Aquaculture intelligent feeding and growth monitoring system based on Internet of Things

Abstract

The invention provides an aquaculture intelligent feeding and growth monitoring system based on the Internet of Things, and relates to the technical field of intelligent aquaculture, and the system comprises the following modules: a multi-mode sensing module, a data processing module, a central processing module, an intelligent feeding module, and a monitoring module. The aquatic product feeding monitoring module is used for accurately calculating the appropriate feeding amount by combining data of current water quality, the number of aquatic products and the growth stage, and analyzing aquatic product images collected by the camera device. An image recognition technology and a deep learning algorithm are used for recognizing aquatic product types, individual sizes and health conditions to carry out three-dimensional form modeling; according to the method, the scientificity and accuracy of breeding decision making are remarkably improved, and detailed and visual growth information is provided for the breeding decision making; and through cooperative work of the intelligent feeding module and the central processing module, accurate adjustment of the feeding amount is achieved, and the feed utilization rate is increased.

Description

Technical Field

[0001] The present invention relates to the field of intelligent aquaculture technology, and in particular to an aquaculture intelligent feeding and growth monitoring system based on the Internet of Things. Background Art

[0002] Aquaculture refers to the cultivation and propagation of aquatic animals and plants in artificially controlled environments, such as ponds, cages, oceans, and freshwater bodies. It encompasses the breeding, management, and harvesting of various aquatic organisms and plants. With the growth of the global population and the increasing demand for high-quality protein, aquaculture is becoming increasingly important as a key protein source.

[0003] In traditional aquaculture, monitoring methods for the aquaculture environment and aquatic conditions are relatively simple and backward. Farmers often rely on limited experience and a few simple measurement tools to obtain environmental parameter information. However, these methods not only fail to fully and real-timely grasp key water quality parameters and environmental factors, but also make it difficult to effectively perceive biological behavior. This means that farmers lack comprehensive and accurate data support when making aquaculture decisions. Decisions are often blind and delayed, which can easily lead to low aquaculture efficiency and even significant economic losses. Secondly, in terms of aquatic growth monitoring, manual sampling is relied upon to measure the size of aquatic products and observe their appearance and health. This consumes a lot of manpower and material resources and cannot accurately reflect the actual growth status of the entire aquaculture population. Relying solely on manual identification and empirical judgment makes it impossible to formulate targeted and scientific aquaculture strategies. In addition, in traditional aquaculture, feeding amounts are often based on the farmer's experience and rough estimates, failing to fully consider changes in water quality, seasonal changes, and differences in aquatic growth stages. Overfeeding or underfeeding are common, resulting in feed waste. Feed residue in the water can pollute the water quality, cause eutrophication, and increase the risk of aquatic disease. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent feeding and growth monitoring system for aquaculture based on the Internet of Things to solve the technical problems existing in the prior art.

[0005] In order to achieve the above-mentioned object of the invention, the technical solution adopted by the present invention is:

[0006] An intelligent feeding and growth monitoring system for aquaculture based on the Internet of Things, comprising the following modules: a multimodal sensing module, comprising a plurality of environmental sensors, water quality sensors and radars, which simultaneously monitors a variety of environmental and water quality parameters and senses biological behavior; the data are pre-processed and then transmitted to a data processing module; the data processing module receives different types of data from the multimodal sensing module, integrates environmental, water quality and biological information to form a unified data set, analyzes, stores and preliminarily processes the data set using a preset algorithm, and generates an analysis environment, water quality monitoring report and feeding suggestions; a central processing module integrates the analysis environment, water quality monitoring report and feeding suggestions generated by the data processing module, performs metabolic energy efficiency modeling based on the data integration results, optimizes the results, and then formulates a final feeding plan and environmental control strategy; the final formulation and strategy results are sent to the intelligent feeding module and the environmental control module, and the entire process is recorded; the intelligent feeding module accurately calculates the appropriate feeding amount based on the feeding plan transmitted by the central processing module, combined with the current water quality, aquatic product quantity and growth stage data; The calculated feeding amount is used to control the intelligent feeding equipment to perform feeding operations, while recording the time, feeding amount, and feeding mode of each feeding, and feeding the above information back to the central processing module; the growth monitoring module analyzes the aquatic images captured by the camera equipment, uses image recognition technology and deep learning algorithms to identify the aquatic species, individual size, and health status for three-dimensional morphological modeling, and then judges the growth status of the aquatic products based on biomass estimation and growth trend, and generates a growth monitoring report. The growth monitoring report is fed back to the central processing module to provide a basis for the next feeding and environmental control; the environmental control module receives the environmental control strategy issued by the central processing module and decides to start or shut down the corresponding environmental control equipment based on the current water quality, water temperature, weather, and optimal environmental parameter standards for aquaculture; when controlling the working process of the environmental control equipment, the environmental parameter changes after its operation are monitored in real time, and the control effect is fed back to the central processing module; the trusted Internet of Things communication module is responsible for the security and stability of data transmission between multiple modules. The data is encrypted using an encryption algorithm during the transmission process, and this module also has an identity authentication mechanism.

[0007] Furthermore, the environmental sensors include: temperature sensor, light intensity sensor, humidity sensor, wind speed and direction sensor and air pressure sensor; the water quality sensors include: dissolved oxygen sensor, pH sensor, ammonia nitrogen sensor, nitrite sensor, salinity sensor and conductivity sensor; the radar includes: ultrasonic bioradar and laser bioradar.

[0008] Furthermore, the ultrasonic bioradar is a 77GHz millimeter wave radar used to capture the movement trajectory of fish schools. The formula for calculating the tail-wagging frequency is:

[0009]

[0010] Where: f beat Aquatic tail-wagging frequency, N number of aquatic species, λ ultrasonic bioradar wavelength, Phase difference and time variable t of the i-th aquatic reflection radar.

[0011] Furthermore, the intelligent feeding module includes the following units: a multi-objective optimization unit, which performs intelligent calculations based on the feeding plan information transmitted from the central processing module, combined with current water quality data, aquatic product quantity and growth stage, to optimize the feeding amount and feeding timing; a pneumatic precision feeding unit, which accurately controls the feed delivery according to the feeding amount and feeding timing calculated by the multi-objective optimization unit, and feeds the aquatic products through the feeding equipment; the feeding equipment supports multiple feeding modes, including: timed feeding, quantitative feeding and an intelligent mode of dynamic adjustment based on real-time monitoring data; an aeration linkage control unit, which monitors the dissolved oxygen level in the water body in real time, and automatically adjusts the aeration intensity of the aeration equipment as needed, so that the dissolved oxygen in the water body is within an appropriate range.

[0012] Furthermore, the growth monitoring module includes the following units: a multispectral image acquisition unit, which uses a 532nm and 850nm dual-wavelength LED array to collect image data of aquatic products in real time, and identifies and processes the collected image data, and transmits the processed data to a three-dimensional morphological modeling unit; a three-dimensional morphological modeling unit, which performs three-dimensional modeling based on the data processed by the multispectral image acquisition unit, including edge detection and point cloud generation, to construct a three-dimensional structure of the aquatic products; the three-dimensional model data is transmitted to a biomass estimation unit for subsequent analysis; the biomass estimation unit calculates the biomass of the aquatic products based on the three-dimensional model and related data generated by the three-dimensional morphological modeling unit; a growth trend prediction unit, which uses the biomass data provided by the biomass estimation unit, combined with historical data and growth models, to analyze the growth trend of the aquatic products to predict future growth conditions; a health assessment unit, which receives health-related data from the three-dimensional morphological modeling unit and the results of the growth trend prediction unit, and analyzes the health of the aquatic products in combination with the morphological characteristics, individual size, growth trend and preset algorithm of the aquatic products; a report generation and feedback unit, which generates a structured report and triggers the update of the control strategy.

[0013] Furthermore, the environmental control equipment includes: an aerator, a water purification device, a water temperature control device and a lighting condition device.

[0014] Compared with the prior art, the present invention has the following beneficial effects:

[0015] The multimodal perception module and the data processing module in the present invention are integrated with each other, so that breeders can fully understand the breeding environment and aquatic conditions, provide a rich and accurate data basis for subsequent analysis, and thus significantly improve the scientificity and accuracy of breeding decisions; among them, the collaborative work of the growth monitoring module and the central processing module realizes the accurate identification of aquatic species, individual size, and health status, and provides detailed and intuitive growth information for breeding decisions by constructing a three-dimensional model, estimating biomass and predicting growth trends; and the collaborative work of the intelligent feeding module and the central processing module enables the present invention to accurately adjust the feeding amount according to different seasons, water quality changes and aquatic growth stages, ensuring that aquatic products obtain sufficient nutrition while reducing the pollution of water quality by feed residues and improving feed utilization. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and technical effect of the present invention more clear, the specific embodiments of the present invention are described below. It should be understood that the specific embodiments described here are only used to explain the present invention and are not used to limit the present invention.

[0017] This embodiment provides an intelligent feeding and growth monitoring system for aquaculture based on the Internet of Things, including the following modules:

[0018] The multimodal perception module includes multiple environmental sensors, water quality sensors and radars, which monitor multiple environmental and water quality parameters and perceive biological behaviors at the same time; the above data are pre-processed and then transmitted to the data processing module; specifically, the environmental sensors include: temperature sensor, light intensity sensor, humidity sensor, wind speed and direction sensor and air pressure sensor; wherein, the temperature sensor is used to measure the temperature of the aquaculture water body and the surrounding air, the light intensity sensor is used to perceive the light intensity, the humidity sensor is used to measure the humidity of the aquaculture environment air, the wind speed and direction sensor obtains the wind speed and direction information of the aquaculture area, and the air pressure sensor is used to measure the atmospheric pressure, which helps the breeder to prevent aquatic hypoxia in advance; the water quality sensor includes: dissolved oxygen sensor, pH sensor, ammonia nitrogen sensor, nitrite sensor, salinity sensor and conductivity sensor; the dissolved oxygen sensor is used to measure the dissolved oxygen content in the water body. When the dissolved oxygen content is too low, aquatic animals will experience hypoxia stress reaction, which may lead to death in severe cases; the pH sensor is used to detect the acidity and alkalinity of the water body, thereby It can judge the acid-base balance of the water body. The ammonia nitrogen sensor is used to measure the concentration of ammonia nitrogen in the water body. Excessive ammonia nitrogen content will damage the gills, liver and other organs of aquatic animals, affecting their growth and immunity. The nitrite sensor monitors the nitrite content in the water body. If there is too much nitrite in the water body, the ferrous hemoglobin in the blood of aquatic animals will be oxidized into methemoglobin, which will lose the ability to bind with oxygen, leading to hypoxia poisoning of aquatic animals. The salinity sensor is used to measure the salinity of the water body. Different types of aquatic animals have different adaptability to salinity. The conductivity sensor measures the conductivity of water to reflect the content of electrolytes such as dissolved salts in the water. The radar includes an ultrasonic bioradar and a laser bioradar. The laser bioradar uses a laser beam to scan the water. When the laser irradiates aquatic animals, it generates scattered light. By detecting the characteristics of the scattered light, the detailed characteristics of the aquatic animals can be accurately obtained, thereby helping to determine the health status and growth stage of the aquatic animals. The ultrasonic bioradar is a 77GHz millimeter wave radar used to capture the movement trajectory of fish schools. The formula for calculating the tail-wagging frequency is:

[0019]

[0020] Where: f beat Aquatic tail-wagging frequency, N number of aquatic species, λ ultrasonic bioradar wavelength, The phase difference and t time variable of the i-th aquatic reflection radar; based on the synergistic effect of the above-mentioned environmental sensors, water quality sensors and radars, full-dimensional perception of the physical environment and biological status is achieved, and a spatiotemporal continuous monitoring network is established.

[0021] A data processing module receives different types of data from the multimodal sensing module, integrates environmental, water quality, and biological information to form a unified data set, analyzes, stores, and preliminarily processes the data set using preset algorithms, and generates analysis reports on the environment and water quality, as well as feeding recommendations. The algorithms include: Kalman filtering, weighted averaging, statistical analysis algorithms, clustering algorithms, and decision trees and random forest algorithms. The Kalman filter is used to estimate the state of a dynamic system, and by integrating data from multiple sensors, it reduces the impact of noise and improves data accuracy. The decision tree and random forest algorithms are used for classification and regression analysis, which can help identify the health status of aquatic products and provide feeding recommendations. The combined use of the above algorithms can effectively process different types of data from the multimodal sensing module, provide accurate environmental monitoring, health assessment, and feeding recommendations, and improve the management efficiency and scientific nature of aquaculture.

[0022] The central processing module integrates the analysis environment, water quality monitoring reports and feeding recommendations generated by the data processing module, performs metabolic energy efficiency modeling based on the data integration results, optimizes the results, and then formulates the final feeding plan and environmental control strategy; sends the final formulation and strategy results to the intelligent feeding module and environmental control module, and records the entire process; the metabolic energy efficiency modeling formula is:

[0023]

[0024] Where: ME(t) net metabolic efficiency, η feed energy conversion rate, F(t) real-time feeding amount, λ temperature compensation coefficient, T real-time water temperature, T opt Optimal growth water temperature, μ basal metabolic coefficient, W(t) real-time biomass, v growth metabolic cost, instantaneous growth rate;

[0025] When ME(t)>0, there is energy surplus, and the central processing module controls the intelligent feeding module to increase the feeding amount; when ME(t)<0, there is energy deficit, and the central processing module controls the intelligent feeding module to reduce the feeding amount.

[0026] The intelligent feeding module accurately calculates the appropriate feeding amount based on the feeding plan transmitted by the central processing module and the data of current water quality, aquatic product quantity and growth stage; controls the intelligent feeding equipment to perform feeding operations based on the calculated feeding amount, and records the time, feeding amount and feeding mode of each feeding, and feeds the above information back to the central processing module; specifically, the intelligent feeding module includes the following units: a multi-objective optimization unit, which performs intelligent calculations based on the feeding plan information transmitted by the central processing module and the current water quality data, aquatic product quantity and growth stage to optimize the feeding amount and feeding timing. In the optimization process, genetic algorithms and particle swarm optimization are required to calculate the corresponding feeding amount and feeding timing while considering multiple objectives; and establishes the Pareto optimal solution of the feeding strategy to balance the three major factors of feed conversion rate, water quality stability and energy efficiency. Objective; the pneumatic precision feeding unit accurately controls the feed delivery according to the feeding amount and feeding timing calculated by the multi-objective optimization unit to ensure the accuracy and consistency of feeding; the aquatic products are fed through the feeding equipment; the feeding equipment supports multiple feeding modes, including: timed feeding, quantitative feeding and an intelligent mode of dynamic adjustment of real-time monitoring data; the aeration linkage control unit monitors the dissolved oxygen level in the water body in real time, and automatically adjusts the aeration intensity of the aeration equipment as needed to keep the dissolved oxygen in the water body within an appropriate range; the working principle is that when the multi-objective optimization unit receives the feeding plan from the central processing module, it calculates the corresponding feeding amount and feeding timing through a preset algorithm, and transmits the above data to the pneumatic precision feeding unit, which controls the feed delivery. At this time, the aeration linkage control unit continuously monitors the dissolved oxygen in the water body and adjusts the aeration equipment as needed.

[0027] The growth monitoring module analyzes the aquatic images captured by the camera equipment, uses image recognition technology and deep learning algorithms to identify the aquatic species, individual size and health status to perform three-dimensional morphological modeling, and then judges the growth status of the aquatic products in combination with biomass estimation and growth trend and generates a growth monitoring report, which is fed back to the central processing module to provide a basis for the next feeding and environmental control; specifically, the growth monitoring module includes the following units: a multispectral image acquisition unit, which uses a 532nm and 850nm dual-wavelength LED array to ensure comprehensive coverage of all aquatic products in the breeding pond, collects image data of aquatic products in real time, and uses a convolutional neural network to identify and process the collected image data, and transmits the processed data to the three-dimensional morphological modeling unit; a three-dimensional morphological modeling unit, which performs three-dimensional modeling based on the data processed by the multispectral image acquisition unit, including edge detection and point cloud generation, to construct a three-dimensional structure of the aquatic products. ; The three-dimensional model data is passed to the biomass estimation unit for subsequent analysis; the biomass estimation unit calculates the biomass of aquatic products based on the three-dimensional model and related data generated by the three-dimensional morphological modeling unit, parses the point cloud data in the three-dimensional model, identifies the individual characteristics of aquatic products, including body shape, body length, and volume, and calculates the biomass of each aquatic individual based on the volume or surface area of the aquatic products, and transmits the biomass data to the growth trend prediction unit as the basic data for its analysis and prediction; the growth trend prediction unit uses the biomass data provided by the biomass estimation unit, combined with historical data and growth models, to analyze the growth trend of aquatic products to predict future growth; the health assessment unit receives health-related data from the three-dimensional morphological modeling unit and the results of the growth trend prediction unit, and analyzes the health of aquatic products in combination with the morphological characteristics, individual size, growth trend and preset algorithm of aquatic products; the report generation and feedback unit generates a structured report and triggers the update of the control strategy.

[0028] The environmental control module receives the environmental control strategy issued by the central processing module, and decides to start or shut down the corresponding environmental control equipment according to the current water quality, water temperature, weather and the optimal environmental parameter standards for aquaculture; when controlling the working process of the environmental control equipment, it monitors the changes in the environmental parameters after its operation in real time, and feeds back the control effect to the central processing module; the environmental control equipment includes: an aerator, a water purification equipment, a water temperature control equipment and a light condition equipment; the aerator is used to increase the dissolved oxygen content in the water body, and the aerator accelerates the dissolution of oxygen into the water by stirring the water body, promoting the contact between air and water, etc., to ensure that the aquatic products have sufficient oxygen for respiratory metabolism; the water purification equipment specifically includes a filtering equipment, a disinfecting equipment and a water quality regulator adding equipment, and the water quality regulator adding equipment is used to add various water quality regulators to the water body, such as lime and microbial preparations, which can decompose organic matter in the water, regulate water quality and inhibit the growth of harmful microorganisms.

[0029] The trusted IoT communication module is responsible for the security and stability of data transmission between multiple modules. The encryption algorithm is used to encrypt the data during the transmission process. At the same time, this module also has an identity authentication mechanism.

[0030] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention.

Claims

1. An intelligent aquaculture feeding and growth monitoring system based on the Internet of Things, characterized by: Includes the following modules: The multimodal perception module, which includes multiple environmental sensors, water quality sensors, and radar, simultaneously monitors multiple environmental and water quality parameters and senses biological behavior; the above data is pre-processed and transmitted to the data processing module; A data processing module receives different types of data from the multimodal sensing module, integrates environmental, water quality, and biological information to form a unified data set, analyzes, stores, and preliminarily processes the data set using a preset algorithm, and generates an analysis of the environment, water quality monitoring report, and feeding recommendations; The central processing module integrates the analysis environment, water quality monitoring reports and feeding recommendations generated by the data processing module, performs metabolic energy efficiency modeling based on the data integration results, optimizes the results, and then formulates the final feeding plan and environmental control strategy; Send the final formulation and strategy results to the intelligent feeding module and environmental control module, and record the entire process; The intelligent feeding module accurately calculates the appropriate feeding amount based on the feeding plan transmitted by the central processing module and the data on current water quality, aquatic product quantity and growth stage; controls the intelligent feeding equipment to perform feeding operations based on the calculated feeding amount, and records the time, feeding amount and feeding mode of each feeding, and feeds the above information back to the central processing module; The growth monitoring module analyzes aquatic images captured by the camera equipment, uses image recognition technology and deep learning algorithms to identify the aquatic species, individual size, and health status to perform three-dimensional morphological modeling, and then combines biomass estimation and growth trend to judge the growth of the aquatic products and generate a growth monitoring report. The growth monitoring report is fed back to the central processing module to provide a basis for the next feeding and environmental control; The environmental control module receives the environmental control strategy issued by the central processing module and decides to start or shut down the corresponding environmental control equipment based on the current water quality, water temperature, weather and the optimal environmental parameter standards for aquaculture; when controlling the working process of the environmental control equipment, it monitors the changes in the environmental parameters after its operation in real time and feeds back the control effect to the central processing module; The trusted IoT communication module is responsible for the security and stability of data transmission between multiple modules. The encryption algorithm is used to encrypt the data during the transmission process. At the same time, this module also has an identity authentication mechanism.

2. The aquaculture intelligent feeding and growth monitoring system based on the Internet of Things according to claim 1 is characterized in that: The environmental sensors include: temperature sensor, light intensity sensor, humidity sensor, wind speed and direction sensor and air pressure sensor; the water quality sensors include: dissolved oxygen sensor, pH sensor, ammonia nitrogen sensor, nitrite sensor, salinity sensor and conductivity sensor; the radar includes: ultrasonic bioradar and laser bioradar.

3. The intelligent feeding and growth monitoring system for aquaculture based on the Internet of Things according to claim 2 is characterized in that: The ultrasonic bioradar is a 77GHz millimeter wave radar used to capture the movement trajectory of fish schools. The formula for calculating the tail-wagging frequency is: Where: f beat Aquatic tail-wagging frequency, N number of aquatic species, λ ultrasonic bioradar wavelength, Phase difference and time variable t of the i-th aquatic reflection radar.

4. The intelligent feeding and growth monitoring system for aquaculture based on the Internet of Things according to claim 1 is characterized in that: The intelligent feeding module includes the following units: The multi-objective optimization unit performs intelligent calculations based on the feeding plan information transmitted by the central processing module, combined with current water quality data, aquatic production quantity and growth stage, to optimize the feeding amount and feeding timing; The pneumatic precision feeding unit accurately controls feed delivery based on the feeding amount and feeding timing calculated by the multi-objective optimization unit, and feeds the aquatic products through the feeding equipment; The feeding equipment supports multiple feeding modes, including timed feeding, quantitative feeding, and intelligent mode with real-time monitoring data and dynamic adjustment; The oxygenation linkage control unit monitors the dissolved oxygen level in the water in real time and automatically adjusts the oxygenation intensity of the oxygenation equipment as needed to keep the dissolved oxygen in the water within an appropriate range.

5. The aquaculture intelligent feeding and growth monitoring system based on the Internet of Things according to claim 1 is characterized in that: The growth monitoring module includes the following units: The multispectral image acquisition unit uses a 532nm and 850nm dual-wavelength LED array to collect image data of aquatic products in real time, identify and process the collected image data, and transmit the processed data to the 3D morphology modeling unit; a three-dimensional morphological modeling unit, which performs three-dimensional modeling based on the data processed by the multispectral image acquisition unit, including edge detection and point cloud generation, so as to construct a three-dimensional structure of the aquatic product; The three-dimensional model data are passed to the biomass estimation unit for subsequent analysis; The biomass estimation unit calculates the biomass of aquatic products based on the three-dimensional model and related data generated by the three-dimensional morphological modeling unit; The growth trend prediction unit uses the biomass data provided by the biomass estimation unit, combined with historical data and growth models, to analyze the growth trend of aquatic products and predict future growth; The health assessment unit receives the health-related data from the 3D morphology modeling unit and the results from the growth trend prediction unit, and analyzes the health of the aquatic products based on their morphological characteristics, individual size, growth trend, and preset algorithms; Report generation and feedback unit generates structured reports and triggers control strategy updates.

6. The aquaculture intelligent feeding and growth monitoring system based on the Internet of Things according to claim 1 is characterized in that: The environmental control equipment includes: an aerator, a water purification device, a water temperature control device and a light condition device.

Images