Efficient and energy-saving recirculating aquaculture system

Abstract

The invention discloses an efficient and energy-saving circulating water culture system, and relates to the technical field of circulating water treatment. Aquatic products are cultured; the mechanical filtering module is used for removing large-particle solid wastes by using a mesh screen, a sedimentation tank or a cyclone separator; the biological filtration module is used for converting ammonia nitrogen into nitrate by utilizing a biological filter bed or a moving bed bioreactor; in the spirulina purification tank, spirulina is used for absorbing nitrate and phosphate in water; spirulina generates oxygen through photosynthesis, and the dissolved oxygen condition of the water body is increased.

Description

Technical Field

[0001] The present application relates to the technical field of circulating water treatment, and more specifically, to a highly efficient and energy-saving circulating water aquaculture system. Background Art

[0002] At present, recirculating aquaculture systems have involved a variety of advanced technologies to improve aquaculture efficiency, reduce energy consumption, and improve water quality management. Let's explore these existing technologies in detail: Mechanical filtration technology: drum filter, sand filter, microfiltration membrane; biological filtration technology, biofilter bed, moving bed biofilm reactor (MBBR), biofilter tower; these technologies together constitute the technical basis of modern recirculating aquaculture systems. Their integrated application has greatly improved aquaculture efficiency and environmental control capabilities.

[0003] However, these technologies still have some limitations: limited intelligence: although there are automatic control systems, most still rely on manual decision-making; the ecological cycle is incomplete and cannot achieve overall adaptive adjustment; existing technologies rely on mechanical aeration and consume a lot of energy.

[0004] In view of this, we propose a highly efficient and energy-saving recirculating aquaculture system. Summary of the invention

[0005] 1. Technical issues to be solved

[0006] The purpose of this application is to provide a highly efficient and energy-saving circulating aquaculture system to solve the technical problems raised in the above-mentioned background technology.

[0007] 2. Technical solution

[0008] The present application embodiment provides a highly efficient and energy-saving circulating aquaculture system, comprising:

[0009] Breeding pond module; used for breeding aquatic products;

[0010] Mechanical filtration modules: use screens, settling tanks or cyclones to remove large solid waste particles;

[0011] This step can reduce the burden on subsequent processing units and improve overall efficiency.

[0012] Biofiltration module: converts ammonia nitrogen into nitrate using a biofilter bed or moving bed bioreactor;

[0013] Spirulina purification pool: Use Spirulina to absorb nitrates and phosphates in the water; Spirulina produces oxygen through photosynthesis, increasing the dissolved oxygen level in the water.

[0014] As an optional solution of the technical solution of this application document,

[0015] Water quality monitoring and control module: Use online sensors to monitor data parameters in real time; automatically adjust the operating parameters of each processing unit according to the monitoring data;

[0016] The water quality monitoring and control module includes:

[0017] Online sensor module: used to monitor data parameters; the data parameters include water quality parameters, environmental parameters and biological parameters;

[0018] Machine learning module: Based on the optimal growth parameters and current farming quantity of different farming species, combined with real-time monitoring data parameters, machine learning algorithms are used to analyze and predict the trend of Spirulina biological parameters;

[0019] Regulation module; the regulation module includes a spirulina growth regulation module; the spirulina growth regulation module is used to regulate the amount of spirulina.

[0020] As an optional solution of the technical solution of this application document,

[0021] The online sensor module includes:

[0022] Water quality sensor: monitors water quality parameters; the water quality parameters include: pH value, dissolved oxygen, ammonia nitrogen, nitrate, phosphate

[0023] Environmental sensor: monitors environmental parameters, including water temperature, light intensity, and water level;

[0024] Biosensor: monitors biological parameters, the biological parameters include biological parameters of aquatic products and biological parameters of spirulina; the biological parameters of aquatic products include density and volume of farmed aquatic products; the biological parameters of spirulina include density of spirulina;

[0025] As an optional solution of the technical solution of this application document,

[0026] Machine learning module: A combination model of random forest and long short-term memory network:

[0027] The specific structure is:

[0028] Data input layer:

[0029] Water quality parameters, environmental parameters and biological parameters of aquatic products in the past N time steps,

[0030] Long Short-Term Memory Network Layer:

[0031] A multi-layer long short-term memory network is used to capture the long-term dependencies of time series; outputs predictions of water quality parameters, environmental parameters, and biological parameters of aquatic products for future time steps;

[0032] Random Forest Layer:

[0033] Input the water quality parameter prediction, environmental parameters and aquatic product biological parameters of the future time step and the real-time data of the current time step; use multiple decision trees for parallel processing; output the final Spirulina biological parameters and control measures;

[0034] Output layer: predict future Spirulina biological parameters and control measures.

[0035] As an optional solution of the technical solution of this application document, it is characterized by:

[0036] The training process of the random forest layer is:

[0037] Split the dataset of data parameters into training and test sets; use the training set to fit the model; use cross-validation to evaluate the performance of the random forest layer; adjust hyperparameters to optimize model performance; use the test set to evaluate the predictive accuracy of the random forest layer.

[0038] As an optional solution of the technical solution of this application document,

[0039] The Spirulina Growth Regulator Module includes:

[0040] Light regulation: According to the predicted biological parameters of Spirulina, the light intensity and time of the Spirulina culture pool are automatically adjusted to promote or inhibit the growth of Spirulina;

[0041] Nutrition supply: Automatically adjust the type and quantity of nutrients added to the Spirulina culture pool according to the biological parameters of Spirulina;

[0042] Temperature control: The temperature of the spirulina culture tank is adjusted through heating or cooling systems to maintain the best growth environment.

[0043] As an optional solution of the technical solution of this application document, it also includes:

[0044] Energy management module: monitors system energy consumption; optimizes energy usage and utilizes solar energy as system power.

[0045] As an optional solution of the technical solution of this application document, it also includes:

[0046] Water circulation management module: optimize water flow rate and circulation path to ensure uniform distribution and full contact; dynamically adjust the circulation ratio according to biological parameters.

[0047] As an optional solution of the technical solution of this application document, it also includes:

[0048] Emergency treatment module: set up additional activated carbon adsorption or ozone treatment to deal with sudden water quality problems.

[0049] 3. Beneficial effects

[0050] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0051] This application ensures comprehensive water purification through a combination of mechanical, biological and chemical methods; utilizes the biological characteristics of Spirulina to achieve the dual goals of water purification and resource recovery; uses water quality monitoring and control modules to achieve adaptive optimization of the system; machine learning algorithms can help achieve accurate prediction of the trends of Spirulina biological parameters, thereby achieving the purpose of regulating water quality and realizing intelligent management of the entire breeding system; this can not only improve the efficiency of water quality management, but also reduce risks, optimize resource utilization, and ultimately improve the output and quality of breeding.

[0052] In this application, the photosynthesis of Spirulina can produce oxygen, reducing the reliance on mechanical aeration, thereby reducing energy consumption. As a biological buffer system, Spirulina can absorb water quality fluctuations and improve the stability of the entire system; BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a schematic diagram of the structure disclosed in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0054] The present application is further described in detail below in conjunction with the accompanying drawings.

[0055] Reference Figure 1 , a highly efficient and energy-saving circulating aquaculture system, characterized by:

[0056] Breeding pond module; used for breeding aquatic products;

[0057] Mechanical filtration module: Use screens, sedimentation tanks or cyclones to remove large solid waste particles; it can also remove fine particles and dissolved organic matter from the water; this step can reduce the burden on subsequent treatment units and improve overall efficiency.

[0058] Biofiltration module: converts ammonia nitrogen into nitrate using a biofilter bed or moving bed bioreactor;

[0059] Spirulina purification pool: Use Spirulina to absorb nitrates and phosphates in the water; Spirulina produces oxygen through photosynthesis, increasing the dissolved oxygen level in the water.

[0060] further;

[0061] Water quality monitoring and control module: Use online sensors to monitor data parameters in real time; automatically adjust the operating parameters of each processing unit according to the monitoring data;

[0062] The water quality monitoring and control module includes:

[0063] Online sensor module: used to monitor data parameters; the data parameters include water quality parameters, environmental parameters and biological parameters;

[0064] Machine learning module: Based on the optimal growth parameters and current farming quantity of different farming species, combined with real-time monitoring data parameters, machine learning algorithms are used to analyze and predict the trend of Spirulina biological parameters;

[0065] Regulation module; the regulation module includes a spirulina growth regulation module; the spirulina growth regulation module is used to regulate the amount of spirulina.

[0066] further;

[0067] The online sensor module includes:

[0068] Water quality sensor: monitors water quality parameters; the water quality parameters include: pH value, dissolved oxygen, ammonia nitrogen, nitrate, phosphate

[0069] Environmental sensor: monitors environmental parameters, including water temperature, light intensity, and water level;

[0070] Biosensor: monitors biological parameters, the biological parameters include biological parameters of aquatic products and biological parameters of spirulina; the biological parameters of aquatic products include density and volume of farmed aquatic products; the biological parameters of spirulina include density of spirulina;

[0071] further;

[0072] Machine learning module: A combination model of random forest and long short-term memory network:

[0073] The specific structure is:

[0074] Data input layer:

[0075] Water quality parameters, environmental parameters and biological parameters of aquatic products in the past N time steps,

[0076] Long Short-Term Memory Network Layer:

[0077] A multi-layer long short-term memory network is used to capture the long-term dependencies of time series; outputs predictions of water quality parameters, environmental parameters, and biological parameters of aquatic products for future time steps;

[0078] Random Forest Layer:

[0079] Input the water quality parameter prediction, environmental parameters and aquatic product biological parameters of the future time step and the real-time data of the current time step; use multiple decision trees for parallel processing; output the final Spirulina biological parameters and control measures;

[0080] Output layer: predict future Spirulina biological parameters and control measures.

[0081] further;

[0082] The training process of the random forest layer is:

[0083] Split the dataset of data parameters into training and test sets; use the training set to fit the model; use cross-validation to evaluate the performance of the random forest layer; adjust hyperparameters to optimize model performance; use the test set to evaluate the predictive accuracy of the random forest layer.

[0084] Predicting Spirulina biological parameters and control measures by training machine learning algorithms;

[0085] 1. Data collection;

[0086] First, the system needs to collect a lot of historical data, including:

[0087] Water quality sensor: monitors water quality parameters; water quality parameters include: pH value, dissolved oxygen, ammonia nitrogen, nitrate, phosphate Environmental sensor: monitors environmental parameters, including water temperature, light intensity, and water level;

[0088] Biosensor: monitors biological parameters, including biological parameters of aquatic products and biological parameters of spirulina; biological parameters of aquatic products include density and volume of farmed aquatic products; biological parameters of spirulina include spirulina density;

[0089] 2. Data preprocessing;

[0090] The collected raw data needs to be cleaned and preprocessed: remove outliers and missing values; standardize / normalize feature engineering to create new relevant features;

[0091] 3. Choose a machine learning model

[0092] A combination model of random forest and long short-term memory network; suitable for predicting continuous time series data and handling complex relationships of multiple features;

[0093] 4. Model training;

[0094] The machine learning model training process includes the following steps:

[0095] Split the dataset into training and test sets; use the training set to fit the model; use cross-validation to evaluate model performance; adjust hyperparameters to optimize model performance;

[0096] 5. Model validation and optimization

[0097] Use the test set to evaluate the model's prediction accuracy; analyze the model's prediction errors to identify areas for improvement; you may need to try a different model or combine multiple models to improve prediction accuracy;

[0098] 6. Feature Importance Analysis

[0099] Analyzing which factors have the greatest impact on the changes in Spirulina biological parameters can help farmers better understand and manage the system.

[0100] 7. Continuous learning and updating

[0101] Models should be able to continuously learn from new data: regularly retrain models with newly collected data; implement online learning algorithms so that models can adjust in real time;

[0102] 8. Forecasting and early warning

[0103] The trained model can: predict the trend of Spirulina biological parameters in the future (such as within 24 hours); issue timely warnings when it is predicted that water quality may deteriorate; and provide optimization suggestions, such as adjusting Spirulina culture parameters or changing breeding strategies.

[0104] In this way, machine learning algorithms can help achieve accurate predictions of Spirulina biological parameter trends, thereby supporting the intelligent management of the entire aquaculture system. This can not only improve the efficiency of water quality management, but also reduce risks, optimize resource utilization, and ultimately improve the yield and quality of aquaculture.

[0105] As an optional solution of the technical solution of this application document,

[0106] The Spirulina Growth Regulator Module includes:

[0107] Light regulation: According to the predicted biological parameters of Spirulina, the light intensity and time of the Spirulina culture pool are automatically adjusted to promote or inhibit the growth of Spirulina;

[0108] Nutrition supply: Automatically adjust the type and quantity of nutrients added to the Spirulina culture pool according to the biological parameters of Spirulina;

[0109] Temperature control: The temperature of the spirulina culture tank is adjusted through heating or cooling systems to maintain the best growth environment.

[0110] Further; also including:

[0111] Energy management module: monitors system energy consumption; optimizes energy usage and utilizes solar energy as system power.

[0112] As an optional solution of the technical solution of this application document, it also includes:

[0113] Water circulation management module: optimize water flow rate and circulation path to ensure uniform distribution and full contact; dynamically adjust the circulation ratio according to biological parameters.

[0114] Further; also including:

[0115] Emergency treatment module: set up additional activated carbon adsorption or ozone treatment to deal with sudden water quality problems.

Claims

1. A highly efficient and energy-saving circulating water aquaculture system, Features: include: Breeding pond module; Used for breeding aquatic products; Mechanical filtration modules: Use screens, settling tanks or cyclones to remove large solid waste particles; Biofiltration module: converts ammonia nitrogen into nitrate using a biofilter bed or moving bed bioreactor; Spirulina purification pool: Use Spirulina to absorb nitrates and phosphates in the water; Spirulina produces oxygen through photosynthesis, increasing the dissolved oxygen content in the water.

2. The circulating aquaculture system according to claim 1, Features: Also includes: Water quality monitoring and control module: Use online sensors to monitor data parameters in real time; Automatically adjust the operating parameters of each processing unit according to the monitoring data; The water quality monitoring and control module includes: Online sensor module: used to monitor data parameters; the data parameters include water quality parameters, environmental parameters and biological parameters; Machine learning module: Based on the optimal growth parameters and current farming quantity of different farming species, combined with real-time monitoring data parameters, machine learning algorithms are used to analyze and predict the trend of Spirulina biological parameters; Regulation module; the regulation module includes a spirulina growth regulation module; the spirulina growth regulation module is used to regulate the amount of spirulina.

3. The circulating aquaculture system according to claim 2, Features: The online sensor module includes: Water quality sensor: monitors water quality parameters; the water quality parameters include: pH value, dissolved oxygen, ammonia nitrogen, nitrate, phosphate Environmental sensor: monitors environmental parameters, including water temperature, light intensity, and water level; Biosensor: monitors biological parameters, the biological parameters include aquatic product biological parameters and spirulina biological parameters; the aquatic product biological parameters include density and volume of farmed aquatic products; the spirulina biological parameters include spirulina density.

4. The circulating aquaculture system according to claim 2, Features: Machine learning module: A combination model of random forest and long short-term memory network: The specific structure is: Data input layer: Water quality parameters, environmental parameters and biological parameters of aquatic products in the past N time steps, Long Short-Term Memory Network Layer: A multi-layer long short-term memory network is used to capture the long-term dependencies of time series; outputs predictions of water quality parameters, environmental parameters, and biological parameters of aquatic products for future time steps; Random Forest Layer: Input the water quality parameter prediction, environmental parameters and aquatic product biological parameters of the future time step and the real-time data of the current time step; use multiple decision trees for parallel processing; output the final Spirulina biological parameters and control measures; Output layer: predict future Spirulina biological parameters and control measures.

5. According to the circulating aquaculture system described in claim 4, Features: The training process of the random forest layer is: Split the dataset of data parameters into training and test sets; use the training set to fit the model; use cross-validation to evaluate the performance of the random forest layer; adjust hyperparameters to optimize model performance; use the test set to evaluate the predictive accuracy of the random forest layer.

6. The circulating aquaculture system according to claim 2, Features: The Spirulina Growth Regulator Module includes: Light regulation: According to the predicted biological parameters of Spirulina, the light intensity and time of the Spirulina culture pool are automatically adjusted to promote or inhibit the growth of Spirulina; Nutrition supply: Automatically adjust the type and quantity of nutrients added to the Spirulina culture pool according to the biological parameters of Spirulina; Temperature control: The temperature of the spirulina culture tank is adjusted through heating or cooling systems to maintain the best growth environment.

7. The circulating aquaculture system according to claim 1, Features: Also includes: Energy management module: monitors system energy consumption; Optimize energy usage and use solar energy as system power.

8. The circulating aquaculture system according to claim 1, Features: Also includes: Water circulation management module: optimizes water flow rate and circulation path to ensure uniform distribution and full contact; Dynamically adjust the circulation ratio according to biological parameters.

9. The circulating aquaculture system according to claim 1, Features: Also includes: Emergency treatment module: set up additional activated carbon adsorption or ozone treatment to deal with sudden water quality problems.

Images