Methods, devices and equipment for insect breeding regulation based on multi-sensor data fusion

Abstract

This invention discloses a method, apparatus, and device for insect farming regulation based on multi-sensor data fusion. The method includes: acquiring environmental sampling data of an insect farming area based on at least two types of sensors; arranging the sensors in a hierarchical layout within the insect farming area; performing data preprocessing on the environmental sampling data to establish a preprocessed dataset; establishing a three-dimensional environmental field of the insect farming area based on the preprocessed dataset; coupling the three-dimensional environmental field with a preset physiological response model; and optimizing the environmental regulation parameters of the insect farming area based on the coupling result. This invention improves monitoring accuracy and data reliability by fusing data from multiple sensors through the establishment of a three-dimensional environmental field of the insect farming area. The coupling between the three-dimensional environmental field and the preset physiological response model enables closed-loop management of farming parameters, improving insect farming management effectiveness and increasing insect growth and survival rates.

Description

Technical Field

[0001] This invention relates to the field of insect farming technology, and in particular to a method, apparatus and equipment for insect farming regulation based on multi-sensor data fusion. Background Technology

[0002] Dung beetles are insects that feed on garbage or feces. Large-scale breeding of dung beetles allows for the resource utilization of feces and garbage, possessing high ecological and economic value.

[0003] Manure insect farming technology typically relies on specialized equipment to provide suitable living conditions for the insects, such as temperature, humidity, ventilation, light, and food. Current technologies usually require various types of sensors, such as temperature and humidity sensors, to monitor and regulate the insects' growth environment. However, existing monitoring technologies for farming equipment have the following problems:

[0004] Firstly, the sensor placement is limited. Sensors are typically installed on the inner walls of aquaculture equipment, making it impossible to monitor the temperature and humidity inside the insect activity area. This results in low accuracy of the sensor data, a high risk of false alarms, and compromises the reliability of aquaculture environment control.

[0005] Secondly, the data from different types of sensors were not coupled. For example, using only temperature sensor data as the criterion for temperature control or only humidity sensor data as the criterion for humidity control makes it difficult to identify abnormal temperature and humidity in dynamic environments, resulting in poor control of temperature and humidity conditions, which in turn affects the growth rate and survival rate of insects. Summary of the Invention

[0006] This invention provides a method, apparatus, and equipment for insect farming regulation based on multi-sensor data fusion. It addresses the problems of low accuracy in monitoring data and poor regulation of growth environments such as temperature and humidity in existing farming equipment due to the single sensor layout and lack of coupling and correlation of data from different types of sensors. By fusing multi-sensor data, the invention improves monitoring accuracy and regulation effectiveness.

[0007] According to one aspect of the present invention, a method for regulating insect farming based on multi-sensor data fusion is provided, comprising: acquiring environmental sampling data of an insect farming area based on at least two types of sensors; wherein the sensors are arranged in a hierarchical layout in the insect farming area; performing data preprocessing on the environmental sampling data to establish a preprocessed dataset; establishing a three-dimensional environmental field of the insect farming area based on the preprocessed dataset; coupling the three-dimensional environmental field with a preset physiological response model, and optimizing the farming environment regulation parameters of the insect farming area according to the coupling result; wherein the preset physiological response model is a function model established based on the physiological response data of insects in different environments.

[0008] Optionally, the coupling of the three-dimensional environmental field with the preset physiological response model and the optimization of the breeding environment control parameters of the insect breeding area based on the coupling result includes: discretizing the three-dimensional environmental field based on a preset size to establish multiple unit grids; independently running the preset physiological response model within each unit grid to obtain physiological response data in different hierarchical spaces; and adjusting the breeding environment control parameters based on the physiological response data.

[0009] Optionally, the preset physiological response model includes at least one of the following: a developmental prediction model, a metabolic rate model, and a behavioral response model; the step of independently running the preset physiological response model within each of the said unit grids to obtain physiological response data within each of the said unit grids includes: obtaining environmental field data within each of the said unit grids; importing the environmental field data into the developmental prediction model, the metabolic rate model, and the behavioral response model respectively; and determining the physiological response data based on at least one of the growth and development data output by the developmental prediction model, the metabolic rate output by the metabolic rate model, and the migration probability output by the behavioral response model.

[0010] Optionally, the developmental prediction model is established based on the nonlinear function coupling between insect development rate and different environmental field data; the metabolic rate model is established based on the coupling of Q10 temperature coefficient model and gas concentration correction term; and the behavioral response model is established based on the coupling of insect tactic movement model to different environmental field data.

[0011] Optionally, establishing the three-dimensional environmental field of the insect breeding area based on the preprocessed dataset includes: defining one type of data in the preprocessed dataset as the main variable, and the data in the preprocessed dataset other than the main variable as auxiliary variables; establishing a variogram matrix for the main variable and the auxiliary variables, and expanding the variogram matrix to establish a co-kriging equation system; interpolating and estimating the target point of the main variable according to the co-kriging equation system; and establishing the three-dimensional environmental field based on the interpolation results of different variables.

[0012] Optionally, establishing the three-dimensional environmental field based on the interpolation results of different variables includes: establishing a three-dimensional grid based on the spatial range and resolution of the insect breeding area; merging the interpolation results into a multi-dimensional vector based on the weight allocation of different variables; and mapping the multi-dimensional vector onto the three-dimensional grid to establish the three-dimensional environmental field.

[0013] Optionally, the step of performing data preprocessing on the environmental sampling data to establish a preprocessed dataset includes: performing spatiotemporal alignment, outlier handling, and normalization on the environmental sampling data; adding hierarchical labels to the normalized data according to the position of the environmental sampling data in the hierarchical layout structure; and storing the normalized data with the hierarchical labels into the preprocessed dataset.

[0014] Optionally, the layered layout structure includes at least: an upper space, an interface space, and a bottom space; wherein, the upper space is located above the substrate of the insect breeding area, and the distance between the upper space and the substrate surface is greater than or equal to a first preset distance; the interface space is located on the substrate surface, and the distance between the interface space and the substrate surface is less than or equal to a second preset distance; the bottom space is located inside the substrate, and the distance between the bottom space and the substrate surface is greater than the second preset distance.

[0015] According to another aspect of the present invention, an insect farming control device based on multi-sensor data fusion is provided, comprising: a sampling module, equipped with at least two types of sensors for acquiring environmental sampling data of an insect farming area; the sensors are arranged in a hierarchical layout in the insect farming area; a preprocessing module, for performing data preprocessing on the environmental sampling data to establish a preprocessed dataset; a three-dimensional field modeling module, for establishing a three-dimensional environmental field of the insect farming area based on the preprocessed dataset; and a parameter optimization module, for coupling the three-dimensional environmental field with a preset physiological response model, and optimizing the farming environment control parameters of the insect farming area according to the coupling result; wherein the preset physiological response model is a function model established based on the physiological response data of insects in different environments.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the above-described multi-sensor data fusion insect breeding control method.

[0017] The technical solution of this invention involves acquiring environmental sampling data of an insect breeding area by setting up at least two types of sensors. These sensors are arranged in a layered layout within the insect breeding area. Data preprocessing is performed on the environmental sampling data to establish a preprocessed dataset. A three-dimensional environmental field of the insect breeding area is established based on the preprocessed dataset. The three-dimensional environmental field is coupled with a preset physiological response model, and the breeding environment control parameters of the insect breeding area are optimized based on the coupling result. This addresses the problems of existing breeding equipment where sensor placement is singular and different types of sensor data are not coupled and correlated, resulting in low monitoring data accuracy and poor control effects on growth environments such as temperature and humidity. By establishing a three-dimensional environmental field of the insect breeding area and fusing data from multiple sensors, monitoring accuracy and data reliability are improved. This avoids malfunctions caused by adjusting temperature or humidity based on single data points. The coupling between the three-dimensional environmental field and the preset physiological response model achieves closed-loop management of breeding environment control parameters, improving insect breeding management effects and increasing insect growth and survival rates.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart of an insect breeding control method based on multi-sensor data fusion provided in an embodiment of the present invention;

[0021] Figure 2 This is a schematic diagram of a layered layout structure of an insect breeding area provided in an embodiment of the present invention;

[0022] Figure 3 A flowchart illustrating a coupling method between a three-dimensional environmental field and a preset physiological response model, provided as an embodiment of the present invention;

[0023] Figure 4 A flowchart illustrating a method for constructing a three-dimensional environmental field according to an embodiment of the present invention;

[0024] Figure 5 This is a schematic diagram of the structure of an insect breeding control device based on multi-sensor data fusion provided in an embodiment of the present invention;

[0025] Figure 6 A schematic diagram of the electronic device used to implement the insect breeding control method of this invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those explicitly listed, but may include those not explicitly listed.

[0028] Figure 1 This is a flowchart illustrating a multi-sensor data fusion method for insect farming control provided in an embodiment of the present invention. This embodiment is applicable to monitoring scenarios involving insect farming in manure. In this invention, manure-infested insects include, but are not limited to, dung beetles, black soldier flies, and houseflies. This method can be executed by an insect farming control device, which can be implemented in hardware and / or software and can be configured in insect farming equipment or independent electronic devices. Figure 1 As shown, this multi-sensor data fusion method for insect farming regulation includes the following steps:

[0029] S1: Acquire environmental sampling data of the insect breeding area based on at least two types of sensors.

[0030] The sensors are arranged in a layered layout within the insect rearing area. Typically, the sensors include, but are not limited to: temperature sensors, humidity sensors, light intensity sensors, and gas sensors. Typically, the gas sensors include, but are not limited to: carbon dioxide sensors and ammonia nitrogen sensors.

[0031] Environmental sampling data can be understood as measured data characterizing the environmental state and dynamic changes within an insect farming area. In this embodiment, environmental sampling data includes, but is not limited to, data on temperature, humidity, light intensity, and gas concentration within the insect farming area.

[0032] Insect breeding areas include, but are not limited to: the internal and external areas of the substrate used for breeding insects, the internal area of ​​the breeding boxes, and the area where the breeding boxes are placed (such as greenhouses or breeding farms).

[0033] A hierarchical layout structure can be understood as a vertical spatial structure based on the activity areas of insect larvae and adults. Figure 2 This is a schematic diagram of a layered layout structure for an insect breeding area provided in an embodiment of the present invention. See also... Figure 2 As shown, the layered layout structure includes at least: an upper space S1, an interface space S2, and a lower space S3; wherein, the upper space S1 is located above the substrate 1 of the insect breeding area, and the distance between it and the substrate surface is greater than or equal to a first preset distance; the interface space S2 is located on the substrate surface, and the distance between it and the substrate surface is less than or equal to a second preset distance; the lower space S3 is located inside the substrate, and the distance between it and the substrate surface is greater than the second preset distance. The first preset distance is greater than the second preset distance. For example, the first preset distance can be set to 10cm, and the second preset distance to 5cm.

[0034] Specifically, a light intensity sensor and a temperature and humidity sensor can be arranged in the upper space S1 to monitor the light intensity, temperature and humidity data of the adult insect activity area; a gas sensor and a temperature sensor can be arranged in the interface space S2 to monitor the metabolic state of the population gathering area; and a temperature sensor and a humidity sensor can be arranged in the lower space S3 to monitor the temperature and moisture content of the larval activity area.

[0035] S2: Perform data preprocessing on the environmental sampling data and establish a preprocessed dataset.

[0036] The preprocessed dataset can be understood as a collection of data created after preliminary fusion of different types of environmental sampling data (including at least one of temperature, humidity, illuminance, and gas concentration). In the preprocessed dataset, a set of environmental sampling data (such as temperature, humidity, illuminance, or gas concentration) from the same location can be stored in array format.

[0037] Optionally, data preprocessing is performed on the environmental sampling data to establish a preprocessed dataset, including: performing spatiotemporal alignment, outlier handling, and normalization on the environmental sampling data; adding hierarchical labels to the normalized data according to the position of the environmental sampling data in the hierarchical layout structure; and storing the normalized data with hierarchical labels into the preprocessed dataset. In this embodiment, the hierarchical labels include, but are not limited to: upper-layer spatial labels, interface spatial labels, and lower-layer spatial labels.

[0038] Specifically, the NTP protocol can be used to unify the timestamps of all sensors and synchronize the environmental sampling data in time; the sensor positions can be unified to the aquaculture box coordinate system through three-dimensional coordinate system mapping; and data such as temperature, humidity, gas concentration, and illuminance can be scaled to a unified [0,1] interval. After normalization, the sampling data in the vertical space can be marked by adding hierarchical labels, providing data sources at different vertical heights for constructing the three-dimensional field.

[0039] S3: Establish a three-dimensional environmental field for the insect breeding area based on the preprocessed dataset.

[0040] Among them, the three-dimensional environmental field can be understood as the mathematical and structured expression of continuously distributed environmental parameters (such as temperature, humidity, light intensity, gas concentration, etc.) within the insect breeding area.

[0041] In this embodiment, a continuous three-dimensional environmental field can be established by interpolation estimation through preprocessing the discretized values ​​in the dataset.

[0042] S4: Couple the three-dimensional environmental field with the preset physiological response model, and optimize the breeding environment control parameters of the insect breeding area based on the coupling results.

[0043] The preset physiological response model is a function model established based on the physiological response data of insects in different environments.

[0044] In this embodiment, the coupling result of the three-dimensional environmental field and the preset physiological response model is used to measure the growth status of insects.

[0045] Specifically, coupling the three-dimensional environmental field with the preset physiological response model means importing data from the three-dimensional environmental field into the preset physiological response model to obtain the insect growth status at different locations within the three-dimensional environmental field. When the insect growth status does not meet expectations, or when the insect survival rate is lower than a preset survival rate threshold, the environmental control parameters of the insect breeding area are optimized.

[0046] Therefore, the technical solution of the present invention improves the monitoring accuracy and data reliability by establishing a three-dimensional environmental field in the insect breeding area and fusing data from multiple sensors. It avoids malfunctions caused by adjusting temperature or humidity based on single data. By coupling the three-dimensional environmental field with a preset physiological response model, it achieves closed-loop management of breeding environment control parameters, improves the insect breeding management effect, and increases the growth rate and survival rate of insects.

[0047] Optionally, Figure 3 A flowchart illustrating a coupling method between a three-dimensional environmental field and a preset physiological response model, provided as an embodiment of the present invention. See also... Figure 3 As shown, in step S4 above, the three-dimensional environmental field is coupled with the preset physiological response model, and the environmental control parameters of the insect breeding area are optimized based on the coupling results, including:

[0048] S401: Discretize the three-dimensional environment field based on preset dimensions to establish multiple unit meshes.

[0049] The preset size can be understood as the size of the cell grid established based on the discretization processing requirements. In this embodiment, the preset size can be set according to the substrate stacking height inside the breeding box. Typically, the preset size can be set to 5cm in length, width, and height.

[0050] S402: Run the preset physiological response model independently within each cell grid to obtain physiological response data in different hierarchical spaces.

[0051] Physiological response data can be understood as predicted values ​​of insect growth status obtained based on environmental field data within a cell grid. Typically, physiological response data includes, but is not limited to: survival rate, growth curve, energy consumption data, and avoidance behavior.

[0052] S403: Adjust the aquaculture environment control parameters based on physiological response data.

[0053] In this embodiment, the breeding environment control parameters are adjusted according to physiological response data, including but not limited to: adjusting the temperature and humidity conditions of the bottom space according to the physiological response data (such as survival rate and development rate) of the unit grid in the bottom space; adjusting the temperature and humidity conditions of the interface space according to the physiological response data (such as metabolic rate or energy consumption data) of the unit grid in the interface space; and adjusting the light intensity and temperature and humidity conditions of the upper space according to the physiological response data (such as avoidance behavior) of the unit grid in the upper space.

[0054] Optionally, the preset physiological response model includes at least one of the following: a developmental prediction model, a metabolic rate model, and a behavioral response model. The developmental prediction model is used to simulate the correspondence between the rearing environment (such as at least one of temperature, humidity, light, and gas concentration) and the individual insect growth curve; the metabolic rate model is used to simulate the correspondence between the rearing environment (such as at least one of temperature, humidity, light, and gas concentration) and the individual insect energy consumption; and the behavioral response model is used to simulate the correspondence between the rearing environment (such as at least one of temperature, humidity, light, and gas concentration) and the insect's avoidance behavior.

[0055] Optionally, a preset physiological response model is run independently within each unit grid to obtain physiological response data within each unit grid, including: obtaining environmental field data within each unit grid; importing the environmental field data into the developmental prediction model, metabolic rate model, and behavioral response model respectively; and determining physiological response data based on at least one of the growth and development data output by the developmental prediction model, the metabolic rate output by the metabolic rate model, and the migration probability output by the behavioral response model.

[0056] Optionally, the developmental prediction model is established based on the nonlinear function coupling between insect development rate and data from different environmental fields. For example, the mathematical form of the nonlinear function between insect development rate and environmental temperature is shown in Equation 1:

[0057] (Formula 1)

[0058] Where T represents the ambient temperature in the environmental field data; This indicates the developmental rate of insects at an ambient temperature T, and the unit can be % / day. The maximum potential coefficient representing the developmental rate reflects the theoretical upper limit of the developmental rate under ideal conditions, and its unit can be % / day; This represents the lower temperature threshold required to maintain insect growth and development; when the ambient temperature T is below a certain level... hour, =0, meaning the insect's development has stopped; This represents the upper temperature threshold for maintaining insect growth and development; when the ambient temperature T approaches... At that time, the developmental rate is inhibited; A parameter representing the steepness of an insect's growth curve, expressed in units of 1 / ℃, is used to control the growth curve from the optimum temperature to... The rate of change of growth rate, The larger the value, the more significant the high-temperature inhibition effect during insect growth; denominator term This represents the inhibition term in the growth curve, used to describe the negative impact of high temperatures on insect growth and development.

[0059] The mathematical form of the nonlinear function between insect development rate and environmental humidity is shown in Formula 2:

[0060] (Formula 2)

[0061] Where H represents the ambient humidity in the environmental field data; The developmental rate of insects under ambient humidity H can be expressed as % / day. Indicates the maximum developmental rate; Indicates that the development rate has reached The humidity value at that time; k represents the kurtosis coefficient of the development rate function curve corresponding to the ambient humidity H; This indicates the offset.

[0062] Combining Formula 1 and Formula 2 above, the developmental prediction model established using the additive coupling method is shown in Formula 3:

[0063] (Formula 3)

[0064] in, This represents the insect metabolic rate output by the developmental prediction model; The coupling weights represent the development rate function corresponding to ambient temperature; The coupling weights represent the growth rate function corresponding to ambient humidity.

[0065] Specifically, by combining formulas one through three above, pre-calibration or custom settings can be implemented. , , , , ,k, , and After obtaining the ambient temperature T and ambient humidity H within any given grid cell, substituting the ambient temperature T into Formula 1 above yields the development rate corresponding to ambient temperature T. Substituting the ambient humidity H into Formula 2 above, we can obtain the development rate corresponding to the ambient humidity H. ,Will and Substituting into Formula 3 above, we can obtain the insect metabolic rate within this cell grid.

[0066] Optionally, the metabolic rate model of the present invention is based on a coupling of the Q10 temperature coefficient model and a gas concentration correction term. For example, the mathematical form of the Q10 temperature coefficient model is shown in Equation 4:

[0067] (Formula 4)

[0068] Where T represents the ambient temperature in the environmental field data; Indicates the preset reference temperature; This represents the metabolic rate corresponding to ambient temperature T. Indicates the preset reference temperature The corresponding basal metabolic rate; This indicates the multiple by which the metabolic rate changes for every 10°C increase in temperature.

[0069] The mathematical form of the gas concentration correction term is shown in Formula 5:

[0070] (Formula 5)

[0071] Wherein, G represents the gas concentration in the environmental field data; This indicates that the metabolic rate is inhibited by gas concentration G; This represents the gas concentration corresponding to a 50% decrease in metabolic rate; n represents the curve steepness coefficient of the gas concentration correction term.

[0072] Combining Equations 4 and 5 above, an additive coupling method is used to couple the Q10 temperature coefficient model and the gas concentration correction term to establish the metabolic rate model as shown in Equation 6:

[0073] (Formula 6)

[0074] in, This represents the metabolic rate output by the metabolic rate model. This represents the inhibition strength coefficient.

[0075] Specifically, by combining formulas four through six above, pre-calibration or custom settings can be implemented. , , , , n and After obtaining the ambient temperature T and gas concentration G within any given grid cell, substituting the ambient temperature T into Formula 4 above yields the metabolic rate corresponding to ambient temperature T. Substituting the gas concentration G into Formula 5 above, we can obtain the metabolic rate inhibition corresponding to gas concentration G. ,Will and Substituting into Formula 6 above, we can obtain the metabolic rate within this cell grid.

[0076] Optionally, the behavioral response model of the present invention is based on the coupling of insect kinetic movement models to different environmental field data (such as temperature, humidity, and gas concentration). For example, the mathematical form of the behavioral response model for gas concentration is shown in Equation 7:

[0077] (Formula 7)

[0078] Wherein, G represents the gas concentration in the environmental field data; This represents the migration probability with respect to gas concentration; Indicates the optimal gas concentration for insect growth; This represents the gas concentration sensitivity coefficient.

[0079] The mathematical form of the behavioral response model to ambient temperature is shown in Equation 8:

[0080] (Formula 8)

[0081] Where T represents the ambient temperature in the environmental field data; This represents the migration probability in relation to ambient temperature; Indicates the optimal temperature for insect growth; This represents the temperature sensitivity coefficient.

[0082] Figure 4 A flowchart illustrating a three-dimensional environment field construction method provided in an embodiment of the present invention. See also... Figure 4 As shown, in step S3 above, the three-dimensional environmental field of the insect breeding area is established based on the preprocessed dataset, including the following steps:

[0083] S301: Define one type of data in the preprocessed dataset as the main variable, and the data in the preprocessed dataset other than the main variable as auxiliary variables.

[0084] S302: Establish a variogram matrix for the main and auxiliary variables, and expand the variogram matrix to establish a co-kriging equation system.

[0085] S303: Interpolate and estimate the target point of the main variable based on the co-kriging equations.

[0086] S304: Establish a three-dimensional environmental field based on the interpolation results of different variables.

[0087] Specifically, temperature can be defined as the primary variable, and humidity and gas concentration as auxiliary variables. A cross-variogram function can be established for the primary and auxiliary variables. For example, taking temperature and humidity as an example, the mathematical form of the established cross-variogram function is shown in Formula 9:

[0088] (Formula Nine)

[0089] in, This represents the cross-variance function between temperature and humidity.

[0090] Taking temperature T, humidity H, and gas concentration G as examples, the established co-kriging equations are shown in Equation 10:

[0091] (Formula 10)

[0092] in, The autocorrelation variability function representing ambient temperature; The autocorrelation variability function representing ambient humidity; The autocorrelation variability function representing gas concentration; The cross-variance function representing ambient temperature and ambient humidity; The cross-variance function representing the relationship between ambient temperature and gas concentration; A unit vector representing ambient temperature; A unit vector representing ambient humidity; A unit vector representing gas concentration; Represents the Lagrange multipliers; , , Indicates the Kriging weighting coefficient; This represents the vector of variogram values ​​between the target point and all temperature observation points; This represents the cross-variance function value between the target point and the humidity observation point; This represents the cross-variance function value between the target point and the gas concentration observation point.

[0093] Specifically, refer to Formula 10; solving the system of linear equations yields the weighting coefficients. , and And combined with the establishment of weighting coefficients , and Interpolated estimate of the target point.

[0094] Optionally, a three-dimensional environmental field is established based on the interpolation results of different variables, including: establishing a three-dimensional grid based on the spatial range and resolution of the insect breeding area; merging the interpolation results into a multi-dimensional vector based on the weight allocation of different variables; and mapping the multi-dimensional vector to the three-dimensional grid to establish a three-dimensional environmental field.

[0095] Specifically, spatial extent can be expressed as × × Resolution can be expressed as The interpolation results are merged into a multidimensional vector based on the weight allocation of different variables (such as temperature, humidity, and gas concentration); the multidimensional vector is then mapped onto a three-dimensional mesh to establish a three-dimensional environmental field.

[0096] Based on the same inventive concept as the above embodiments, the present invention also provides an insect breeding control device for multi-sensor data fusion, used to execute the insect breeding control method for multi-sensor data fusion provided in any of the above embodiments, and having the corresponding functional modules and beneficial effects for executing the insect breeding control method for multi-sensor data fusion.

[0097] Figure 5 This is a schematic diagram of a multi-sensor data fusion insect breeding control device provided in an embodiment of the present invention. Figure 5 As shown, the insect breeding control device based on multi-sensor data fusion includes: a sampling module 101, a preprocessing module 102, a three-dimensional field modeling module 103, and a parameter optimization module 104.

[0098] The sampling module 101 is equipped with at least two types of sensors to acquire environmental sampling data of the insect breeding area. The sensors are arranged in a layered layout in the insect breeding area. The preprocessing module 102 is used to perform data preprocessing on the environmental sampling data and establish a preprocessed dataset. The three-dimensional field modeling module 103 is used to establish a three-dimensional environmental field of the insect breeding area based on the preprocessed dataset. The parameter optimization module 104 is used to couple the three-dimensional environmental field with a preset physiological response model and optimize the breeding environment control parameters of the insect breeding area according to the coupling result. The preset physiological response model is a function model established based on the physiological response data of insects in different environments.

[0099] Optionally, the three-dimensional environmental field is coupled with a preset physiological response model, and the breeding environment control parameters of the insect breeding area are optimized based on the coupling result. This includes: discretizing the three-dimensional environmental field based on a preset size to establish multiple unit grids; independently running the preset physiological response model in each unit grid to obtain physiological response data in different layered spaces; and adjusting the breeding environment control parameters based on the physiological response data.

[0100] Optionally, the preset physiological response model includes at least one of the following: a developmental prediction model, a metabolic rate model, and a behavioral response model; the preset physiological response model is run independently within each cell grid to obtain physiological response data within each cell grid, including: obtaining environmental field data within each cell grid; importing the environmental field data into the developmental prediction model, the metabolic rate model, and the behavioral response model respectively; and determining physiological response data based on at least one of the growth and development data output by the developmental prediction model, the metabolic rate output by the metabolic rate model, and the migration probability output by the behavioral response model.

[0101] Optionally, the developmental prediction model is established based on the nonlinear function coupling between insect development rate and data from different environmental fields; the metabolic rate model is established based on the coupling of the Q10 temperature coefficient model, humidity correction term, and light intensity correction term; and the behavioral response model is established based on the coupling of insect tactic movement model to data from different environmental fields.

[0102] Optionally, a three-dimensional environmental field of the insect breeding area is established based on the preprocessed dataset, including: defining one type of data in the preprocessed dataset as the main variable and the data in the preprocessed dataset other than the main variable as auxiliary variables; establishing a variogram matrix for the main variable and auxiliary variables, and expanding the variogram matrix to establish a co-kriging equation system; interpolating and estimating the target point of the main variable according to the co-kriging equation system; and establishing a three-dimensional environmental field based on the interpolation results of different variables.

[0103] Optionally, a three-dimensional environmental field is established based on the interpolation results of different variables, including: establishing a three-dimensional grid based on the spatial range and resolution of the insect breeding area; merging the interpolation results into a multi-dimensional vector based on the weight allocation of different variables; and mapping the multi-dimensional vector to the three-dimensional grid to establish a three-dimensional environmental field.

[0104] Optionally, data preprocessing is performed on the environmental sampling data to establish a preprocessed dataset, including: performing spatiotemporal alignment, outlier handling, and normalization on the environmental sampling data; adding hierarchical labels to the normalized data according to the position of the environmental sampling data in the hierarchical layout structure; and storing the normalized data with hierarchical labels into the preprocessed dataset.

[0105] Optionally, the layered layout structure includes at least: an upper space, an interface space, and a lower space; wherein, the upper space is located above the substrate of the insect breeding area, and the distance between the upper space and the substrate surface is greater than or equal to a first preset distance; the interface space is located on the substrate surface, and the distance between the interface space and the substrate surface is less than or equal to a second preset distance; the lower space is located inside the substrate, and the distance between the interface space and the substrate surface is greater than the second preset distance.

[0106] Based on the above embodiments, the present invention also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the above-described multi-sensor data fusion insect breeding control method.

[0107] Figure 6This is a schematic diagram of an electronic device for implementing the insect breeding control method of this invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0108] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0109] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0110] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the insect breeding control method based on multi-sensor data fusion described above.

[0111] In some embodiments, the above-described multi-sensor data fusion method for insect farming control can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the above-described multi-sensor data fusion method for insect farming control can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the above-described multi-sensor data fusion method for insect farming control by any other suitable means (e.g., by means of firmware).

[0112] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0113] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0114] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0115] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0116] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0117] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0118] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0119] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for regulating insect farming using multi-sensor data fusion, characterized in that, include: Environmental sampling data of insect breeding areas are acquired based on at least two types of sensors; The sensors are arranged in a layered layout in the insect breeding area; The layered layout structure includes at least: an upper space, an interface space, and a bottom space; wherein, the upper space is located above the substrate of the insect breeding area, and the distance between the upper space and the substrate surface is greater than or equal to a first preset distance; the interface space is located on the substrate surface, and the distance between the interface space and the substrate surface is less than or equal to a second preset distance; the bottom space is located inside the substrate, and the distance between the bottom space and the substrate surface is greater than the second preset distance. Perform data preprocessing on the environmental sampling data to create a preprocessed dataset; A three-dimensional environmental field of the insect breeding area is established based on the preprocessed dataset; The three-dimensional environmental field is coupled with a preset physiological response model, and the breeding environment control parameters of the insect breeding area are optimized based on the coupling results. The preset physiological response model is a function model established based on the physiological response data of insects in different environments; The coupling of the three-dimensional environmental field with the preset physiological response model, and the optimization of the breeding environment control parameters of the insect breeding area based on the coupling result, includes: discretizing the three-dimensional environmental field based on a preset size to establish multiple unit grids; independently running the preset physiological response model within each unit grid to obtain physiological response data in different hierarchical spaces; and adjusting the breeding environment control parameters based on the physiological response data. The preset physiological response model includes at least one of the following: a developmental prediction model, a metabolic rate model, and a behavioral response model; The step of independently running the preset physiological response model within each of the aforementioned cell grids to obtain physiological response data within each cell grid includes: acquiring environmental field data within each of the aforementioned cell grids; importing the environmental field data into the developmental prediction model, the metabolic rate model, and the behavioral response model, respectively; and determining the physiological response data based on at least one of the growth and development data output by the developmental prediction model, the metabolic rate output by the metabolic rate model, and the migration probability output by the behavioral response model. The developmental prediction model includes a nonlinear function model relating insect development rate to ambient temperature. Nonlinear function model of insect development rate and environmental humidity and developmental coupling model Where T represents the ambient temperature. Indicates developmental rate, The coefficient representing the maximum potential for developmental rate. This represents the lower temperature threshold required to maintain insect growth and development. This indicates the upper limit of the temperature threshold required to maintain insect growth and development. The kurtosis parameter of the insect growth curve, denominator term The term represents the inhibition phase of the growth curve; H represents ambient humidity. Indicates developmental rate, Indicates the maximum developmental rate. Indicates that the development rate has reached The humidity value at that time; k represents the kurtosis coefficient of the development rate function curve corresponding to the ambient humidity H; Indicates the offset; This represents the insect metabolic rate output by the developmental prediction model; The coupling weights represent the development rate function corresponding to ambient temperature; The coupling weights represent the growth rate function corresponding to ambient humidity. The metabolic rate model includes: the Q10 temperature coefficient model. Gas concentration correction term and metabolic coupling model ;in, Indicates the preset reference temperature; This represents the metabolic rate corresponding to ambient temperature T. Indicates the preset reference temperature The corresponding basal metabolic rate; This indicates the factor by which the metabolic rate changes for every 10°C increase in temperature; G represents the gas concentration. This indicates that the metabolic rate is inhibited by gas concentration G; This represents the gas concentration corresponding to a 50% decrease in metabolic rate; n represents the curve steepness coefficient of the gas concentration correction term. The behavioral response model includes: a behavioral response model for gas concentration. and behavioral response models for ambient temperature ;in, This represents the migration probability with respect to gas concentration G; Indicates the optimal gas concentration for insect growth; Indicates the gas concentration sensitivity coefficient; This represents the migration probability in relation to ambient temperature T; Indicates the optimal temperature for insect growth; This represents the temperature sensitivity coefficient.

2. The insect farming control method based on multi-sensor data fusion according to claim 1, characterized in that, The process of establishing a three-dimensional environmental field for the insect breeding area based on the preprocessed dataset includes: Define one type of data in the preprocessed dataset as the main variable, and the data in the preprocessed dataset other than the main variable as auxiliary variables; A variogram matrix is ​​established for the main variables and the auxiliary variables, and the variogram matrix is ​​expanded to establish a co-kriging equation system; The target point of the main variable is estimated by interpolation based on the co-kriging equations. The three-dimensional environmental field is established based on the interpolation results of different variables.

3. The insect farming control method based on multi-sensor data fusion according to claim 2, characterized in that, The process of establishing the three-dimensional environmental field based on the interpolation results of different variables includes: A three-dimensional mesh is established based on the spatial extent and resolution of the insect breeding area; The interpolation results are merged into a multidimensional vector based on the weight allocation of different variables; The multidimensional vector is mapped onto the three-dimensional mesh to establish the three-dimensional environment field.

4. The insect farming control method based on multi-sensor data fusion according to claim 1, characterized in that, The step of performing data preprocessing on the environmental sampling data to establish a preprocessed dataset includes: The environmental sampling data is subjected to spatiotemporal alignment, outlier handling, and normalization. Add hierarchical labels to the normalized data based on the position of the environmental sampling data in the hierarchical layout structure; The normalized data with the hierarchical labels is stored in the preprocessed dataset.

5. A multi-sensor data fusion-based insect farming control device, characterized in that, The apparatus for implementing the insect farming control method for multi-sensor data fusion according to any one of claims 1-4 includes: The sampling module is equipped with at least two types of sensors to acquire environmental sampling data of the insect breeding area; the sensors are arranged in a layered layout in the insect breeding area. The preprocessing module is used to perform data preprocessing on the environmental sampling data and establish a preprocessed dataset; A 3D field modeling module is used to establish a 3D environmental field of the insect breeding area based on the preprocessed dataset. The parameter optimization module is used to couple the three-dimensional environmental field with the preset physiological response model, and optimize the breeding environment control parameters of the insect breeding area based on the coupling result; The preset physiological response model is a function model established based on the physiological response data of insects in different environments.

6. An electronic device, characterized in that, The electronic device includes: at least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the insect breeding control method of multi-sensor data fusion as described in any one of claims 1-4.

Images