Fish culture system and method for land-based circulating water

By integrating data monitoring, strategy optimization, bait treatment and salvage modules in land-based circulating aquaculture systems, precise monitoring and management of fish populations is achieved, and the problem of difficult improvement of aquaculture efficiency and aquatic product quality in the existing technology is solved. , improves the breeding efficiency and aquatic product quality.

CN118917959APending Publication Date: 2024-11-08HEILONGJIANG RIVER FISHERY RES INST CHINESE ACADEMY OF FISHERIES SCI
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202410962938.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing land-based circulating aquaculture system lacks detailed monitoring and management of individual fish populations, which makes it difficult to improve the breeding efficiency and aquatic product quality.

Method used

A fish farming system including data monitoring module, strategy optimization module, bait processing module and salvage module was designed. Through sonar, X-ray and water quality monitoring units, data on fish population number, weight, length and bone structure were collected in real time, and the data on fish population number, weight, length and bone structure were constructed. Growth and water quality prediction models, optimize breeding strategies, and automatically adjust bait placement and remove residual bait, monitor and salvage dead fish.

Benefits of technology

Accurate monitoring and management of individual fish is achieved, breeding efficiency and aquatic product quality are improved, and breeding strategies are optimized through real-time data collection and prediction models, which improves the accuracy of fish population growth and water quality control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917959A_ABST
    Figure CN118917959A_ABST
Patent Text Reader

Abstract

The invention discloses a fish culture system and method for land-based circulating water. The system comprises a data monitoring module, a strategy optimization module, a bait processing module and a fishing module. The data monitoring module is used for collecting fish school quantity data, weight data of individual fishes, body length data of the individual fishes, internal skeleton structures of the individual fishes and water quality conditions in a culture pond in real time. The strategy optimization module updates growth conditions and water quality information of fishes in a culture pond in real time based on fish school quantity data, weight data of individual fishes, body length data of the individual fishes, internal skeleton structures and water quality conditions, and constructs a fish body growth prediction model and a water quality prediction model. Optimizing a breeding strategy according to the growth prediction model and the water quality prediction model; the bait processing module automatically adjusts the bait feeding amount based on the optimized breeding strategy and regularly detects and removes residual bait; and the automatic fishing module is used for monitoring the dead fish condition and positioning and fishing the dead fish based on the dead fish condition.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of circulating water detection, and in particular relates to a fish breeding system and method for land-based circulating water. Background Art

[0002] The development of land-based recirculating aquaculture systems (RAS) benefits from the increase in environmental protection needs, the pursuit of efficient resource utilization, the advantages of spatial flexibility, the emphasis on food safety and quality control, the growth of market demand, scientific and technological progress, policy support, and considerations of climate change adaptability. This system reduces dependence on natural water bodies and improves the efficiency of water resource utilization through a closed cycle. At the same time, it achieves precise control of the aquaculture environment and meets the market demand for high-quality aquatic products. With the application of modern technology and policy support, RAS has become an important direction for the sustainable development of modern aquaculture. However, this system is more about monitoring the growth status of the entire fish school, lacking a detailed analysis of an individual in the fish school. Therefore, it is urgent to design a land-based recirculating aquaculture system that can achieve precise monitoring and management of individual fish and improve aquaculture efficiency and the quality of aquatic products. Summary of the invention

[0003] The present invention aims to solve the deficiencies of the prior art and provides the following solutions:

[0004] A fish farming system for land-based circulating water, comprising: a data monitoring module, a strategy optimization module, a bait processing module and a salvage module;

[0005] The data monitoring module is used to collect data on the number of fish in the breeding pond, weight data of individual fish, body length data of individual fish, internal bone structure of individual fish and water quality in real time;

[0006] The strategy optimization module updates the growth status and water quality information of the fish in the breeding pond in real time based on the fish population data, the weight data of the individual fish, the body length data of the individual fish, the internal skeletal structure and the water quality status, and constructs a fish growth prediction model and a water quality prediction model, and optimizes the breeding strategy according to the growth prediction model and the water quality prediction model;

[0007] The bait processing module automatically adjusts the amount of bait based on the optimized breeding strategy, and regularly detects and removes residual bait;

[0008] The automatic salvaging module is used to monitor the dead fish situation, and locate and salvage the dead fish based on the dead fish situation.

[0009] Preferably, the data monitoring module includes: a sonar monitoring unit, an X-ray monitoring unit and a water quality monitoring unit;

[0010] The sonar monitoring unit is installed inside the breeding pond, and the sonar monitoring unit is used to collect the fish quantity data, the weight data of the individual fish and the body length data of the individual fish in the breeding pond in real time;

[0011] The X-ray monitoring unit is installed inside the breeding pond, and the X-ray monitoring unit is used to regularly photograph the internal skeletal structure of individual fish;

[0012] The water quality monitoring unit is installed inside the breeding pond, and is used to collect water quality parameters in the breeding pond in real time, and evaluate the water quality status in the breeding pond based on the water quality parameters.

[0013] Preferably, the workflow of the sonar monitoring unit includes: establishing a relationship model between sonar echoes and fish body data based on historical sonar data and historical fish body data; collecting sonar data in real time, and determining the fish population data, the individual fish weight data and the individual fish body length data in the breeding pond based on the relationship model and the sonar data collected in real time.

[0014] Preferably, the strategy optimization module includes: a fish growth prediction unit, a water quality prediction unit and a strategy optimization unit;

[0015] The fish growth prediction unit is used to construct a machine learning model, and the machine learning model is trained based on historical fish school data and historical fish body data to obtain the fish growth prediction model;

[0016] The fish growth prediction unit also predicts the growth of the fish in the breeding pond based on the fish population data, the weight data of the individual fish, the body length data of the individual fish and the internal skeletal structure using the fish growth prediction model to obtain a fish growth prediction result;

[0017] The water quality prediction unit constructs a water quality prediction model based on historical water quality data, environmental influencing factors and bait influencing factors, and predicts the water quality in the breeding pond based on the water quality status to obtain a water quality prediction result;

[0018] The strategy optimization unit formulates a breeding strategy based on the fish growth prediction result and the water quality prediction result.

[0019] The present invention also provides a method for fish farming in land-based circulating water, which is applied to any of the above-mentioned systems and comprises the following steps:

[0020] S1. Real-time collection of fish population data, individual fish weight data, individual fish length data, internal bone structure and water quality of individual fish in the breeding pond;

[0021] S2. Based on the fish population data, the weight data of the individual fish, the body length data of the individual fish, the internal skeletal structure and the water quality conditions, the growth status and water quality information of the fish in the breeding pond are updated in real time, and a fish growth prediction model and a water quality prediction model are constructed, and the breeding strategy is optimized according to the growth prediction model and the water quality prediction model;

[0022] S3. Automatically adjust the feeding amount based on the optimized breeding strategy, and regularly check and remove the remaining bait;

[0023] S4. Monitor the dead fish situation, and locate and salvage the dead fish based on the dead fish situation.

[0024] Preferably, the S1 comprises:

[0025] Installing a sonar monitoring unit, an X-ray monitoring unit and a water quality monitoring unit inside the culture pond;

[0026] The sonar monitoring unit is used to collect the fish population data, the weight data of the individual fish, and the body length data of the individual fish in the breeding pond in real time;

[0027] The X-ray monitoring unit is used to regularly photograph the internal skeletal structure of individual fish;

[0028] The water quality monitoring unit is used to collect water quality parameters in the breeding pond in real time, and evaluate the water quality status in the breeding pond based on the water quality parameters.

[0029] Preferably, the workflow of the sonar monitoring unit includes: establishing a relationship model between sonar echoes and fish body data based on historical sonar data and historical fish body data; collecting sonar data in real time, and determining the fish population data, the individual fish weight data and the individual fish body length data in the breeding pond based on the relationship model and the sonar data collected in real time.

[0030] Preferably, S2 includes:

[0031] Constructing a machine learning model, and training the machine learning model based on historical fish school data and historical fish body data to obtain the fish body growth prediction model;

[0032] Based on the fish population data, the individual fish weight data, the individual fish length data and the internal skeletal structure, the fish growth in the breeding pond is predicted using the fish growth prediction model to obtain a fish growth prediction result;

[0033] Constructing a water quality prediction model based on historical water quality data, environmental influencing factors and bait influencing factors, and predicting the water quality in the aquaculture pond based on the water quality status to obtain a water quality prediction result;

[0034] A breeding strategy is formulated based on the fish growth prediction results and the water quality prediction results.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] The present invention installs sonar equipment in the breeding pond, installs X-ray equipment near the breeding pond, adds automatic water quality monitoring equipment, deploys intelligent feeding equipment, and configures an automatic residual bait removal device; uses the sonar device to collect real-time data on the number of fish and the weight and length of individual fish, uses the X-ray device to regularly photograph the internal bone structure of the fish, and uses water quality monitoring equipment to collect water quality parameters in real time, thereby achieving accurate monitoring and management of individual fish, thereby improving breeding efficiency and the quality of aquatic products. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0038] Figure 1 A schematic diagram of the system structure of an embodiment of the present invention;

[0039] Figure 2 The figure is a schematic diagram of a method flow of an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0042] Embodiment 1

[0043] In this embodiment, if Figure 1 As shown, a fish farming system for land-based circulating water includes: a data monitoring module, a strategy optimization module, a bait processing module and a salvage module

[0044] The data monitoring module is used to collect real-time data on the number of fish in the breeding pond, the weight data of individual fish, the body length data of individual fish, the internal bone structure of individual fish and the water quality conditions.

[0045] The data monitoring module includes: a sonar monitoring unit, an X-ray monitoring unit and a water quality monitoring unit. The sonar monitoring unit is installed inside the breeding pond, and is used to collect the fish population data, individual fish weight data and individual fish body length data in the breeding pond in real time; the X-ray monitoring unit is installed inside the breeding pond, and is used to regularly photograph the internal skeletal structure of individual fish; the water quality monitoring unit is installed inside the breeding pond, and is used to collect the water quality parameters in the breeding pond in real time, and evaluate the water quality status in the breeding pond based on the water quality parameters. The workflow of the sonar monitoring unit includes: establishing a relationship model between sonar echoes and fish body data based on historical sonar data and historical fish body data; collecting sonar data in real time, and determining the fish population data, individual fish weight data and individual fish body length data in the breeding pond based on the relationship model and the real-time collected sonar data.

[0046] In this embodiment, the sonar monitoring unit detects the number of fish and the size of individuals through ultrasound, establishes a relationship model between sonar echoes and fish weight and length through the accumulation of previous big data, collects sonar data in real time, and determines the number of fish in the breeding pond, the weight of individual fish, and the length of individual fish based on the relationship model and the real-time collected sonar data. An automated mobile platform is provided in the X-ray monitoring unit for tracking the target fish and photographing the target to obtain the internal skeletal structure of the individual target fish.

[0047] The strategy optimization module updates the growth status and water quality information of the fish in the breeding pond in real time based on the fish population data, individual fish weight data, individual fish length data, internal bone structure and water quality conditions, and constructs fish growth prediction model and water quality prediction model, and optimizes the breeding strategy according to the growth prediction model and water quality prediction model.

[0048] The strategy optimization module includes: fish growth prediction unit, water quality prediction unit and strategy optimization unit. The fish growth prediction unit is used to construct a machine learning model, and the machine learning model is trained based on historical fish data and historical fish data to obtain a fish growth prediction model. In this embodiment, the machine learning model includes a linear regression model and a random forest model. The specific training method includes: first, the weight and body length of a large number of individual fish are fitted and analyzed using a linear regression model to obtain a calculation formula for weight and body length, and then the random forest model is used to analyze and predict the future weight and body length of individual fish based on the weight and body length calculation formula and the collected weight data and body length data of individual fish; the fish growth prediction unit also predicts the growth of fish in the breeding pond based on the fish population data, the weight data of individual fish, the body length data of individual fish and the internal bone structure using the fish growth prediction model to obtain a fish growth prediction result; the water quality prediction unit constructs a water quality prediction model based on historical water quality data, environmental influencing factors and bait influencing factors, and predicts the water quality in the breeding pond based on the water quality status to obtain a water quality prediction result; the strategy optimization unit formulates a breeding strategy based on the fish growth prediction result and the water quality prediction result.

[0049] The feed processing module automatically adjusts the feed amount based on the optimized breeding strategy, and regularly checks and removes residual feed.

[0050] In this embodiment, the bait processing module accurately delivers bait according to the breeding strategy, covers different areas of the breeding pond, monitors the distribution of bait during the feeding process, records the amount and time of each feeding, as well as the corresponding water quality changes and fish eating conditions; regularly checks the residual bait situation and automatically removes the residual bait.

[0051] The automatic salvage module is used to monitor the dead fish situation, and locate and salvage the dead fish based on the dead fish situation.

[0052] In this embodiment, the automatic salvage module is equipped with salvage equipment, cameras and sensors. An automatic salvage mechanism is set in the salvage equipment, and the camera and sensors are used to detect the presence of dead fish in the breeding pond in real time. Once dead fish are detected, the salvage equipment is immediately triggered for cleaning.

[0053] Embodiment 2

[0054] In this embodiment, the installation and operation process of the breeding system will be described in detail.

[0055] Install sonar monitoring units, X-ray monitoring units and water quality monitoring units inside the breeding pond. Use the sonar monitoring unit to detect the number of fish and individual size. Through the accumulation of previous big data, establish a relationship model between sonar echoes and fish weight and length; use the X-ray monitoring unit to regularly detect the internal bone morphology of fish, and set up an automated mobile platform in the X-ray monitoring unit to take pictures of target fish; the water quality monitoring unit includes a variety of water quality sensors for real-time monitoring of water quality parameters. The sensors are connected to the strategy optimization module, and the data can be transmitted to the strategy optimization module in real time. Install a bait processing module inside the breeding pond, connect the sonar monitoring unit and the water quality monitoring unit, intelligently control the amount of bait according to real-time data, and configure an automatic device for removing residual bait. Install an automatic salvage module inside the breeding pond. The automatic salvage module is equipped with salvage equipment, cameras and sensors to detect the presence of dead fish in the breeding pond in real time, set up an automatic salvage mechanism, and immediately trigger the salvage equipment for cleaning once a dead fish is detected.

[0056] Furthermore, the sonar monitoring unit and the camera of the automatic salvage module are used to monitor the status of the fish school in real time and identify abnormal behavior and dead fish. Once a dead fish is detected, the automatic salvage module records the location and issues a salvage command to start the salvage equipment. According to the recorded location information, the dead fish are accurately salvaged and transferred to the designated collection area. After each salvage, the number of dead fish, location and related environmental parameters are recorded, and the database information is updated.

[0057] Furthermore, the data of sonar, X-ray, water quality monitoring, dead fish salvage and feeding equipment are concentrated in the strategy optimization module. The strategy optimization module uses historical data and real-time data to train the fish growth prediction model to predict the growth of fish. The model input includes individual weight, body length, number of fish, and water quality parameters. The output is the fish growth prediction result, including the growth rate, expected weight and body length of the fish. A water quality prediction model is established to predict the future trend of water quality changes. The model input includes current water quality parameters, historical data and environmental factors, and the output is the water quality prediction result. The strategy optimization module uses the fish growth prediction model and the water quality prediction model to perform fusion analysis on multi-source data, uses the fish growth data to establish individual and group growth models, predict future growth trends, set warning thresholds, and automatically issue warnings when water quality parameters, fish health indicators or the number of dead fish exceed the normal range. The strategy optimization module integrates the data of fish population, water quality parameters and fish growth status, analyzes the needs of the breeding pond in real time, and formulates breeding strategies. The feed processing module automatically adjusts the feeding amount according to the formulated breeding strategy, accurately releases the feed, and covers different areas of the breeding pond. At the same time, it regularly detects the residual feed, automatically removes the residual feed, records the amount and time of each feeding, as well as the corresponding water quality changes and fish eating conditions, and uses historical data and machine learning models to optimize the feeding strategy.

[0058] This embodiment may further include using a sonar monitoring unit, a water quality monitoring unit, a camera and an RFID tag to collect the number of fish schools, the weight and length of individual fish, water quality parameters and fish behavior data in real time, and using wireless communication or a wired network to transmit the data in real time to a strategy optimization module. The strategy optimization module here may also include a central data processing system and an edge device, perform preliminary processing and screening before data transmission, perform preliminary analysis on the edge device, detect abnormal conditions and send early warning signals, and the bait processing module accurately releases bait according to system instructions to cover different areas of the breeding pond, monitor the distribution of bait during the feeding process, record the amount and time of each feeding, as well as the corresponding water quality changes and fish eating conditions. The strategy optimization module optimizes the feeding plan according to the health status and growth status of individual fish. An abnormality detection algorithm may also be set in the strategy optimization module to monitor the growth and health status of fish in real time and identify abnormal conditions. When an abnormality is detected, an early warning is automatically triggered and a notification is sent to the farmer.

[0059] Furthermore, real-time monitoring data is used and input into a fish growth prediction model to predict the growth of individual fish. The prediction results include the changing trends of weight and length in the future. Based on the growth prediction results, breeding strategies are formulated, including feed input, feed type, and water quality control. Specific feeding plans are provided for fish at different growth stages to optimize growth rate and health status.

[0060] Embodiment 3

[0061] In this embodiment, if Figure 2 As shown, a method for fish farming using land-based circulating water comprises the following steps:

[0062] S1. Collect data on the number of fish in the breeding pond, the weight of individual fish, the length of individual fish, the internal bone structure of individual fish and the water quality in real time.

[0063] S1 includes: installing a sonar monitoring unit, an X-ray monitoring unit and a water quality monitoring unit inside the breeding pond; using the sonar monitoring unit to collect data on the number of fish in the breeding pond, the weight data of individual fish and the body length data of individual fish in real time; using the X-ray monitoring unit to regularly photograph the internal skeletal structure of individual fish; using the water quality monitoring unit to collect water quality parameters in the breeding pond in real time, and evaluating the water quality status in the breeding pond based on the water quality parameters.

[0064] The workflow of the sonar monitoring unit includes: establishing a relationship model between sonar echoes and fish body data based on historical sonar data and historical fish body data; collecting sonar data in real time, and determining the number of fish in the breeding pond, the weight data of individual fish, and the body length data of individual fish based on the relationship model and the real-time collected sonar data.

[0065] S2. Update the growth status and water quality information of fish in the breeding pond in real time based on the fish population data, individual fish weight data, individual fish length data, internal bone structure and water quality conditions, and build fish growth prediction model and water quality prediction model, and optimize the breeding strategy according to the growth prediction model and water quality prediction model.

[0066] S2 includes: constructing a machine learning model, training the machine learning model based on historical fish data and historical fish data to obtain a fish growth prediction model; based on fish population data, individual fish weight data, individual fish body length data and internal bone structure, using the fish growth prediction model to predict the growth of fish in the breeding pond to obtain fish growth prediction results; constructing a water quality prediction model based on historical water quality data, environmental influencing factors and bait influencing factors, and predicting the water quality in the breeding pond based on the water quality conditions to obtain water quality prediction results; formulating a breeding strategy based on the fish growth prediction results and the water quality prediction results.

[0067] S3. Automatically adjust the feeding amount based on the optimized breeding strategy, and regularly check and remove the remaining bait.

[0068] S3 includes: accurately placing bait according to the breeding strategy to cover different areas of the breeding pond, monitoring the distribution of bait during the feeding process, recording the amount and time of each feeding, as well as the corresponding water quality changes and fish eating conditions; regularly checking the residual bait situation and automatically removing the residual bait.

[0069] S4. Monitor the dead fish situation, and locate and salvage the dead fish based on the dead fish situation.

[0070] S4 includes: installing salvaging equipment, cameras and sensors in the breeding pond, and setting an automatic salvaging mechanism in the salvaging equipment, using the camera and sensors to detect the presence of dead fish in the breeding pond in real time, and once dead fish are detected, immediately triggering the salvaging equipment for cleaning.

[0071] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A fish farming system for land-based circulating water, characterized in that: include: Data monitoring module, strategy optimization module, bait processing module and salvage module; The data monitoring module is used to collect data on the number of fish in the breeding pond, weight data of individual fish, body length data of individual fish, internal bone structure of individual fish and water quality in real time; The strategy optimization module updates the growth status and water quality information of the fish in the breeding pond in real time based on the fish population data, the weight data of the individual fish, the body length data of the individual fish, the internal skeletal structure and the water quality status, and constructs a fish growth prediction model and a water quality prediction model, and optimizes the breeding strategy according to the growth prediction model and the water quality prediction model; The bait processing module automatically adjusts the amount of bait based on the optimized breeding strategy, and regularly detects and removes residual bait; The automatic salvaging module is used to monitor the dead fish situation, and locate and salvage the dead fish based on the dead fish situation.

2. A fish farming system for land-based circulating water according to claim 1, characterized in that: The data monitoring module includes: a sonar monitoring unit, an X-ray monitoring unit and a water quality monitoring unit; The sonar monitoring unit is installed inside the breeding pond, and the sonar monitoring unit is used to collect the fish population data, the weight data of the individual fish and the body length data of the individual fish in the breeding pond in real time; The X-ray monitoring unit is installed inside the breeding pond, and the X-ray monitoring unit is used to regularly photograph the internal skeletal structure of individual fish; The water quality monitoring unit is installed inside the breeding pond, and is used to collect water quality parameters in the breeding pond in real time, and evaluate the water quality status in the breeding pond based on the water quality parameters.

3. A fish farming system for land-based circulating water according to claim 2, characterized in that: The workflow of the sonar monitoring unit includes: establishing a relationship model between sonar echoes and fish body data based on historical sonar data and historical fish body data; collecting sonar data in real time, and determining the fish population data, the weight data of the individual fish, and the body length data of the individual fish in the breeding pond based on the relationship model and the sonar data collected in real time.

4. A fish farming system for land-based circulating water according to claim 1, characterized in that: The strategy optimization module includes: a fish growth prediction unit, a water quality prediction unit and a strategy optimization unit; The fish growth prediction unit is used to construct a machine learning model, and the machine learning model is trained based on historical fish school data and historical fish body data to obtain the fish growth prediction model; The fish growth prediction unit also predicts the growth of the fish in the breeding pond based on the fish population data, the weight data of the individual fish, the body length data of the individual fish and the internal skeletal structure using the fish growth prediction model to obtain a fish growth prediction result; The water quality prediction unit constructs a water quality prediction model based on historical water quality data, environmental influencing factors and bait influencing factors, and predicts the water quality in the breeding pond based on the water quality status to obtain a water quality prediction result; The strategy optimization unit formulates a breeding strategy based on the fish growth prediction result and the water quality prediction result.

5. A method for fish farming in land-based circulating water, the method being applied to the system according to any one of claims 1 to 4, characterized in that: The following steps are involved: S1. Real-time collection of fish population data, individual fish weight data, individual fish length data, internal bone structure and water quality of individual fish in the breeding pond; S2. Based on the fish population data, the weight data of the individual fish, the body length data of the individual fish, the internal skeletal structure and the water quality conditions, the growth status and water quality information of the fish in the breeding pond are updated in real time, and a fish growth prediction model and a water quality prediction model are constructed, and the breeding strategy is optimized according to the growth prediction model and the water quality prediction model; S3. Automatically adjust the feeding amount based on the optimized breeding strategy, and regularly check and remove the remaining bait; S4. Monitor the dead fish situation, and locate and salvage the dead fish based on the dead fish situation.

6. A fish farming method for land-based circulating water according to claim 5, characterized in that: The S1 includes: Installing a sonar monitoring unit, an X-ray monitoring unit and a water quality monitoring unit inside the culture pond; The sonar monitoring unit is used to collect the fish population data, the weight data of the individual fish, and the body length data of the individual fish in the breeding pond in real time; The X-ray monitoring unit is used to regularly photograph the internal skeletal structure of individual fish; The water quality monitoring unit is used to collect water quality parameters in the breeding pond in real time, and evaluate the water quality status in the breeding pond based on the water quality parameters.

7. A fish farming method for land-based circulating water according to claim 6, characterized in that: The workflow of the sonar monitoring unit includes: establishing a relationship model between sonar echoes and fish body data based on historical sonar data and historical fish body data; collecting sonar data in real time, and determining the fish population data, the weight data of the individual fish, and the body length data of the individual fish in the breeding pond based on the relationship model and the sonar data collected in real time.

8. A fish farming method for land-based circulating water according to claim 5, characterized in that: The S2 includes: Constructing a machine learning model, and training the machine learning model based on historical fish school data and historical fish body data to obtain the fish body growth prediction model; Based on the fish population data, the individual fish weight data, the individual fish length data and the internal skeletal structure, the fish growth in the breeding pond is predicted using the fish growth prediction model to obtain a fish growth prediction result; Constructing a water quality prediction model based on historical water quality data, environmental influencing factors and bait influencing factors, and predicting the water quality in the aquaculture pond based on the water quality status to obtain a water quality prediction result; A breeding strategy is formulated based on the fish growth prediction results and the water quality prediction results.

Citation Information

Cited By

  • Method for managing VNN-free fry farm for cynoglossus semilaevis cultivation

    CN120198240A

  • A management method for a VNN-free seedling farm for Cynoglossus semilaevis aquaculture

    CN120198240B

  • Q-elastic yellow croaker culture control system based on ecological dynamic model

    CN120202968A

  • Aquatic product supervision system based on multi-modal breeding data analysis

    CN120450890A