Intelligent barley pest feeding system

Abstract

The invention discloses an intelligent barley pest breeding system, and relates to the technical field of barley pest breeding, and the system comprises an environment regulation and control module, an automatic feeding module, a growth monitoring module, an intelligent processing module and an early warning prompt module. A full-life-cycle data acquisition system covering an egg stage, a larva stage, a pupal stage and an adult stage is constructed, AI image analysis of a visual monitoring unit can accurately identify insect body length and body surface abnormity, a physiological monitoring unit tracks body weight change and body temperature fluctuation in real time, and a growth prediction model is combined to predict the growth of insects. According to the method, the incubation time and key growth nodes of an ecdysis window are accurately pre-judged, the strategy optimization unit dynamically adjusts environment parameters based on the growth stage, cross-dimension correlation analysis of breeding data is achieved, data support is provided for formulating a standardized breeding process, and the industry is promoted to be changed into intelligent management of data driving from experience driving.

Description

Technical Field

[0001] This invention relates to the field of mealworm farming technology, specifically to an intelligent mealworm rearing system. Background Technology

[0002] As a high-quality source of animal protein, the larvae, pupae, and adults of mealworms are rich in protein, amino acids, and trace elements. They are widely used in the fields of special aquaculture feed, biopharmaceutical raw materials, and functional food development. With the transformation of modern aquaculture towards large-scale and intelligent operations, the demand for efficient and precise feeding techniques in the mealworm farming industry is becoming increasingly urgent.

[0003] Currently, traditional farming methods rely on manual temperature and humidity control, manual feeding, and experience-based management, which suffers from high labor intensity, significant fluctuations in environmental parameters, and inconsistent growth cycles. This results in high farming costs and poor product quality stability. Furthermore, the survival rate of mealworms using traditional methods is only 60%-70%, and the growth cycle is as long as 120-150 days, making it difficult to meet the yield and quality requirements of industrial production. Moreover, existing intelligent mealworm farming does not incorporate dynamic adjustments based on the physiological characteristics of mealworms, and its visualization and decision support capabilities are weak. Traditional systems only present environmental parameters as data lists and cannot intuitively display the distribution of the microenvironment within the breeding box. Farmers cannot predict growth trends or simulate the effects of strategy adjustments based on historical data, and the reliance on manual experience for decision-making has not fundamentally changed.

[0004] In summary, existing technologies lack full life-cycle growth data collection and visual decision support, making it difficult to balance the efficiency and quality of mealworm farming. There is an urgent need for a new type of breeding system that integrates biometric monitoring and digital twin technology to achieve a technological upgrade from "extensive environmental control" to "precise growth intervention," thereby promoting the transformation of the mealworm farming industry towards intelligence and refinement. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies and provide an intelligent feeding system for mealworms. This system, through deep integration of a growth monitoring module and an intelligent processing module, constructs a full life-cycle data collection system covering the egg, larval, pupal, and adult stages. The AI ​​image analysis of the visual monitoring unit can accurately identify body length and surface abnormalities. The physiological monitoring unit tracks weight changes and body temperature fluctuations in real time. Combined with a growth prediction model, it enables precise prediction of key growth nodes such as hatching time and molting windows. The strategy optimization unit dynamically adjusts environmental parameters based on growth stages, achieving cross-dimensional correlation analysis of breeding data. This provides data support for the development of standardized breeding processes and promotes the industry's shift from experience-driven to data-driven intelligent management.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an intelligent feeding system for mealworms, the system comprising: an environmental control module, an automatic feeding module, a growth monitoring module, an intelligent processing module, and an early warning module.

[0007] The environmental control module collects the environmental parameters inside the feeding box in real time and uploads the data to the intelligent processing module via wireless transmission. The automatic feeding module receives feeding control commands from the intelligent processing module, controls the amount and frequency of feed feeding, and uses infrared sensing to monitor remaining feed and trigger refeeding. The growth monitoring module is used to collect real-time growth data of individual and group mealworms and transmit it to the intelligent processing module, while also receiving monitoring strategy instructions from the intelligent processing module. The intelligent processing module integrates CET digital twin visualization technology to receive data collected by the monitoring module and to analyze and process the data. The early warning module is equipped with an audible and visual alarm device. When the intelligent processing module detects abnormal environmental parameters and the camera captures abnormal growth of mealworms, the early warning module immediately issues an audible and visual alarm to remind the farmers to take timely action.

[0008] Furthermore, the environmental control module integrates a temperature control unit, a humidity control unit, a light control unit, and a ventilation unit to continuously monitor the growth environment of mealworms at different growth stages. The temperature control unit includes a temperature sensor and a temperature actuator. The temperature sensor collects temperature data in the rearing box in real time and transmits it to the intelligent processing module. The temperature actuator drives the heating and cooling equipment to operate according to the control instructions of the intelligent processing module, so that the temperature in the rearing box is maintained in the temperature range for the growth of mealworms. The humidity control unit includes a humidity sensor and a humidity actuator. The humidity sensor monitors the ambient humidity in real time and feeds it back to the intelligent processing module. The humidity actuator controls the humidification and dehumidification equipment to work according to the instructions of the intelligent processing module to maintain the ambient humidity. The light control unit includes an LED light source and a light sensor. The LED light source supports independent control of red and blue light bands and is dynamically adjusted according to the differentiated photoperiod requirements of the four growth stages of the barley insect: egg, larva, pupa, and adult. Specifically, the light duration is 8-10 hours per day during the egg stage, 10-12 hours per day during the larval stage, 12-14 hours per day during the pupa stage, and ≥16 hours of light avoidance per day during the adult stage, with ultraviolet light stimulation only activated during the mating period for 2-4 hours per day. The light sensor is used to detect light intensity in real time and feed it back to the intelligent processing module; The ventilation unit includes a variable frequency fan and a carbon dioxide concentration sensor. The carbon dioxide concentration sensor monitors the carbon dioxide concentration in the chamber in real time. When the concentration exceeds 1500 ppm, the variable frequency fan automatically starts and adjusts its speed to maintain the oxygen concentration in the chamber at 18%-21% and the carbon dioxide concentration below 1000 ppm, ensuring air circulation and oxygen supply.

[0009] Furthermore, the automatic feeding module consists of a feed storage bin, a quantitative feeding unit, and a feeding control unit. The feed storage bin is used to store feed. After receiving instructions from the intelligent processing module, the quantitative feeding mechanism delivers the measured feed to the breeding area. The feeding control unit ensures that the feeding process is accurate and timely. The inner wall of the feed storage bin is equipped with a weight sensor and a minimum inventory sensor. The weight sensor monitors the weight of the feed in the storage bin in real time and transmits it to the intelligent processing module. The minimum inventory sensor triggers a feeding warning signal when the remaining feed is below a preset threshold. The quantitative feeding unit delivers feed to the feeding control unit according to the feeding instructions of the intelligent processing module. The feeding stops when the four growth stages of barley worm eggs, larvae, pupae and adults reach the preset single feeding amount. The feeding control unit integrates a timing module and an infrared feed sensor. The timing module sends feeding requests to the intelligent processing module according to the mealworm's life cycle. The infrared feed sensor is located in the feed placement area of ​​the breeding area, and the feed amount... The feeding frequency is dynamically adjusted, among which... This refers to the amount fed per feeding. The insect population density correction factor and =0.8-1.2, The number of insects. As an ambient temperature compensation factor, and when the temperature detected by the temperature sensor increases by a certain amount... β increases by 0.05. This is the time since the last feeding.

[0010] Furthermore, the feeding frequency adjustment rule of the feeding control unit is as follows: When the residual feed rate is greater than 15%, the reduced feeding delay interval mode is triggered, that is, the feeding amount is 80% of the original feeding amount, and the time between the last feeding is increased by 30%. When the residual rate is less than 5%, the incremental supplementary feeding mode is activated, that is, the feeding amount is 120% of the original feeding amount, and the time since the last feeding is reduced by 20%.

[0011] Furthermore, the growth monitoring module includes a visual monitoring unit, a physiological monitoring unit, a behavioral monitoring unit, and a data fusion interface; The visual monitoring unit consists of a multi-angle camera matrix and an AI image analysis subunit. The camera matrix captures images of mealworm growth at a fixed frame rate. The AI ​​image analysis subunit is used to identify the growth stages of mealworm eggs, larvae, pupae, and adults, as well as the phenotypic characteristics of the insect body length, surface damage, and abnormal body color in real time. It also counts the population density and uploads the analysis results to the intelligent processing module. The physiological monitoring unit uses an infrared thermal imager to monitor the activity intensity and abnormal behavior of the insect swarm in real time, including feeding activity based on movement trajectory tracking and early warning of diseased individuals through abnormal fluctuations in body temperature. The behavior monitoring unit includes ultrasonic positioning and vibration sensors. The ultrasonic positioning module tracks the movement trajectory of the mealworms and calculates the average activity speed and the proportion of resting time. The vibration sensor is attached to the bottom of the breeding box to detect the vibration frequency when the group is feeding, analyze and judge the palatability of the feed and the feeding intensity, and abnormal vibration signals automatically trigger the early warning process of the intelligent processing module. The data fusion interface synchronizes insect growth data, behavioral characteristic data, and physiological data to the intelligent processing module, and dynamically updates the 3D growth model of the insect swarm through the digital twin display unit.

[0012] Furthermore, the intelligent processing module includes a data fusion unit, a growth modeling unit, a strategy optimization unit, and a twin interaction unit. These units work together to achieve intelligent control and visualized decision-making throughout the entire aquaculture process. The data fusion unit performs spatiotemporal alignment and feature fusion of the growth data, behavioral characteristic data, and physiological data transmitted by the growth monitoring module and the temperature, humidity, light, and gas concentration data uploaded by the environmental control module to generate multidimensional aquaculture status data in a unified format. The growth modeling unit trains a growth prediction model based on historical aquaculture data using machine learning algorithms. It inputs the current growth stage, environmental parameters, and individual phenotypic data from multidimensional aquaculture status data and outputs the predicted growth rate, molting time window, and survival rate. At the same time, it establishes a standard database for mealworm growth, which includes the optimal range of environmental parameters and feeding standards for different growth stages. The strategy optimization unit dynamically generates environmental control strategies and feeding strategies based on the prediction results of the growth modeling unit and the standard database. Specifically, for the environmental control module, it outputs the target values ​​and adjustment rates of temperature / humidity / light; for the automatic feeding module, it calculates the amount of food fed at one time and the feeding time interval. The twin interaction unit constructs a 1:1 scale virtual breeding scene based on CET digital twin technology. It maps the prediction results of the growth modeling unit to the environmental parameters, distribution and activity trajectory of the physical breeding box in real time. It supports breeders to interact with the twin scene through touch screen and mobile APP, including remotely adjusting environmental parameter thresholds, viewing historical data playback at any time point, and simulating the growth effect under different control strategies.

[0013] Furthermore, the growth standard database is divided into four stages according to the mealworm's growth cycle: egg stage, larval stage, pupal stage, and adult stage. It stores the optimal environmental parameter range and feeding standard parameters for each stage, namely: Egg stage: Temperature 20-23℃, humidity 40%-50%, light intensity 0-50 lux, egg density ≤500 eggs / ㎡; Larval stage: Temperature 22-25℃, humidity 50%-60%, light intensity 200-300 lux, larval density ≤2000 larvae / ㎡; Pupal stage: Temperature 25-28℃, humidity 60%-70%, light intensity 100-200 lux, pupa density ≤800 pupae / ㎡; Adult stage: Temperature 25-28℃, humidity 60%-70%, light intensity 300-400 lux, adult density ≤500 insects / ㎡.

[0014] Furthermore, the strategy optimization unit includes an environmental strategy subunit and a feeding strategy subunit, which achieves precise adjustment of breeding conditions through dynamic feedback control; The environmental strategy subunit performs closed-loop adjustment of environmental parameters, using the stage standard parameters output by the growth modeling unit as the target value, and calculates the deviation between the current environmental parameters and the target value in real time to perform environmental regulation. Temperature control: When the temperature of the feeding box deviates from the target value by more than 1°C, the power adjustment command of the heating / cooling equipment is output to make the temperature fluctuation range ≤ ±0.5°C; Humidity control: When the humidity deviation is >5%RH, output the operating time command of the humidification / dehumidification equipment to stabilize the humidity within the target value ±3%RH range; Light control: Based on the light requirements of the four growth stages, the duty cycle of the LED light source is adjusted to achieve dynamic adjustment of light intensity with an adjustment accuracy of ±10 lux; The feeding strategy subunit dynamically calculates the amount of food to be fed based on the growth rate prediction from the growth modeling unit and the total population weight. Between feedings.

[0015] Compared with existing technologies, this intelligent superworm rearing system has the following advantages: I. This invention constructs a full life-cycle data collection system covering the egg, larval, pupal, and adult stages through deep integration of the growth monitoring module and the intelligent processing module. The AI ​​image analysis of the visual monitoring unit can accurately identify the insect's body length and surface abnormalities, while the physiological monitoring unit tracks weight changes and body temperature fluctuations in real time. Combined with the growth prediction model, it enables accurate prediction of key growth nodes such as hatching time and molting window. The strategy optimization unit dynamically adjusts environmental parameters based on the growth stage, realizing cross-dimensional correlation analysis of breeding data. This provides data support for the formulation of standardized breeding processes and promotes the industry's shift from experience-driven to data-driven intelligent management.

[0016] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0017] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0018] Figure 1 A flowchart illustrating the operation of an intelligent superworm rearing system; Figure 2 This is a schematic diagram illustrating the working principle of the intelligent processing module. Detailed Implementation

[0019] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0020] Example 1 This embodiment discloses an intelligent feeding system for mealworms. Through the coordinated operation of an environmental control module, an automatic feeding module, a growth monitoring module, an intelligent processing module, and an early warning module, an intelligent feeding and management system covering the entire life cycle of egg, larval, pupal, and adult stages is constructed. The system combines CET digital twin visualization and growth prediction models to achieve dynamic optimization of breeding environment parameters, precise adjustment of feeding strategies, and real-time tracking of growth status, providing an efficient and intelligent technical solution for large-scale mealworm breeding.

[0021] This embodiment of the intelligent superworm rearing system uses an intelligent processing module as its core. A growth monitoring module collects biological characteristic data in real time, an environmental control module dynamically adjusts the rearing microenvironment, and an automatic feeding module executes a precise feeding strategy. These modules interact via a wireless transmission network. The environmental control module, acting as the execution layer of the physical rearing environment, includes a temperature control unit, a humidity control unit, a light control unit, and a ventilation unit. Its working principle is to maintain the temperature, humidity, light intensity, and gas concentration within the rearing box at the optimal range for each growth stage. Specifically, the temperature control unit is the data acquisition layer. High-precision digital temperature sensors are deployed in the rearing box, collecting three-dimensional spatial temperature data every 20 seconds to avoid the limitations of single-location temperature measurement. The sensors transmit the data to the intelligent processing module, forming a temperature field distribution heatmap. Based on the stage temperature standard (22-25℃ for larvae) output by the growth modeling unit, the intelligent processing module calculates the power commands for the heating / cooling equipment. When the measured temperature deviates from the target value by more than 1℃, the heating equipment is activated at a rate of 0.5℃ / minute until the temperature returns to the target range. The humidity control unit... The temperature and humidity sensors are integrated into the same node, synchronously uploading temperature and humidity data. When the humidity deviation exceeds 5%RH, the intelligent processing module selects a humidification or dehumidification strategy based on the current growth stage. For example, if the humidity is below 40% during the egg stage, the ultrasonic humidifier is activated to increase the humidity at a rate of 2%RH / minute. If the humidity is above 70% during the adult stage, the dehumidifier is activated and the ventilation unit is activated in conjunction with it. By reducing the moisture content of the air inside the chamber and accelerating airflow circulation, the humidity is controlled within the target value ±3%RH range. The light control unit uses an LED light source and supports red and blue light bands. Independently adjustable to meet the photoperiod requirements of different growth stages (0-50 lux for weak light protection during the egg stage, and 300-400 lux for mating promotion during the adult stage). A light sensor is deployed in the center of the enclosure top to provide real-time feedback on light intensity and spectral distribution. The intelligent processing module generates a four-stage lighting strategy based on a growth standard database: 8 hours of light per day during the egg stage (simulating a light-shielding soil environment), 10 hours during the larval stage, 12 hours during the pupal stage, and 14 hours during the adult stage. By adjusting the duty cycle of the light source, linear changes in light intensity are achieved (adjustment accuracy ±10 lux), avoiding damage to the insects caused by strong light stimulation. Stress response: The carbon dioxide sensor and electrochemical oxygen sensor in the ventilation unit collect data every 10 minutes. When the CO2 concentration exceeds 1500 ppm (the threshold that threatens the respiratory efficiency of mealworms) or the O concentration is below 18%, the ventilation mechanism is triggered. The variable frequency fan automatically adjusts its speed according to the concentration deviation. For example, when the CO2 concentration is 1800 ppm, the fan runs at medium speed; if it rises to 2500 ppm, it runs at full speed until the concentration drops below 1000 ppm, while maintaining the O2 concentration in the appropriate range of 18%-21% to ensure the normal metabolic activity of mealworms.

[0022] The automatic feeding module achieves full automation from feed storage and precise metering to strategy adjustment through the collaboration of feed storage, quantitative feeding unit, and feeding control unit. Weight sensors and minimum inventory sensors are installed on the inner wall of the storage tank. The weight sensors monitor feed weight in real time, and when the remaining amount approaches a threshold, a supplementary feeding warning signal is triggered to the intelligent processing module to avoid feed shortages. The system shuts off immediately after feeding to prevent external moisture and pests from contaminating the feed, ensuring its freshness. The quantitative feeding unit delivers feed to the feeding control unit according to the feeding instructions from the intelligent processing module. Preset single-feed amounts are set for the egg, larval, pupal, and adult stages. Feeding stops when the threshold is reached, and feeding is stopped during the pupal stage, with the system automatically blocking feeding instructions for that stage. The feeding control unit presets a basic feeding frequency according to the four-stage growth cycle and dynamically fine-tunes it based on the growth rate prediction value from the intelligent processing module. For example, if the larval growth rate is 10% higher than the standard value, the feeding frequency increases to 1.2 times / day. Infrared supplementary feeding sensors are deployed in the feed placement area to determine the remaining amount through the intensity of the reflected signal. When the feed residue rate is >15% (indicating overfeeding), the "reduced feeding delay interval mode" is triggered: the next feeding amount is adjusted to 80% of the original amount, and the feeding interval is extended by 30%; if the residue rate is <5% (vigorous feeding), the "increased feeding mode" is activated: the feeding amount is increased to 120%, and the interval is shortened by 20%. This mechanism gradually approaches the optimal feeding parameters through more than 3 feeding data iterations, and the single feeding amount... ,in, This is a correction factor for insect population density (0.8-1.2), dynamically adjusted based on population density data from the growth monitoring module (e.g., at high densities). Take 1.2 (to avoid fighting for food). The environmental temperature compensation factor has an initial value of 0.1. For every 1°C increase in temperature, β increases by 0.05 (the metabolism of mealworms is accelerated under high temperature conditions, so the amount of food needs to be increased). The time elapsed since the last feeding reflects the decay effect of feed consumption over time.

[0023] The growth monitoring module, through the collaboration of visual, physiological, and behavioral monitoring units, constructs a biological characteristic database of the entire life cycle of mealworms. The visual monitoring unit consists of a matrix of top-view cameras and side infrared cameras to capture images of mealworms. An AI image analysis subunit can identify four stages: egg (0.5-1mm in diameter), larva (5-20mm in length), pupa (20-30mm in length), and adult (25-30mm in length). It measures the insect's body length in real time and detects surface damage (such as severed legs or shell damage) and abnormal body color (a warning is issued when melanization rate >5%), providing a basis for stratified management of the rearing box. The physiological monitoring unit uses an infrared thermal imager to non-contactly measure the insect's surface temperature. When the larval body temperature fluctuates by more than ±1℃ / hour, or the pupal body temperature remains below 25℃ for 2 hours, it is determined to be an abnormal metabolic state, triggering an early warning process. A pressure sensor array is embedded in the bottom grid of the rearing box to monitor individual... The weight changes and pressure waveforms of mealworms are analyzed to identify key physiological behaviors: pressure fluctuations during larval molting exhibit periodic peaks (approximately every 2 hours); and pressure distribution during adult mating shows localized aggregation characteristics, which are used to correct growth prediction models. An ultrasonic transmitter installed on the top of the enclosure tracks the mealworms' movements and calculates the ratio of average activity speed to resting time. For example, the normal activity speed of adults is 5-10 cm / s; if it is below 2 cm / s for 30 consecutive minutes, it is considered abnormal activity. The data fusion interface preprocesses three types of monitoring data: growth data is labeled with timestamps and spatial coordinates; physiological data is associated with the insect's growth stage; and behavioral data is matched with environmental parameter snapshots, generating a unified format multidimensional data stream. This ensures that the intelligent processing module receives synchronized, context-specific, and effective data, which is used to construct a growth standard database and growth prediction model.

[0024] like Figure 2As shown, the intelligent processing module achieves intelligent transformation from data to decision-making through data fusion, growth modeling, strategy optimization, and twin interaction units. Specifically, the data fusion unit performs spatiotemporal calibration on the biological data (stage, body length, weight, body temperature, activity speed) from the growth monitoring module and the environmental data (temperature, humidity, light intensity, gas concentration) from the environmental control module, eliminating sensor noise and asynchronous errors, constructing a correlation matrix, identifying influencing factors, and generating feature vectors for growth modeling to improve the efficiency of subsequent prediction models. The growth modeling unit constructs a growth prediction model based on the feature vectors and trains it using full-cycle data to predict egg hatching time, larva / pupa development time, and other related factors. The study analyzed adult growth rate and survival rate at each stage, and established a database of optimal environmental parameters and feeding standards for different growth stages: egg stage: temperature 20-23℃, humidity 40%-50%, no light (0-50 lux), density ≤500 eggs / m²; larval stage: temperature 22-25℃, humidity 50%-60%, light 200-300 lux, density ≤2000 individuals / m²; pupal stage: temperature 25-28℃, humidity 60%-70%, light 100-200 lux, density ≤800 individuals / m²; adult stage: temperature 25-28℃, humidity 60%-70%, light 300 lux, density ≤800 individuals / m². -400 lux, density ≤500 birds / m², the strategy optimization unit includes an environmental strategy subunit and a feeding strategy subunit. It achieves precise adjustment of breeding conditions through dynamic feedback control. Based on the prediction results of the growth modeling unit and a standard database, it dynamically generates environmental control strategies and feeding strategies. Specifically: for the environmental control module, it outputs target values ​​and adjustment rates for temperature / humidity / light; for the automatic feeding module, it calculates the amount of feed given per feeding and the feeding time interval. Specifically, for temperature: when the deviation between the measured value and the target value is >1℃, it outputs a power command for heating / cooling equipment, adjusting in steps of 0.5℃ / minute to ensure a return to the target range within 20 minutes; for humidity: deviation >5%R... H: Calculate the humidification / dehumidification equipment runtime (e.g., if a 5% RH increase is needed during the larval stage, start the humidification equipment for 3 minutes) and coordinate with the ventilation unit to balance the humidity gradient; Lighting: Based on stage requirements (e.g., 14 hours / day during the adult stage), control the LED light source switch via PWM signal to achieve precise control of lighting duration; Feeding strategy subunit dynamically adjusts based on growth rate prediction: Larval stage: default interval 24 hours; if the residual rate is <10% for two consecutive times, shorten the interval to 20 hours and increase the feed amount by 10%; Adult stage: default interval 12 hours; if the residual rate is >30%, extend the interval to 14 hours and reduce the feed amount by 15%, single feed amount... This ensures that feed supply matches growth needs; the twin interaction unit constructs a 1:1 scale virtual breeding scene based on CET digital twin technology, and maps the prediction results of the growth modeling unit to the environmental parameters, distribution and activity trajectory of the physical breeding box in real time. It supports breeders to interact with the twin scene through touch screen and mobile APP, including remotely adjusting environmental parameter thresholds, viewing historical data playback at any time point, and simulating the growth effect under different control strategies.

[0025] The early warning module, based on the anomaly discrimination rule library of the intelligent processing module, implements three levels of early warning: Level I (prompt): If the insect body length increases by less than 0.3 mm for two consecutive days, or the humidity deviates from the target value by ±3%RH, a text reminder will be pushed to the APP; Level II (alarm): If the CO2 concentration is greater than 1800 ppm, or the survival rate of adult insects decreases by 5% for two consecutive days, an audible and visual alarm will be triggered; Level III (emergency): If the temperature is greater than 30℃ for 30 minutes (the lethal threshold for the larval stage), or the hatching rate of eggs is less than 60%, the system will automatically activate the emergency plan: shut down the heating equipment, open all ventilation vents, and send an emergency notification to the administrator's mobile phone.

[0026] This embodiment constructs an intelligent management and control system for the entire life cycle of mealworm rearing through deep collaboration among various modules. The environmental control module achieves precise control of temperature and humidity, the growth monitoring module provides a growth profile from phenotypic to physiological through multimodal data acquisition, and the digital twin technology of the intelligent processing module is used to visualize the rearing status, realize precise control of the rearing environment and intuitive monitoring of growth status, and improve rearing efficiency and quality.

[0027] Example 2 like Figure 1 As shown, this embodiment describes in detail the entire life cycle process of raising mealworms using an intelligent mealworm rearing system. The specific steps of this process are as follows: System initialization and parameter configuration: Start the intelligent processing module and initialize the twin interaction unit; Based on the growth stages of the mealworm (egg stage, larval stage, pupal stage, and adult stage), the optimal environmental parameter thresholds and feeding strategies for the corresponding stages are set in the intelligent processing module.

[0028] Real-time monitoring of environmental parameters: The environmental control module collects real-time environmental data inside the feeding box through temperature and humidity sensors and gas sensors.

[0029] Data is synchronized to the intelligent processing module, which generates a heat map of environmental parameters and maps it to the digital twin virtual scene.

[0030] Growth data collection and analysis: The growth monitoring module activates a multi-angle camera matrix, an infrared thermal imager, and a vibration sensor: The data fusion interface uploads multi-dimensional data to the intelligent processing module.

[0031] Intelligent policy generation and optimization: The growth modeling unit predicts molting time windows and growth rates based on historical data and current monitoring values.

[0032] The strategy optimization unit dynamically adjusts the target values ​​of environmental parameters and generates feeding amount and environmental dynamic control instructions. The environmental control module receives and executes instructions.

[0033] Precision feeding and leftover feed management: The quantitative feeding unit calculates the feeding amount and accurately delivers feed. An infrared residual feed sensor monitors the residual amount and triggers a supplementary feeding or reduction mechanism.

[0034] Abnormal Warning and Emergency Response: The early warning module monitors the system status in real time. When environmental parameters exceed the threshold or an abnormal insect is detected, an audible and visual alarm is triggered. The digital twin display unit generates emergency response plans.

[0035] Digital twin interaction and remote management: Breeders can view the real-time distribution of insect swarms in a virtual breeding scenario via touchscreen or mobile app; Simulate the impact of different control strategies on the growth cycle, and remotely adjust parameter thresholds or issue commands.

[0036] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A smart feeding system for mealworms, characterized in that, The system consists of: an environmental control module, an automatic feeding module, a growth monitoring module, an intelligent processing module, and an early warning module; The environmental control module collects the environmental parameters inside the feeding box in real time and uploads the data to the intelligent processing module via wireless transmission. The automatic feeding module receives feeding control commands from the intelligent processing module, controls the amount and frequency of feed feeding, and uses infrared sensing to monitor remaining feed and trigger refeeding. The growth monitoring module is used to collect real-time growth data of individual and group mealworms and transmit it to the intelligent processing module, while also receiving monitoring strategy instructions from the intelligent processing module. The intelligent processing module integrates CET digital twin visualization technology to receive data collected by the monitoring module and to analyze and process the data. The early warning module is equipped with an audible and visual alarm device. When the intelligent processing module detects abnormal environmental parameters and the camera captures abnormal growth of mealworms, the early warning module immediately issues an audible and visual alarm to remind the farmers to take timely action.

2. The intelligent feeding system for mealworms according to claim 1, characterized in that, The environmental control module integrates a temperature control unit, a humidity control unit, a light control unit, and a ventilation unit to continuously monitor the growth environment of mealworms at different growth stages. The temperature control unit includes a temperature sensor and a temperature actuator. The temperature sensor collects temperature data in the rearing box in real time and transmits it to the intelligent processing module. The temperature actuator drives the heating and cooling equipment to operate according to the control instructions of the intelligent processing module, so that the temperature in the rearing box is maintained in the temperature range for the growth of mealworms. The humidity control unit includes a humidity sensor and a humidity actuator. The humidity sensor monitors the ambient humidity in real time and feeds it back to the intelligent processing module. The humidity actuator controls the humidification and dehumidification equipment to work according to the instructions of the intelligent processing module to maintain the ambient humidity. The light control unit includes an LED light source and a light sensor. The LED light source supports independent control of red and blue light bands and is dynamically adjusted according to the differentiated photoperiod requirements of the four growth stages of the barley insect: egg, larva, pupa, and adult. The light sensor is used to detect the light intensity in real time and feed it back to the intelligent processing module. The ventilation unit includes a variable frequency fan and a carbon dioxide concentration sensor. The carbon dioxide concentration sensor monitors the carbon dioxide concentration in the chamber in real time. When the concentration exceeds 1500 ppm, the variable frequency fan automatically starts and adjusts its speed to maintain the oxygen concentration in the chamber at 18%-21% and the carbon dioxide concentration below 1000 ppm, ensuring air circulation and oxygen supply.

3. The intelligent feeding system for mealworms according to claim 1, characterized in that, The automatic feeding module consists of a feed storage bin, a quantitative feeding unit, and a feeding control unit. The feed storage bin is used to store feed. After receiving instructions from the intelligent processing module, the quantitative feeding mechanism delivers the measured feed to the breeding area. The feeding control unit ensures that the feeding process is accurate and timely. The inner wall of the feed storage bin is equipped with a weight sensor and a minimum inventory sensor. The weight sensor monitors the weight of the feed in the storage bin in real time and transmits it to the intelligent processing module. The minimum inventory sensor triggers a feeding warning signal when the remaining feed is below a preset threshold. The quantitative feeding unit delivers feed to the feeding control unit according to the feeding instructions of the intelligent processing module. The feeding stops when the four growth stages of barley worm eggs, larvae, pupae and adults reach the preset single feeding amount. The feeding control unit integrates a timing module and an infrared feed sensor. The timing module sends feeding requests to the intelligent processing module according to the mealworm's life cycle. The infrared feed sensor is located in the feed placement area of ​​the breeding area, and the feed amount... The feeding frequency is dynamically adjusted, among which... This refers to the amount fed per feeding. The insect population density correction factor and =0.8-1.2, The number of insects. As an ambient temperature compensation factor, and when the temperature detected by the temperature sensor increases by a certain amount... β increases by 0.

05. This is the time since the last feeding.

4. The intelligent feeding system for mealworms according to claim 3, characterized in that, The feeding frequency adjustment rule of the feeding control unit is as follows: When the residual feed rate is greater than 15%, the reduced feeding delay interval mode is triggered, that is, the feeding amount is 80% of the original feeding amount, and the time between the last feeding is increased by 30%. When the residual rate is less than 5%, the incremental supplementary feeding mode is activated, that is, the feeding amount is 120% of the original feeding amount, and the time since the last feeding is reduced by 20%.

5. The intelligent feeding system for mealworms according to claim 1, characterized in that, The growth monitoring module includes a visual monitoring unit, a physiological monitoring unit, a behavioral monitoring unit, and a data fusion interface; The visual monitoring unit consists of a multi-angle camera matrix and an AI image analysis subunit. The camera matrix captures images of mealworm growth at a fixed frame rate. The AI ​​image analysis subunit is used to identify the growth stages of mealworm eggs, larvae, pupae, and adults, as well as the phenotypic characteristics of the insect body length, surface damage, and abnormal body color in real time. It also counts the population density and uploads the analysis results to the intelligent processing module. The physiological monitoring unit uses an infrared thermal imager to monitor the activity intensity and abnormal behavior of the insect swarm in real time, including feeding activity based on movement trajectory tracking and early warning of diseased individuals through abnormal fluctuations in body temperature. The behavior monitoring unit includes ultrasonic positioning and vibration sensors. The ultrasonic positioning module tracks the movement trajectory of the mealworms and calculates the average activity speed and the proportion of resting time. The vibration sensor is attached to the bottom of the breeding box to detect the vibration frequency when the group is feeding, analyze and judge the palatability of the feed and the feeding intensity, and abnormal vibration signals automatically trigger the early warning process of the intelligent processing module. The data fusion interface synchronizes insect growth data, behavioral characteristic data, and physiological data to the intelligent processing module, and dynamically updates the 3D growth model of the insect swarm through the digital twin display unit.

6. The intelligent feeding system for mealworms according to claim 1, characterized in that, The intelligent processing module includes a data fusion unit, a growth modeling unit, a strategy optimization unit, and a twin interaction unit. These units work together to achieve intelligent control and visualized decision-making throughout the entire aquaculture process. The data fusion unit performs spatiotemporal alignment and feature fusion of the growth data, behavioral characteristic data, and physiological data transmitted by the growth monitoring module and the temperature, humidity, light, and gas concentration data uploaded by the environmental control module to generate multidimensional aquaculture status data in a unified format. The growth modeling unit trains a growth prediction model based on historical aquaculture data using machine learning algorithms. It inputs the current growth stage, environmental parameters, and individual phenotypic data from multidimensional aquaculture status data and outputs the predicted growth rate, molting time window, and survival rate. The strategy optimization unit dynamically generates environmental control strategies and feeding strategies based on the prediction results of the growth modeling unit and the standard database. Specifically, for the environmental control module, it outputs the target values ​​and adjustment rates of temperature / humidity / light; for the automatic feeding module, it calculates the amount of food fed at one time and the feeding time interval. The twin interaction unit constructs a 1:1 scale virtual breeding scene based on CET digital twin technology. It maps the prediction results of the growth modeling unit to the environmental parameters, distribution and activity trajectory of the physical breeding box in real time. At the same time, it establishes a growth standard database for mealworms, which includes the optimal environmental parameter range and feeding standards for different growth stages. It supports breeders to interact with the twin scene through touch screen and mobile APP, including remotely adjusting environmental parameter thresholds, viewing historical data playback at any time point, and simulating the growth effect under different control strategies.

7. The intelligent feeding system for mealworms according to claim 6, characterized in that, The growth standard database is divided into four stages according to the mealworm growth cycle: egg stage, larval stage, pupal stage, and adult stage. It stores the optimal environmental parameter range and feeding standard parameters for each stage, namely: Egg stage: Temperature 20-23℃, humidity 40%-50%, light intensity 0-50 lux, egg density ≤500 eggs / ㎡; Larval stage: Temperature 22-25℃, humidity 50%-60%, light intensity 200-300 lux, larval density ≤2000 larvae / ㎡; Pupal stage: Temperature 25-28℃, humidity 60%-70%, light intensity 100-200 lux, pupa density ≤800 pupae / ㎡; Adult stage: Temperature 25-28℃, humidity 60%-70%, light intensity 300-400 lux, adult density ≤500 insects / ㎡.

8. The intelligent feeding system for mealworms according to claim 6, characterized in that, The strategy optimization unit includes an environmental strategy subunit and a feeding strategy subunit, which achieves precise adjustment of breeding conditions through dynamic feedback control; The environmental strategy subunit performs closed-loop adjustment of environmental parameters, using the stage standard parameters output by the growth modeling unit as the target value, and calculates the deviation between the current environmental parameters and the target value in real time to perform environmental regulation. Temperature control: When the temperature of the feeding box deviates from the target value by more than 1°C, the power adjustment command of the heating / cooling equipment is output to make the temperature fluctuation range ≤ ±0.5°C; Humidity control: When the humidity deviation is >5%RH, output the operating time command of the humidification / dehumidification equipment to stabilize the humidity within the target value ±3%RH range; Light control: Based on the light requirements of the four growth stages, the duty cycle of the LED light source is adjusted to achieve dynamic adjustment of light intensity with an adjustment accuracy of ±10 lux; The feeding strategy subunit dynamically calculates the amount of food to be fed based on the growth rate prediction from the growth modeling unit and the total population weight. Between feedings.

Images