Intelligent circulating system for recirculating aquaculture

Abstract

The invention relates to the technical field of aquaculture, in particular to an intelligent circulating system for circulating aquaculture. According to the technical scheme, the system comprises a water quality monitoring module used for monitoring water quality parameters such as oxygen concentration, pH value, ammonia nitrogen concentration, temperature and salinity in a water body in real time, an intelligent control module used for controlling operation of equipment through a self-adaptive adjustment algorithm based on data monitored in real time, and an energy optimization module used for optimizing energy in combination with power consumption and electric power price of the equipment. The operation power and time of the equipment are dynamically adjusted through an intelligent scheduling algorithm, and the culture data analysis module collects culture environment and growth data and predicts water quality change, cultured organism growth conditions and possible abnormal fluctuation in real time. By introducing an intelligent control module, big data analysis, a machine learning algorithm and a multi-objective optimization model, the automation level, the energy-saving effect and the water quality control capability of the system are further improved, and finally efficient utilization of resources and minimization of the system cost are achieved.

Description

Technical Field

[0001] This invention relates to the field of aquaculture technology, and in particular to an intelligent recirculation system for recirculating aquaculture. Background Technology

[0002] Recirculating aquaculture systems (RAS) are a novel aquaculture model. Compared to traditional open aquaculture systems, RAS can effectively recover water resources from a body of water, maintaining stable and efficient water quality through filtration, treatment, and reuse, thus significantly reducing water consumption and environmental pollution. However, traditional RAS face several challenges:

[0003] Water quality control is challenging: various water quality indicators, such as temperature, pH, oxygen concentration, and ammonia nitrogen concentration, are affected by factors such as the aquaculture environment, stocking density, and feeding strategies. How to control water quality parameters in real time while ensuring the healthy growth of aquaculture organisms remains a pressing problem to be solved.

[0004] Energy efficiency and cost issues: Traditional recirculating aquaculture systems have low energy efficiency, especially in terms of equipment energy consumption, management, and maintenance. The long-term high-load operation of equipment such as pumps, aeration devices, and heating / cooling equipment leads to high system operating costs, especially when electricity market prices fluctuate significantly.

[0005] Low levels of automation and intelligence: Currently, most aquaculture systems still rely on manual intervention and monitoring, lacking efficient intelligent control methods, resulting in slow system response, delayed decision-making, and an inability to dynamically adjust equipment operating parameters and water quality control strategies based on real-time data.

[0006] Therefore, we propose an intelligent recirculation system for recirculating aquaculture to solve the existing problems. Summary of the Invention

[0007] The purpose of this invention is to address the problems existing in the background technology by proposing an intelligent recirculation system for recirculating aquaculture.

[0008] To achieve the above objectives, the present invention provides the following technical solution: an intelligent recirculation system for recirculating aquaculture, including a water quality monitoring module for real-time monitoring of various water quality parameters such as oxygen concentration, pH value, ammonia nitrogen concentration, temperature and salinity in the water, and transmitting the monitoring data in real time;

[0009] The intelligent control module, based on real-time monitoring data, uses an adaptive adjustment algorithm to control the operation of various devices such as water pumps, filters, aeration equipment, and dosing devices, ensuring that various water quality parameters in the water body are within the preset ideal range;

[0010] The energy optimization module combines the power consumption of the equipment with electricity market price information and uses intelligent scheduling algorithms to dynamically adjust the operating power and time of the equipment, thereby optimizing energy utilization and reducing energy consumption.

[0011] The aquaculture data analysis module collects aquaculture environment and growth data, and uses big data analysis and machine learning technology to predict water quality changes, aquaculture organism growth and possible abnormal fluctuations in real time, and provides decision support.

[0012] Preferably, the water quality monitoring module includes sensors for monitoring oxygen concentration, pH value, ammonia nitrogen concentration, temperature, and salinity in the water. The monitoring data is transmitted to the intelligent control module in real time via wireless or wired means, enabling the system to respond immediately when water quality changes. Through real-time monitoring and data transmission, the system can ensure rapid adjustment of water quality, thereby providing a stable and healthy growth environment for aquaculture organisms.

[0013] Preferably, the adaptive adjustment algorithm dynamically adjusts the operating status of each device in the system based on the real-time monitored water quality parameter error and its rate of change. Specifically, the control module automatically adjusts the working status of the device according to the water quality error, i.e., the difference between the water quality parameter and the target value, and the error change rate, i.e. the rate of water quality change, to ensure that the water quality is within the optimal range, thereby improving aquaculture efficiency and the accuracy of water quality management.

[0014] Preferably, the adjustment algorithm adopts a fuzzy control mechanism. Through fuzzy analysis of water quality errors and their rate of change, appropriate control parameters are calculated in real time, and the working intensity of the water pump is automatically adjusted, the output power of the aeration equipment is adjusted, the running time of the filter is increased or decreased, and the dosing frequency of the dosing device is adjusted. Through fuzzy control technology, the system can cope with complex nonlinear water quality changes and adjust the equipment operating status in real time, making the system more stable and reliable in the face of various changes. This fuzzy control mechanism can avoid the over-adjustment or under-adjustment phenomena that may occur in traditional control methods, thereby effectively ensuring water quality stability.

[0015] Preferably, the energy optimization module automatically schedules the switching time and workload of the equipment based on real-time electricity market price fluctuations to avoid peak electricity price periods, reduce the overall energy cost of the system, and optimize the operating efficiency of the equipment during off-peak periods, thereby reducing the total energy consumption of the equipment and saving breeding costs. In addition, it further optimizes the load distribution of the equipment by minimizing the total power consumption of the equipment by combining the power characteristics and operating time factors of the equipment.

[0016] Preferably, the aquaculture data analysis module uses big data analytics and machine learning technologies to analyze the aquaculture environment, the growth status of aquaculture organisms, and water quality trends. Based on historical and real-time data, the aquaculture data analysis module can predict future water quality changes in real time and detect abnormal fluctuations in water quality changes, such as a sudden increase in ammonia nitrogen concentration or a decrease in oxygen concentration, through machine learning algorithms. This allows for early warnings, reminding operators to take necessary measures to ensure the health and stability of the aquaculture environment. When water quality fluctuates, the system increases energy consumption to achieve precise regulation; while when water quality is stable, it further reduces power consumption by minimizing unnecessary equipment operation, thereby improving energy efficiency.

[0017] Preferably, the intelligent control module includes an integrated control unit that can adjust the operating parameters of the equipment in real time based on the data fed back by the water quality sensor, so as to optimize key water quality indicators such as oxygen concentration, pH value, ammonia nitrogen concentration, temperature and salinity in the water.

[0018] Preferably, the system further includes a data storage module for storing historical data during the aquaculture process, including water quality monitoring data, equipment operating status data, and energy consumption data, for subsequent analysis, optimization, and system maintenance. The system also includes a decision support module that combines water quality data, equipment load, energy consumption information, and electricity market prices during the aquaculture process to generate an optimal equipment scheduling plan and automatically execute the plan to ensure that operating costs are minimized while ensuring water quality.

[0019] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0020] Efficient water quality management: The system collects water quality data in real time and combines it with feedback information from water quality sensors to dynamically adjust water quality control parameters, ensuring that water quality remains stable within the ideal range. Through the automatic adjustment of the intelligent control module, the system can effectively avoid the impact of water quality fluctuations on the health of aquatic organisms and improve aquaculture efficiency. The combination of water quality optimization objective function and fuzzy PID control algorithm can accurately regulate changes in different water quality parameters, so that key water quality indicators in the water body can always be kept within the preset range, thereby reducing aquaculture losses caused by substandard water quality.

[0021] Optimized equipment scheduling and energy efficiency management: Through a decision support module, the system optimizes equipment operation scheduling based on water quality requirements and equipment load conditions. Especially when electricity prices fluctuate significantly, the system can prioritize equipment operation when prices are low, reducing energy consumption and operating costs. The equipment scheduling module, combined with big data analytics and machine learning, learns equipment operating patterns and energy efficiency data, automatically adjusting equipment operating times and workloads to achieve optimal energy efficiency. By minimizing unnecessary equipment power consumption, the system can significantly reduce energy costs.

[0022] The system's intelligence and automation levels are improved: Based on integrated sensors and monitoring equipment, the system collects various data on the breeding environment and equipment operation in real time. Combined with intelligent control algorithms, it can automatically analyze and make decisions. This intelligent and automated control method greatly reduces the need for manual intervention and improves the accuracy and flexibility of the breeding process.

[0023] Reduce system operating costs: Through intelligent scheduling and energy efficiency optimization, the system provided by this invention can minimize energy consumption, especially in the operation of high-energy-consuming equipment such as water pumps and aeration devices. Through reasonable scheduling and power allocation, it can reduce electricity and energy costs.

[0024] In summary, by introducing intelligent control modules, big data analysis, machine learning algorithms, and multi-objective optimization models, the system's automation level, energy-saving effect, and water quality control capabilities can be further improved, ultimately achieving efficient resource utilization and minimizing system costs. Attached Figure Description

[0025] Figure 1 This is a schematic diagram of the structure of the present invention; Detailed Implementation

[0026] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] Example 1

[0028] like Figure 1 As shown, the present invention proposes an intelligent recirculating aquaculture system, which includes the following steps:

[0029] Step 1: System Architecture and Module Design

[0030] The water quality monitoring module uses a sensor array to monitor various water quality parameters in the water body in real time, such as oxygen concentration, pH value, ammonia nitrogen concentration, temperature and salinity, and transmits the monitoring data in real time.

[0031] The intelligent control module, based on real-time monitoring data, uses an adaptive adjustment algorithm to control the operation of various devices such as water pumps, filters, aeration equipment, and dosing devices, ensuring that various water quality parameters in the water body are within the preset ideal range;

[0032] The energy optimization module combines the power consumption of the equipment with electricity market price information and uses intelligent scheduling algorithms to dynamically adjust the operating power and time of the equipment, thereby optimizing energy utilization and reducing energy consumption.

[0033] The aquaculture data analysis module collects aquaculture environment and growth data, and uses big data analysis and machine learning technology to predict water quality changes, aquaculture organism growth and possible abnormal fluctuations in real time, and provides decision support.

[0034] Step Two: Water Quality Monitoring and Intelligent Control

[0035] The water quality monitoring module includes sensors for monitoring oxygen concentration, pH value, ammonia nitrogen concentration, temperature, and salinity in the water. The monitoring data is transmitted to the intelligent control module in real time via wireless or wired means, enabling the system to respond immediately when water quality changes. Through real-time monitoring and data transmission, the system can ensure rapid adjustment of water quality, thereby providing a stable and healthy growth environment for aquaculture organisms.

[0036] It collects key parameters in the water body in real time and defines the range of variation for each parameter: oxygen concentration should be maintained between 6-8 mg / L, pH value should be between 7.5-8.5, ammonia nitrogen concentration should be less than 0.5 mg / L, temperature should be maintained between 18℃-28℃, and salinity should be close to 0.

[0037] The adaptive adjustment algorithm dynamically adjusts the operating status of various devices in the system based on real-time monitoring of water quality parameter errors and their rates of change. Specifically, the control module automatically adjusts the operating status of the equipment according to the difference between the water quality error (i.e., the difference between the water quality parameter and the target value) and the rate of error change (i.e., the rate of water quality change), ensuring that the water quality is within the optimal range, thereby improving aquaculture efficiency and the accuracy of water quality management. The adjustment algorithm adopts a fuzzy control mechanism. Through fuzzy analysis of water quality errors and their rates of change, it calculates appropriate control parameters in real time and automatically adjusts the working intensity of the water pump, the output power of the aeration equipment, the running time of the filter, and the dosing frequency of the dosing device. Through fuzzy control technology, the system can cope with complex nonlinear water quality changes and adjust the operating status of the equipment in real time, making the system more stable and reliable in the face of various changes. This fuzzy control mechanism can avoid over-adjustment or under-adjustment phenomena that may occur in traditional control methods, thereby effectively ensuring water quality stability. Based on real-time monitoring data, the control system not only uses the conventional PID algorithm for adjustment but also adopts an adaptive fuzzy control mechanism to automatically adjust the PID parameters according to different water quality fluctuations, thereby achieving more precise control. We introduce a fuzzy PID control model, specifically represented as follows:

[0038]

[0039] in:

[0040] u(t) represents the control output (pump speed, aeration equipment output power, filter running time, and dosing frequency of the dosing device);

[0041] e(t) is the error between the expected water quality parameter and the actual measured water quality parameter;

[0042] K p K i K d These are proportional, integral, and differential gains, respectively.

[0043] To address system nonlinear fluctuations, the three gain parameters of the PID controller are adjusted in real time using a fuzzy controller, with the following adjustment rules:

[0044] K p (t)=μ p (e(t),Δe(t))

[0045] K i (t)=μ i (e(t),∫e(t)dt)

[0046] K d (t)=μ d (e(t),Δe(t))

[0047] Where, μ p μ i μ d These are adjustment functions output by the fuzzy logic controller, which adjust the PID gain based on the error e(t) and its rate of change or integral.

[0048] The control strategy uses a fuzzy logic algorithm to dynamically adjust the PID parameters according to the actual situation, ensuring that the system can maintain stable water quality even under unstable conditions.

[0049] Most importantly, the oxygen concentration in the water is affected by the metabolism of cultured organisms, aeration equipment, temperature, and salinity. We introduce a kinetic model to describe the changes in oxygen concentration, considering the effects of temperature and the consumption of oxygen by the metabolic activities of organisms, as shown below:

[0050]

[0051] in:

[0052] R a (T) represents the rate at which oxygen is introduced by the aeration equipment, taking into account the effect of temperature T on oxygen dissolution. This term can be expressed by an empirical formula:

[0053] R a (T)=R a (25)·(1+α(R-25))

[0054] Where α is the empirical coefficient for the effect of temperature on dissolved oxygen, T is the current water temperature, and R... a (25) is the dissolved oxygen rate at 25℃;

[0055] R b (DO,T,S) is the rate of oxygen consumption by biological metabolism, which depends on oxygen concentration, temperature, and salinity (S).

[0056]

[0057] Where K1 and K2 are constants, and β and γ are the influence coefficients of temperature and salinity;

[0058] k w It is the oxygen transfer coefficient in water;

[0059] V is the volume of the water body;

[0060] DO ambient It refers to the oxygen concentration in the environment.

[0061] Step 3: Energy Optimization and Intelligent Dispatch

[0062] The energy optimization module automatically schedules equipment switching times and workloads based on real-time electricity market price fluctuations to avoid peak electricity price periods, thereby reducing overall system energy costs. It also optimizes equipment operating efficiency during off-peak hours, reducing total energy consumption and saving on breeding costs. Furthermore, it combines equipment power characteristics and operating time factors to further optimize equipment load distribution by minimizing the objective function of total equipment power consumption.

[0063] Assuming that the power consumption of each device in the system has a non-linear relationship with the load L, it can be expressed by the following polynomial:

[0064]

[0065] in,

[0066] P i This is the power consumption of the i-th device;

[0067] L i This refers to the load on the equipment (pump speed, aeration equipment output power, filter operating time, and dosing frequency of the dosing device);

[0068] a i b i c i These are the parameters to be adjusted.

[0069] During the dispatching process, fluctuations in electricity market prices affect the system's energy costs. To rationally schedule equipment operating times, we need to express this using the following cost function:

[0070]

[0071] Among them, C i (t) is the unit power cost of the i-th device, which depends not only on the power consumption of the device itself, but also on the fluctuation of the market electricity price P. market (t) Related:

[0072] C i (t)=c i ·(1+α·P market (t))

[0073] Among them, C i α is the basic power cost of the equipment, and α is the sensitivity coefficient of cost to fluctuations in the electricity market.

[0074] In optimal scheduling, it is assumed that the runtime of each device is limited, and the goal is to minimize overall energy consumption. The objective function of scheduling can be expressed in the following form:

[0075]

[0076] Among them, T i Let be the running time of the i-th device, and the goal is to minimize the total operating cost by adjusting the operating time and power of each device.

[0077] Step Four: Big Data and Machine Learning

[0078] The aquaculture data analysis module utilizes big data analytics and machine learning technologies to analyze the aquaculture environment, the growth status of aquatic organisms, and water quality trends. Based on historical and real-time data, the module can predict future water quality changes in real time and detect abnormal fluctuations in water quality through machine learning algorithms, such as sudden increases in ammonia nitrogen concentration or decreases in oxygen concentration. This allows for early warnings, reminding operators to take necessary measures to ensure a healthy and stable aquaculture environment. When water quality fluctuates, the system increases energy consumption for precise regulation; conversely, when water quality is stable, it reduces unnecessary equipment operation to further decrease power consumption, thereby improving energy efficiency.

[0079] Machine learning algorithms, such as support vector machines, are used to predict trends in water quality changes. A time series prediction model based on historical data is established:

[0080] y t = f(x1,x2,…,x) n )+∈ t

[0081] in:

[0082] y t These are the predicted water quality parameters (oxygen concentration, pH value, ammonia nitrogen concentration, temperature, and salinity) at time t.

[0083] x1,x2,…,x n It is a characteristic of historical data, containing water quality data from several past time points;

[0084] f(x1,x2,…,x n The prediction function is trained based on historical data.

[0085] ∈ t It is the prediction error.

[0086] By combining changes in multiple water quality parameters, a predictive model can be generated that can detect potential abnormal fluctuations in real time.

[0087] Simultaneously, by incorporating information from multiple factors such as water quality changes, equipment operation, and market prices, this system designs a multi-objective optimization model to support aquaculture decision-making. The objective function of this model is:

[0088] min x (α·f cost (x)+β·f quality (x)+γ·f energy (x))

[0089] in:

[0090] f cost (x) is the objective function related to breeding costs;

[0091] f quality (x) is the objective function related to water quality;

[0092] f energy (x) is the objective function related to energy consumption;

[0093] α, β, γ are the weighting coefficients for each objective.

[0094] This optimization model takes into account factors such as cost, water quality, and energy efficiency to generate the optimal aquaculture decision.

[0095] The intelligent control module includes a comprehensive control unit that can adjust the equipment's operating parameters in real time based on data from water quality sensors to optimize key water quality indicators such as oxygen concentration, pH value, ammonia nitrogen concentration, temperature, and salinity. The system also includes a data storage module for storing historical data during the aquaculture process, including water quality monitoring data, equipment operating status data, and energy consumption data, for subsequent analysis, optimization, and system maintenance. The system also includes a decision support module that combines water quality data, equipment load, energy consumption information, and electricity market prices during the aquaculture process to generate an optimal equipment scheduling plan and automatically execute the plan to minimize operating costs while ensuring water quality.

[0096] The above specific embodiments are merely several preferred embodiments of the present invention. Based on the technical solutions of the present invention and the relevant teachings of the above embodiments, those skilled in the art can make various alternative improvements and combinations to the above specific embodiments.

[0097] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, it is intended that all variations falling within the meaning and scope of equivalents of the claims be included within the present invention.

Claims

1. A recirculating aquaculture intelligent circulation system, characterized in that, include: The water quality monitoring module is used to monitor various water quality parameters such as oxygen concentration, pH value, ammonia nitrogen concentration, temperature and salinity in the water in real time, and transmit the monitoring data in real time. The intelligent control module, based on real-time monitoring data, uses an adaptive adjustment algorithm to control the operation of various devices such as water pumps, filters, aeration equipment, and dosing devices, ensuring that various water quality parameters in the water body are within the preset ideal range; The energy optimization module combines the power consumption of the equipment with electricity market price information and uses intelligent scheduling algorithms to dynamically adjust the operating power and time of the equipment, thereby optimizing energy utilization and reducing energy consumption. The aquaculture data analysis module collects aquaculture environment and growth data, and uses big data analysis and machine learning technology to predict water quality changes, aquaculture organism growth and possible abnormal fluctuations in real time, and provides decision support.

2. The intelligent recirculating aquaculture system according to claim 1, characterized in that: The water quality monitoring module includes sensors for monitoring oxygen concentration, pH value, ammonia nitrogen concentration, temperature, and salinity in the water. The monitoring data is transmitted to the intelligent control module in real time via wireless or wired means, enabling the system to respond immediately when water quality changes. Through real-time monitoring and data transmission, the system can ensure rapid adjustment of water quality, thereby providing a stable and healthy growth environment for aquaculture organisms.

3. The intelligent recirculating aquaculture system according to claim 1, characterized in that: The adaptive adjustment algorithm dynamically adjusts the operating status of each device in the system based on the real-time monitoring of water quality parameter errors and their rate of change. Specifically, the control module automatically adjusts the working status of the equipment according to the water quality error, i.e., the difference between the water quality parameters and the target value, and the error change rate, i.e. the rate of water quality change, to ensure that the water quality is within the optimal range, thereby improving aquaculture efficiency and the accuracy of water quality management.

4. The intelligent recirculating system for recirculating aquaculture as described in claim 3, characterized in that: The adjustment algorithm adopts a fuzzy control mechanism. Through fuzzy analysis of water quality errors and their rate of change, it calculates appropriate control parameters in real time and automatically adjusts the working intensity of the water pump, adjusts the output power of the aeration equipment, increases or decreases the running time of the filter, and adjusts the dosing frequency of the dosing device.

5. The intelligent recirculating aquaculture system according to claim 1, characterized in that: The energy optimization module automatically schedules the switching time and workload of equipment based on real-time electricity market price fluctuations to avoid peak electricity price periods, reduce overall system energy costs, and optimize equipment operating efficiency during off-peak periods, thereby reducing total energy consumption and saving breeding costs. In addition, it further optimizes the load distribution of equipment by minimizing the total power consumption of the equipment by combining the power characteristics and operating time factors of the equipment.

6. The intelligent recirculating system for recirculating aquaculture as described in claim 1, characterized in that: The aquaculture data analysis module uses big data analytics and machine learning technologies to analyze the aquaculture environment, the growth status of aquaculture organisms, and water quality trends. Based on historical and real-time data, the module can predict future water quality changes in real time and detect abnormal fluctuations in water quality through machine learning algorithms, thereby issuing early warnings to remind operators to take necessary measures to ensure the health and stability of the aquaculture environment.

7. The intelligent recirculating system for recirculating aquaculture as described in claim 1, characterized in that: The intelligent control module includes a comprehensive control unit that can adjust the operating parameters of the equipment in real time based on data fed back from the water quality sensor, so as to optimize key water quality indicators such as oxygen concentration, pH value, ammonia nitrogen concentration, temperature and salinity in the water.

8. The intelligent recirculating system for recirculating aquaculture as described in claim 1, characterized in that: The system also includes a data storage module for storing historical data during the aquaculture process, including water quality monitoring data, equipment operating status data, and energy consumption data, for subsequent analysis, optimization, and system maintenance. The system also includes a decision support module that combines water quality data, equipment load, energy consumption information, and electricity market prices during the aquaculture process to generate an optimal equipment scheduling plan and automatically execute the plan to ensure that operating costs are minimized while maintaining water quality.

Images