Accurate feeding control system for marine product seedling culture

Abstract

The invention relates to the technical field of aquaculture, and discloses a marine product seedling raising accurate feeding control system which comprises an intelligent recognition module, a data analysis and decision module, an accurate feeding execution module, an environment monitoring module and a remote control and information management module. Through a high-definition camera and a computer vision processing unit of the intelligent identification module, key information such as the body type, the number and the activity state of the fry is accurately identified by adopting a deep learning algorithm. The big data analysis unit is combined with fry growth stages, types and density factors, a machine learning technology and a preset biological growth model are used for accurately calculating the real-time feed demand of each area, and the decision making unit generates an accurate feeding strategy according to the real-time feed demand. And a feeder of the precise feeding execution module realizes timed, quantitative and fixed-point feeding according to the strategy, so that the problem of inaccurate feeding amount caused by experience judgment in a traditional feeding mode is effectively avoided, the feed waste is greatly reduced, and the feed utilization rate is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of aquaculture, and in particular to a precise feeding control system for seafood seedling cultivation. Background Art

[0002] In traditional seafood seedling farming operations, the feeding process mainly relies on the experience and judgment of the breeders, which has many disadvantages. On the one hand, it is difficult to accurately control the feed requirements of fry at different growth stages, types and densities, which easily leads to feed waste and increases breeding costs; on the other hand, excessive feeding often causes water quality deterioration, affects the living environment of fry, and reduces survival rate and growth rate. At the same time, manual feeding is labor-intensive and inefficient, making it difficult to meet the needs of large-scale breeding. With the rise of technologies such as the Internet of Things, big data, and computer vision, intelligent breeding has become a key path to solving the difficulties of traditional breeding and achieving industrial upgrading, and this invention has come into being. Summary of the Invention

[0003] In response to the shortcomings of the existing technology, the present invention provides a precise feeding control system for seafood seedlings, which solves the problems of high labor intensity, low efficiency and difficulty in meeting the needs of large-scale aquaculture due to manual feeding.

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: A seafood seedling precision feeding control system, comprising:

[0005] An intelligent recognition module, comprising a high-definition camera for capturing real-time images of fry in the nursery pond and a computer vision processing unit for intelligently identifying and analyzing the images captured by the camera to extract key information such as the fry's size, number, and activity status;

[0006] A data analysis and decision-making module comprises a data receiving unit, a big data analysis unit, and a decision-making unit. The data receiving unit receives the fry information transmitted by the intelligent recognition module. The big data analysis unit analyzes the received data and calculates the real-time feed demand of each area based on the growth stage, species, and density of the fry. The decision-making unit formulates a precise feeding strategy based on the analysis results, including but not limited to feeding time, feeding amount, and feeding area.

[0007] A precision feeding execution module, which consists of multiple feeders that deliver precise feed based on the output of the decision-making unit and a metering and control system that ensures the correct amount of feed is delivered each time and monitors the operating status of the feeders.

[0008] An environmental monitoring module, comprising a sensor network and an alarm and emergency processing unit. The sensor network includes, but is not limited to, water temperature, water quality, and dissolved oxygen sensors, which monitor the environmental parameters in the nursery pond in real time. When the environmental parameters exceed the set range, the alarm and emergency processing unit issues an alarm signal and triggers appropriate emergency response measures.

[0009] The remote control and information management module is equipped with a remote communication interface and an information management unit. The remote communication interface supports remote monitoring and operation of the system through mobile phones and computer terminal devices. The information management module records, counts and analyzes feeding and environmental data to provide decision support for breeding management.

[0010] Preferably, the intelligent recognition module uses a deep learning algorithm to accurately identify and analyze fry information to improve the accuracy and efficiency of recognition.

[0011] Preferably, the big data analysis unit uses machine learning, combined with a preset biological growth model and feeding strategy, to automatically calculate and adjust the optimal feeding amount to achieve precise feeding.

[0012] Preferably, the feeder of the precision feeding module is equipped with a metering system and a control system, which can accurately deliver feed to a designated area according to the feeding strategy provided by the data analysis and decision-making module, thereby achieving timed, quantitative and fixed-point feeding.

[0013] Preferably, the sensor network of the environmental monitoring module monitors the water temperature, water quality and dissolved oxygen environmental parameters in the nursery pond in real time. When the environmental parameters exceed the set range, the feeding strategy is automatically adjusted or an alarm signal is issued to ensure that the fry grow in the best growth environment.

[0014] Preferably, the remote communication interface of the remote control and information management module supports remote monitoring and operation of the system through mobile phones and computer terminal devices. Users can check the system operation status, adjust feeding parameters, and receive alarm information at any time. At the same time, the information management unit conducts in-depth analysis of the collected data to provide users with customized breeding suggestions and optimize breeding strategies.

[0015] The present invention provides a precise feeding control system for seafood seedlings. It has the following beneficial effects:

[0016] 1. The present invention uses a high-definition camera and a computer vision processing unit of the intelligent recognition module to adopt a deep learning algorithm to accurately identify key information such as the size, quantity and activity status of the fry. The big data analysis unit combines the growth stage, type and density factors of the fry, and uses machine learning technology and a preset biological growth model to accurately calculate the real-time feed demand of each region. The decision-making unit generates a precise feeding strategy based on this. The feeder of the precise feeding execution module implements timing, quantity and fixed-point feeding according to this strategy, effectively avoiding the problem of inaccurate feeding amount caused by experience judgment in traditional feeding methods, greatly reducing feed waste and significantly improving feed utilization. With the efficient use of feed, the fry can obtain a more suitable nutritional supply, grow faster, and improve the survival rate, thereby improving the overall breeding efficiency and bringing more substantial economic returns to the farmers.

[0017] 2. The sensor network of the environmental monitoring module of the present invention accurately and in real time monitors environmental parameters within the nursery pond. If any parameter exceeds a set range, the alarm and emergency response unit quickly issues an alarm signal and initiates appropriate emergency measures, such as automatically adjusting water temperature, operating water exchangers, and operating aerators, to quickly restore a suitable growth environment. This effectively reduces the risk of fish disease and mortality caused by environmental degradation, ensuring that the fish are always in an optimal growth environment, providing a solid foundation for their healthy growth and helping to maintain the stability and sustainability of aquaculture production.

[0018] 3. The remote communication interface of the remote control and information management module of the present invention supports remote monitoring and operation of terminal devices such as mobile phones and computers. No matter where the farmers are, they can check the system operation status, adjust feeding parameters, and receive alarm information at any time, which greatly improves the convenience and timeliness of breeding management. The information management unit comprehensively records, compiles statistics and conducts in-depth analysis of feeding and environmental data, uses data visualization technology to display data trends, and combines expert knowledge and industry experience to provide users with customized breeding suggestions. This information helps farmers accurately grasp the breeding dynamics and timely optimize breeding strategies, such as adjusting feeding plans, optimizing environmental control parameters, etc., to achieve scientific breeding management, further improve breeding efficiency and quality, and enhance market competitiveness.

[0019] 4. The present invention integrates functions such as intelligent identification, data analysis, precise feeding, environmental monitoring and remote management, and realizes the automation and intelligence of the seedling feeding process. Compared with traditional manual feeding and simple mechanical feeding equipment, the present invention significantly reduces the intensity of manual labor, reduces the input of human cost, and improves production efficiency and breeding quality. Its advantages in improving feed utilization, ensuring the growth environment of fry, and optimizing breeding decisions will help promote the transformation and upgrading of the aquaculture industry from traditional extensive to modern refined and intelligent directions. It is of great significance to the sustainable development of the entire seafood seedling breeding industry. While improving the economic benefits of the industry, it also promotes the practice of ecological and environmentally friendly breeding concepts. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a system block diagram of the present invention;

[0021] Figure 2 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0022] The following will clearly and completely describe the technical solution of the present invention in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0023] Please see the attached Figure 1 and attached Figure 2 The present invention provides a precision feeding control system for seafood seedlings. The system consists of an intelligent recognition module, a data analysis and decision-making module, a precision feeding execution module, an environmental monitoring module, and a remote control and information management module. These modules work together to form a closed-loop intelligent aquaculture control system.

[0024] Intelligent recognition module

[0025] High-definition camera: Choose a high-resolution camera with good low-light shooting performance and install it in a suitable position above the nursery pond to ensure that it can capture comprehensive and clear images of fry activities. The image acquisition frequency can be adjusted according to actual needs to ensure that the image information obtained is real-time and continuous.

[0026] Computer Vision Processing Unit: This unit uses advanced deep learning algorithms, such as object detection and recognition technology based on convolutional neural networks (CNNs), to process images captured by the camera. Trained with extensive labeled seafood fry image data, it can accurately identify the body contours of fry, precisely count their number, and analyze their activity status, such as swimming speed and activity level, providing reliable foundational data for subsequent analysis.

[0027] Data analysis and decision-making module

[0028] Data receiving unit: It has efficient data transmission and receiving capabilities, can quickly and stably receive the fry information transmitted by the intelligent identification module, and perform preliminary sorting and verification of the data to ensure the integrity and accuracy of the data.

[0029] The Big Data Analysis Unit has built a database containing extensive seafood fry growth data, including standard growth indicators and feed requirement curves for different fry species and stages. Using machine learning algorithms such as linear regression and decision trees, combined with pre-defined biological growth models and feeding strategies, this data is deeply mined and analyzed. Taking into account factors such as the fry's growth stage, species, and density, the unit dynamically calculates the real-time feed requirements for each area, ensuring that the feed rate meets the fry's growth needs while avoiding waste.

[0030] Decision-making Unit: Develops detailed feeding strategies based on the calculations from the Big Data Analysis Unit. Feeding times are accurately calculated down to the minute, tailored to the fry's diurnal activity patterns and digestive characteristics. Feeding amounts are precisely controlled based on real-time calculations, with minimal error. Feeding areas are precisely located based on the layout of the nursery pond and the distribution of fry, ensuring efficient feed utilization.

[0031] Precision feeding execution module

[0032] Feeders: Consisting of multiple feeders located at different locations in the nursery pond, their structural design ensures uniform and stable feed delivery. Equipped with a high-precision metering system, the feeders utilize technologies such as electronic scales and flow sensors to precisely control the amount of feed delivered each time. Furthermore, the control system responds quickly and accurately to instructions from the decision-making unit, enabling timed, quantitative, and targeted feeding.

[0033] Metering and control system: Real-time monitoring of the feeder's operating status, including motor speed, feed flow, valve opening and closing status and other parameters. Once an abnormality is detected, the alarm mechanism is immediately activated and corresponding protective measures are taken, such as stopping feeding and automatically adjusting equipment parameters, to ensure the safety, stability and accuracy of the feeding process.

[0034] Environmental monitoring module

[0035] Sensor Network: Water temperature and water quality sensors are strategically distributed throughout the nursery ponds. High-precision, high-reliability sensors enable real-time and accurate monitoring of environmental parameters within the ponds. The frequency of sensor data collection can be adjusted based on sensitivity to environmental changes, ensuring timely detection of environmental anomalies.

[0036] Alarm and Emergency Response Unit: Sets reasonable thresholds for various environmental parameters. When a monitored parameter exceeds the set range, it immediately issues an audible and visual alarm signal and transmits the alarm information to a remote terminal device via a wireless communication module. Simultaneously, based on the specific environmental anomaly, it automatically initiates appropriate emergency response measures, such as activating aerators, water exchangers, and water quality regulators, to quickly restore the nursery pond to a suitable environment and ensure a stable growth environment for the fry.

[0037] Remote control and information management module

[0038] Remote communication interface: Supports multiple mainstream communication protocols, such as Wi-Fi, 4G / 5G, ensuring stable connections between the system and terminal devices such as mobile phones and computers. Users can log in to the system anytime, anywhere through a specially developed mobile application (APP) or web platform for remote monitoring and operation.

[0039] The Information Management Unit comprehensively records, compiles, and analyzes feeding and environmental data generated during system operation. Data visualization techniques, such as charts and graphs, are used to visually display information such as fry growth trends, feed consumption, and environmental parameter changes, providing farmers with clear insights into the current state of the fish farming process. Furthermore, data analysis results, combined with expert knowledge and industry experience, provide users with customized farming recommendations, such as adjusting feeding strategies and optimizing environmental control parameters, helping them optimize management decisions and improve farming efficiency.

[0040] In this embodiment, after the system is started, the high-definition camera of the intelligent recognition module begins to collect real-time images of the fry in the nursery pond and transmits them to the computer vision processing unit for analysis and recognition. The computer vision processing unit transmits the extracted key information of the fry to the data receiving unit of the data analysis and decision-making module.

[0041] After the data receiving unit processes the data, the big data analysis unit combines the growth model and feeding strategy in the database to calculate the real-time feed demand of each area and pass the results to the decision-making unit. The decision-making unit generates a specific feeding strategy and sends it to the precision feeding execution module.

[0042] The feeder in the precision feeding execution module delivers feed according to the feeding strategy, while the metering and control system monitors the feeding process in real time to ensure the accuracy of feeding quantity and feeding location. Simultaneously, the sensor network in the environmental monitoring module continuously monitors environmental parameters within the nursery pond. If an anomaly is detected, the alarm and emergency response unit responds immediately to ensure a safe growth environment for the fry.

[0043] The remote control and information management module maintains a connection to the terminal device via a remote communication interface, allowing users to log in at any time to check operating status, adjust feeding parameters, or receive alarm messages. The information management unit continuously analyzes and processes data in the background, regularly providing users with farming reports and recommendations to help them optimize farming management.

[0044] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A precise feeding control system for seafood seedlings, characterized in that: include: An intelligent recognition module, comprising a high-definition camera for capturing real-time images of fry in the nursery pond and a computer vision processing unit for intelligently identifying and analyzing the images captured by the camera to extract key information such as the fry's size, number, and activity status; A data analysis and decision-making module comprises a data receiving unit, a big data analysis unit, and a decision-making unit. The data receiving unit receives the fry information transmitted by the intelligent recognition module. The big data analysis unit analyzes the received data and calculates the real-time feed demand of each area based on the growth stage, species, and density of the fry. The decision-making unit formulates a precise feeding strategy based on the analysis results, including but not limited to feeding time, feeding amount, and feeding area. A precision feeding execution module, which consists of multiple feeders that deliver precise feed based on the output of the decision-making unit and a metering and control system that ensures the correct amount of feed is delivered each time and monitors the operating status of the feeders. An environmental monitoring module, comprising a sensor network and an alarm and emergency processing unit. The sensor network includes, but is not limited to, water temperature, water quality, and dissolved oxygen sensors, which monitor the environmental parameters in the nursery pond in real time. When the environmental parameters exceed the set range, the alarm and emergency processing unit issues an alarm signal and triggers appropriate emergency response measures. The remote control and information management module is equipped with a remote communication interface and an information management unit. The remote communication interface supports remote monitoring and operation of the system through mobile phones and computer terminal devices. The information management module records, counts and analyzes feeding and environmental data to provide decision support for breeding management.

2. A seafood seedling precision feeding control system according to claim 1, characterized in that: The intelligent recognition module uses a deep learning algorithm to accurately identify and analyze fry information to improve the accuracy and efficiency of recognition.

3. A seafood seedling precision feeding control system according to claim 1, characterized in that: The big data analysis unit uses machine learning, combined with a preset biological growth model and feeding strategy, to automatically calculate and adjust the optimal feeding amount to achieve precise feeding.

4. A seafood seedling precision feeding control system according to claim 1, characterized in that: The feeder of the precision feeding module is equipped with a metering system and a control system, which can accurately deliver feed to a designated area according to the feeding strategy provided by the data analysis and decision-making module, thereby achieving regular, quantitative and fixed-point feeding.

5. A seafood seedling precision feeding control system according to claim 1, characterized in that: The sensor network of the environmental monitoring module monitors the water temperature, water quality and dissolved oxygen environmental parameters in the nursery pond in real time. When the environmental parameters exceed the set range, the feeding strategy is automatically adjusted or an alarm signal is issued to ensure that the fry grow in the best growth environment.

6. A seafood seedling precision feeding control system according to claim 1, characterized in that: The remote communication interface of the remote control and information management module supports remote monitoring and operation of the system through mobile phones and computer terminal devices. Users can check the system operation status, adjust feeding parameters, and receive alarm information at any time. At the same time, the information management unit conducts in-depth analysis of the collected data to provide users with customized breeding suggestions and optimize breeding strategies.

Images