate the real-time temperature change rate; Among them, the signal characteristics include T max , T min , Range, σ, RMS, the specific calculation formulas are as follows: T max =max(T(t)) T min =min(T(t)) Range=T max -T min Where T(t) is the temperature value that changes with time; The calculation formula of the temperature change rate is: Where ΔT is the temperature change within the Δt time range, Δt is the time change, T1 and T2 are the temperature values ​​at two different times, and t1 and t2 are the corresponding time values.

9. The method for managing heat stress in sheep according to claim 5, characterized in that: A heat stress assessment model is constructed according to the signal characteristics and the temperature change rate to determine the heat stress state of the tested individual, specifically: The signal characteristics and the temperature change rate are used as independent variables, and the heat stress state of the individual is used as the dependent variable. The association between the independent variable and the heat stress state is established through the Y function, and a coefficient correction method is set to prevent overfitting. The first-level decision threshold is dynamically adjusted according to the real-time monitoring data to adapt to the physiological changes of the individual and the fluctuations of environmental conditions. When the heat stress probability predicted by the model exceeds the set threshold, the system will determine that the individual is in a heat stress state. By setting different second-level decision thresholds, the heat stress assessment can identify different state levels with different sensitivities; The calculation formula of the Y function is: Y=U+S×Range+Equation(a)+Equation(b)+Equation(c) Where, the calculation formulas of Equation (a), Equation (b), and Equation (c) are: Equation(a)=e (0.00182×RH+1.8×Am-5×RT×RH) ×(0.0054×T max 2 +0.00192×T min -0.0285)×(RH-30) Equation(c)=0.0076×T max -0.02×RMS×T min +0.5×Range 2 ×0.1×Sd-2 In the formula, U is the coefficient term, Y is the dependent variable vector of heat stress state, RT is the ambient temperature, RH is the ambient humidity, Am is the ammonia concentration, and Sd is the sulfur dioxide concentration; The dynamically adjusting the first-level decision threshold according to the real-time monitoring data specifically includes: P new =P old +K p ·(P base -P measured ) Where P new is the updated first-level decision threshold, P old is the first-level decision threshold before updating, K p is the decision gain, P base is the benchmark decision threshold, P measured Real-time monitoring data; P base The calculation formula is: By setting different secondary decision thresholds, heat stress assessment can identify different status levels with different sensitivities, including: according to the primary decision threshold, the secondary decision threshold is set with a fluctuation of 10% up and down; Wherein, the secondary decision threshold is divided into two categories, namely the first threshold and the second threshold; The heat stress state is divided into three levels: mild heat stress, moderate heat stress and severe heat stress.

10. The method for managing heat stress in sheep according to claim 5, characterized in that: Implement thermal management measures according to the heat stress state, specifically: When the heat stress assessment model determines that the tested sheep are in a state of heat stress, the corresponding heat stress management measures are automatically triggered according to the level of heat stress. Among them, the preset feedback mechanism dynamically adjusts the intensity of heat stress management measures according to the real-time physiological parameter monitoring results of the tested sheep.

Images