Reclaimed water irrigation method and system with intelligent monitoring and adjusting functions

Abstract

The invention provides an intelligent monitoring and adjusting reclaimed water irrigation method and system, and relates to the technical field of water resource utilization, and the method comprises the steps: deploying a sensor network which comprises a water quality sensor, a flow sensor and a pressure sensor; the sensor network monitors parameters of the irrigation system in real time and sends the parameters to the intelligent controller; the intelligent controller uploads the parameters to a cloud server; the cloud server analyzes the parameters through an intelligent control algorithm and dynamically adjusts water resource distribution; the intelligent controller receives an adjusting instruction of the cloud server and automatically adjusts parameters of the irrigation system.

Description

Technical Field

[0001] The present invention belongs to the technical field of water resource utilization, and in particular relates to a reclaimed water irrigation method and system with intelligent monitoring and regulation. Background Art

[0002] In the context of increasingly tight global water resources, the use of recycled water has become particularly important. Traditional irrigation methods usually rely on manual adjustment and fixed irrigation time, lacking targeted and dynamic adjustment capabilities, resulting in waste of water resources. At the same time, modern agriculture has increasingly higher requirements for irrigation parameters such as water quality, flow, and pressure. How to efficiently use recycled water and maximize the utilization of water resources while ensuring the healthy growth of crops has become an important topic in the current agricultural field.

[0003] Existing irrigation systems mostly use a single parameter monitoring mode, lack real-time data analysis and automatic adjustment capabilities, and cannot dynamically adjust irrigation according to environmental changes and the actual needs of crops. Therefore, it is urgent to develop an intelligent and automated recycled water irrigation method. 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 method for intelligently monitoring and regulating recycled water irrigation, comprising:

[0006] Deploy a sensor network, which includes water quality sensors, flow sensors, and pressure sensors;

[0007] The sensor network monitors the irrigation system parameters in real time and sends the parameters to the intelligent controller;

[0008] The intelligent controller uploads the parameters to the cloud server;

[0009] The cloud server analyzes the parameters through intelligent control algorithms and dynamically adjusts water resource allocation;

[0010] The intelligent controller receives adjustment instructions from the cloud server and automatically adjusts the irrigation system parameters.

[0011] In a feasible implementation manner, the above-mentioned deployment of the sensor network includes:

[0012] The sensor node set is S = (X 1 , Y 1 ), (X 2 , Y2 ),...,(X N , Y N ), where N is the number of sensors, (X i , Y i ) represents the coordinates of the i-th sensor, and the optimization goal is to minimize the total distance between the sensor and the central controller, while each important area is covered by at least one sensor;

[0013] The optimization objective function is:

[0014]

[0015] Where λ is the Lagrange multiplier; A is the number of key regions; δ a For each key area, whether it has been covered; i is the weight of the i-th sensor;

[0016] d(X i , Y i ) is the distance function between the sensor and the control center, expressed as:

[0017]

[0018] In the formula, (X c , Y c ) represents the coordinates of the i-th sensor;

[0019] Cover all key areas, that is, each key area R a At least one sensor node S i satisfy:

[0020] d(S i , R a )≤d max

[0021] Where, d max It is the effective coverage radius of the sensor.

[0022] In a feasible implementation manner, the weight w of the above sensor is i Determined based on the following formula:

[0023]

[0024] In the formula, is the initial weight of the i-th sensor; I(S i , S j ) is the sensor S i and S j The mutual information between them; α is the adjustment coefficient;

[0025] Mutual information I(Si , S j ) is calculated as:

[0026]

[0027] In the formula, p(x i , x j ) is the sensor S i and S j The joint probability distribution of the collected data; p(x i ) and p(x j ) are their respective marginal probability distributions.

[0028] In a feasible implementation manner, the intelligent controller performs a data fusion operation before uploading the parameters to the cloud server, including:

[0029] Set each sensor S i The value collected at time t is S i (t), the data fusion function is expressed as:

[0030]

[0031] In the formula, S i (t) is the sensor S i The collected value at time t; β and ε are weight coefficients, which control the influence of direct fusion and spatiotemporal correlation respectively; γ ij For sensor S i and S j The spatiotemporal correlation between them; Δt is the time delay, which indicates the influence of the data of the previous time step on the current data;

[0032] Time-space correlation γ ij It is expressed as:

[0033]

[0034] In the formula, H(S i ) and H(S j ) are sensors S i and sensor S j The entropy of .

[0035] In a feasible implementation, the cloud server analyzes parameters through an intelligent control algorithm and dynamically adjusts water resource allocation, including:

[0036] Use a recurrent neural network to predict future states X t+1 To make a prediction, the formula is:

[0037]

[0038] In the formula, is the next moment state X predicted based on historical time series data t+1 ; f(X t ) is the state transfer function; W is the number of time steps; W step is the weight of the time step; g(X t-step ) is the state at the historical moment t-step; X t is the overall state of the irrigation system at time t;

[0039] The prediction of RNN is corrected by Kalman filter. The Kalman filter formula is expressed as:

[0040]

[0041] In the formula, is the preliminary prediction result given by the RNN model; X t is the system state vector; Y t is the sensor data vector; K t is the adaptive gain matrix; H is the observation matrix;

[0042] In order to optimize water resource allocation, the optimal operation O opt , maximize the benefits of water resource utilization water (t) and minimize the operation adjustment cost C adjust (O o ), the optimization objective function is:

[0043]

[0044] In the formula, O o is an optional operation scheduling scheme; U water (t) is the benefit function of water resource utilization, which depends on time t; C adjust (O o ) is the operation adjustment cost, representing the implementation of a specific operation O o The required resource consumption.

[0045] In a feasible implementation, the adaptive gain matrix K t Determined based on the following formula:

[0046] K t =P t ·H T ·(H·P t ·H T +R t ) -1

[0047] Where P t is the covariance matrix of the system state; R tis the covariance matrix of the measurement noise.

[0048] In a feasible implementation manner, the intelligent controller receives adjustment instructions from the cloud server and automatically adjusts the irrigation system parameters, including:

[0049] The nonlinear adaptive control model is constructed and described by the following formula:

[0050]

[0051] Where u(t) is the output control variable of the controller at time t; y(t) is the state variable of the current system; y set (t) is the set target value; K is the adaptive gain matrix;

[0052] The adaptive gain matrix K adjustment rule is determined based on the following formula:

[0053]

[0054] In the formula, K 0 is the initial gain value; γ is the adaptive adjustment coefficient; Sensitivity is the sensitivity parameter; |y(t)-y set (t)| is the deviation between the current state and the set value.

[0055] In the second aspect, the present application proposes a reclaimed water irrigation device with intelligent monitoring and regulation, comprising:

[0056] A deployment unit, used to deploy a sensor network, the sensor network includes a water quality sensor, a flow sensor, and a pressure sensor;

[0057] Monitoring unit, which is used for real-time monitoring of irrigation system parameters by sensor network and sends the parameters to the intelligent controller;

[0058] Transmission unit, used by the intelligent controller to upload parameters to the cloud server;

[0059] Analysis unit, used by the cloud server to analyze parameters through intelligent control algorithms and dynamically adjust water resource allocation;

[0060] The receiving unit is used for the intelligent controller to receive adjustment instructions from the cloud server and automatically adjust the irrigation system parameters.

[0061] 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 intelligent monitoring and regulating reclaimed water irrigation method as claimed in any one of claims 1 to 7 when executing the computer program stored in the memory.

[0062] In a fourth aspect, the present application further proposes a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the intelligent monitoring and regulating reclaimed water irrigation method as described in any one of claims 1 to 7 is implemented.

[0063] In summary, the present invention can monitor the key parameters in the irrigation system in real time by deploying a sensor network including water quality sensors, flow sensors and pressure sensors, ensuring that each irrigation link is in the best state; the intelligent controller can analyze the data collected by the sensors through the intelligent control algorithm of the cloud server, and adjust the allocation of water resources in real time, avoiding the manual adjustment error in traditional irrigation, and greatly improving the efficiency of irrigation; the optimized sensor layout and adaptive weight adjustment model can reduce the transmission of redundant data while ensuring the monitoring coverage, effectively reducing the operating cost and energy consumption of the system, thereby achieving dual savings in water resources and energy; the system can automatically adjust the irrigation parameters according to the adjustment instructions issued by the cloud server. When an abnormal situation is detected (such as water quality exceeding the standard, flow abnormality, etc.), the system can promptly start the emergency response mechanism to ensure the safe and stable operation of the system and reduce the waste of resources caused by abnormal situations; based on the intelligent algorithm of recursive neural network (RNN) and Kalman filtering, the system can accurately predict future irrigation needs, optimize the scheduling and allocation of water resources in combination with actual conditions, and further improve the utilization efficiency of water resources.

[0064] The tunnel advanced geological prediction monitoring method 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

[0065] 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:

[0066] Figure 1 A schematic diagram of a process flow of a reclaimed water irrigation method for intelligent monitoring and regulation in this application;

[0067] Figure 2 A schematic diagram of a reclaimed water irrigation structure for intelligent monitoring and regulation in this application;

[0068] Figure 3 A schematic diagram of an electronic device for intelligent monitoring and regulation of recycled water irrigation according to the present application. DETAILED DESCRIPTION

[0069] 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.

[0070] See also Figure 1 , which is a flow chart of a tunnel advanced geological prediction monitoring method provided in an embodiment of the present application, which may specifically include:

[0071] S110, deploying a sensor network, the sensor network including a water quality sensor, a flow sensor, and a pressure sensor;

[0072] For example, an efficient sensor network and intelligent control system are constructed to ensure accurate monitoring of key parameters (such as water quality, flow, pressure, etc.) in the irrigation system, and reduce delays and improve data collection efficiency through optimized sensor layout and data transmission paths.

[0073] First, optimize the layout of the sensor network. Sensor types include:

[0074] Water quality sensor: detects water pH value, salt content, pollutant concentration, etc.

[0075] Flow Sensor: Monitors water flow rate and volume.

[0076] Pressure sensor: monitors water pressure to ensure the normal operation of water pumps and piping systems.

[0077] The system adopts a distributed sensor deployment model, which ensures that sensors in key areas are densely deployed through mathematical optimization to maximize data coverage and accuracy. The core of the deployment optimization problem is how to effectively deploy sensors in a non-uniform environment to maximize the coverage area while minimizing the data transmission cost.

[0078] The sensor network optimization problem can be reduced to a multi-objective optimization problem. Suppose the sensor node set is S = (X 1 , Y1 ), (X 2 , Y 2 ),...,(X N , Y N ), where N is the number of sensors, (X i , Y i ) represents the coordinates of the th sensor. The optimization goal is to minimize the total distance between the sensors and the central controller while ensuring that each important area is covered by at least one sensor.

[0079] The optimization objective function is:

[0080]

[0081] Where λ is the Lagrange multiplier used to balance the objectives and constraints; A is the number of critical areas, that is, the total number of important areas that need to be covered by sensors; δ a For each key area, whether it has been covered or not, if it has been covered, then δ a =1, otherwise 0; w i is the weight of the ith sensor, representing its importance (for example, sensors in water source areas have greater weights).

[0082] d(X i , Y i ) is the distance function between the sensor and the control center, defined as the Euclidean distance, expressed as:

[0083]

[0084] In the formula, (X c , Y c ) represents the coordinates of the i-th sensor.

[0085] Constraints ensure that all key areas are covered, that is, each key area R a There is at least one sensor node S i satisfy:

[0086] d(S i ,R a )≤d max

[0087] Where, d max It is the effective coverage radius of the sensor.

[0088] The sensor weights are adaptively adjusted. According to the actual monitoring needs, the weights can be dynamically adjusted over time. The initial weights can be set according to the environmental risks and importance, and then gradually optimized through the feedback mechanism. This application introduces an adaptive adjustment formula for sensor weights. The weights are not only affected by the environment, but also related to the mutual information between sensors. That is, if the information collected by two sensors is highly redundant, the weight of one of them needs to be reduced.

[0089] Adaptive weight adjustment formula:

[0090]

[0091] In the formula, is the initial weight of the i-th sensor; I(S i , S j ) is the sensor S i and S j The mutual information between them indicates the similarity of the information collected by the two sensors. A larger mutual information means a higher data redundancy. α is the adjustment coefficient, which is used to balance the initial weight and information redundancy.

[0092] Mutual information I(S i , S j ) is calculated as:

[0093]

[0094] In the formula, p(x i , x j ) is the sensor S i and S j The joint probability distribution of the collected data; p(x i ) and p(x j ) are their respective marginal probability distributions.

[0095] S120, the sensor network monitors the irrigation system parameters in real time and sends the parameters to the intelligent controller;

[0096] For example, in order to improve the data transmission efficiency, the data transmission path from the sensor to the central controller needs to be optimized. Suppose all possible transmission paths P = {P 1 , P 2 , ..., P M}, we need to choose an optimal path P optimal , so that the total transmission cost and delay are minimized.

[0097] Optimal path selection formula:

[0098]

[0099] Where P routeis a candidate path; k is the kth transmission path; P optimal is the optimal transmission path; D lat (P k ) is the delay of data transmission, which is affected by the path length and network bandwidth. The longer the path and the lower the bandwidth, the longer the delay. trans (P k ) is the path through P k The cost of data transmission, considering the transmission energy consumption and data volume, is expressed as:

[0100]

[0101] In the formula, E l is the energy consumption of node l on the path; L l is the amount of data transmitted through the path;

[0102] For example, the sensor layout optimization formula reduces the distance to the central controller by adjusting the sensor position, and adjusts the sensor density according to the needs of different areas. The data transmission path optimization formula selects the path with the lowest transmission energy consumption and the smallest delay to ensure the rapidity and efficiency of data transmission. The mutual information in the weight formula is used to determine the redundancy of different sensors. If the information collected by two sensors is similar, the weight is automatically adjusted to reduce the transmission of redundant data.

[0103] S130, the intelligent controller uploads the parameters to the cloud server;

[0104] For example, the collected irrigation system data is uploaded to the cloud server in real time through the intelligent controller and the IoT platform to achieve remote monitoring. The intelligent controller aggregates the data collected by each sensor and uploads it to the cloud through the IoT platform. In order to improve the stability of data transmission, a dynamic distributed data fusion model is used to minimize the transmission delay of data between network nodes and ensure data accuracy.

[0105] Multidimensional spatiotemporal data fusion model: The data collected by sensors often have spatiotemporal correlation, so before transmitting the data, it is necessary to fuse and preprocess the data. i The value collected at time is S i (t), the overall data fusion function can be expressed as:

[0106]

[0107] In the formula, S i (t) is the sensor S i The collected value at time t; β and ε are weight coefficients, which control the influence of direct fusion and spatiotemporal correlation respectively; γ ijFor sensor S i and S j The spatiotemporal correlation between them reflects the correlation between the values ​​collected by the two sensors at different times; Δt is the time delay, which indicates the influence of the data of the previous time step on the current data.

[0108] Time-space correlation γ ij It is expressed as:

[0109]

[0110] In the formula, H(S i ) and H(S j ) are sensors S i and S j The entropy represents the uncertainty of the data.

[0111] S140, the cloud server analyzes the parameters through intelligent control algorithms and dynamically adjusts water resource allocation;

[0112] For example, the data received by the cloud server is analyzed and predicted using intelligent control algorithms to identify potential problems in the system and make optimization decisions. The purpose is to ensure efficient use and reasonable allocation of water resources, avoid waste, and achieve automatic regulation during the monitoring of recycled water irrigation.

[0113] The system obtains data (such as water quality, flow, pressure and other parameters) through the sensor network, and after being processed by the cloud server, uses an algorithm that combines adaptive control and deep learning for analysis and prediction. The system combines multidimensional recursive neural network (RNN) and adaptive Kalman filter (AKF) technology to detect and predict potential problems in the irrigation system in real time, and optimizes scheduling based on the prediction results to provide the best irrigation plan.

[0114] Relying on multi-dimensional prediction and adaptive filtering models and optimization scheduling models: Multi-dimensional prediction and adaptive filtering models are used to predict the future system status and continuously correct the prediction error based on sensor data. The optimization scheduling model is used to generate the optimal irrigation plan, which achieves global optimization by maximizing the benefits of water resource utilization and minimizing the operation adjustment cost.

[0115] Multi-dimensional prediction and adaptive filtering models, including:

[0116] System Status X t Represents the overall state of the irrigation system at time t, including multiple dimensions such as water quality, flow, and pressure. A recursive neural network (RNN) combined with an adaptive Kalman filter is used to predict the future state X t+1 To make predictions, the prediction phase of the recurrent neural network (prediction based on historical data) formula is:

[0117]

[0118] In the formula, is the next moment state X predicted based on historical time series data t+1 ; f(X t ) is the state transfer function, which is the prediction of the system state at the current time t. Assuming that the system state changes over time, the state transfer function f can describe the internal dynamics of the system. For example, in water resource scheduling, it may represent the natural change trend of water flow; W is the number of time steps, W step is the weight of each time step, reflecting the importance of historical data to the current prediction. Recent data may have a greater weight than distant data; g(X t-step ) is the state at the historical moment t-step, reflecting the change of the system state at a certain moment in the past and providing background support for the current state.

[0119] Kalman filter correction phase (combined with real-time observation data correction). In this phase, the prediction from RNN is corrected by Kalman filter, combined with the current observation data Y t , in order to improve the accuracy of prediction, the Kalman filter formula can be expressed as:

[0120]

[0121] In the formula, This is the preliminary prediction result given by the RNN model. This prediction result may be inaccurate because it is only based on historical data; X t is the system state vector, indicating the current system state; Y t is the sensor data vector, which represents the observation data collected by the sensor at time t, and the sensor observation data at the current time t. The sensor observation provides a true reflection of the current system state and is used to correct the prediction results of the RNN; K t It is an adaptive gain matrix, which is dynamically adjusted by Kalman filtering to correct the system prediction error, Kalman gain, which determines how to adjust the prediction result to make it closer to the actual observation value. Gain matrix K t The size of is determined by the uncertainty of system prediction and observation noise. By calculating the Kalman gain, the uncertainty of the system can be adapted. H is the observation matrix, which represents the mapping from state to sensor observation data.

[0122] The core of Kalman filtering is to use sensor data to correct the system state and dynamically adjust the gain matrix K t , to minimize the prediction error, the state update formula of Kalman filter is:

[0123] K t =Pt ·H T ·(H·P t ·H T +R t ) -1

[0124] Where P t is the covariance matrix of the system state, which represents the state uncertainty; H is the observation matrix, which maps the system state to sensor data; R t is the covariance matrix of the measurement noise.

[0125] Optimize the scheduling model, including:

[0126] To optimize water resource allocation, the system solves the optimal operation O opt , maximize the benefits of water resource utilization water (t) and minimize the operation adjustment cost C adjust (O o ), the optimization objective function is:

[0127]

[0128] In the formula, O o is an optional operation scheduling scheme; U water (t) is the benefit function of water resource utilization, which depends on time t; C adjust (O o ) is the operation adjustment cost, representing the implementation of a specific operation O o The required resource consumption.

[0129] For example, the RNN model recursively predicts future states through historical data, and uses historical water quality, flow, pressure and other parameters to predict future irrigation needs. The adaptive Kalman filter corrects the system prediction error through real-time data from sensors to ensure the accuracy of the prediction. The optimization scheduling model generates a set of optimal irrigation plans based on the current system status, which can not only meet the irrigation needs, but also maximize the utilization efficiency of water resources and reduce unnecessary waste.

[0130] S150, the intelligent controller receives adjustment instructions from the cloud server and automatically adjusts the irrigation system parameters.

[0131] For example, through the instructions issued by the cloud server, the intelligent controller automatically adjusts the various parameters of the irrigation system to ensure that the operating status of the system can remain stable under various changing environments and achieve efficient utilization of irrigation resources.

[0132] The intelligent controller will dynamically adjust the operating parameters of the irrigation system according to the adjustment instructions generated by the cloud server after data analysis and decision-making (S140). This includes valve opening, pump start and stop time, and flow control. In this process, a nonlinear adaptive control algorithm is used to adapt to changes in various environmental parameters in the system (for example, water pressure, flow, humidity, etc.), ensuring that the irrigation system can still operate efficiently and stably under changing conditions.

[0133] Nonlinear adaptive control model: The control quantity u(t) in the system (such as valve opening or pump start and stop instructions) is adjusted in real time according to the current system state. The nonlinear adaptive control model can be described by the following formula:

[0134]

[0135] Where u(t) is the output control variable of the controller at time t; y(t) is the state variable of the current system, such as the water flow or pressure in the current irrigation system; y set (t) is the set target value, such as the water flow or pressure setting value that the system needs to achieve; K is the adaptive gain matrix, which is used to dynamically adjust the response strength of the controller to the state deviation.

[0136] State error control, the first term of the above formula is used to directly respond to the deviation between the system state and the set value. If the current system state deviates from the target set value, the controller will correct this deviation by adjusting the valve opening or the state of the pump. The size of the gain matrix K determines the speed and strength of the controller's response to this deviation.

[0137] The second term in the above formula is the integral part of the controller, which is used to eliminate the steady-state error in the system. This term plays the role of accumulating errors in the control system, ensuring that the system can achieve accurate setpoint tracking during long-term operation.

[0138] Nonlinear adaptive gain matrix adjustment: In order to improve the robustness and adaptability of the control system, the gain matrix K can be dynamically adjusted according to the feedback signal of real-time operation. The basic rule of gain matrix adjustment can be described by the following formula:

[0139]

[0140] In the formula, K 0 is the initial gain value; γ is the adaptive adjustment coefficient; Sensitivity is the sensitivity parameter, which determines the speed and amplitude of gain adjustment; |y(t)-y set (t)| is the deviation between the current state and the set value.

[0141] This formula shows that when the deviation between the system state and the target value is large, the gain matrix will increase rapidly and the controller's response will become more intense to correct the system state as quickly as possible. When the deviation is small, the gain matrix tends to be stable, ensuring that the system maintains smooth operation and avoids unnecessary over-adjustment.

[0142] By combining the above-mentioned nonlinear adaptive control model and real-time feedback mechanism, the irrigation system can achieve highly intelligent automatic adjustment to ensure the optimal effect of water resource utilization.

[0143] For example, when the system detects an abnormal situation (such as water quality parameters exceeding the standard, abnormal flow, etc.), the intelligent controller will immediately activate the emergency response mechanism to ensure the safe and stable operation of the irrigation system and avoid waste of resources or system failure.

[0144] The system uses a combination of dynamic fault detection algorithms and fuzzy logic control to identify the system's operating status in real time, especially abnormalities in water quality and flow parameters. Anomaly detection relies on time series analysis, combined with data from the sensor network, to ensure that problems can be identified in the shortest possible time and that corresponding treatment measures can be taken quickly through the emergency response control mechanism. During the emergency response process, the intelligent controller will stabilize the system and restore normal status according to the system's preset rules (such as closing valves, starting standby pumps, etc.).

[0145] Dynamic fault detection model: This model is used to detect abnormal conditions in the system, such as excessive water quality, excessive flow, etc. By calculating the rate of change of the system state and the difference between sensors, the source of the abnormality can be quickly located, expressed as:

[0146]

[0147] Where R(t) is the fault diagnosis function, which is used to evaluate the abnormality of the system at time t; S i (t) is the measurement value of the i-th sensor at time t (such as water quality, flow rate and other parameters); W i is the weight of the i-th sensor, reflecting the importance of the sensor to the system. For example, sensors in key areas will be given higher weights; is a tuning parameter used to balance the effects of the rate of state change and the differences between sensors; is the rate of change of the i-th sensor measurement value, indicating the dynamic change of the system state; (S i (t)-S j (t)) 2 is the difference between the measured values ​​of the i-th sensor and the j-th sensor, indicating the abnormal difference between the two sensors. If the difference is too large, it means that there is an abnormality in the system.

[0148] Sensor state change: The first item evaluates the system's operating status through the rate of change of the sensor measurement value. If the water quality or flow rate in the system changes too quickly, the system will consider that there is an abnormality. Sensor weight W i Ensure sensors in critical areas can react faster.

[0149] Sensor difference analysis: The second item is used to compare the measurements of different sensors. When multiple sensors in the system measure the same parameter, if the measurement values ​​of some sensors are too different from other sensors, it may be that there is an abnormality in that area.

[0150] Fuzzy logic emergency response control model: After detecting an anomaly, the system generates an emergency response strategy based on the fuzzy logic control model. The model responds based on the membership function of the sensor state and the system's preset emergency rules.

[0151] The control rules for emergency response can be expressed by the following formula:

[0152] E resp =min(μ A (A i ),μ B (B j ))

[0153] In the formula, E resp is the control output of the emergency response, indicating the execution intensity of the current emergency treatment; μ A (A i ) is abnormal state A i The membership function of μ represents the severity of the current abnormal state; B (B j ) is the emergency response rule B j The membership function represents the execution conditions of the corresponding emergency treatment measures.

[0154] Membership function: Membership function μ A and μ B It is a core concept in fuzzy logic and is used to define the abnormal state of the system and the degree of execution of emergency measures. For example, when the water quality detects that the pollutants exceed the standard, the system will use μ A Determine the severity of the pollution exceeding the standard and use μ B Match the most appropriate emergency response measure, such as closing valves or activating filtration systems.

[0155] Minimization strategy: The operation of min in the model shows that the execution intensity of emergency response depends on the matching degree between abnormal state and response rules. Only when the abnormal state reaches a certain severity, the system will execute the corresponding compulsory measures.

[0156] Through the combination of dynamic fault detection and fuzzy logic emergency response, the system can achieve fast and accurate exception handling in complex environments, ensuring the stable and efficient operation of the irrigation system.

[0157] See also Figure 2 , which is a schematic diagram of the structure of a reclaimed water irrigation device with intelligent monitoring and regulation provided in an embodiment of the present application, comprising:

[0158] A deployment unit 21 is used to deploy a sensor network, the sensor network includes a water quality sensor, a flow sensor, and a pressure sensor;

[0159] Monitoring unit 22, used for real-time monitoring of irrigation system parameters by sensor network and sending the parameters to the intelligent controller;

[0160] Transmission unit 23, used for the intelligent controller to upload parameters to the cloud server;

[0161] An analysis unit 24 is used for the cloud server to analyze parameters through an intelligent control algorithm and dynamically adjust water resource allocation;

[0162] The receiving unit 25 is used for the intelligent controller to receive adjustment instructions from the cloud server and automatically adjust the irrigation system parameters.

[0163] 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 of intelligent monitoring and regulation of recycled water irrigation are implemented.

[0164] Since the electronic device introduced in this embodiment is a device used to implement a reclaimed water irrigation device with intelligent monitoring and regulation 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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 A step that specifies a function in one or more boxes.

[0171] 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 Figure 1 The process of the intelligent monitoring and regulating recycled water irrigation method in the corresponding embodiment.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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 method for irrigation with recycled water with intelligent monitoring and regulation, characterized in that: The method comprises: Deploy a sensor network, which includes water quality sensors, flow sensors, and pressure sensors; The sensor network monitors the irrigation system parameters in real time and sends the parameters to the intelligent controller; The intelligent controller uploads the parameters to the cloud server; The cloud server analyzes the parameters through intelligent control algorithms and dynamically adjusts water resource allocation; The intelligent controller receives adjustment instructions from the cloud server and automatically adjusts the irrigation system parameters.

2. The intelligent monitoring and regulating reclaimed water irrigation method according to claim 1 is characterized in that: The deploying of the sensor network comprises: The sensor node set is S = (X1, Y1), (X2, Y2), ..., (X N , Y N ), where N is the number of sensors, (X i , Y i ) represents the coordinates of the i-th sensor, and the optimization goal is to minimize the total distance between the sensor and the central controller, while each important area is covered by at least one sensor; The optimization objective function is: Where λ is the Lagrange multiplier; A is the number of key regions; δ a For each key area, whether it has been covered; i is the weight of the i-th sensor; d(X i , Y i ) is the distance function between the sensor and the control center, expressed as: In the formula, (X c , Y c ) represents the coordinates of the i-th sensor; Cover all key areas, that is, each key area R a At least one sensor node S i satisfy: d(S i ,R a )≤d max Where, d max It is the effective coverage radius of the sensor.

3. The intelligent monitoring and regulating reclaimed water irrigation method according to claim 2 is characterized in that: The weight w of the sensor i Determined based on the following formula: In the formula, is the initial weight of the i-th sensor; I(S i , S j ) is the sensor S i and S j The mutual information between them; α is the adjustment coefficient; Mutual information I(S i , S j ) is calculated as: In the formula, p(x i , x j ) is the sensor S i and S j The joint probability distribution of the collected data; p(x i ) and p(x j ) are their respective marginal probability distributions.

4. The intelligent monitoring and regulating reclaimed water irrigation method according to claim 1, characterized in that: The intelligent controller performs data fusion operations before uploading the parameters to the cloud server, including: Set each sensor S i The value collected at time t is S i (t), the data fusion function is expressed as: In the formula, S i (t) is the sensor S i The collected value at time t; β and ε are weight coefficients, which control the influence of direct fusion and spatiotemporal correlation respectively; γ ij For sensor S i and S j The spatiotemporal correlation between them; Δt is the time delay, which indicates the influence of the data of the previous time step on the current data; Time-space correlation γ ij It is expressed as: In the formula, H(S i ) and H(S j ) are sensors S i and sensor S j The entropy of .

5. The intelligent monitoring and regulating reclaimed water irrigation method according to claim 1, characterized in that: The cloud server analyzes parameters through intelligent control algorithms and dynamically adjusts water resource allocation, including: Use a recurrent neural network to predict future states X t+1 To make a prediction, the formula is: In the formula, is the next moment state X predicted based on historical time series data t+1 ; f(X t ) is the state transfer function; W is the number of time steps; W step is the weight of the time step; g(X t-step ) is the state at the historical moment t-step; X t is the overall state of the irrigation system at time t; The prediction of RNN is corrected by Kalman filter. The Kalman filter formula is expressed as: In the formula, is the preliminary prediction result given by the RNN model; X t is the system state vector; Y t is the sensor data vector; K t is the adaptive gain matrix; H is the observation matrix; In order to optimize water resource allocation, the optimal operation O opt , maximize the benefits of water resource utilization water (t) and minimize the operation adjustment cost C adjust (O o ), the optimization objective function is: In the formula, O o is an optional operation scheduling scheme; U water (t) is the benefit function of water resource utilization, which depends on time t; C adjust (O o ) is the operation adjustment cost, representing the implementation of a specific operation O o The required resource consumption.

6. The intelligent monitoring and regulating reclaimed water irrigation method according to claim 5, characterized in that: The adaptive gain matrix K t Determined based on the following formula: K t -P t ·H T ·(H·P t ·H T +R t ) -1 Where P t is the covariance matrix of the system state; R t is the covariance matrix of the measurement noise.

7. The intelligent monitoring and regulating reclaimed water irrigation method according to claim 1, characterized in that: The intelligent controller receives adjustment instructions from the cloud server and automatically adjusts the irrigation system parameters, including: The nonlinear adaptive control model is constructed and described by the following formula: Where u(t) is the output control quantity of the controller at time t; y(t) is the state variable of the current system; y set (t) is the set target value; K is the adaptive gain matrix; The adaptive gain matrix K adjustment rule is determined based on the following formula: Where K0 is the initial gain value; γ is the adaptive adjustment coefficient; Sensitivity is the sensitivity parameter; |y(t)-y set (t)| is the deviation between the current state and the set value.

8. An intelligent monitoring and regulating reclaimed water irrigation device, characterized in that: include: A deployment unit, used to deploy a sensor network, the sensor network includes a water quality sensor, a flow sensor, and a pressure sensor; Monitoring unit, which is used for real-time monitoring of irrigation system parameters by sensor network and sends the parameters to the intelligent controller; Transmission unit, used by the intelligent controller to upload parameters to the cloud server; Analysis unit, used by the cloud server to analyze parameters through intelligent control algorithms and dynamically adjust water resource allocation; The receiving unit is used for the intelligent controller to receive adjustment instructions from the cloud server and automatically adjust the irrigation system parameters.

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 intelligent monitoring and regulating reclaimed water irrigation method 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 a processor, the intelligent monitoring and regulating reclaimed water irrigation method as described in any one of claims 1 to 7 is implemented.

Images