A water quality monitoring and regulating system and method for abalone culture

Abstract

The application discloses a water quality monitoring and regulating system and method for abalone culture, and relates to the technical field of water quality monitoring and regulating; the application aims at the problems of poor real-time performance, low intelligent level, insufficient system adaptability and the like of the existing abalone culture water quality monitoring and regulating system; the application effectively solves the above problems by fusing a multi-parameter water quality sensor, cloud intelligent analysis modeling, an automatic control response mechanism and a green energy power supply system; the system has high-frequency and multi-dimensional data acquisition capability, realizes trend prediction and grade response branch control in combination with a cloud modeling algorithm, can actively trigger a linkage device to intervene when water quality data is abnormal, and improves the intelligent and response capabilities of the system; meanwhile, a solar energy + storage battery power supply mode is adopted, so that stable operation of the system in a bay or the like without commercial power is ensured; a graphic management interface and an early warning mechanism are matched, and the scientific nature and efficiency of culture management are significantly improved.

Description

Technical Field

[0001] This invention relates to the field of water quality monitoring and control technology, specifically to a water quality monitoring and control system and method for abalone farming. Background Technology

[0002] With the continuous development of aquaculture, abalone has become one of the key farmed species due to its high economic and nutritional value. However, abalone is extremely sensitive to water quality, and its growth, reproduction, and survival rate are significantly affected by various water quality parameters such as temperature, dissolved oxygen, pH, salinity, ammonia nitrogen, and flow rate. Traditional water quality monitoring methods rely heavily on manual sampling and testing, which is not only inefficient and lacks real-time performance but also makes it difficult to detect water quality anomalies in a timely manner, thus affecting the healthy growth of abalone and the profitability of aquaculture. Therefore, there is an urgent need for an integrated and intelligent water quality monitoring and control system that can collect, analyze, and control the parameters of the aquaculture water in real time, achieving dynamic management of water quality and thereby improving the scientific and automated level of abalone farming.

[0003] Existing water quality monitoring and control systems still have many shortcomings in practical abalone farming applications; they are difficult to achieve comprehensive perception and dynamic adjustment of the farming environment; the control system usually relies on manual operation and lacks an intelligent response mechanism that links with real-time data, making it difficult to respond to sudden environmental changes in a timely manner, which affects the health of abalone and farming yield. Summary of the Invention

[0004] The present invention addresses the problems mentioned in the background section by proposing a water quality monitoring and control system and method for abalone farming.

[0005] The objective of this invention can be achieved through the following technical solution: a water quality monitoring and control system for abalone farming, comprising: a control device and an analysis and control module;

[0006] The control device automatically adjusts the aquaculture environment based on water quality data feedback; after adjusting the aquaculture environment, the water quality data is re-detected, an analysis and control command is generated and sent to the analysis and control module;

[0007] The analysis and control module, upon receiving the analysis and control command, analyzes water quality data within the same water level to obtain instructions for adjusting cage depth, starting the aerator pump, and adjusting the feeding strategy; then, it substitutes the water quality data within the same water level into a preset model to analyze the interaction mechanism between water quality data to obtain an environmental cross-influence execution strategy; it combines the water quality data to conduct a comprehensive evaluation of the aquaculture environment, and obtains a comprehensive evaluation coefficient of the aquaculture environment through multivariate fusion modeling analysis; and it classifies the aquaculture environment level according to the comprehensive evaluation coefficient of the aquaculture environment.

[0008] Based on the comprehensive evaluation coefficient of the aquaculture environment and the execution strategy of cross-influence of the environment, the net cage depth control command, feed reduction control command, floating plant replenishment control command, feeding cessation control command and oxygenation control command are analyzed and output.

[0009] In a preferred embodiment of the present invention, the process by which the analysis and control module analyzes water quality data within the same water level is as follows:

[0010] Analyze water temperature, pH, dissolved oxygen, salinity, ammonia nitrogen, and flow velocity at the same water level:

[0011] The water temperature is compared with the set range of the optimal growth zone for abalone. If the temperature is not within the set range, the cage depth adjustment command is triggered.

[0012] Record the real-time pH value. When the pH value is less than 7.5 or greater than 8.5, generate a command indicating a risk of water quality deterioration and send it to the corresponding smart terminal for notification.

[0013] The dissolved oxygen concentration in the water is continuously monitored, and its correlation with time, temperature, and feeding activities is analyzed to obtain the oxygen consumption risk index. If the current dissolved oxygen concentration is lower than 5 mg / L or the oxygen consumption risk index is greater than or equal to 0.8, an instruction to start the oxygenation pump is generated.

[0014] The system continuously monitors the salinity of the water. If the salinity is greater than 35‰ or less than 27‰ within a fixed time period after real-time, it generates a command indicating an abnormal water salinity and sends it to the corresponding smart terminal for notification.

[0015] The correlation between ammonia nitrogen fluctuation trends and parameters such as feed amount and water exchange frequency is analyzed to obtain an ammonia nitrogen risk index. If the current ammonia nitrogen concentration is greater than 0.2 mg / L and continues to exceed the preset time threshold, or if the ammonia nitrogen risk index is greater than or equal to 0.7, an adjustment feeding strategy is generated.

[0016] Continuously monitor the water flow velocity V. If the current flow velocity is greater than 0.8 m / s or less than 0.01 m / s and the duration exceeds the preset time threshold or the flow velocity risk index is greater than or equal to 0.8, generate a cage depth adjustment strategy.

[0017] As a preferred embodiment of the present invention, the specific process of obtaining the environmental cross-influence execution strategy through the analysis of the interaction mechanism between water quality data is as follows:

[0018] S001: Obtain real-time water quality data stream and model the relationship between parameters; define the parameter vector at the current moment;

[0019] S002: Analyze the cross-influence between water quality data;

[0020] S201: Analysis of water temperature and dissolved oxygen: The relationship between water temperature and dissolved oxygen is obtained through a model;

[0021] S202: Analysis of the relationship between feeding amount and the increase in ammonia nitrogen and the decrease in dissolved oxygen: The relationship between feeding amount, ammonia nitrogen, and dissolved oxygen was obtained through modeling;

[0022] S203: Analysis of photosynthesis in relation to pH increase and dissolved oxygen decrease: If the daily pH change is small, photosynthesis is weak;

[0023] S204: Analysis of the increased sensitivity of salinity abrupt changes to all water quality data: if a rapid change in salinity leads to biological stress, increased respiration, decreased dissolved oxygen, and increased ammonia nitrogen;

[0024] S205: When dissolved oxygen is below the threshold, oxygenation measures will be automatically activated;

[0025] S206: Integrate the cross-influences between different water quality data to generate an environmental cross-influence execution strategy;

[0026] In a preferred embodiment of the present invention, the step of obtaining the comprehensive evaluation coefficient of the aquaculture environment through multivariate fusion modeling analysis specifically involves:

[0027] S301: Constructing a comprehensive evaluation model for water quality data fusion:

[0028] Input parameter vector: X = [T, pH, DO, S, NH3, V];

[0029] The target output is the comprehensive evaluation coefficient of the aquaculture environment: Score∈[0,1];

[0030] The weighted scoring model was chosen as the backbone model.

[0031] S302: Set the ideal range and weighting coefficients for each water quality data;

[0032] S303: Different normalization strategies are used to process water quality data; the normalization strategies include interval normalization and one-sided restriction normalization;

[0033] S304: The comprehensive evaluation coefficient of the aquaculture environment is obtained by calculating the comprehensive coefficient.

[0034] In a preferred embodiment of the present invention, the step of classifying the aquaculture environment level according to the comprehensive evaluation coefficient of the aquaculture environment is as follows:

[0035] If the comprehensive evaluation coefficient of the breeding environment is greater than or equal to 0.85, it is considered excellent; if the comprehensive evaluation coefficient of the breeding environment is greater than or equal to 0.70 and less than 0.85, it is considered good; if the comprehensive evaluation coefficient of the breeding environment is greater than or equal to 0.50 and less than 0.70, it is considered average; if the comprehensive evaluation coefficient of the breeding environment is less than 0.50, it is considered poor.

[0036] In a preferred embodiment of the present invention, the comprehensive evaluation coefficient of the aquaculture environment and the implementation strategy for the cross-influence of the environment are specifically as follows:

[0037] S401: Based on the comprehensive evaluation coefficient level of the aquaculture environment, proceed to different response branches:

[0038] If the comprehensive evaluation coefficient of the aquaculture environment is excellent, maintain the status quo and no intervention is required; if the comprehensive evaluation coefficient of the aquaculture environment is good, enter the mild intervention mode; if the comprehensive evaluation coefficient of the aquaculture environment is average, enter the moderate intervention mode and activate the cross-mechanism analysis; if the comprehensive evaluation coefficient of the aquaculture environment is poor, enter the strong intervention mode and activate the real-time linkage control system.

[0039] S402: Conduct linkage analysis of water quality data mechanisms:

[0040] S421: In terms of water temperature and dissolved oxygen, when the water temperature is greater than 22℃ and the dissolved oxygen is less than 5mg / L, a net cage depth control command is generated; the electric winch is started; the net cage is slowly moved down 0.5 to 2 meters, and then automatically stops and locks its position after reaching the layer; the changes in water temperature and dissolved oxygen during the descent are monitored in real time; the new depth, new water temperature, and new dissolved oxygen are recorded, and the trend of change is observed within 1 hour.

[0041] S422: When the amount of feed increases and the ammonia nitrogen increases while the dissolved oxygen decreases, a feed reduction control command is generated when the ammonia nitrogen is greater than 0.2 mg / L and the dissolved oxygen is less than 5 mg / L.

[0042] S423: When photosynthesis is insufficient and pH fluctuations are small, a floating plant control command is generated when the absolute pH value is less than 0.2 for consecutive days.

[0043] S424: When the sensitivity of salinity and water quality data increases, a stop-feeding control command is generated when the salinity is less than 27 or greater than 35 and the ammonia nitrogen or dissolved oxygen fluctuates drastically.

[0044] S425: In the linkage control of dissolved oxygen less than threshold, when dissolved oxygen is less than 5 mg / L, the dissolved oxygen level rises to the point where ammonia nitrogen toxicity increases to the point where feeding is inhibited, and the pH value decreases, an oxygenation control command is generated.

[0045] In a preferred embodiment of the present invention, the control device automatically adjusts the aquaculture environment based on water quality data feedback; specifically:

[0046] Receive commands for cage depth control, feeding reduction control, floating plant replenishment control, feeding stop control, and oxygenation control;

[0047] When a depth control command for the net cage is received, the electric winch or hydraulic lifting system is activated; the net cage is moved down 0.5 to 2 meters and then automatically stops and locks its position; the changes in water temperature and dissolved oxygen during the descent are monitored in real time; the new depth, new water temperature, and new dissolved oxygen are recorded, and the trend of change is observed within 1 hour;

[0048] When a feeding control command is received, control the feeding equipment to avoid feeding during periods of high temperature or low oxygen.

[0049] When a floating plant replenishment control command is received, the algae feeding device is controlled to add algae seed packets.

[0050] When a stop-feeding control command is received, feeding is temporarily stopped, and water dilution or freshwater injection is performed.

[0051] When an oxygenation control command is received, the oxygenation pump is automatically activated. If it is a zone management system, the oxygenation device in the target area is activated. Local high-efficiency oxygenation equipment is selected first, and the default start time is 30 minutes to 1 hour. Dissolved oxygen data is fed back every 10 minutes during this period. If the dissolved oxygen still does not recover to ≥6.0mg / L, the working cycle is automatically extended or the backup oxygenation equipment is activated.

[0052] Another aspect of the present invention provides a water quality monitoring and control method for abalone farming, the method comprising:

[0053] Step 1: Collect water quality data. After the data is processed by the embedded controller, it is remotely synchronized to the cloud.

[0054] Step 2: Compare and evaluate the collected data, set risk thresholds based on the ideal growth range of abalone, trigger an early warning when the threshold is exceeded, and suggest adjusting the cage depth, oxygenation, dilution, or optimizing the feeding strategy.

[0055] Step 3: Construct the interaction mechanism between water quality data to obtain the environmental cross-impact execution strategy;

[0056] Step 4: Normalize and weight the water quality data according to their ideal range and weight to obtain the comprehensive evaluation coefficient of the aquaculture environment, determine the water quality level, and guide the response strategy.

[0057] Step 5: Based on the correlation between the rating level and water quality data, control commands are automatically generated to realize actions such as adjusting the cage depth, intelligent feeding reduction, oxygenation activation, algae replenishment intervention, and active water quality regulation.

[0058] Compared with the prior art, the beneficial effects of the present invention are:

[0059] 1. This invention integrates multiple technologies such as multi-parameter sensing and monitoring, intelligent analysis and modeling, automatic control response, and green energy power supply. The system can collect water quality data such as water temperature, pH, dissolved oxygen, salinity, ammonia nitrogen, and flow rate in real time, and perform data modeling and trend prediction through cloud analysis modules to achieve accurate perception and dynamic adjustment of nitrogen in the aquaculture environment. According to environmental changes, the system can automatically adjust the cage depth, control oxygenation equipment, and optimize feeding strategies, which greatly improves the intelligence, automation, and risk resistance of abalone farming.

[0060] 2. This invention has significant advantages in real-time performance, intelligence, and system adaptability. By constructing a multivariate fusion model to comprehensively score the aquaculture environment and dividing it into graded response branches, it ensures rapid intervention by control equipment in abnormal situations. Simultaneously, the system uses a combination of solar energy and battery power to ensure stable operation in environments without mains power; coupled with a graphical interface and early warning mechanism, it provides scientific decision support for aquaculture managers, improving aquaculture efficiency and economic benefits. Attached Figure Description

[0061] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0062] Figure 1 This is a schematic diagram of the principle of the present invention;

[0063] Figure 2 This is a flowchart of the method steps of the present invention. Detailed Implementation

[0064] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. 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 of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0065] It should be understood that the terms “comprising” and “including” used in this disclosure and claims indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0066] It should also be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure. As used in this disclosure and claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this disclosure and claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations.

[0067] Please see Figure 1 As shown, the present invention provides a water quality monitoring and control system for abalone farming, comprising: a water quality monitoring device, a control device, an analysis and control module, and an energy supply module, which is suitable for abalone farming in a floating cage in a bay in a simulated ecological farming scenario.

[0068] The water quality monitoring device consists of multi-parameter water quality sensors that monitor water quality data including water temperature, pH value, dissolved oxygen, salinity, ammonia nitrogen, and flow rate. The sensor components are corrosion-resistant and can be used in long-term operation in seawater environments. The monitoring data is acquired and processed by an embedded acquisition controller (such as STM32 or ESP32), which supports wired (such as RS485) or wireless (such as LoRa, NB-IoT, Wi-Fi) transmission of data to a server or cloud platform to achieve remote real-time data synchronization.

[0069] The control device is used to automatically adjust the aquaculture environment based on water quality data feedback. Specifically, it includes: controlling the sampling depth of water quality sensors to monitor water quality at different water layers; adjusting the floating depth of the net cages and the abalone farming density to cope with changes in the marine environment; and controlling the start and stop of equipment such as aerators and water pumps based on dissolved oxygen concentration.

[0070] The analysis and control module is deployed on a cloud or local server for the storage, analysis, and modeling of water quality data. The system can present the changing trends of water quality data through a visual interface, and supports historical data comparison and anomaly detection. If an anomaly is detected, it will immediately issue an alert to the management personnel via SMS, APP, etc., so as to facilitate timely intervention and reduce aquaculture risks.

[0071] The energy supply module uses a combination of solar panels and batteries to ensure the system's continuous operation at sea or in areas without mains power; solar power provides power during the day and batteries replenish power at night, ensuring the system operates uninterruptedly around the clock and providing stable energy support for water quality monitoring and control.

[0072] The analysis and control module is deployed on a cloud platform or local server and undertakes the data processing and intelligent decision-making functions of the entire system. It mainly includes five sub-modules: data acquisition, storage, modeling, analysis and early warning.

[0073] The system can display the changing trends of water quality data (such as water temperature, pH value, dissolved oxygen, salinity, ammonia nitrogen, etc.) in real time through a graphical visual interface, and supports historical data backtracking and multi-time period comparison analysis to help managers judge the patterns of water quality changes and potential risks.

[0074] The specific water quality monitoring data analysis is as follows:

[0075] Water temperature, pH value, dissolved oxygen, salinity, and ammonia nitrogen were collected at the same water level.

[0076] Compare the water temperature with the optimal growth range for abalone (e.g., 16℃~22℃). If the temperature deviates from the set range, an early warning will be triggered and it will be recommended to adjust the cage depth or activate the water exchange mechanism.

[0077] Record real-time pH readings and combine them with daily variation curves to determine if there are any abnormal photosynthesis or ammonia nitrogen accumulation problems; when the pH value is less than 7.5 or greater than 8.5, generate a water quality deterioration risk command and send it to the corresponding smart terminal for prompting;

[0078] Continuously monitor dissolved oxygen concentration in the water and analyze its correlation with time, temperature, and feeding activities:

[0079] Divide the 24 hours into multiple time periods (such as early morning, morning, noon, afternoon, evening, and night), and statistically analyze the mean, minimum, and rate of change of dissolved oxygen concentration in each time period to identify the periodic pattern of daily changes in dissolved oxygen concentration; for example, early morning and noon are high-risk periods when dissolved oxygen is prone to decline.

[0080] By constructing temperature-dissolved oxygen scatter plots and fitting curves, the stability and rate of decrease of dissolved oxygen under different water temperatures (e.g., 15℃~35℃) were analyzed. It was determined that water temperature (e.g., greater than 30℃) usually leads to a faster decrease in dissolved oxygen, especially during the midday period when the temperature is high and the light is strong.

[0081] Record the specific time and amount of feed for each feeding, and use the sliding window analysis method to calculate the decrease in dissolved oxygen within 30 minutes after feeding to evaluate the impact of feeding on oxygen consumption; for example, if the average decrease in dissolved oxygen exceeds 1.5 mg / L after a large feeding, the time period is marked as a high-risk response period.

[0082] Based on the periodic patterns of daily variations in feed quantity, water temperature, and dissolved oxygen concentration, the oxygen consumption risk index under the current environment is calculated in real time using a model: The output oxygen consumption risk index DOFX ranges from 0 to 1, with a higher value indicating a greater risk of oxygen consumption.

[0083] Among them, F t F represents the current feeding amount.max T is the maximum amount of feed that the system is set to be given in a single feeding. t T represents the current water temperature. opt To achieve the optimal water temperature for aquaculture, T max The set critical high temperature value (e.g., 35℃), DOt is the current dissolved oxygen concentration, and D avg (t) represents the average dissolved oxygen concentration at the current time point in the past (reference value for daily variation); A1, A2, and A3 are weighting coefficients that satisfy A1+A2+A3=1, and can be optimized based on actual experience or training; for example: A1=0.4, A2=0.3, A3=0.3;

[0084] If the current dissolved oxygen concentration is below 5 mg / L or the oxygen consumption risk index is greater than or equal to 0.8, an instruction to start the oxygenation pump will be generated, and the event will be recorded as a reference for subsequent modeling and optimization.

[0085] The system continuously monitors the salinity of the water. If the salinity is greater than 35‰ or less than 27‰ within a fixed time period after real-time, it generates a command indicating an abnormal water salinity and sends it to the corresponding smart terminal for notification.

[0086] The correlation between ammonia nitrogen fluctuation trends and parameters such as feed amount and water exchange frequency was analyzed to construct a "farming activity-ammonia nitrogen response" model. In the model, abnormal increases in ammonia nitrogen concentration are usually related to high feed intensity, low water exchange rate, and temperature rise. The system utilizes multivariate correlation analysis and trend fitting algorithms to establish the following risk assessment mechanism:

[0087] Output Ammonia Nitrogen Risk Index (ARI); a higher value indicates a greater cumulative risk of ammonia nitrogen.

[0088] Among them, F avg The recommended daily feed amount corresponding to the set unit stocking density; W f This represents the current water exchange frequency; W opt The minimum reasonable water exchange frequency recommended by the system; NH base This represents the safe benchmark ammonia nitrogen concentration in aquaculture standards. B1, B2, and B3 are preset weighting coefficients, and the sum of B1, B2, and B3 equals 1 (e.g., B1 = 0.4, B2 = 0.3, B3 = 0.3; specific values ​​can be determined by technical personnel based on actual usage, such as through subjective assignment). If the current ammonia nitrogen concentration is greater than 0.2 mg / L and continues to exceed the preset time threshold (e.g., 6 hours) or the ammonia nitrogen risk index is greater than or equal to 0.7, an adjustment feeding strategy is generated. For example, the feeding amount is automatically reduced by 10% to 30% according to the current feeding plan, the main daily feeding time is adjusted to avoid high ammonia nitrogen periods, and the water exchange frequency is increased or the aeration / overflow device is turned on to accelerate ammonia nitrogen dilution.

[0089] Then, the collected parameters such as water temperature, pH, dissolved oxygen, salinity, ammonia nitrogen and flow rate are input into the preset model to analyze the interaction mechanism between water quality data, determine whether there are any abnormalities or imbalances, and then make an intelligent response.

[0090] Finally, a comprehensive evaluation of the aquaculture environment was conducted by combining water quality data, and the comprehensive evaluation coefficient of the aquaculture environment was obtained through multivariate fusion modeling analysis.

[0091] The specific process of the interaction mechanism between the analyzed water quality data is as follows:

[0092] S001: Model the relationship between real-time data stream and parameters; define the parameter vector at the current moment as:

[0093]

[0094] Where: T is water temperature, pH is water acidity / alkalinity, DO is dissolved oxygen, S is salinity, NH3 is ammonia nitrogen concentration, V is flow rate, F is feed amount, and A is aerator status.

[0095] S002: Analyze the cross-influence between water quality data;

[0096] S201: Analysis of water temperature → dissolved oxygen: Through the model: DO(t)=DO0-α×T(t) (it is found that the higher the water temperature, the lower the dissolved oxygen capacity of the water).

[0097] S202: Analysis of the feeding amount F → ammonia nitrogen (NH3↑) + dissolved oxygen (DO↓): using the model: NH3(t) = NH 3,0 +β×F(t)-λ×E(t), (The more feed is given, the more uneaten feed and excrement there is, and the ammonia nitrogen level rises);

[0098] This will also increase oxygen consumption: DO(t)=DO(t)-δ×F(t);

[0099] S203: Analysis of photosynthesis (daytime) → pH↑, DO↑: If the daily pH change is small, it may indicate weak photosynthesis (phytoplankton deficiency or pollution); Analysis model:

[0100]

[0101] S204: Analysis of sensitivity to salinity abrupt change S → ↑ of all water quality data: rapid salinity change → biological stress → increased respiration → decreased dissolved oxygen and increased ammonia nitrogen;

[0102] S205: When dissolved oxygen is < threshold, oxygenation measures will be automatically activated to alleviate other problems: low dissolved oxygen will exacerbate ammonia nitrogen toxicity and inhibit feeding → pH decreases and NH3 increases;

[0103] S206: Flow velocity (V) → Dissolved oxygen (DO) ↑ → Ammonia nitrogen (NH3) ↓ → pH fluctuation regulation → Water temperature (T) distribution evenness. Increased flow helps the water body fully exchange oxygen, alleviates local hypoxia, and improves the overall DO level; through dilution and substance diffusion, it reduces areas with high local ammonia nitrogen concentrations, slows down the ammonia nitrogen accumulation rate, and improves phytoplankton distribution and light uniformity, indirectly improving photosynthetic efficiency; it eliminates water layer temperature stratification, avoiding surface overheating or bottom hypoxia.

[0104] S207: Integrate the cross-influences between different water quality data to generate an environmental cross-influence execution strategy;

[0105] The comprehensive evaluation coefficient of the aquaculture environment obtained through multivariate fusion modeling analysis is as follows:

[0106] S301: Constructing a comprehensive evaluation model for water quality data fusion:

[0107] Define the input parameter vector: X = [T, pH, DO, S, NH3, V];

[0108] The target output is the comprehensive evaluation coefficient of the aquaculture environment: Score∈[0,1];

[0109] We choose a weighted scoring model as the backbone model; it can be further expanded to machine learning models (such as SVM, RandomForest) for training and optimization.

[0110] S302: Set the ideal range and weighting coefficients; it should be noted that the specific recommended weights are obtained from the mortality sensitivity of various water quality data of the abalone in the experiment, and the ideal range is set from the ideal growth environment of the corresponding species.

[0111] The reference ranges and recommended weights for each water quality data point are as follows:

[0112] Water quality data Ideal range Weight Water temperature T 16～22℃ 0.10 pH value 7.5～8.5 0.20 Dissolved oxygen (DO) ≥5mg / L 0.25 Salinity S 27～35‰ 0.15 <![CDATA[Ammonia nitrogen NH3]]> ≤0.2mg / L 0.25 Flow velocity V 5~15cm / 0.05

[0113] S303: Different normalization strategies are used for water quality data; the strategies include: interval normalization and lateral normalization;

[0114] Water temperature, pH, and salinity in the water quality data were normalized using interval-based methods.

[0115] Taking pH as an example, the ideal range is [L i U i = [7.5, 8.5]:

[0116]

[0117] Dissolved oxygen and ammonia nitrogen in water quality data were subjected to lateral normalization.

[0118] DO:

[0119]

[0120] NH2:

[0121]

[0122] S303: Comprehensive coefficient calculation; all normalized coefficients are denoted as Score. i The comprehensive evaluation coefficient of the aquaculture environment is:

[0123]

[0124] Among them, Score T Score DO Score S Score PH Score NH3 and Score V These are respectively denoted as Score1, Score2, Score3, Score4, Score5, and Score6;

[0125] S304: Based on the comprehensive evaluation coefficient (Score) of the aquaculture environment, the aquaculture environment is classified into different levels.

[0126] If Score ≥ 0.85 → Excellent: Suitable for aquaculture, the system maintains the status quo; if 0.70 ≤ Score < 0.85 → Good: Aquaculture can continue, but slight adjustments are recommended; if 0.50 ≤ Score < 0.70 → Average: Aquaculture risk increases, the system prompts caution; if Score < 0.50 → Poor: Water quality abnormalities exist, the system issues a high-level warning.

[0127] Then, based on the cross-influence between the final score and the water quality data, the data is fused to further infer and output control commands; specifically:

[0128] S401: Based on the score level, proceed to different response branches:

[0129] If the final score is excellent, maintain the status quo and no intervention is needed; if the final score is good, enter the mild intervention mode; if the final score is average, enter the moderate intervention mode and activate the cross-analysis mechanism; if the final score is poor, enter the strong intervention mode and activate the real-time linkage control system.

[0130] S402: Water Quality Data Linkage Analysis:

[0131] S421: Water temperature T → Dissolved oxygen DO. When T > 22℃ and DO < 5DO, generate a net cage depth control command; start the electric winch or hydraulic lifting system; slowly move the net cage down 0.5 to 2 meters, the specific depth is set according to the previous water profile monitoring data (e.g., the target is a water layer of 20 to 21℃); monitor the changes in water temperature and DO during the descent in real time; automatically stop and lock the position after reaching the predetermined target layer; record the new depth, new temperature, and new DO, and observe the trend of change within 1 hour;

[0132] S422: Feeding amount F → ammonia nitrogen (NH3) ↑, dissolved oxygen (DO) ↓. When NH3 > 0.2 and DO < 5DO, a feed reduction control command is generated; the system supports "intelligent selective feeding": controlling feeding equipment to avoid feeding during high temperature or low oxygen periods;

[0133] S423: Insufficient photosynthesis → small pH fluctuations; when ΔpH < 0.2 for consecutive days, generate a floating plant control command; control the algae feeding equipment to carefully add algae seed packets;

[0134] S424: Salinity mutation S → Water quality data sensitivity ↑. When S < 27 or S > 35, and NH3 or DO fluctuates drastically, a stop feeding control command is generated; feeding is temporarily stopped (e.g., stop feeding for 2 hours), and water dilution or freshwater injection is performed.

[0135] S425: DO < threshold (<5) → linkage control; when DO < 5 → NH3 toxicity ↑ → inhibits feeding → pH ↓, generate oxygenation control command; automatically activate oxygenation pump, if it is a zone management system, start oxygenation device in the target area (such as micro-nano oxygenation pump, air aeration system, waterwheel aerator, etc.); prioritize local high-efficiency oxygenation equipment, the default start time is 30 minutes to 1 hour, during which DO data feedback is performed every 10 minutes; if DO still does not recover to ≥6.0mg / L, automatically extend the working cycle or start the backup oxygenation equipment.

[0136] S426: Continuously monitor the water flow velocity V. If the current flow velocity is greater than 0.8 m / s or less than 0.01 m / s and the duration exceeds the preset time threshold or the flow velocity risk index is greater than or equal to 0.8, generate a cage depth adjustment strategy.

[0137] Please see Figure 2 As shown, another aspect of the present invention provides a water quality monitoring and control method for abalone farming, comprising:

[0138] Step 1: Real-time water quality data, including water temperature (T), pH value, dissolved oxygen (DO), salinity (S), ammonia nitrogen (NH3), and flow velocity (V), are collected by multi-parameter water quality sensors deployed in the floating cages in the bay. The sensors are corrosion-resistant and adapted to long-term operation in seawater. The data is collected and processed by an embedded acquisition controller and transmitted to a server or cloud platform via wired or wireless means (such as LoRa or NB-IoT) to achieve remote real-time data synchronization.

[0139] Step 2: The collected data is processed by the analysis and control module. Combined with the ideal growth environment of abalone, various water quality data are compared and analyzed, and risk thresholds are set for judgment: if T exceeds 16-22℃, pH is less than 7.5 or greater than 8.5, DO is less than 5mg / L, salinity is less than 27‰ or greater than 35‰, or NH3 is greater than 0.2mg / L, the corresponding risk warning will be triggered, and it will be recommended to adjust the cage depth, oxygenation, dilution, or feeding, so as to achieve the initial identification of water quality abnormalities.

[0140] Step 3: Based on the data collection and analysis, this method further constructs a model of the mutual influence between various water quality data: such as increased water temperature → decreased DO, increased feeding → increased NH3 and decreased DO, enhanced photosynthesis → increased pH and DO, and abrupt changes in salinity → increased sensitivity of water quality data; a time series relationship model based on the current parameter vector [X = T, pH, DO, S, NH3] and management behavior vectors (such as F = feeding amount, A = oxygenation status) is established to gain a deeper understanding of the water quality fluctuation mechanism and provide a decision-making basis for response control;

[0141] Step 4: By setting ideal ranges and weights for each water quality data point, normalization is applied followed by weighted calculation to obtain a comprehensive score for the aquaculture environment, Score ∈ [0,1]. Based on the score, the environment is classified into four levels: "Excellent," "Good," "Average," and "Poor," where Score ≥ 0.85 is considered Excellent, and Score < 0.50 is considered Poor. This score is used to determine the current state of the aquaculture water quality and provides a basis for subsequent control response selection. The scoring weights and algorithm performance can be continuously optimized using machine learning models.

[0142] Step 5: Based on the scoring level and parameter cross-influence model, the system automatically generates response control strategies and issues control commands, specifically including: controlling the cage to submerge when water temperature (T) is high and DO is low; adjusting the feeding plan when NH3 is high and DO is low; triggering algae replenishment measures when photosynthesis is abnormal; temporarily stopping feeding and performing water dilution when salinity changes abruptly; automatically starting the aeration equipment and dynamically adjusting its working duration when DO is below the set threshold; through linkage control, proactive intervention in water quality fluctuations is achieved to ensure the stability and efficiency of the abalone farming environment.

[0143] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A water quality monitoring and control system for abalone farming, comprising: The control device and analysis module are characterized by: The control device automatically adjusts the aquaculture environment based on water quality data feedback; after adjusting the aquaculture environment, the water quality data is re-detected, an analysis and control command is generated and sent to the analysis and control module; The analysis and control module, upon receiving the analysis and control command, analyzes water quality data within the same water level to obtain instructions for adjusting cage depth, starting the aerator pump, and adjusting the feeding strategy. The process of substituting the water quality data within the same water level into a preset model to analyze the interaction mechanism between water quality data is as follows: S001: Obtain real-time water quality data stream and model the parameter relationship; define the parameter vector at the current moment; S002: Analyze the cross-influence between water quality data; S201: Analyze water temperature and dissolved oxygen: obtain the relationship between water temperature and dissolved oxygen through the model; S202: Analyze the feeding amount and the increase in ammonia nitrogen and the decrease in dissolved oxygen: obtain the relationship between feeding amount and ammonia nitrogen and dissolved oxygen through the model. The relationship between dissolved oxygen, pH, and dissolved oxygen; S203: Analysis of photosynthesis and pH increase / dissolved oxygen decrease: if the daily pH change is small, photosynthesis is weak; S204: Analysis of salinity abrupt change and increased sensitivity of all water quality data: if salinity changes rapidly, leading to biological stress, increased respiration, decreased dissolved oxygen, and increased ammonia nitrogen; S205: When dissolved oxygen is below the threshold, oxygenation measures are automatically activated; S206: The cross-influence between different water quality data is integrated to generate an environmental cross-influence execution strategy; a comprehensive evaluation of the aquaculture environment is conducted based on water quality data, and a comprehensive evaluation coefficient of the aquaculture environment is obtained through multivariate fusion modeling analysis; the aquaculture environment is classified into levels based on the comprehensive evaluation coefficient of the aquaculture environment; Based on the comprehensive evaluation coefficient of the aquaculture environment and the execution strategy of cross-influence of the environment, the net cage depth control command, feed reduction control command, floating plant replenishment control command, feeding cessation control command and oxygenation control command are analyzed and output.

2. The water quality monitoring and control system for abalone farming according to claim 1, characterized in that, The process by which the analysis and control module analyzes water quality data within the same water level is as follows: Analyze water temperature, pH, dissolved oxygen, salinity, ammonia nitrogen, and flow velocity at the same water level: The water temperature is compared with the set range of the optimal growth zone for abalone. If the temperature is not within the set range, the cage depth adjustment command is triggered. Record the real-time pH value. When the pH value is less than 7.5 or greater than 8.5, generate a command indicating a risk of water quality deterioration and send it to the corresponding smart terminal for notification. The dissolved oxygen concentration in the water is continuously monitored, and its correlation with time, temperature, and feeding activities is analyzed to obtain the oxygen consumption risk index. If the current dissolved oxygen concentration is lower than 5 mg / L or the oxygen consumption risk index is greater than or equal to 0.8, an instruction to start the oxygenation pump is generated. The system continuously monitors the salinity of the water. If the salinity is greater than 35‰ or less than 27‰ within a fixed time period after real-time, it generates a command indicating an abnormal water salinity and sends it to the corresponding smart terminal for notification. The correlation between ammonia nitrogen fluctuation trends and parameters such as feed amount and water exchange frequency is analyzed to obtain an ammonia nitrogen risk index. If the current ammonia nitrogen concentration is greater than 0.2 mg / L and continues to exceed the preset time threshold, or if the ammonia nitrogen risk index is greater than or equal to 0.7, an adjustment feeding strategy is generated. Continuously monitor the water flow velocity V. If the current flow velocity is greater than 0.8 m / s or less than 0.01 m / s and the duration exceeds the preset time threshold or the flow velocity risk index is greater than or equal to 0.8, generate a cage depth adjustment strategy.

3. The water quality monitoring and control system for abalone farming according to claim 2, characterized in that, The comprehensive evaluation coefficient of the aquaculture environment obtained through multivariate fusion modeling analysis is as follows: S301: Constructing a comprehensive evaluation model for water quality data fusion: Input parameter vector: X=[T,pH,DO,S,NH3,V], where T is water temperature, pH is pH value, DO is dissolved oxygen, S is salinity, NH3 is ammonia nitrogen, and V is flow rate; The target output is the comprehensive evaluation coefficient of the aquaculture environment: Score∈[0,1]; Choose the weighted scoring model as the backbone model; S302: Set the ideal range and weighting coefficients for each water quality data; S303: Different normalization strategies are used to process water quality data; the normalization strategies include interval normalization and one-sided restriction normalization; S304: The comprehensive evaluation coefficient of the aquaculture environment is obtained by calculating the comprehensive coefficient.

4. The water quality monitoring and control system for abalone farming according to claim 3, characterized in that, The aquaculture environment is classified into different levels based on a comprehensive evaluation coefficient; specifically: If the comprehensive evaluation coefficient of the aquaculture environment is greater than or equal to 0.85, it is considered excellent; if the comprehensive evaluation coefficient of the aquaculture environment is greater than or equal to 0.70 and less than 0.85, it is considered good. If the comprehensive evaluation coefficient of the aquaculture environment is greater than or equal to but less than 0.70, it is considered average; if the comprehensive evaluation coefficient of the aquaculture environment is less than 0.50, it is considered poor.

5. A water quality monitoring and control system for abalone farming according to claim 4, characterized in that, The comprehensive evaluation coefficient of the aquaculture environment and the implementation strategy for the cross-influence of the environment are as follows: S401: Based on the comprehensive evaluation coefficient level of the aquaculture environment, proceed to different response branches: If the comprehensive evaluation coefficient of the aquaculture environment is excellent, maintain the status quo and no intervention is required; if the comprehensive evaluation coefficient of the aquaculture environment is good, enter the mild intervention mode; if the comprehensive evaluation coefficient of the aquaculture environment is average, enter the moderate intervention mode and activate the cross-mechanism analysis. If the comprehensive evaluation coefficient of the aquaculture environment is poor, the system will enter a strong intervention mode and activate the real-time linkage control system. S402: Conduct linkage analysis of water quality data mechanisms: S421: In terms of water temperature and dissolved oxygen, when the water temperature is greater than 22℃ and the dissolved oxygen is less than 5mg / L, a net cage depth control command is generated; the electric winch is started; the net cage is slowly moved down 0.5 to 2 meters, and then automatically stops and locks its position after reaching the layer; the changes in water temperature and dissolved oxygen during the descent are monitored in real time; the new depth, new water temperature, and new dissolved oxygen are recorded, and the trend of change is observed within 1 hour. S422: When the amount of feed increases and the ammonia nitrogen increases while the dissolved oxygen decreases, a feed reduction control command is generated when the ammonia nitrogen is greater than 0.2 mg / L and the dissolved oxygen is less than 5 mg / L. S423: In cases of insufficient photosynthesis and small pH fluctuations; When the absolute pH value is less than 0.2 for consecutive days, a re-floating plant control command is generated; S424: When the sensitivity of salinity and water quality data increases, a stop-feeding control command is generated when the salinity is less than 27 or greater than 35 and the ammonia nitrogen or dissolved oxygen fluctuates drastically. S425: In the linkage control of dissolved oxygen less than threshold, when dissolved oxygen is less than 5 mg / L, the dissolved oxygen level rises to the point where ammonia nitrogen toxicity increases to the point where feeding is inhibited, and the pH value decreases, an oxygenation control command is generated.

6. A water quality monitoring and control system for abalone farming according to claim 1, characterized in that, The control device automatically adjusts the aquaculture environment based on water quality data feedback; specifically: Receive commands for cage depth control, feeding reduction control, floating plant replenishment control, feeding stop control, and oxygenation control; When a depth control command for the net cage is received, the electric winch or hydraulic lifting system is activated; the net cage is moved down 0.5 to 2 meters and then automatically stops and locks its position; the changes in water temperature and dissolved oxygen during the descent are monitored in real time; the new depth, new water temperature, and new dissolved oxygen are recorded, and the trend of change is observed within 1 hour; When a feeding control command is received, control the feeding equipment to avoid feeding during periods of high temperature or low oxygen. When a floating plant replenishment control command is received, the algae feeding device is controlled to add algae seed packets. When a stop-feeding control command is received, feeding is temporarily stopped, and water dilution or freshwater injection is performed. When an oxygenation control command is received, the oxygenation pump is automatically activated. If it is a zone management system, the oxygenation device in the target area is activated. Local high-efficiency oxygenation equipment is selected first, and the default start time is 30 minutes to 1 hour. Dissolved oxygen data is fed back every 10 minutes during this period. If the dissolved oxygen still does not recover to ≥6.0mg / L, the working cycle is automatically extended or the backup oxygenation equipment is activated.

7. A method for water quality monitoring and control in abalone farming, characterized in that, The method, applied to the implementation of the water quality monitoring and control system for abalone farming as described in any one of claims 1-6, comprises: Step 1: Collect water quality data. After the data is processed by the embedded controller, it is remotely synchronized to the cloud. Step 2: Compare and evaluate the collected data, set risk thresholds based on the ideal growth range of abalone, trigger an early warning when the threshold is exceeded, and suggest adjusting the cage depth, oxygenation, dilution, or optimizing the feeding strategy. Step 3: Construct the interaction mechanism between water quality data to obtain the environmental cross-impact execution strategy; Step 4: Normalize and weight the water quality data according to their ideal range and weight to obtain the comprehensive evaluation coefficient of the aquaculture environment, determine the water quality level, and guide the response strategy. Step 5: Based on the correlation between the rating level and water quality data, control commands are automatically generated to realize actions such as adjusting the cage depth, intelligent feeding reduction, oxygenation activation, algae replenishment intervention, and active water quality regulation.

Images