Water quality and feeding linkage management method and system based on Internet of Things

Abstract

The invention provides a water quality and feeding linkage management method and system based on the Internet of Things, and relates to the technical field of feeding management, and the method comprises the steps: deploying a sensor, and collecting water quality data; a water quality and feeding linkage model is constructed based on the water quality data, and the feeding amount is dynamically adjusted; feeding the feed based on the feeding amount, and optimizing the feeding amount according to real-time feedback; establishing a water quality abnormity monitoring model, and monitoring water quality data; if the water quality is abnormal, starting an adjusting mechanism; water quality data and feeding amount are remotely monitored, trend analysis is performed based on historical data, and automatic decision making is realized through an intelligent algorithm.

Description

Technical Field

[0001] The present application relates to the field of feeding management technology, and in particular to a water quality and feeding linkage management method and system based on the Internet of Things. Background Art

[0002] At present, with the rapid development of aquaculture, water quality and feeding management have become key factors affecting aquaculture results and production benefits. Water quality is directly related to the healthy growth of fish, while the control of feeding amount affects the feeding rate and feed utilization rate of fish. In traditional aquaculture, water quality monitoring and feeding control often rely on manual operation, which makes it difficult to achieve accurate and efficient management. At the same time, due to the complex relationship between water quality and feeding, simple empirical feeding methods are difficult to cope with the problem of unstable aquaculture environment caused by water quality changes. Especially in large-scale aquaculture environments, water quality fluctuations and improper feeding amount control often lead to water pollution, fish stress response and loss of economic benefits.

[0003] The rapid development of Internet of Things technology has provided new solutions for aquaculture. Through the Internet of Things sensor nodes, real-time monitoring of water quality can be achieved, and intelligent feeding can be achieved in combination with automated equipment. However, most of the current Internet of Things applications focus on single water quality monitoring or feeding management, lacking an effective water quality and feeding linkage management mechanism, resulting in insufficient precision in water quality control and feeding optimization during the aquaculture process, and the inability to achieve dynamic adjustment. Therefore, it is urgent to develop a method for linkage management of water quality and feeding. Summary of the invention

[0004] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Description of the Invention section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0005] In the first aspect, the present application proposes a water quality and feeding linkage management method based on the Internet of Things, including:

[0006] Deploy sensors to collect water quality data;

[0007] Build a water quality and feeding linkage model based on water quality data to dynamically adjust the feeding amount;

[0008] Feed is placed based on the feeding amount, and the feeding amount is optimized according to real-time feedback;

[0009] Establish a water quality abnormality monitoring model to monitor water quality data; if the water quality is abnormal, activate the adjustment mechanism;

[0010] Remotely monitor water quality data and feeding amounts, perform trend analysis based on historical data, and make automated decisions through intelligent algorithms.

[0011] In a feasible implementation, sensors are deployed to collect water quality data, including:

[0012] Set N monitoring points in the water body, at each monitoring point N i Sensors are installed on the ground; the data of each monitoring point P i (t) is expressed as a time series:

[0013]

[0014] in, is the dissolved oxygen concentration at the ith monitoring point; is the dissolved oxygen concentration at the ith monitoring point; pH i (t) is the pH value of the ith monitoring point; T i (t) is the water temperature at the i-th monitoring point;

[0015] The data of all monitoring points are summarized into the water quality parameter matrix P(t), which is expressed as:

[0016]

[0017] For each parameter P i (t), its original data By calibration factor C i Converted to real value, expressed as:

[0018]

[0019] Among them, C i is the calibration factor based on laboratory measurements and adjustment for equipment errors;

[0020] All parameters were normalized and the normal range of each parameter was set. i，min , P i，max ], normalize it to the interval [0,1], expressed as:

[0021]

[0022] The normalized parameter matrix is:

[0023]

[0024] In a feasible implementation, a water quality and feeding linkage model is constructed based on water quality data to dynamically adjust the feeding amount, including:

[0025] Dynamic calculation of feeding amount T according to water quality changes w(t), the formula of the linkage model is expressed as:

[0026]

[0027] Among them, T w (t) is the feeding amount at time t; α is the dissolved oxygen regulation factor; β1 is the ammonia nitrogen regulation factor; β2 is the water temperature regulation factor; γ is the feeding rate regulation factor; F rate (t) is the fish feeding rate;

[0028] The nonlinear coupling relationship between dissolved oxygen and ammonia nitrogen is:

[0029]

[0030] in, is the initial dissolved oxygen concentration; k1 and k2 are coupling coefficients;

[0031] The pH value is adjusted according to the change of dissolved oxygen through a logarithmic function, expressed as:

[0032]

[0033] Among them, pH0 is the initial pH value; k3 is the coupling coefficient of pH and dissolved oxygen.

[0034] In a feasible implementation, the dynamic adjustment factors α, β1, β2, and γ are determined based on the following formula:

[0035]

[0036] Among them, θ1 is the adjustment sensitivity; is the threshold value of dissolved oxygen;

[0037]

[0038] Among them, θ2 is the inhibitory effect of controlling ammonia nitrogen on the feeding amount; is the safety threshold of ammonia nitrogen;

[0039] β2=(1+θ3·|T(t)-T opt |) -1

[0040] Among them, θ3 is the sensitivity parameter of the water temperature adjustment factor; T opt For the best water temperature;

[0041]

[0042] Among them, θ4 is the regulatory sensitivity for controlling the feeding rate; is the average feeding rate of fish.

[0043] In a feasible implementation, feed is delivered based on the feeding amount, and the feeding amount is optimized according to real-time feedback, including:

[0044] Construct a variable feedback control model to monitor the changes in water quality and the feeding behavior of fish in real time during the feeding process, and dynamically adjust the feeding amount. The feedback control formula is:

[0045]

[0046] Among them, F adj (t) is the feeding amount after feedback adjustment; T w (t) is the calculated initial feeding amount; ΔP(t) = P(t) - P0(t), which represents the difference between the current water quality parameter P(t) and the initial water quality parameter P0(t); P max is the maximum amplitude of water quality fluctuation allowed; ζ is the feeding behavior feedback coefficient; C feed (t) is the fish feeding rate monitored in real time;

[0047] Through the camera and image recognition technology, the feeding behavior of the fish school is monitored in real time, and the feeding rate C of the fish school is calculated. feed (t):

[0048]

[0049] Among them, C feed (t) is the feeding rate of the fish school; N f is the number of fish in the feeding area; A I (t) is the feeding activity of the first fish during the feeding process; A total (t) is the total fish activity in the camera coverage area;

[0050] The intelligent feeding machine can accurately deliver feed according to the feeding amount F adj (t) Control the release rate of feed R feed (t), expressed as:

[0051] R feed (t) = η·F adj (t)

[0052] Among them, R feed (t) represents the release rate of feed; η is the conversion coefficient of the feeding machine.

[0053] In a feasible implementation, a water quality abnormality monitoring model is established to monitor water quality data, including:

[0054] The detection formula for abnormal water quality is:

[0055]

[0056] Among them, E(t) is the abnormal monitoring function; P i (t) is the real-time parameter of water quality; is the safety threshold of each water quality parameter; δ is the preset abnormality detection threshold, when E(t)>δ, it is considered abnormal.

[0057] In one feasible implementation, water quality data and feeding amount are remotely monitored, trend analysis is performed based on historical data, and automated decision making is achieved through intelligent algorithms, including:

[0058] The real-time data P(t), feeding amount F adj (t) and water purification equipment operation data Q clean (t) Data storage, the data storage format is:

[0059] S total (t)=[P(t),T w (t), F adj (t), Q clean (t), E(t)]

[0060] Where P(t) is the water quality parameter at a certain time; T w (t) is the initial feeding amount; F adj (t) is the actual feeding amount after feedback adjustment; Q clean (t) is the operating intensity of the purification equipment; E(t) is the monitoring value of the abnormal degree of water quality;

[0061] Based on S total (t) to fit the water quality parameters P(t) at future times and adjust the feeding strategy T w (t), analyze the historical trend of water quality parameter P(t), the expression is:

[0062]

[0063] in, is to predict the water quality parameters at the future time t+n; φ1, φ2 are autoregressive coefficients; θ1, θ2 are moving average coefficients; ∈(t) is the noise term at time t;

[0064] The formula for adjusting the feeding amount is:

[0065]

[0066] Automated decision-making is achieved through the linkage algorithm. The linkage algorithm uses a reinforcement learning model to train the optimal strategy through multiple feeding-feedback cycles. The optimization objective function is:

[0067]

[0068] Among them, J(π) is the long-term return of the strategy; strategy π is a decision rule; is the mathematical expectation symbol; r t is the reward function for each time step;

[0069] Reward function r t It is expressed as:

[0070] r t =-(|T w (t)-F adj (t)|+ω1·|E(t)|+ω2·Q clean (t))

[0071] Among them, ω1 and ω2 are weight coefficients, which respectively measure the negative impact of abnormal water quality and purification equipment operation on the system; |T w (t)-F adj (t)| is the deviation of feeding amount.

[0072] In the second aspect, the present application proposes a water quality and feeding linkage management device based on the Internet of Things, including:

[0073] A deployment unit, used to deploy sensors and collect water quality data;

[0074] The adjustment unit is used to build a water quality and feeding linkage model based on water quality data and dynamically adjust the feeding amount;

[0075] An optimization unit is used to place feed based on the feeding amount and optimize the feeding amount according to real-time feedback;

[0076] Establish a unit for establishing a water quality abnormality monitoring model and monitoring water quality data; if the water quality is abnormal, the adjustment mechanism is activated;

[0077] The decision-making unit is used to remotely monitor water quality data and feeding amounts, conduct trend analysis based on historical data, and achieve automated decision-making through intelligent algorithms.

[0078] In a third aspect, an electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to implement the steps of the water quality and feeding linkage management method based on the Internet of Things as described in any one of claims 1 to 7 when executing the computer program stored in the memory.

[0079] In a fourth aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the water quality and feeding linkage management method based on the Internet of Things as described in any one of claims 1-7 is implemented.

[0080] In summary, the present invention monitors multiple key water quality parameters (such as dissolved oxygen, ammonia nitrogen, pH value and water temperature) in the water body in real time by deploying Internet of Things sensors, and calibrates and normalizes the data through intelligent algorithms to ensure the accuracy and real-time nature of the monitoring data; dynamically adjusts the feeding amount based on water quality monitoring data and fish feeding behavior. The linkage algorithm can automatically calculate the optimal feeding amount according to the changes in water quality and fish feeding rate, avoiding water quality deterioration due to excessive feeding or affecting fish growth due to insufficient feeding; through the trend analysis of the remote monitoring system and historical data, the system can autonomously adjust the feeding strategy and dynamically optimize it in combination with real-time feedback. At the same time, using the linkage algorithm trained by the reinforcement learning model, the system can make automatic decisions over a long period of time, improve management efficiency, and reduce manual intervention; when the water quality is abnormal, the system can adjust the feeding amount in time and start the water purification equipment to avoid water quality deterioration. At the same time, the dynamic control mechanism of the feeding amount and purification equipment can reduce feed waste and energy consumption and improve breeding efficiency.

[0081] The water quality and feeding linkage management method based on the Internet of Things proposed by the present invention, other advantages, objectives and features of the present invention will be reflected in part through the following description, and in part will be understood by technical personnel in the field through research and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0083] Figure 1 This is a flow chart of the water quality and feeding linkage management method based on the Internet of Things in this application;

[0084] Figure 2 This is a schematic diagram of the water quality and feeding linkage management structure based on the Internet of Things in this application;

[0085] Figure 3 This is a schematic diagram of the water quality and feeding linkage management electronic device based on the Internet of Things in this application. DETAILED DESCRIPTION

[0086] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0087] See also Figure 1 , which is a flow chart of the water quality and feeding linkage management method based on the Internet of Things provided in the embodiment of the present application, which may specifically include:

[0088] S110, deploy sensors to collect water quality data;

[0089] For example, in step S110, multiple water quality parameters are monitored by IoT sensor nodes, including dissolved oxygen (DO), ammonia nitrogen concentration (NH4 + ), pH value and water temperature (Temp), which will be used as input for subsequent calculations to adjust the feeding strategy.

[0090] The sensor layout and data collection process are as follows:

[0091] Set N monitoring points in the water body, at each monitoring point N i Different types of sensors are installed on the surface. The acquisition frequency of each sensor is f i (Unit: seconds -1 ) are set based on how quickly a specific parameter changes; for example, dissolved oxygen requires frequent monitoring, while ammonia may be monitored less frequently.

[0092] The data P of each monitoring point i (t) can be expressed as a set of dynamically changing time series:

[0093]

[0094] in, is the dissolved oxygen concentration at the ith monitoring point, changing with time t; is the dissolved oxygen concentration at the ith monitoring point; pH i(t) is the pH value of the ith monitoring point; T i (t) is the water temperature at the i-th monitoring point.

[0095] The data of all monitoring points are summarized into the total water quality parameter matrix P(t), which is expressed as:

[0096]

[0097] Since the data collected by the sensor may be interfered by environmental factors, we need to calibrate and normalize the data. i (t), its original data By calibration factor C i Converted to real value, expressed as:

[0098]

[0099] Among them, C i is the calibration factor based on laboratory measurements and adjustment for equipment errors.

[0100] All parameters were normalized and the normal range of each parameter was set. i，min , P i，max ], normalize it to the interval [0,1], expressed as:

[0101]

[0102] The normalized parameter matrix is:

[0103]

[0104] S120, build a water quality and feeding linkage model based on water quality data, and dynamically adjust the feeding amount;

[0105] Exemplarily, in step S110, multi-parameter water quality data P(t), including the dynamic evolution of dissolved oxygen, ammonia nitrogen concentration, pH value and water temperature, are collected through the Internet of Things node; step S120 dynamically adjusts the feeding strategy based on these water quality data, combined with fish feeding behavior and biofeedback model.

[0106] The linkage between water quality and feeding is not only affected by the current water quality, but also needs to consider historical feeding behavior and fish health status. Therefore, this step introduces a complex linkage model that dynamically calculates the feeding amount T according to changes in water quality. w (t).

[0107] The core formula of the linkage model is as follows:

[0108]

[0109] Among them, T w (t) is the feeding amount at time t; α is the dissolved oxygen regulation factor; β1 is the ammonia nitrogen regulation factor; β2 is the water temperature regulation factor; γ is the feeding rate regulation factor; F rate (t) is the fish feeding rate, which is calculated based on historical data and water quality dynamics.

[0110] The relationship between dissolved oxygen, ammonia nitrogen, pH and water temperature is not just a linear one, but coupled through nonlinear functions. The complex nonlinear coupling relationship between dissolved oxygen and ammonia nitrogen is:

[0111]

[0112] in, is the initial dissolved oxygen concentration; k1 and k2 are coupling coefficients, which control the attenuation rate of ammonia nitrogen to dissolved oxygen.

[0113] The pH value is adjusted according to the change of dissolved oxygen through a logarithmic function, expressed as:

[0114]

[0115] Among them, pH0 is the initial pH value; k3 is the coupling coefficient of pH and dissolved oxygen.

[0116] These nonlinear relationships reflect the complex dynamic interactions of water quality parameters, ensuring that feeding strategies can be flexibly adapted to varying water conditions.

[0117] In the above linkage formula, α, β1, β2, and γ are dynamic adjustment factors. In order to make the model more flexible, it is necessary to adjust it according to the real-time monitoring of water quality and fish status. The specific adjustment formula is as follows:

[0118]

[0119] Among them, θ1 is the adjustment sensitivity; It is the threshold of dissolved oxygen. When the dissolved oxygen is lower than this value, the system will reduce the feeding amount.

[0120]

[0121] Among them, θ2 is the inhibitory effect of controlling ammonia nitrogen on the feeding amount; is the safety threshold of ammonia nitrogen.

[0122] β2=(1+θ3·|T(t)-T opt |) -1

[0123] Among them, θ3 is the sensitivity parameter of the water temperature adjustment factor; T opt This is the optimal water temperature. When the temperature exceeds this range, the system will automatically reduce the feeding amount.

[0124]

[0125] Among them, θ4 is the regulatory sensitivity for controlling the feeding rate; is the average feeding rate of fish.

[0126] The above formula describes the linkage mechanism between water quality and feeding:

[0127] The complex coupling relationship between dissolved oxygen, ammonia nitrogen and pH is expressed through exponential and logarithmic functions, ensuring that the model can accurately capture the impact of water quality changes on fish health.

[0128] Through dynamic adjustment factors, the system can flexibly respond to different water quality conditions and adjust the feeding amount in real time.

[0129] S130, feeding is performed based on the feeding amount, and the feeding amount is optimized according to real-time feedback;

[0130] For example, in step S120, the feeding amount T is obtained by the water quality and feeding linkage algorithm. w (t). However, the actual feeding process not only needs to consider the initial feeding amount, but also needs to make dynamic feedback adjustments during the feeding process based on the real-time feeding behavior of fish monitored by the camera, water quality changes, feed consumption and other factors. Therefore, the core of step S130 is to feed through the intelligent feeding machine and continuously optimize the feeding strategy based on real-time feedback.

[0131] In this step, the system will use a multivariable feedback control model to monitor the changes in water quality and the feeding behavior of fish in real time during the feeding process, and dynamically adjust the feeding amount accordingly. The feedback control formula is:

[0132]

[0133] Among them, F adj (t) is the feeding amount after feedback adjustment; T w (t) is the initial feeding amount calculated in step S2; ΔP(t) = P(t) - P0(t), which represents the difference between the current water quality parameter P(t) and the initial water quality parameter P0(t); P max is the maximum amplitude of water quality fluctuation allowed, which is used to limit the impact of excessive feeding on water quality; ζ is the feeding behavior feedback coefficient; C feed (t) is the fish feeding rate monitored in real time by cameras and other equipment.

[0134] Feeding behavior feedback: The system uses cameras and image recognition technology to monitor the feeding behavior of fish in real time. The image data captured by the camera will be used to calculate the feeding rate of the fish through the following model: feed (t):

[0135]

[0136] In the formula, C feed (t) is the feeding rate of the fish school; N f is the number of fish in the feeding area; A I (t) is the feeding activity of the first fish during the feeding process; A total (t) is the total fish activity in the camera coverage area. feed (t) is incorporated into the feedback control equation, helping the system to increase the amount of feed when the fish are actively feeding and reduce the amount of feed when feeding activity decreases.

[0137] The system uses an intelligent feeder to accurately deliver feed. The feeder adjusts the feed amount F in real time. adj (t) Control the release rate of feed R feed (t), expressed as:

[0138] R feed (t) = η·F addj (t)

[0139] Among them, R feed (t) represents the release rate of feed (unit: g / s); η is the conversion coefficient of the feeding machine, which represents the conversion relationship between the feeding amount and the actual feed release rate.

[0140] Through the above formula and model, step S130 realizes dynamic feedback control of the feeding process:

[0141] Feeding behavior feedback: monitor the real-time feeding situation of fish through cameras, and use feeding activity to adjust the feeding amount to ensure that the feeding amount can match the actual needs of fish.

[0142] Water quality feedback: Based on the real-time monitoring of the rate of change of water quality, the system can prevent excessive feeding amounts from having a negative impact on water quality, and reduce the feeding amount in time to maintain water quality balance.

[0143] Intelligent feeder control, based on feeding adjustment amount E adj (t), the intelligent feeding machine can accurately control the feed release rate to avoid feed waste and water pollution.

[0144] The dynamic feedback control mechanism provides the system with high-precision feeding management capabilities, combining the dual feedback of feeding behavior and water quality to ensure efficient and stable aquaculture.

[0145] S140, establish a water quality abnormality monitoring model to monitor water quality data; if the water quality is abnormal, activate the adjustment mechanism;

[0146] For example, in step S130, the feeding amount is adjusted by real-time feedback control. However, the water quality may fluctuate abnormally during the feeding process, which requires the system to monitor in real time and automatically adjust the feeding strategy when necessary, or even trigger the water purification equipment.

[0147] The core of step S140 is to establish a water quality abnormality monitoring model. When the water quality parameters exceed the safety threshold, the system automatically responds and restores the water quality by reducing the feeding amount or starting the purification equipment.

[0148] When any water quality parameter exceeds the safe range, the system will regard it as abnormal water quality and activate the adjustment mechanism.

[0149] The detection formula for abnormal water quality is:

[0150]

[0151] Among them, E(t) is the abnormal monitoring function, which represents the comprehensive abnormal degree of water quality at the current moment; P i (t) is the real-time parameter of water quality; is the safety threshold of each water quality parameter; δ is the preset abnormality detection threshold, when E(t)>δ, it is considered abnormal.

[0152] When abnormal water quality is detected, the system will take corresponding measures according to the different types of abnormalities. The adjustment mechanism can be divided into the following aspects:

[0153] (1) Reduce the amount of feeding:

[0154] If the water quality is slightly abnormal, the system will first reduce the feeding amount to prevent the water quality from further deteriorating. The formula for adjusting the feeding amount is:

[0155]

[0156] Among them, F adj (t) is the adjusted feeding amount; Δ max This is the maximum abnormal range allowed by the system to ensure that the feeding amount will not drop below zero.

[0157] (2) Start water purification equipment:

[0158] When the water quality is seriously abnormal (E(t)>>δ), the system will automatically start the water purification equipment. The operating intensity of the purification equipment is proportional to the degree of water quality abnormality:

[0159] Q clean (t) = λ·E(t)

[0160] Among them, Q clean (t) is the operating intensity of the purification equipment (such as the amount of filtered water or the power of the oxygenation equipment); Q clean(t) is the adjustment coefficient of the purification equipment.

[0161] Through the above formula and model, step S140 realizes the function of abnormal water quality monitoring and automatic adjustment:

[0162] Abnormal water quality monitoring: Through the abnormal detection formula E(t) of comprehensive water quality parameters, the system can accurately capture water quality fluctuations and take corresponding measures in a timely manner.

[0163] Automatic adjustment mechanism: When abnormal water quality is detected, the system first relieves water quality pressure by reducing the feeding amount, and if necessary, starts the purification equipment to restore water quality.

[0164] S150, remotely monitors water quality data and feeding amount, conducts trend analysis based on historical data, and realizes automated decision-making through intelligent algorithms.

[0165] For example, in step S150, the system realizes remote management and control of water quality and feeding linkage through the Internet of Things platform. The core content of this step includes: remote monitoring of water quality and feeding status, trend analysis and optimization based on historical data, and automatic decision-making through intelligent algorithms. This content ensures that the system can optimize management autonomously without human intervention, and provides a remote control interface for managers to view and adjust breeding strategies in real time.

[0166] The system will collect all the real-time monitoring data P(t), feeding amount F adj (t) and water purification equipment operation data Q clean (t) The system is integrated into the central control system through the Internet of Things platform and provided to managers for remote access. The data in the system is stored in a time series to record the historical conditions of water quality and feeding process for trend analysis and optimization.

[0167] The data storage format is:

[0168] S total (t)=[P(r),T w (t),F adj (t),Q clean (t),E(t)]

[0169] Where P(t) is the water quality parameter at a certain time; T w (t) is the initial feeding amount; F adj (t) is the actual feeding amount after feedback adjustment; Q clean (t) is the operating intensity of the purification equipment; E(t) is the monitoring value of the abnormal degree of water quality.

[0170] The system can not only remotely monitor real-time data, but also perform trend analysis and forecasting through historical data. Using time series analysis algorithms, the system can identify water quality and feeding patterns, and predict future water quality conditions and feeding needs.

[0171] Specifically, the system will use S total (t) historical data (t = t0, t1, ..., t n ) to fit the water quality parameters P(t) at future moments, and adjust the feeding strategy T based on these prediction results w (t).

[0172] The autoregressive moving average model (ARIMA) is used to analyze the historical trend of water quality parameter P(t), and the expression is:

[0173]

[0174] in, is the water quality parameter predicted at the future time t+n; is the historical water quality data at time t, taken from S total (t); φ1 and φ2 are autoregressive coefficients, which are estimated by fitting historical data; θ1 and θ2 are moving average coefficients, which capture the noise in water quality data; ∈(t) is the noise term at time t, which reflects unpredictable external interference.

[0175] This model is based on S total (t) to fit the future water quality trend. Once the system predicts the future water quality parameters It will be used to adjust future feeding strategies. For example, if the predicted dissolved oxygen O2(t+n) is below a certain threshold The system will reduce the future feeding amount T in advance w (t+n) to avoid further deterioration of water quality.

[0176] The adjustment formula is:

[0177]

[0178] If the system predicts the degree of water quality abnormality in the future If the set threshold is exceeded, the system can also start the purification equipment in advance. clean (t+n) to reduce the impact of water quality deterioration.

[0179] By S total (t) The system can comprehensively analyze the complex relationship between feeding amount, purification equipment operation, and water quality changes, and apply trend analysis through the following process:

[0180] For example, from S total(t) Extract water quality parameters, feeding amount and purification equipment data; use S total (t) to train the ARIMA model with historical data to fit the future trend of water quality parameters; the water quality parameters at the future time t+n are predicted by the trained ARIMA model Dynamically adjust future feeding strategies based on predicted water quality parameters T w (t+n) and the operating intensity Q of the purification equipment clean (t+n).

[0181] The system achieves automated decision-making through linkage algorithms, integrating the previous water quality monitoring, feeding behavior feedback and water quality purification adjustments, and can automatically optimize the feeding amount and water quality adjustment measures. The linkage automated decision-making algorithm uses a reinforcement learning model (such as Q-Learning) to train the optimal strategy through multiple feeding-feedback cycles.

[0182] The optimization objective function is:

[0183]

[0184] Among them, J(π) is the long-term benefit of the strategy, that is, the total expected reward accumulated within the time range T. The larger the value, the better the performance of strategy π. Strategy π is a decision rule that defines the action taken at each time t, that is, how to choose the feeding amount or water quality adjustment operation. is the mathematical expectation symbol, which represents the expected value after weighted average of all possible states and action sequences. In reinforcement learning, the state transitions and rewards of the environment are usually random, so it is necessary to calculate the average return after multiple executions of strategy π; r t The reward function for each time step is defined as the balance between feeding amount and water quality fluctuations.

[0185] r t It is the instantaneous reward value obtained by the system when executing a certain strategy π at time t. In the water quality and feeding linkage management system, the reward value represents the overall performance of the system at this moment.

[0186] The reward function is usually designed as:

[0187] If the system is within the safe range of water quality and the feeding amount is reasonable, the reward r t Higher;

[0188] If there is a problem with water quality or too much / too little feeding, reward r t Will decrease.

[0189] Reward function r t It is expressed as:

[0190] r t=-(|T w (t)-F adj (t)+ω1·|E(t)|+ω2·Q clean (t))

[0191] Among them, ω1 and ω2 are weight coefficients, which respectively measure the negative impact of abnormal water quality and purification equipment operation on the system; |T w (t)-F adj (t)| is the deviation of feeding amount. The larger the deviation, the lower the reward. E(t) is the degree of water quality abnormality. The more serious the water quality abnormality, the lower the reward. Q clean (t) is the operating cost of the purification equipment. The greater the operating intensity, the lower the reward.

[0192] The goal of this formula is to maximize the total cumulative reward over the entire time frame T. In other words, the system hopes to maintain stable water quality, reasonable feeding, and minimize the use of water purification equipment over a long period of time. By optimizing the strategy π, the system can take the best actions at different time points to obtain the highest total reward.

[0193] Through the linkage automated decision-making algorithm, the system can autonomously adjust the feeding amount and the operating intensity of the water purification equipment without human intervention. It can respond quickly and accurately to avoid delays and human errors by ingesting real-time monitoring data (such as water quality parameters, feeding behavior, etc.) and combining historical data for automatic decision-making. When the system detects a decrease in dissolved oxygen or an increase in ammonia nitrogen concentration, the linkage algorithm can quickly reduce the feeding amount or start the purification equipment to prevent further deterioration of water quality. This adaptive adjustment process greatly improves management efficiency.

[0194] By continuously optimizing feeding strategies and water quality control, the linked automated decision-making algorithm can maintain the stability of water quality and reduce the risks caused by drastic fluctuations in water quality. This is crucial for the healthy growth of fish. Excessive fluctuations in water quality often cause stress reactions in fish, affecting their health or causing diseases. The automated decision-making algorithm adjusts feeding and purification equipment to avoid water quality deterioration and quickly restores it to a safe state when water quality is abnormal, ensuring the stability of the breeding environment.

[0195] The core significance of the linkage automation decision algorithm is to respond to changes in water quality and feeding behavior in real time through intelligent algorithms, optimize feeding and purification strategies, and thus improve the autonomy, efficiency and long-term stability of the system. It reduces labor costs, optimizes the breeding environment, and continuously improves feeding strategies through continuous learning, ultimately promoting the sustainable development of aquaculture.

[0196] See also Figure 2 , which is a schematic diagram of a water quality and feeding linkage management device based on the Internet of Things provided in an embodiment of the present application, including:

[0197] A deployment unit 21, used to deploy sensors to collect water quality data;

[0198] An adjustment unit 22 is used to construct a water quality and feeding linkage model based on water quality data and dynamically adjust the feeding amount;

[0199] An optimization unit 23 is used to place feed based on the feeding amount and optimize the feeding amount according to real-time feedback;

[0200] Establishing unit 24, used to establish a water quality abnormality monitoring model and monitor water quality data; if the water quality is abnormal, the adjustment mechanism is activated;

[0201] The decision-making unit 25 is used to remotely monitor water quality data and feeding amount, conduct trend analysis based on historical data, and realize automated decision-making through intelligent algorithms.

[0202] See also Figure 3 The embodiment of the present application also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, the steps of any of the above-mentioned methods for water quality and feeding linkage management based on the Internet of Things are implemented.

[0203] Since the electronic device introduced in this embodiment is a device used to implement a water quality and feeding linkage management device based on the Internet of Things in the embodiment of the present application, based on the method introduced in the embodiment of the present application, the technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by the technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0204] During the specific implementation process, when the computer program 311 is executed by a processor, any implementation method in the embodiments corresponding to the first aspect can be implemented.

[0205] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0206] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-readable program code.

[0207] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0208] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0209] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0210] An embodiment of the present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device executes the process of a water quality and feeding linkage management method based on the Internet of Things.

[0211] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0212] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0213] In the several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0214] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0215] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0216] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0217] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

[0218] Although the preferred embodiments of this specification have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of this specification.

[0219] Obviously, those skilled in the art can make various changes and modifications to this specification without departing from the spirit and scope of this specification. Thus, if these modifications and variations of this specification fall within the scope of the claims of this specification and their equivalents, this specification is also intended to include these modifications and variations.

Claims

1. A water quality and feeding linkage management method based on the Internet of Things, characterized in that: The method comprises: Deploy sensors to collect water quality data; Build a water quality and feeding linkage model based on water quality data to dynamically adjust the feeding amount; Feed is placed based on the feeding amount, and the feeding amount is optimized according to real-time feedback; Establish a water quality abnormality monitoring model to monitor water quality data; if the water quality is abnormal, activate the adjustment mechanism; Remotely monitor water quality data and feeding amounts, perform trend analysis based on historical data, and make automated decisions through intelligent algorithms.

2. The water quality and feeding linkage management method based on the Internet of Things according to claim 1 is characterized in that: Deploy sensors to collect water quality data, including: Set N monitoring points in the water body, at each monitoring point N i Sensors are installed on the ground; the data of each monitoring point P i (t) is expressed as a time series: in, is the dissolved oxygen concentration at the ith monitoring point; is the dissolved oxygen concentration at the ith monitoring point; pH i (t) is the pH value of the ith monitoring point; T i (t) is the water temperature at the i-th monitoring point; The data of all monitoring points are summarized into the water quality parameter matrix P(t), which is expressed as: For each parameter P i (t), its original data By calibration factor C i Converted to real value, expressed as: Among them, C i is the calibration factor based on laboratory measurements and adjustment for equipment errors; All parameters were normalized and the normal range of each parameter was set. i，min , P i，max ], normalize it to the interval [0,1], expressed as: The normalized parameter matrix is:

3. The water quality and feeding linkage management method based on the Internet of Things according to claim 2 is characterized in that: Based on water quality data, a water quality and feeding linkage model is built to dynamically adjust the feeding amount, including: Dynamic calculation of feeding amount T according to water quality changes w (t), the formula of the linkage model is expressed as: Among them, T w (t) is the feeding amount at time t; α is the dissolved oxygen regulation factor; β1 is the ammonia nitrogen regulation factor; β2 is the water temperature regulation factor; γ is the feeding rate regulation factor; F rate (t) is the fish feeding rate; The nonlinear coupling relationship between dissolved oxygen and ammonia nitrogen is: in, is the initial dissolved oxygen concentration; k1 and k2 are coupling coefficients; The pH value is adjusted according to the change of dissolved oxygen through a logarithmic function, expressed as: Among them, pH0 is the initial pH value; k3 is the coupling coefficient of pH and dissolved oxygen.

4. The water quality and feeding linkage management method based on the Internet of Things according to claim 3 is characterized in that: The dynamic regulation factors α, β1, β2, and γ are determined based on the following formulas: Among them, θ1 is the adjustment sensitivity; is the threshold value of dissolved oxygen; Among them, θ2 is the inhibitory effect of controlling ammonia nitrogen on the feeding amount; is the safety threshold of ammonia nitrogen; β2=(1+θ3·|T(t)-T opt |) -1 Among them, θ3 is the sensitivity parameter of the water temperature adjustment factor; T opt For the best water temperature; Among them, θ4 is the regulatory sensitivity for controlling the feeding rate; is the average feeding rate of fish.

5. The water quality and feeding linkage management method based on the Internet of Things according to claim 4 is characterized in that: Feeding is based on feeding amount, and feeding amount is optimized according to real-time feedback, including: Construct a variable feedback control model to monitor the changes in water quality and the feeding behavior of fish in real time during the feeding process, and dynamically adjust the feeding amount. The feedback control formula is: Among them, F adj (t) is the feeding amount after feedback adjustment; T w (t) is the calculated initial feeding amount; ΔP(t) = P(t) - P0(t), which represents the difference between the current water quality parameter P(t) and the initial water quality parameter P0(t); P max is the maximum amplitude of water quality fluctuation allowed; ζ is the feeding behavior feedback coefficient; C feed (t) is the fish feeding rate monitored in real time; Through the camera and image recognition technology, the feeding behavior of the fish school is monitored in real time, and the feeding rate C of the fish school is calculated. feed (t): Among them, C feed (t) is the feeding rate of the fish school; N f is the number of fish in the feeding area; A I (t) is the feeding activity of the first fish during the feeding process; A total (t) is the total fish activity in the camera coverage area; The intelligent feeding machine can accurately deliver feed according to the feeding amount F adj (t) Control the release rate of feed R feed (t), expressed as: R feed (t)=η·F adj (t) Among them, R feed (t) represents the release rate of feed; η is the conversion coefficient of the feeding machine.

6. The water quality and feeding linkage management method based on the Internet of Things according to claim 4 is characterized in that: Establish a water quality anomaly monitoring model to monitor water quality data, including: The detection formula for abnormal water quality is: Among them, E(t) is the abnormal monitoring function; P i (t) is the real-time parameter of water quality; is the safety threshold of each water quality parameter; δ is the preset anomaly detection threshold, when E(t)>δ, it is considered abnormal.

7. The water quality and feeding linkage management method based on the Internet of Things according to claim 1 is characterized in that: Remotely monitor water quality data and feeding amount, conduct trend analysis based on historical data, and make automated decisions through intelligent algorithms, including: The real-time data P(t), feeding amount F adj (t) and water purification equipment operation data Q clean (t) Data storage, the data storage format is: S total (t)=[P(t),T w (t),F adj (t),Q clean (t),E(t)] Where P(t) is the water quality parameter at a certain time; T w (t) is the initial feeding amount; F adj (t) is the actual feeding amount after feedback adjustment; Q clean (t) is the operating intensity of the purification equipment; E(t) is the monitoring value of the abnormal degree of water quality; Based on S total (t) to fit the water quality parameters P(t) at future times and adjust the feeding strategy T w (t), analyze the historical trend of water quality parameter P(t), the expression is: in, is to predict the water quality parameters at the future time t+n; φ1, φ2 are autoregressive coefficients; θ1, θ2 are moving average coefficients; ∈(t) is the noise term at time t; The formula for adjusting the feeding amount is: Automated decision-making is achieved through the linkage algorithm. The linkage algorithm uses a reinforcement learning model to train the optimal strategy through multiple feeding-feedback cycles. The optimization objective function is: Among them, J(π) is the long-term return of the strategy; strategy π is a decision rule; is the mathematical expectation symbol; r t is the reward function for each time step; Reward function r t It is expressed as: r t =-(|T w (t)-F adj (t)+ω1·|E(t)|+ω2·Q clean (t)) Among them, ω1 and ω2 are weight coefficients, which respectively measure the negative impact of abnormal water quality and purification equipment operation on the system; |T w (t)-F adj (t)| is the deviation of feeding amount.

8. The water quality and feeding linkage management device based on the Internet of Things is characterized by: include: A deployment unit, used to deploy sensors and collect water quality data; The adjustment unit is used to build a water quality and feeding linkage model based on water quality data and dynamically adjust the feeding amount; An optimization unit is used to place feed based on the feeding amount and optimize the feeding amount according to real-time feedback; Establishing a unit for establishing a water quality abnormality monitoring model and monitoring water quality data; If the water quality is abnormal, the adjustment mechanism is activated; The decision-making unit is used to remotely monitor water quality data and feeding amounts, conduct trend analysis based on historical data, and achieve automated decision-making through intelligent algorithms.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is used to implement the steps of the water quality and feeding linkage management method based on the Internet of Things as described in any one of claims 1 to 7 when executing the computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the water quality and feeding linkage management method based on the Internet of Things is implemented as described in any one of claims 1 to 7.

Images