A method, system and storage medium for controlling black soldier fly breeding

Abstract

The present application discloses a method, system and storage medium for controlling the breeding of black soldier flies; the breeding area of ​​black soldier flies is divided into a number of cells. Each cell represents a local area of ​​the breeding area, including its own environmental parameters such as humidity, temperature, oxygen content, and exhaust gas content; 1. Automated control: The intelligent breeding environment control system can automatically monitor, predict and adjust the environmental parameters such as humidity, temperature, oxygen content, and exhaust gas content of the breeding area. Through the cellular automaton model and D-S theory verification, the system can autonomously predict and verify environmental parameters, realize automated breeding environment regulation, and greatly reduce the need for manual intervention. 2. Efficient optimization: By continuously predicting and adjusting at each time step, the intelligent breeding environment control system can optimize the environmental conditions of the breeding area to make it more suitable for the growth and reproduction of black soldier flies.

Description

Technical Field

[0001] The present application relates to the technical field of black soldier fly breeding, and in particular to a black soldier fly breeding control method, system and storage medium. Background Art

[0002] The black soldier fly is an insect belonging to the family Muscidae, with the scientific name Hermetia illucens. They are usually found in warm climates and prefer to inhabit places such as compost, decaying organic matter and feces. Black soldier flies are very useful bioconversion tools in their larval stage. They are considered to be good biodegraders that can convert organic waste (such as food scraps, kitchen garbage, etc.) into high-protein insect protein and fat. Because its larvae are rich in protein and fat, black soldier fly larvae have become an important substitute for poultry feed and fish feed.

[0003] In addition, black soldier flies are also considered a potential tool for sustainable agriculture and environmental management. They can help reduce the accumulation of organic waste and reduce landfills, thereby helping to reduce greenhouse gas emissions. Due to the ecological and economic value of black soldier flies, the application areas of their research and utilization are gradually expanding.

[0004] However, after long-term work and research, the inventors found that the traditional black soldier fly breeding technology has the following technical problems that need to be solved urgently:

[0005] (1) Difficulty in manual control: Traditional black soldier fly farming usually requires farmers to manually adjust environmental conditions, such as temperature and humidity. Such manual control methods may be limited by technical level and experience, and are prone to errors and instability;

[0006] (2) Unable to respond in time: Traditional aquaculture technology usually relies on experience and routine operations to regulate the environment. It cannot respond to environmental changes in the aquaculture area in a timely and accurate manner, which may lead to unsatisfactory growth conditions for black soldier flies and affect the aquaculture effect.

[0007] (3) Waste of resources: Traditional farming techniques may lead to waste of resources, such as heating / cooling, adding / dehumidifying, ventilation or exhaust gas treatment, resulting in energy waste and environmental burden;

[0008] (4) Unable to adapt to complex environments: Traditional farming technologies usually lack the ability to accurately perceive and handle the complex environment of the farming area, and are difficult to adapt to the complex and changeable conditions of the farming site.

[0009] To this end, a black soldier fly breeding control method, system and storage medium are proposed. Summary of the invention

[0010] In view of this, the embodiments of the present application hope to provide a black soldier fly breeding control method, system and storage medium to solve or alleviate the technical problems existing in the prior art, namely, difficulty in manual control, inability to respond in time, waste of resources and inability to adapt to complex environments, and at least provide a beneficial option for this.

[0011] The technical solution of the embodiment of the present application is implemented as follows:

[0012] First aspect

[0013] A method for controlling black soldier flies breeding:

[0014] 1. Introduction

[0015] This application aims to optimize the environmental factors such as humidity, temperature, oxygen content, exhaust gas content, etc. in the black soldier fly breeding area to improve the breeding efficiency and yield of black soldier flies. This method is based on the cellular automaton model and DS theory verification, and has the advantages of automation, efficient optimization, precise control and strong adaptability.

[0016] 2. Content

[0017] (2.1) Cellular automaton model: First, the black soldier fly breeding area is divided into several cells. Each cell represents a local area of ​​the breeding area, including its own environmental parameters such as humidity, temperature, oxygen content, and exhaust gas content. According to the characteristics and needs of the breeding area, the transformation functions (FH, FT, FO, FW) are defined to describe the relationship and evolution law between the environmental parameters of the cells. At each time step, the cellular automaton model predicts the environmental parameter value of the next time step through the transformation function based on the state of the current cell and the state of the surrounding cells;

[0018] (2.2) Sensor data acquisition: The system is equipped with multiple sensors for real-time monitoring of environmental parameters such as humidity, temperature, oxygen content, and exhaust gas content in the breeding area. The sensors transmit real-time data to the data acquisition module for subsequent processing and analysis;

[0019] (2.3) Data processing and verification: The data acquisition module compares the real-time data from the sensor with the predicted values ​​output by the cellular automaton model. These predicted values ​​are calculated based on the cellular automaton model and the conversion function, and are used to describe the predicted results of the environmental parameters in the next time step. Then, the DS theory verification module is used to fuse and verify the predicted values ​​output by the cellular automaton and the sensor detection values. The confidence of each environmental parameter is calculated through the Dempster synthesis rule, and the consistency between the predicted value and the actual value is judged;

[0020] (2.4) Environmental control and prediction: If the predicted value output by the cellular automaton is successfully verified by the DS theory, that is, the confidence reaches a certain threshold, indicating that the predicted value is consistent with the actual value, the aquaculture environment control system relies on the humidity, temperature, oxygen content, and exhaust gas content predicted by the cellular automaton for pre-adjustment in the next time step. According to the predicted environmental parameters, the control algorithm adjusts the heating, ventilation, humidification, and oxygen supply equipment in the aquaculture environment control system to optimize the environmental conditions of the aquaculture area and provide an environment more suitable for the growth of black soldier flies;

[0021] (2.5) Iterative update: The entire process is continuously iterated, and data collection, prediction, verification and adjustment are performed at each time step. Through multiple iterative updates, the aquaculture environment control system can continuously adapt to the growth needs and environmental changes of black soldier flies and continuously optimize aquaculture conditions;

[0022] (3) This breeding control method combines the cellular automaton model with DS theory verification to achieve intelligent control and optimization of the black soldier fly breeding environment. Through automated prediction and adjustment, the system can improve breeding efficiency and output, reduce resource waste, and provide a more suitable growth environment for black soldier flies, promoting the sustainable development of black soldier fly breeding.

[0023] Second aspect

[0024] A black soldier fly breeding control system: including the following contents:

[0025] (1) Sensor component: The system is equipped with multiple sensors, including humidity sensors, temperature sensors, oxygen content sensors and exhaust gas content sensors. These sensors can monitor the humidity, temperature, oxygen content, exhaust gas content and other environmental parameters in the breeding area in real time. The sensor component transmits the collected real-time data to the data acquisition module, providing an accurate data basis for subsequent breeding environment control;

[0026] (2) Data acquisition module: The data acquisition module is one of the core components of the system, responsible for receiving data from sensors, processing and storing the data. This module will integrate real-time data with historical data, build an environmental parameter database for the breeding area, and provide input data for the cellular automation model and DS theory verification module;

[0027] (3) Cellular automaton model: The system uses a cellular automaton model to model and predict the breeding area. The cellular automaton model divides the breeding area into several cells, each of which represents the environmental state of a local area. According to the preset conversion function, the cellular automaton model predicts the humidity, temperature, oxygen content, exhaust gas content and other environmental parameters of the next time step based on the current cell state and the surrounding cell state in each time step cycle;

[0028] (4) DS theory verification module: The predicted value of the environmental parameters of the next time step output by the cellular automaton model needs to be verified by the DS theory. The DS theory verification module uses the Dempster synthesis rule to fuse and verify the parameter values ​​predicted by the cellular automaton with the actual values ​​detected by the sensor. By calculating the confidence level, it is determined whether the predicted value conforms to the change trend of the actual environmental parameters;

[0029] (5) Controller: The controller is another important component of the system. According to the above-mentioned aquaculture control method, it controls the heating, ventilation, humidification and oxygen supply equipment. When the predicted value output by the cellular automaton model is successfully verified by the DS theory, it means that the predicted value is consistent with the actual value. The controller makes pre-adjustments based on these predicted values. According to the predicted humidity, temperature, oxygen content, exhaust gas content and other parameters, the controller will automatically adjust the corresponding equipment to optimize the aquaculture environment and provide more suitable conditions for the growth of black soldier flies.

[0030] Compared with the prior art, the beneficial effects of this application are:

[0031] 1. Automated control: The intelligent aquaculture environment control system can automatically monitor, predict and adjust environmental parameters such as humidity, temperature, oxygen content, and exhaust gas content in the aquaculture area. Through the cellular automaton model and DS theory verification, the system can autonomously predict and verify environmental parameters, realize automated aquaculture environment control, and greatly reduce the need for manual intervention;

[0032] 2. Efficient optimization: By continuously predicting and adjusting at each time step, the intelligent aquaculture environment control system can optimize the environmental conditions in the aquaculture area to make it more suitable for the growth and reproduction of black soldier flies. The system can make intelligent decisions based on real-time and historical data to improve aquaculture efficiency and increase production;

[0033] 3. Precision control: The intelligent breeding environment control system adopts the cellular automaton model to divide the breeding area into fine-grained parts, and can accurately predict and adjust the environmental parameters of each cell. Such precision control can better meet the changes in the different growth stages and needs of black soldier flies;

[0034] 4. Strong adaptability: Since the system adopts an automated and intelligent control method, it can be flexibly adjusted according to the actual situation and needs of the black soldier fly breeding area. The system can adapt to different breeding sites, different seasons, different climatic conditions and other diverse situations, providing an environment more suitable for the growth of black soldier flies. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 This is a logical diagram of this application;

[0037] Figure 2 This is one of the control program schematic diagrams of Embodiment 8 of the present application;

[0038] Figure 3 This is the second control program schematic diagram of the eighth embodiment of the present application;

[0039] Figure 4 This is the third control program diagram of the eighth embodiment of the present application;

[0040] Figure 5 This is the fourth control program diagram of the eighth embodiment of the present application; DETAILED DESCRIPTION

[0041] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the specific embodiments disclosed below.

[0042] Black soldier flies are insects, also known as flies or black mosquitoes. They are organisms that have a strong ability to decompose organic waste and decaying substances, so they have important application value in agriculture, environmental protection and the feed industry. In the breeding process of black soldier flies, the breeding environment and management must be strictly controlled. Breeders also need to reasonably adjust the ratio of feed and substrate to ensure the healthy growth and high-quality output of black soldier flies. To this end, please refer to Figure 1 This specific implementation will provide relevant technical solutions to further improve the above-mentioned control of the breeding environment and management effects:

[0043] A method for controlling the breeding of black soldier flies comprises an environmental system, wherein the environmental system detects and controls the humidity, temperature, oxygen content and exhaust gas in a breeding area of ​​black soldier flies, and implements the following steps:

[0044] S1. Use the cellular automaton model for modeling and prediction: divide the black soldier fly breeding area into several cells, define the humidity, temperature, oxygen content, and exhaust gas of the cells, use the humidity, temperature, oxygen content, and exhaust gas content and conversion function input by the environmental system, and cyclically detect the humidity, temperature, oxygen content, and exhaust gas content required by each cell in the next time step at each time step, and output them to S2;

[0045] S2. Verification using DS theory: The evidence comes from the humidity, temperature, oxygen content, and exhaust gas content detected by the sensors of the environmental system in the current time step and the previous time step. The Dempster synthesis rule is used to determine whether the predicted required humidity, temperature, oxygen content, and exhaust gas content of the next time step output by the cellular automaton conform to the Dempster synthesis rule, and pre-adjustment is performed based on the humidity, temperature, oxygen content, and exhaust gas content of the next time step predicted by the cellular automaton.

[0046] In this specific implementation: S1, cellular automaton model: The cellular automaton model is a discrete dynamic system used to simulate and predict the changes in environmental factors such as humidity, temperature, oxygen content and exhaust gas content in the black soldier fly breeding area. In this model, the breeding area is divided into a number of cells, each cell represents a local area of ​​the breeding area. Each cell has four attributes, namely humidity, temperature, oxygen content and exhaust gas content.

[0047] Specifically, define the cell properties: the cellular automaton model clearly defines the humidity, temperature, oxygen content, and waste gas content of each cell. These properties are important factors in describing the breeding environment and affect the growth and reproduction of black soldier flies.

[0048] Specifically, the environmental system inputs: At each time step, the environmental system inputs the humidity, temperature, oxygen content, and exhaust gas content data detected by real-time sensors into the cellular automaton model. The data detected by these sensors are the environmental parameters of the current time step and the previous time step.

[0049] Specifically, transition function: The cellular automaton model uses predefined transition functions to describe the relationship and evolution law between cell properties. The transition functions FH, FT, FO and FW are responsible for calculating the humidity, temperature, oxygen content and exhaust gas content required by each cell in the next time step.

[0050] Specifically, loop detection: At each time step, the cellular automation model loops to detect the attribute value of each cell. Based on the environmental parameters of the current time step and the previous time step, as well as the conversion function, the model calculates the predicted values ​​of humidity, temperature, oxygen content, and exhaust gas content at the next time step.

[0051] Specifically, output to S2: The cellular automaton model outputs the predicted humidity, temperature, oxygen content, and exhaust gas content of the next time step to the S2 module for use by the DS theory verification module.

[0052] In this specific implementation: S2, DS theory: DS theory is a mathematical theory used for uncertainty reasoning and decision-making, which is used to verify whether the predicted value output by the cellular automaton model conforms to the change trend of the actual environmental parameters. In the aquaculture control system, the DS theory verification module plays a role in screening and confirmation.

[0053] Specifically, the source of evidence: The DS theory verification module uses the sensor detection data of the environmental system in the current time step and the previous time step, including parameters such as humidity, temperature, oxygen content, and exhaust gas content as the source of evidence. These sensor data are direct measurements of actual environmental parameters, which are used to compare with the predicted values ​​output by the cellular automaton model.

[0054] Specifically, Dempster synthesis rule: The DS theory verification module uses Dempster synthesis rule to synthesize and fuse the predicted values ​​of humidity, temperature, oxygen content and exhaust gas content in the next time step output by the cellular automaton model. After synthesis, the confidence of each parameter is obtained to measure the consistency between the predicted value and the actual value.

[0055] Specifically, the judgment criteria are: if the confidence of the predicted value output by the cellular automaton model reaches a certain threshold after verification by the DS theory, it means that the predicted value is consistent with the actual value, indicating that the predicted value is credible.

[0056] Specifically, pre-adjustment: After the DS theory is verified, the controller pre-adjusts the humidity, temperature, oxygen content and exhaust gas content of the next time step according to the cellular automaton prediction. According to the predicted values, the controller automatically adjusts the heating, ventilation, humidification and oxygen supply equipment to optimize the breeding environment and provide more suitable conditions for the growth of black soldier flies.

[0057] The technical features of the above-described specific embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described specific embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. Embodiment 1

[0058] In order to make the above specific implementation methods of the present application more obvious and easy to understand, the present application will be described in detail in the form of embodiments. The present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the embodiments disclosed below.

[0059] In S1: Divide the breeding area into several cells, and define the humidity, temperature, oxygen content and exhaust gas content of each cell. Assume that the breeding area is divided into an M*N two-dimensional grid, where each grid intersection is a cell;

[0060] Specifically, the cell representation: This embodiment uses C (i, j, t) to represent the state of the cell in the i-th row and j-th column at time step t, where i and j are the indexes of the row and column respectively. In this way, this embodiment can access the state of each cell at different time steps through C (i, j, t).

[0061] Specifically, define the properties of the cell: In this embodiment, the humidity, temperature, oxygen content and exhaust gas content of the cell are defined as H(i, j, t), T(i, j, t), O(i, j, t) and W(i, j, t), respectively. These properties are important factors in describing the breeding environment and have an important impact on the growth and reproduction of black soldier flies.

[0062] Specifically, C(i, j, t) is used to represent the state of the cell in the i-th row and j-th column at time step t, including humidity H(i, j, t), temperature T(i, j, t), oxygen content O(i, j, t) and exhaust gas content W(i, j, t). Based on these properties, the cellular automaton model can predict the humidity, temperature, oxygen content and exhaust gas content required for each cell in the next time step.

[0063] Furthermore, the breeding area is divided into several cells: by dividing the breeding area into an M*N two-dimensional grid, each grid intersection is a cell, the discretization of the breeding area is achieved, which is convenient for establishing a cellular automation model and making predictions.

[0064] Furthermore, the humidity, temperature, oxygen content and exhaust gas content of the cell are defined: By defining the humidity, temperature, oxygen content and exhaust gas content of the cell, the environmental state of each cell at different time steps is clarified, providing input parameters for the cellular automaton model.

[0065] It can be understood that in this embodiment, the cellular automaton model can predict the humidity, temperature, oxygen content and exhaust gas content of the next time step based on the cell state and surrounding cell state of the current time step and the predefined conversion function. In this way, the breeding environment control system can be intelligently adjusted and optimized according to the predicted values ​​to provide environmental conditions more suitable for the growth of black soldier flies.

[0066] The above embodiments only express the implementation methods of the relevant practical applications of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims. Embodiment 2

[0067] In order to make the above specific implementation methods of the present application more obvious and easy to understand, the present application will be described in detail in the form of embodiments. The present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the embodiments disclosed below.

[0068] In S1:

[0069] Transformation function F: takes the cell state at the current time step t and the input of the aquaculture environment control system as input, and outputs the cell state at the next time step t+1;

[0070] Specifically, in this embodiment: In S1, this embodiment defines a transition function F, which is the core part of the cellular automaton model and is used to predict the state of each cell in the breeding area at the next time step t+1. The input of the transition function F is the cell state at the current time step t and the input of the breeding environment control system, and the output is the cell state at the next time step t+1.

[0071] The specific expression is as follows: Transformation function F: Transformation function F is a function that accepts multiple parameters as input and outputs a new cell state. Its mathematical expression is as follows:

[0072] ;

[0073] Among them, C(i, j, t) represents the state of the cell in the i-th row and j-th column at time step t, including humidity H(i, j, t), temperature T(i, j, t), oxygen content O(i, j, t) and exhaust gas content W(i, j, t). Input(t) represents the input of the aquaculture environment control system at time step t, including control operations such as adjusting heating, ventilation or humidification equipment, oxygen supply equipment, etc.

[0074] Further: The logical principle of the transition function F is to predict the cell state at the next time step t+1 based on the cell state at the current time step t and the surrounding cell states, as well as the input of the aquaculture environment control system. In the cellular automaton model, the state of each cell is affected by the state of its surrounding cells, and the state is evolved and transmitted through the transition function F.

[0075] Further: Cell state at current time step t: The input of the conversion function F includes the cell state C(i, j, t) at current time step t. These states include humidity H(i, j, t), temperature T(i, j, t), oxygen content O(i, j, t) and exhaust gas content W(i, j, t).

[0076] Further: surrounding cell states: The transition function F also accepts the states of surrounding cells as input, including C(i-1, j, t), C(i+1, j, t), C(i, j-1, t), and C(i, j+1, t). These states represent the states of neighboring cells of the current cell in the four directions of up, down, left, and right, and their values ​​will also affect the evolution of the current cell.

[0077] Further: Input of the aquaculture environment control system: The conversion function F also accepts the input input(t) of the aquaculture environment control system at the current time step t. These inputs include control operations such as adjusting heating, ventilation or humidification equipment, oxygen supply equipment, etc. These operations will affect the aquaculture environment and thus affect the state evolution of the cell.

[0078] It can be understood that by taking the cell state of the current time step, the surrounding cell state and the input of the aquaculture environment control system as the input of the conversion function F, this embodiment can predict the cell state C(i,j, t+1) of the next time step t+1. In this way, this embodiment can detect the humidity, temperature, oxygen content and exhaust gas content required by each cell in the next time step in a cycle at each time step, provide a prediction value for the subsequent DS theory verification, and perform intelligent adjustment of the aquaculture environment after the verification is passed.

[0079] The above embodiments only express the implementation methods of the relevant practical applications of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims. Embodiment 3

[0080] In order to make the above specific implementation methods of the present application more obvious and easy to understand, the present application will be described in detail in the form of embodiments. The present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the embodiments disclosed below.

[0081] In S1, this embodiment will detect the humidity, temperature, oxygen content and exhaust gas content required by each cell at the next time step t+1 in a loop at each time step. This embodiment uses conversion functions FH, FT, FO and FW to predict the humidity, temperature, oxygen content and exhaust gas content of each cell at the next time step t+1 respectively. That is:

[0082] Specifically, the conversion function FH is used to predict the humidity H(i, j, t+1) of each cell at the next time step t+1. Its mathematical expression is as follows:

[0083] ;

[0084] Among them, H(i, j, t) represents the humidity of the cell in the i-th row and j-th column at time step t, and H(i-1, j, t), H(i+1, j, t), H(i, j-1, t), and H(i, j+1, t) represent the humidity of the neighboring cells of the current cell in the four directions of up, down, left, and right. Input (t) represents the input of the aquaculture environment control system at time step t, including control operations such as adjusting heating, ventilation or humidification equipment, and oxygen supply equipment.

[0085] Specifically, the transformation function FT is used to predict the temperature T(i, j, t+1) of each cell at the next time step t+1. Its mathematical expression is as follows:

[0086] ;

[0087] Among them, T(i, j, t) represents the temperature of the cell in the i-th row and j-th column at time step t, and T(i-1, j, t), T(i+1, j, t), T(i, j-1, t), and T(i, j+1, t) represent the temperatures of the neighboring cells of the current cell in the four directions of up, down, left, and right, respectively.

[0088] Specifically, the conversion function FO is used to predict the oxygen content O(i, j, t+1) of each cell at the next time step t+1. Its mathematical expression is as follows:

[0089] ;

[0090] Among them, O(i, j, t) represents the oxygen content of the cell in the i-th row and j-th column at time step t, and O(i-1, j, t), O(i+1, j, t), O(i, j-1, t), and O(i, j+1, t) represent the oxygen content of the neighboring cells of the current cell in the four directions of up, down, left, and right, respectively.

[0091] Specifically, the conversion function FW is used to predict the exhaust gas content W(i, j,t+1) of each cell at the next time step t+1. Its mathematical expression is as follows:

[0092] ;

[0093] Among them, W(i, j, t) represents the exhaust gas content of the cell in the i-th row and j-th column at time step t, and W(i-1, j, t), W(i+1, j, t), W(i, j-1, t), and W(i, j+1, t) represent the exhaust gas content of the neighboring cells of the current cell in the four directions of up, down, left, and right, respectively.

[0094] Through the conversion functions FH, FT, FO and FW, this embodiment can predict the humidity, temperature, oxygen content and exhaust gas content of each cell at the next time step t+1 based on the humidity, temperature, oxygen content and exhaust gas content at the current time step t, as well as the state of the surrounding cells and the input of the aquaculture environment control system.

[0095] In this way, this embodiment can cyclically detect the humidity, temperature, oxygen content and exhaust gas content required by each cell in the next time step at each time step, and input these predicted values ​​into S2 to verify the DS theory, and finally intelligently adjust the breeding environment according to the verification results to provide more suitable environmental conditions for the growth and reproduction of black soldier flies.

[0096] Preferably, FH, FT, FO, and FW are all linear weighted functions. The mathematical form of the linear weighted function is intuitive and simple, and the influence of each neighbor cell on the current cell is linearly combined through a weight factor. This makes the prediction results of the model easier to explain, and the present embodiment can intuitively understand the contribution of each neighbor cell to the current cell state. The weight factor of the linear weighted function is adjustable. By adjusting the weight factor, the present embodiment can flexibly control the influence of each neighbor cell on the current cell, thereby adapting to different breeding environments and conditions. This allows the present embodiment to optimize and adjust the model according to actual conditions to obtain better prediction results. The linear weighted function usually has good numerical stability. It does not introduce complex nonlinear transformations, reduces problems that may occur in numerical calculations, and is easier to process and debug.

[0097] Further preferably, for FH, FT, FO, and FW, this embodiment may define them in the following forms:

[0098] ;

[0099] ;

[0100] ;

[0101] ;

[0102] Among them, a1, a2, a3, a4, a5, a6, b1, b2, b3, b4, b5, b6, c1, c2, c3, c4, c5, c6, d1, d2, d3, d4, d5, d6 are adjustable weight factors, which are used to represent the influence of each neighbor cell on the current cell and the influence of the aquaculture environment control system. They can be adjusted according to the actual situation so that the model can better predict the changes in humidity, temperature, oxygen content and exhaust gas content in the aquaculture area.

[0103] Exemplarily, taking the formula of the transfer function FO as an example, this embodiment will list an exemplary scenario, derive the transfer function by way of example, and demonstrate its principle:

[0104] Assume that this embodiment has a 2x2 breeding area, in which each cell represents a small area. This embodiment uses FO to derive the predicted value of the oxygen content of one of the cells at the next time step t+1.

[0105] Assume that at the current time step t, the oxygen content of the first cell is O(1, 1, t), and the oxygen content of its four neighboring cells above, below, left, and right are O(1, 2, t), O(2, 1, t), O(1, 0, t), and O(0, 1, t), respectively. At the same time, the input of the aquaculture environment control system is input(t).

[0106] The conversion function FO will predict the oxygen content O(1, 1, t+1) of the first cell at the next time step t+1 based on the oxygen content at the current time step t and the oxygen content of the neighboring cells, as well as the input input(t) of the aquaculture environment control system.

[0107] Example derivation: Assume that the conversion function FO is a linear weighted function, that is, each neighbor cell has the same influence weight on the current cell. In this embodiment, parameter a is used to represent the influence weight of the neighbor cell on the current cell.

[0108] The mathematical expression of the conversion function FO can be written as:

[0109] .

[0110] Now assume that this example has the following data:

[0111] ;

[0112] ;

[0113] Assume that the influence weight of the neighbor cell on the current cell is a = 0.2.

[0114] Substitute the data into the expression of the conversion function FO:

[0115] ;

[0116] Therefore, at the next time step t+1, the predicted value of the oxygen content of the first cell is 52.8.

[0117] In this way, this embodiment can use the conversion function FO to predict the oxygen content of each cell at the next time step t+1 according to the oxygen content at the current time step t and the oxygen content of the neighboring cells, as well as the input of the breeding environment control system, so as to intelligently adjust the breeding environment, provide more optimized conditions, and promote the growth and reproduction of black soldier flies.

[0118] The above embodiments only express the implementation methods of the relevant practical applications of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims. Embodiment 4

[0119] In order to make the above specific implementation methods of the present application more obvious and easy to understand, the present application will be described in detail in the form of embodiments. The present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the embodiments disclosed below.

[0120] In S2:

[0121] The humidity, temperature, oxygen content and exhaust gas content of the next time step t+1 output by the cellular automaton are verified using the DS theory. To this end, in this embodiment, the humidity detected by the sensor at the current time step t is Hs(i, j, t), the temperature is Ts(i, j, t), the oxygen content is Os(i, j, t), and the exhaust gas content is Ws(i, j, t). At the same time, in this embodiment, it is assumed that the sensor detection values ​​at the previous time step t-1 are Hs(i, j, t-1), Ts(i, j, t-1), Os(i, j, t-1), and Ws(i, j, t-1).

[0122] According to the Dempster synthesis rule, the confidence of the humidity, temperature, oxygen content, and exhaust gas content at the next time step t+1 is calculated; specifically, the confidence of the humidity, temperature, oxygen content, and exhaust gas content at the next time step t+1 is calculated using the Dempster synthesis rule. Bel(H(i, j, t+1)), Bel(T(i, j, t+1)), Bel(O(i, j, t+1)), and Bel(W(i, j, t+1)) represent the confidence of the humidity, temperature, oxygen content, and exhaust gas content at the next time step t+1 output by the cellular automaton in this embodiment under the sensor detection value at the current time step t and the sensor detection value at the previous time step t-1:

[0123] First, according to the DS theory, this embodiment calculates the uncertainty of humidity, temperature, oxygen content and exhaust gas content at the current time step t:

[0124] ;

[0125] ;

[0126] ;

[0127] .

[0128] Then, the confidence of humidity, temperature, oxygen content and exhaust gas content at the next time step t+1 is calculated:

[0129] ;

[0130] ;

[0131] ;

[0132] ;

[0133] Through the above calculations, this embodiment obtains the confidence levels Bel(H(i, j, t+1)), Bel(T(i, j, t+1)), Bel(O(i, j, t+1)) and Bel(W(i, j, t+1)) about the humidity, temperature, oxygen content and exhaust gas content at the next time step t+1. These confidence levels reflect the reliability of the prediction of the cellular automaton output at the next time step by this embodiment. In practical applications, this embodiment can select appropriate adjustment strategies based on these confidence levels to pre-adjust the breeding environment to optimize the breeding environment of black soldier flies and improve their growth and reproduction efficiency.

[0134] Among them, Bel represents the confidence of the corresponding state, and DempsterCombination represents the Dempster synthesis rule.

[0135] The above embodiments only express the implementation methods of the relevant practical applications of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims. Embodiment 5

[0136] In order to make the above specific implementation methods of the present application more obvious and easy to understand, the present application will be described in detail in the form of embodiments. The present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the embodiments disclosed below.

[0137] In the above DempsterCombination, this embodiment uses DS theory to synthesize the confidence of humidity, temperature, oxygen content and exhaust gas content output by the cellular automaton, and the confidence of humidity, temperature, oxygen content and exhaust gas content detected by the sensor.

[0138] For the confidence Bel(H(i, j, t+1)) of humidity output by the cellular automaton, this embodiment assumes that the predicted result of humidity output by the cellular automaton is H-pred(i, j, t+1). According to the definition of confidence, this embodiment uses the following formula to calculate the confidence of humidity:

[0139] ;

[0140] Wherein, α is a parameter that controls the confidence decay rate. When the absolute difference between the humidity output by the cellular automaton and the humidity detected by the sensor is smaller, the confidence is closer to 1, indicating that the prediction result of the humidity in this embodiment is more confident.

[0141] For the confidence Bel(Hs(i, j, t+1)) of the humidity detected by the sensor, this embodiment assumes that the precision and accuracy of the sensor is σ-s. According to the probability density function of the normal distribution, this embodiment uses the following formula to calculate the confidence of the humidity detected by the sensor:

[0142] .

[0143] After obtaining the humidity confidence Bel (H(i, j, t+1)) output by the cellular automaton and the humidity confidence Bel (Hs(i, j, t+1)) detected by the sensor, this embodiment uses the Dempster synthesis rule to synthesize them to obtain the comprehensive humidity confidence Bel-combined (H(i, j, t+1)):

[0144] .

[0145] Similarly, this embodiment may use similar methods to calculate the confidence levels of temperature, oxygen content, and exhaust gas content.

[0146] When this embodiment pre-adjusts the cellular automation prediction result according to the confidence level, this embodiment uses the normalized confidence level as the weight. For the pre-adjustment of humidity, this embodiment uses the following formula:

[0147] .

[0148] Similarly, this embodiment can pre-adjust the temperature, oxygen content and exhaust gas content according to a similar method. Here, H-adjusted (i, j, t+1) represents the final humidity value obtained after pre-adjusting the humidity according to the confidence level at the next time step t+1. In this way, by using the confidence level as a weight, this embodiment can adjust the breeding environment according to the information detected by the sensor and the prediction results of the cellular automaton, thereby optimizing the growth and reproduction conditions of the black soldier fly.

[0149] The above embodiments only express the implementation methods of the relevant practical applications of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims. Embodiment 6

[0150] In order to make the above specific implementation methods of the present application more obvious and easy to understand, the present application will be described in detail in the form of embodiments. The present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the embodiments disclosed below.

[0151] In S2:

[0152] Humidity prediction and verification: The humidity output by the cellular automaton is H(i, j, t+1), which is obtained by the conversion function FH. The humidity detected by the sensor is Hs(i, j, t+1), and the confidence level about the humidity is Bel-combined(H(i, j, t+1));

[0153] Temperature prediction and verification: The temperature output by the cellular automaton is T(i, j, t+1), which is obtained by the transformation function FT. The temperature detected by the sensor is Ts(i, j, t+1), as well as the confidence level about the temperature Bel-combined(T(i, j, t+1));

[0154] Oxygen content prediction and verification: The oxygen content output by the cellular automaton is O(i, j, t+1), which is obtained by the conversion function FO. The oxygen content detected by the sensor is Os(i, j, t+1), and the confidence level about the oxygen content is Bel-combined(O(i,j, t+1));

[0155] Exhaust gas content prediction and verification: The exhaust gas content output by the cellular automaton is W(i, j, t+1), which is obtained by the conversion function FW. The exhaust gas content detected by the sensor is Ws(i, j, t+1), as well as the confidence level about the exhaust gas content Bel-combined(W(i, j, t+1)).

[0156] Next, this embodiment uses the judgment standard function D (t + 1) to judge whether the humidity, temperature, oxygen content, and exhaust gas content meet the judgment standard of the DS theory using the Dempster synthesis rule. The judgment standard function D (t + 1) is expressed by the following formula:

[0157] ;

[0158] Among them, DH, DT, DO, and DW are binary indicator functions used to determine whether humidity, temperature, oxygen content, and exhaust gas content meet the judgment criteria of DS theory using Dempster's synthesis rule.

[0159] DH = 1, if the humidity H(i, j, t+1) output by the cellular automaton matches the humidity Hs(i, j, t+1) detected by the sensor, otherwise DH = 0.

[0160] DT = 1, if the temperature T(i, j, t+1) output by the cellular automaton matches the temperature Ts(i, j, t+1) detected by the sensor, otherwise DT = 0.

[0161] DO = 1, if the oxygen content O(i, j, t+1) output by the cellular automaton matches the oxygen content Os(i, j, t+1) detected by the sensor, otherwise DO = 0.

[0162] DW = 1, if the exhaust gas content W(i, j, t+1) output by the cellular automaton matches the exhaust gas content Ws(i, j, t+1) detected by the sensor, otherwise DW = 0.

[0163] If the value of D(t+1) is equal to 4, it means that the humidity, temperature, oxygen content, and exhaust gas content at the next time step t+1 output by the cellular automaton meet the judgment criteria of the DS theory using the Dempster synthesis rule. In this case, the present embodiment relies on the humidity, temperature, oxygen content, and exhaust gas content at the next time step t+1 predicted by the cellular automaton for pre-adjustment, thereby optimizing the breeding environment and providing conditions more suitable for the growth and reproduction of black soldier flies.

[0164] For example, taking the above-mentioned “temperature prediction and verification” as an example, assuming that at a certain time step t, this embodiment has the following parameters and data:

[0165] The temperature output by the cellular automaton is T(i, j, t+1) = 25°C (derived from the transfer function FT), the temperature detected by the sensor is Ts(i, j, t+1) = 23°C, and the precision and accuracy of the sensor is σ-s = 1°C.

[0166] This embodiment now calculates the confidence Bel-combined (T (i, j, t+1)) about temperature.

[0167] First, according to the α coefficient in the formula, this embodiment assumes that α = 0.1, which represents the decay rate of confidence.

[0168] Then, this embodiment uses the following formula to calculate the confidence Bel(T(i, j,t+1)) of the cellular automaton output temperature:

[0169] .

[0170] Substitute the data and calculate:

[0171] ;

[0172] The calculation results are:

[0173] .

[0174] Next, the judgment criterion function DT is used to determine whether the temperature meets the judgment criterion of the DS theory using the Dempster synthesis rule:

[0175] DT = 1, if the temperature T(i, j, t+1) output by the cellular automaton matches the temperature Ts(i, j, t+1) detected by the sensor, otherwise DT = 0.

[0176] Substitute the data and calculate: DT = 0, because

[0177]

[0178] Now, this embodiment can calculate the confidence Bel-combined(T(i, j, t+1)) about the temperature:

[0179] .

[0180] Substitute the data and calculate:

[0181] ;

[0182] We obtain Bel-combined(T(i, j, t+1)) ≈ 1, indicating that the confidence in the temperature is very high.

[0183] Finally, during pre-adjustment, this embodiment uses the normalized confidence as the weight and adjusts the cellular automation prediction result according to the following formula:

[0184] .

[0185] Substitute the data and calculate:

[0186] ;

[0187] Through pre-adjustment, the temperature T(i, j, t+1) predicted by the cellular automaton is obtained, and the adjusted temperature after confidence weighting is

[0188] ;

[0189] This adjusted temperature will be used for automatic temperature regulation in the breeding environment control system, thereby optimizing the breeding environment for black soldier flies.

[0190] The above embodiments only express the implementation methods of the relevant practical applications of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims. Embodiment 7

[0191] In order to make the above specific implementation methods of the present application more obvious and easy to understand, the present application will be described in detail in the form of embodiments. The present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the embodiments disclosed below.

[0192] This embodiment discloses a black soldier fly breeding control system:

[0193] (1) Sensor component selection: Select sensors suitable for the black soldier fly breeding environment, including humidity sensors, temperature sensors, oxygen content sensors, and exhaust gas content sensors. Since the breeding environment may be in a complex and changeable state, it is necessary to ensure that the sensors can monitor parameters quickly and accurately and have anti-interference capabilities;

[0194] (2) Data acquisition module development: Using embedded development technology, design a data acquisition module to receive data from sensors and perform real-time processing and storage. This module needs to have efficient data processing capabilities and storage capacity to cope with large amounts of data streams;

[0195] (3) Selection of cellular automaton model: Select a suitable cellular automaton model based on the size and complexity of the breeding area. This model will help simulate and predict changes in humidity, temperature, oxygen content, and exhaust gas content in the breeding area. It is preferred to consider using an automaton model implemented in programming languages ​​such as Python, MATLAB, or C++;

[0196] (4) Development of DS theory verification module: Through embedded development technology, develop a DS theory verification module to verify the predicted value of the environmental parameters of the next time step output by the cellular automaton model. This module needs to be able to calculate the confidence level using the Dempster synthesis rule based on the sensor detection data and previous detection results to determine the reliability of the predicted value;

[0197] (5) Controller selection and development: To realize the operation of heating, ventilation, humidification and oxygen supply equipment in the aquaculture control method, select a suitable controller. This is preferably a hardware-based controller, and it is also preferably a software controller implemented through embedded development technology. The controller needs to automatically adjust according to the environmental parameters predicted by the cellular automation model to optimize the aquaculture environment of black soldier flies;

[0198] (6) System integration: Integrate sensor components, data acquisition modules, cellular automaton models, DS theory verification modules and controllers to ensure that they can collaborate with each other to achieve the complete functions of the aquaculture control system;

[0199] (7) Optimization of non-standard functions: Further optimize system functions according to actual needs, such as adding automatic alarm, remote monitoring, adaptive control and other features to better meet the requirements of black soldier fly breeding;

[0200] (8) Testing and debugging: Test and debug in the breeding area to verify the stability and accuracy of the system. Adjust and optimize according to the actual application scenario to ensure that the system can run stably and achieve the expected results.

[0201] The above embodiments only express the implementation methods of the relevant practical applications of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims. Embodiment 8

[0202] In order to make the above specific implementation methods of the present application more obvious and easy to understand, the present application will be described in detail in the form of embodiments. The present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the embodiments disclosed below.

[0203] This embodiment discloses a storage medium, in which program instructions for executing the farming control method described in embodiments 1 to 6 are stored. Figure 2-Figure 5 As shown, it uses C++ pseudo code to show its logical relationship, and its principle is as follows:

[0204] (1) cellularAutomatonModel() function: This function is used to implement the cellular automaton model. It detects the humidity, temperature, oxygen content, and exhaust gas content required by each cell in the next time step in a loop at each time step and outputs them to S2. The humidity, temperature, oxygen content, and exhaust gas content of each cell in the next time step t+1 are predicted through the transformation functions FH, FT, FO, and FW according to the rules of the cellular automaton model, the states of adjacent cells, and the input of the control system;

[0205] Input parameters: the cell state at the current time step t and the input of the aquaculture environment control system;

[0206] Output: The cell state at the next time step t+1.

[0207] (2) DSVerification() function: This function is used to perform DS theory verification, verifying the humidity, temperature, oxygen content, and exhaust gas content at the next time step t+1 output by the cellular automaton with the data detected by the sensor. Calculate the confidence level Bel-combined between the cellular automaton output and the sensor detection data.

[0208] Input parameters: humidity, temperature, oxygen content, exhaust gas content output by the cellular automaton and humidity, temperature, oxygen content, exhaust gas content detected by the sensor.

[0209] Output: Humidity, temperature, oxygen content, exhaust gas content confidence Bel-combined.

[0210] (3) controller() function: This function is used to control the operation of heating, ventilation, humidification and oxygen supply equipment. It pre-adjusts the cellular automaton prediction results according to the results and confidence of DS theory verification. Using the normalized confidence as the weight, the cellular automaton prediction results and the sensor detection results are weighted averaged to obtain the adjusted results.

[0211] Input parameters: humidity, temperature, oxygen content, exhaust gas content and corresponding confidence levels output by the cellular automation.

[0212] Output: Regulated humidity, temperature, oxygen content, exhaust gas content, used to control the operation of the equipment.

[0213] Through the combination of these functions, the entire black soldier fly breeding control system can realize the prediction and adjustment of the cellular automaton model, and ensure the consistency of the prediction results with the actual sensor detection results through DS theory verification, thereby realizing intelligent control of the breeding environment. Such a control system can improve the efficiency and output of black soldier fly breeding, while reducing energy consumption and operating costs.

[0214] The above embodiments only express the implementation methods of the relevant practical applications of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for controlling the breeding of black soldier flies, comprising an environmental system, wherein the environmental system detects and controls the humidity, temperature, oxygen content and exhaust gas in the breeding area of ​​black soldier flies, and is characterized in that: Follow these steps: S1. Use the cellular automaton model for modeling and prediction: divide the black soldier fly breeding area into several cells, define the humidity, temperature, oxygen content, and exhaust gas of the cells, use the humidity, temperature, oxygen content, and exhaust gas content and conversion function input by the environmental system, and cyclically detect the humidity, temperature, oxygen content, and exhaust gas content required by each cell in the next time step at each time step, and output them to S2; S2. Verification using DS theory: The evidence comes from the humidity, temperature, oxygen content, and exhaust gas content detected by the sensors of the environmental system in the current time step and the previous time step. The Dempster synthesis rule is used to determine whether the predicted required humidity, temperature, oxygen content, and exhaust gas content of the next time step output by the cellular automaton conform to the Dempster synthesis rule, and pre-adjustment is performed based on the humidity, temperature, oxygen content, and exhaust gas content of the next time step predicted by the cellular automaton. In said S1: 1) Divide the breeding area into several cells: Assume that the breeding area is divided into an M*N two-dimensional grid, where each grid intersection is a cell: represents the state of the cell in the i-th row and j-th column at time step t, where i and j are the indices of the row and column respectively; Define the humidity, temperature, oxygen content, and exhaust gas content of the cell: represents the humidity of the cell in the i-th row and j-th column at time step t, T(i, j, t) represents the temperature, O(i, j, t) represents the oxygen content, and W(i, j, t) represents the exhaust gas content; In said S1: Transformation function F: takes the cell state at the current time step t and the input of the aquaculture environment control system as input, and outputs the cell state at the next time step t+1: ； Input (t) represents the input of the aquaculture environment control system at time step t, including the adjustment of heating, ventilation and humidification equipment, and oxygen supply equipment; In said S1: At each time step, the humidity, temperature, oxygen content, and exhaust gas content required by each cell in the next time step are detected cyclically: the humidity, temperature, oxygen content, and exhaust gas content of each cell in the next time step t+1 are predicted using the conversion function F, that is: ； ； ； ； Wherein, FH, FT, FO, and FW respectively represent conversion functions for predicting the humidity, temperature, oxygen content, and exhaust gas content at the next time step t+1 according to the humidity, temperature, oxygen content, and exhaust gas content at the current time step t, as well as the adjacent cell states and the input of the aquaculture environment control system, and are input into S2; In said S2: Use DS theory to verify the humidity, temperature, oxygen content, and exhaust gas content of the next time step t+1 output by the cellular automaton; Assume that the humidity detected by the sensor at the current time step t is Hs(i, j, t), the temperature is Ts(i, j, t), the oxygen content is Os(i, j, t), and the exhaust gas content is Ws(i, j, t); The sensor detection values ​​at the previous time step t-1 are Hs(i, j, t-1), Ts(i, j, t-1), Os(i, j, t-1), Ws(i, j, t-1); According to the Dempster synthesis rule, the confidence of humidity, temperature, oxygen content and exhaust gas content at the next time step t+1 is calculated: ； ； ； ； Among them, Bel represents the confidence of the corresponding state, and DempsterCombination represents the Dempster synthesis rule; The DempsterCombination: Bel(H(i, j, t+1)): represents the confidence level of the humidity output by the cellular automaton; Bel(Hs(i, j, t+1)): represents the confidence level of the humidity detected by the sensor; For Bel(H(i, j, t+1)): Let the predicted humidity output by the cellular automaton be H-pred(i, j, t+1): ； The coefficient α is used to control the decay rate of confidence; For Bel(Hs(i, j, t+1)): The precision and accuracy of the sensor is expressed as σ-s: ； Next, use the Dempster synthesis rule to synthesize Bel(H(i, j, t+1)) and Bel(Hs(i, j, t+1)) to obtain the humidity confidence Bel-combined(H(i, j, t+1)): ； When preconditioning the cellular automaton predictions based on confidence, the normalized confidence is used as the weight: ； In said S2: The humidity output by the cellular automaton is H(i, j, t+1), which is obtained by the conversion function FH. The humidity detected by the sensor is Hs(i, j, t+1), and the confidence level about the humidity is Bel-combined(H(i, j, t+1)); The temperature output by the cellular automaton is T(i, j, t+1), which is obtained by the transformation function FT. The temperature detected by the sensor is Ts(i, j, t+1), and the confidence level about the temperature is Bel-combined(T(i, j, t+1)); The oxygen content output by the cellular automaton is O(i, j, t+1), which is obtained by the conversion function FO. The oxygen content detected by the sensor is Os(i, j, t+1), and the confidence level about the oxygen content is Bel-combined(O(i, j, t+1)); The exhaust gas content output by the cellular automaton is W(i, j, t+1), which is obtained by the conversion function FW. The exhaust gas content detected by the sensor is Ws(i, j, t+1), and the confidence level about the exhaust gas content is Bel-combined(W(i, j, t+1)); Judgment criterion function D(t+1): ； DH, DT, DO, and DW are binary indicator functions used to determine whether humidity, temperature, oxygen content, and exhaust gas content meet the criteria of DS theory using Dempster's synthesis rule; DH = 1, if the humidity H(i, j, t+1) output by the cellular automaton matches the humidity Hs(i, j, t+1) detected by the sensor, otherwise DH = 0; DT = 1, if the temperature T(i, j, t+1) output by the cellular automaton matches the temperature Ts(i, j, t+1) detected by the sensor, otherwise DT = 0; DO = 1, if the oxygen content O(i, j, t+1) output by the cellular automaton matches the oxygen content Os(i, j, t+1) detected by the sensor, otherwise DO = 0; DW = 1, if the exhaust gas content W(i, j, t+1) output by the cellular automaton matches the exhaust gas content Ws(i, j, t+1) detected by the sensor, otherwise DW = 0; If the value of D(t+1) is greater than 4, it means that the humidity, temperature, oxygen content, and exhaust gas content at the next time step t+1 output by the cellular automaton meet the judgment criteria of the DS theory using the Dempster synthesis rule, and pre-adjustment is performed based on the humidity, temperature, oxygen content, and exhaust gas content at the next time step t+1 predicted by the cellular automaton.

2. A black soldier fly breeding control system, characterized in that: Sensor components: used to monitor the humidity, temperature, oxygen content, and exhaust gas content in the breeding area in real time; Data acquisition module: The data acquisition module is responsible for receiving data from sensors, processing and storing them; Cellular automaton model: The cellular automaton model is used to simulate and predict changes in humidity, temperature, oxygen content, exhaust gas content and environmental factors in the breeding area; DS theory verification module: The predicted value of the environmental parameters at the next time step output by the cellular automaton model must be verified by the DS theory; Controller: The controller controls the operation of heating, ventilation, humidification and oxygen supply equipment according to the aquaculture control method according to claim 1.

3. A storage medium, characterized in that: The storage medium stores program instructions for executing the farming control method according to claim 1.

Images