CN119234673A

CN119234673A - A method and system for intelligent monitoring and regulation of recycled water irrigation

Info

Publication number: CN119234673A
Application number: CN202411309201.XA
Authority: CN
Inventors: 卢路; 贾海燕; 李玮; 辛小康; 李建; 刘红; 刘聪; 廖沛涵
Original assignee: YANGTZE RIVER WATER RESOURCES PROTECTION SCIENCE RESEARCH INSTITUTE
Current assignee: YANGTZE RIVER WATER RESOURCES PROTECTION SCIENCE RESEARCH INSTITUTE
Priority date: 2024-09-19
Filing date: 2024-09-19
Publication date: 2025-01-03

Abstract

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

Description

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

Technical Field

The invention belongs to the technical field of water resource utilization, and particularly relates to an intelligent monitoring and adjusting reclaimed water irrigation method and system.

Background

In the context of increasingly stringent global water resources, the use of reclaimed water has become particularly important. Traditional irrigation methods generally rely on manual adjustment and fixed irrigation time, and lack targeting and dynamic adjustment capabilities, resulting in waste of water resources. Meanwhile, the requirements of modern agriculture on irrigation parameters such as water quality, flow rate, pressure and the like are higher and higher, how to efficiently utilize reclaimed water, and maximize the utilization rate of water resources while ensuring healthy growth of crops become an important subject in the current agriculture field.

The existing irrigation system mostly adopts a single parameter monitoring mode, lacks real-time data analysis and automatic adjustment capability, and cannot dynamically adjust irrigation according to environmental changes and actual demands of crops. Therefore, there is a need to develop an intelligent, automated method of secondary water irrigation.

Disclosure of Invention

In the summary, a series of concepts in a simplified form are introduced, which will be further described in detail in the detailed description. The summary of the application is not intended to define the key features and essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

In a first aspect, the present application provides a method for intelligent monitoring and adjustment of secondary water irrigation, comprising:

deploying a sensor network, wherein the sensor network comprises a water quality sensor, a flow sensor and a pressure sensor;

The sensor network monitors 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 an intelligent control algorithm and dynamically adjusts water resource allocation;

and the intelligent controller receives the adjustment instruction of the cloud server and automatically adjusts the irrigation system parameters.

In a possible implementation manner, the deployment sensor network includes:

The set of sensor nodes is s= (X ₁,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, the objective of the optimization 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:

wherein λ is the Lagrangian multiplier, A is the number of key regions, δ _a is whether each key region has been covered, w _i is the weight of the ith sensor;

d (X _i,Y_i) is a distance function between the sensor and the control center, expressed as:

Wherein (X _c,Y_c) represents the coordinates of the ith sensor;

Covering all critical areas, i.e. each critical area R _a at least one sensor node S _i satisfies:

d(S_i,R_a)≤d_max

Where d _max is the effective radius of coverage of the sensor.

In one possible embodiment, the weight w _i of the sensor is determined based on the following equation:

in the formula, I (S _i,S_j) is the mutual information quantity between the sensors S _i and S _j;

The calculation formula of the mutual information amount I (S _i,S_j) is as follows:

Where p (x _i,x_j) is the joint probability distribution of the data acquired by the sensors S _i and S _j, and p (x _i) and p (x _j) are the respective marginal probability distributions.

In a possible implementation manner, the data fusion operation performed before the intelligent controller uploads the parameters to the cloud server includes:

setting the value acquired by each sensor S _i at time t as S _i (t), the data fusion function is expressed as:

Wherein S _i (t) is an acquisition value of the sensor S _i at time t, beta and epsilon are weight coefficients for respectively controlling the influence of direct fusion and space-time association, gamma _ij is the space-time association degree between the sensors S _i and S _j, and delta t is time delay for indicating the influence of the data of the previous time step on the current data;

the spatio-temporal correlation degree γ _ij is expressed as:

Where H (S _i) and H (S _j) are the entropy of sensor S _i and sensor S _j, respectively.

In a possible implementation manner, the cloud server analyzes parameters through an intelligent control algorithm, dynamically adjusts water resource allocation, and includes:

the recurrent neural network is used for predicting the future state X _t+1, and the formula is as follows:

in the formula, The next time state X _t+1;f(X_t predicted based on the historical time sequence data is a state transfer function, W is the number of time steps, W _step is the weight of the time steps, g (X _t-step) is the state of the historical time t-step, and X _t is the overall state of the irrigation system at the time t;

Correcting the RNN predictions by a kalman filter, the kalman filter formula being expressed as:

in the formula, Preliminary prediction results given for an RNN model, X _t as a system state vector, Y _t as a sensor data vector, K _t as an adaptive gain matrix and H as an observation matrix;

to optimize water resource allocation, by solving the optimal operation O _opt, the water resource utilization benefit U _water (t) is maximized and the operation adjustment cost C _adjust(O_o is minimized, the optimization objective function is:

Where O _o is an optional operational scheduling scheme, U _water (t) is a benefit function of water resource utilization, dependent on time t, and C _adjust(O_o) is an operational tuning cost, representing the resource consumption required to implement a particular operation O _o.

In one possible embodiment, the adaptive gain matrix K _t is determined based on the following equation:

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, and R _t is the covariance matrix of the measurement noise.

In a possible implementation manner, the intelligent controller receives an adjustment instruction of the cloud server, automatically adjusts irrigation system parameters, and includes:

Constructing a nonlinear self-adaptive control model, and describing by the following formula:

Wherein u (t) is the output control quantity of the controller at the moment of time t, y (t) is the state variable of the current system, and y _set (t) is the target value set by the controller;

the adaptive gain matrix K adjustment rule is determined based on the following equation:

Wherein K ₀ is an initial gain value, gamma is an adaptive adjustment coefficient, sensitivity is a Sensitivity parameter, and y (t) -y _set (t) is a deviation between a current state and a set value.

In a second aspect, the present application provides an intelligent monitoring and adjusting reclaimed water irrigation device, comprising:

the deployment unit is used for deploying a sensor network, and the sensor network comprises a water quality sensor, a flow sensor and a pressure sensor;

The monitoring unit is used for monitoring the parameters of the irrigation system in real time by the sensor network and sending the parameters to the intelligent controller;

the transmission unit is used for uploading the parameters to the cloud server by the intelligent controller;

The analysis unit is used for analyzing the parameters through the intelligent control algorithm by the cloud server and dynamically adjusting water resource allocation;

The receiving unit is used for receiving the adjusting instruction of the cloud server by the intelligent controller and automatically adjusting the irrigation system parameters.

In a third aspect, an electronic device comprising a memory, a processor and a computer program stored in said memory and executable on said processor, characterized in that said processor is adapted to implement the steps of the intelligent monitoring and regulation regeneration water irrigation method according to any of claims 1-7 when executing the computer program stored in the memory.

In a fourth aspect, the present application also proposes a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for intelligent monitoring and regulation of reclaimed water irrigation as described in any of claims 1 to 7.

In summary, the intelligent irrigation system can monitor key parameters in the irrigation system in real time by deploying a sensor network comprising a water quality sensor, a flow sensor and a pressure sensor, ensure that each irrigation link is in an optimal state, the intelligent controller can analyze according to data acquired by the sensor through an intelligent control algorithm of a cloud server, adjust the distribution of water resources in real time, avoid manual adjustment errors in traditional irrigation, greatly improve the irrigation efficiency, the optimized sensor arrangement and the self-adaptive weight adjustment model can reduce the transmission of redundant data while ensuring the monitoring coverage, effectively reduce the operation cost and the energy consumption of the system, thereby realizing the double saving of water resources and energy sources, the system can automatically adjust the irrigation parameters according to an adjustment instruction issued by the cloud server, and when abnormal conditions (such as water quality exceeding standard, flow abnormality and the like) are detected, the system can timely start an emergency response mechanism, ensure the safe and stable operation of the system, reduce the resource waste caused by the abnormal conditions, the intelligent algorithm based on the Recursive Neural Network (RNN) and the Kalman filtering can accurately improve the irrigation demand, and further optimize the water resource distribution and the actual water resource utilization.

Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the specification. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:

FIG. 1 is a schematic flow diagram of a method for intelligently monitoring and regulating reclaimed water irrigation according to the present application;

FIG. 2 is a schematic diagram of an intelligent monitoring and regulating reclaimed water irrigation architecture according to the present application;

FIG. 3 is a schematic diagram of an intelligent monitoring and regulating reclaimed water irrigation electronic device of the present application.

Detailed Description

The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments.

Referring to fig. 1, a schematic flow chart of a method for monitoring advanced geological forecast of a tunnel according to an embodiment of the present application may specifically include:

s110, deploying a sensor network, wherein the sensor network comprises a water quality sensor, a flow sensor and a pressure sensor;

By way of example, an efficient sensor network and an intelligent control system are constructed, key parameters (such as water quality, flow rate, pressure and the like) in an irrigation system are accurately monitored, delay is reduced through optimized sensor arrangement and data transmission paths, and data acquisition efficiency is improved.

First, the sensor network is optimally arranged. The sensor types include:

the water quality sensor detects the PH value, salt content, pollutant concentration, etc. of water.

Flow sensor, monitoring water flow speed and volume.

And the pressure sensor monitors the water pressure and ensures the normal operation of the water pump and the pipeline system.

The system adopts a distributed sensor arrangement model, and the model ensures the dense arrangement of the sensors in the key area through mathematical optimization so as to furthest improve the coverage and the accuracy of data. The core of the layout optimization problem is how to efficiently arrange the sensors in a non-uniform environment such that the coverage area is maximized while the data transmission costs are minimized.

The sensor network optimization problem can be reduced to a multi-objective optimization problem. Let the set of sensor nodes be s= (X ₁,Y₁),(X₂,Y₂),...,(X_N,Y_N), where N is the number of sensors and (X _i,Y_i) represents the coordinates of the first sensor. The goal of the optimization 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.

The optimization objective function is:

Where λ is the lagrange multiplier used to balance the target and constraint, a is the number of critical areas, i.e., the total number of important areas that need to be covered by the sensor, δ _a is whether each critical area has been covered, δ _a =1 if covered, or 0;w _i is the weight of the ith sensor, representing its importance (e.g., the sensor weight of the water source area is greater).

D (X _i,Y_i) is a distance function between the sensor and the control center, defined as Euclidean distance, expressed as:

Where (X _c,Y_c) represents the coordinates of the i-th sensor.

Constraint conditions ensuring that all critical areas are covered, i.e. that each critical area R _a has at least one sensor node S _i satisfying:

d(S_i,R_a)≤d_max

Where d _max is the effective radius of coverage of the sensor.

The application introduces an adaptive adjustment formula of the sensor weight, the weight is not only influenced by the environment, but also related to mutual information between the sensors, namely, if the information redundancy acquired by the two sensors is higher, one weight needs to be reduced.

An adaptive weight adjustment formula:

in the formula, The method comprises the steps of obtaining initial weight of an ith sensor, obtaining mutual information quantity between the sensors S _i and S _j, wherein the mutual information quantity is the similarity of information collected by the two sensors, the mutual information quantity is high, the data redundancy is high, and alpha is an adjusting coefficient and used for balancing the initial weight and the information redundancy.

S120, monitoring irrigation system parameters in real time by a sensor network, and sending the parameters to an intelligent controller;

For example, to improve the data transmission efficiency, the data transmission path from the sensor to the central controller needs to be optimized, and all possible transmission paths p= { P ₁,P₂,...,P_M }, one optimal path P _optimal needs to be selected, so that the total transmission cost and delay are minimized.

The optimal path selection formula:

Where P _route is a candidate path, P _k is a k-th transmission path, P _optimal is an optimal transmission path, D _lat(P_k) is a delay of data transmission, and the longer path and the lower bandwidth are affected by the path length and the network bandwidth, and C _trans(P_k) is a cost of data transmission through the path P _k, and the transmission energy consumption and the data amount are considered and expressed as:

Wherein E _l is the energy consumption of node L on the path, L _l is the data quantity transmitted through the path;

Illustratively, the sensor placement optimization formula reduces the distance to the central controller by adjusting the sensor position, while adjusting the sensor density according to the needs of different areas. And a data transmission path optimization formula is adopted, and a path with the lowest transmission energy consumption and the smallest delay is selected, so that the rapidity and the high efficiency of data transmission are ensured. And the mutual information quantity in the weight formula is used for judging the redundancy degree of different sensors, and if the information acquired by the two sensors is similar, the weight is automatically adjusted, so that the transmission of redundant data is reduced.

S130, the intelligent controller uploads the parameters to the cloud server;

By way of example, the intelligent controller and the internet of things platform upload collected irrigation system data to the cloud server in real time to realize remote monitoring. The intelligent controller gathers the data that each sensor gathered and uploads to the high in the clouds through thing networking platform. In order to improve the data transmission stability, a dynamic distributed data fusion model is used, so that the transmission delay of the data between network nodes is minimized, and the data accuracy is ensured.

The multidimensional space-time data fusion model is characterized in that data acquired by a sensor often have space-time correlation, so that the data are required to be fused and preprocessed before being transmitted. Assuming that the value acquired by each sensor S _i at time instant is S _i (t), the total data fusion function can be expressed as:

Wherein S _i (t) is the acquisition value of the sensor S _i at time t, beta and epsilon are weight coefficients for respectively controlling the influence of direct fusion and space-time association, gamma _ij is the space-time association degree between the sensors S _i and S _j and reflects the correlation of the acquisition values of the two sensors at different times, and delta t is time delay and represents the influence of the data of the previous time step on the current data.

The spatio-temporal correlation degree γ _ij is expressed as:

Where H (S _i) and H (S _j) are the entropy of the sensors S _i and S _j, respectively, representing the uncertainty of the data.

S140, the cloud server analyzes the parameters through an intelligent control algorithm and dynamically adjusts water resource allocation;

By way of example, data received through a cloud server is analyzed and predicted using an intelligent control algorithm, potential problems in the system are identified, and optimization decisions are presented. The purpose is in the monitoring regeneration water irrigation process, ensures the high-efficient utilization and the reasonable distribution of water resource, avoids waste, and realizes automatic adjustment.

The system analyzes and predicts the data (such as parameters of water quality, flow, pressure and the like) acquired by the sensor network by using an algorithm combining self-adaptive control and deep learning after the data are processed by the cloud server. The system combines a multidimensional Recurrent Neural Network (RNN) technology and an Adaptive Kalman Filtering (AKF) technology, can detect and predict potential problems in an irrigation system in real time, and performs optimal scheduling according to a prediction result to provide an optimal irrigation scheme.

The multi-dimensional prediction and self-adaptive filtering model is used for predicting future system states and continuously correcting prediction errors according to sensor data. The optimal scheduling model is used for generating an optimal irrigation scheme, and global optimization is achieved by maximizing water resource utilization benefit and minimizing operation and adjustment cost.

A multidimensional prediction and adaptive filtering model comprising:

The system state X _t represents the overall state of the irrigation system at time t, including multiple dimensions of water quality, flow, pressure, etc., and a Recurrent Neural Network (RNN) is used in combination with adaptive kalman filtering to predict the future state X _t+1, and the prediction stage (prediction based on historical data) of the recurrent neural network has the formula:

in the formula, For the next time state X _t+1;f(X_t predicted based on the historical time series data) is a state transfer function, the prediction of the system state at the current time t is assumed that the system state changes along with time, and the state transfer function f can describe the internal dynamic state of the system, for example, in water resource scheduling, the natural change trend of water flow can be represented, W is the number of time steps, W _step is the weight of each time step, and the importance of the historical data on the current prediction is reflected. The data in the shorter time may have a larger weight than the data in the longer time, g (X _t-step) is the state of the history time t-step, reflects the system state change in the past at a certain time, and supports the background of the current state.

A correction stage of the kalman filter (in combination with correction of real-time observation data), at which the prediction from RNN is corrected by the kalman filter, and the observation data Y _t at the current time is combined to improve the accuracy of the prediction, the kalman filter formula can be expressed as:

in the formula, The preliminary prediction result given for the RNN model may have errors because it is derived based only on historical data, X _t is a system state vector representing the current system state, Y _t is a sensor data vector representing the observed data collected by the sensor at time t, the sensor observed data at the current time t. The sensor observation provides real reflection of the current system state and is used for correcting the prediction result of RNN, K _t is an adaptive gain matrix, and is dynamically adjusted through Kalman filtering and used for correcting the error of system prediction, and the Kalman gain determines how to adjust the prediction result to be more approximate to the actual observation value. The magnitude of the gain matrix K _t is determined by the uncertainty of system prediction and observation noise, and can adapt to the uncertainty of the system by calculating Kalman gain, and H is an observation matrix and represents the mapping from the state to the sensor observation data.

The kernel of the Kalman filtering is to correct the system state by using sensor data, dynamically adjust the gain matrix K _t to minimize the prediction error, and the state updating formula of the Kalman filtering is as follows:

K_t＝P_t·H^T·(H·P_t·H^T+R_t)^-1

Wherein P _t is a covariance matrix of the system state, which represents the state uncertainty, H is an observation matrix, the system state is mapped into sensor data, and R _t is a covariance matrix of the measurement noise.

Optimizing a scheduling model, comprising:

To optimize water resource allocation, the system maximizes water resource utilization benefit U _water (t) and minimizes operational tuning cost C _adjust(O_o by solving for optimal operation O _opt, optimizing the objective function as:

Illustratively, the RNN model recursively predicts future conditions via historical data, and predicts future irrigation demands using historical water quality, flow, pressure, etc. The adaptive Kalman filtering corrects the system prediction error through the real-time data of the sensor, so that the accuracy of prediction is ensured. The optimal scheduling model generates a set of optimal irrigation scheme according to the current system state, so that irrigation requirements can be met, the utilization efficiency of water resources can be maximized, and unnecessary waste is reduced.

And S150, the intelligent controller receives an adjusting instruction of the cloud server and automatically adjusts irrigation system parameters.

By way of example, through the instruction issued by the cloud server, the intelligent controller automatically adjusts various parameters of the irrigation system, ensures that the running state of the system can be kept stable under various changing environments, and realizes efficient irrigation resource utilization.

The intelligent controller dynamically adjusts the operation parameters of the irrigation system according to the adjustment instruction generated by the cloud server after the data analysis and decision (S140). This includes valve opening, pump start-up and shut-down times, flow control, etc. In the process, a nonlinear self-adaptive control algorithm is adopted, so that the system can adapt to the change of various environmental parameters (such as water pressure, flow, humidity and the like) in the system, and the irrigation system can still operate efficiently and stably under the changed conditions.

The nonlinear self-adaptive control model is characterized in that a control quantity u (t) (such as a valve opening degree or a start-stop instruction of a pump) in the system is adjusted in real time according to the current state of the system, and the nonlinear self-adaptive control model can be described by the following formula:

Wherein u (t) is the output control quantity of the controller at the moment of 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 target value set by the system, such as the water flow or pressure set value required to be achieved by the system, and K is the self-adaptive gain matrix for dynamically adjusting the response force of the controller to the state deviation.

State error control, the first term of the above equation is used to directly respond to the deviation between the system state and the set point. If the current system state deviates from the target set point, the controller will correct this deviation by adjusting the valve opening or the state of the pump. The magnitude of the gain matrix K determines the speed and magnitude of the response of the controller to such deviations.

The second term of the above equation is the integral part of the controller to eliminate steady state errors in the system. The system plays a role of accumulating errors in the control system, and ensures that the system can realize accurate set value tracking in a long-term operation process.

In order to improve the robustness and the adaptability of the control system, the gain matrix K can be dynamically adjusted according to a feedback signal running in real time, and the basic rule of the gain matrix adjustment can be described by the following formula:

Wherein K ₀ is an initial gain value, gamma is an adaptive adjustment coefficient, sensitivity is a Sensitivity parameter, the speed and the amplitude of gain adjustment are determined, and y (t) -y _set (t) is the deviation between the current state and the set value.

The formula shows that when the deviation of the system state from the target value is large, the gain matrix increases rapidly, and the response of the controller becomes more intense to correct the system state as soon as possible. When the deviation is smaller, the gain matrix tends to be stable, so that the system is ensured to keep stable operation, and unnecessary over-adjustment is avoided.

By combining the nonlinear self-adaptive control model and the real-time feedback mechanism, the irrigation system can realize highly intelligent automatic adjustment and ensure the optimal effect of water resource utilization.

For example, when the system detects an abnormal condition (such as exceeding of water quality parameters and abnormal flow), the intelligent controller can immediately start an emergency treatment mechanism so as to ensure safe and stable operation of the irrigation system and avoid resource waste or system failure.

The system recognizes the running state of the system, especially the abnormality of water quality and flow parameters in real time by the technology of combining a dynamic fault detection algorithm and fuzzy logic control. The anomaly detection relies on time series analysis, and by combining data in a sensor network, the problem can be identified in the shortest time, and corresponding processing measures can be quickly taken through an emergency response control mechanism. In the emergency response process, the intelligent controller can stabilize the system according to preset rules of the system (such as closing a valve, starting a standby pump and the like) and restore the normal state.

And the dynamic fault detection model is used for detecting abnormal states in the system, such as water quality exceeding standard, excessive flow and the like. By calculating the rate of change of system state and the difference between sensors, the source of the anomaly is located quickly, expressed as:

Wherein R (t) is a fault diagnosis function for evaluating the abnormality degree of the system at time t, S _i (t) is the measured value (such as parameters of water quality, flow and the like) of the ith sensor at the time t, W _i is the weight of the ith sensor and reflects the importance of the sensor to the system. For example, sensors in critical areas may be given higher weights; For adjusting parameters for balancing the influence of the state change rate and the difference between the sensors; And S _i(t)-S_j(t))² is the difference of the measured values of the ith sensor and the jth sensor, and represents the abnormal difference between the two sensors, if the difference is too large, the system is indicated to have abnormality.

Sensor state change-the first term evaluates the operating state of the system by the rate of change of the sensor measurements. If parameters such as water quality or flow rate in the system change too fast, the system can consider that an abnormal condition exists. The sensor weight W _i ensures that the sensors of the critical area can react faster.

Sensor differential analysis-a second term is used to compare measurements from different sensors. When multiple sensors in the system measure the same parameter, if some sensors differ too much from others, it may be that the area is abnormal.

And the system generates an emergency response strategy according to the fuzzy logic emergency response control model after the abnormality is detected. The model responds based on membership functions of the sensor states and emergency rules preset by the system.

The control rules for the emergency response may be expressed by the following formula:

E_resp＝min(μ_A(A_i),μ_B(B_j))

Wherein E _resp is the control output of the emergency response and represents the execution intensity of the current emergency treatment, mu _A(A_i) is the membership function of the abnormal state A _i and represents the severity of the current abnormal state, mu _B(B_j) is the membership function of the emergency response rule B _j and represents the execution condition of the corresponding emergency treatment measures.

Membership functions mu _A and mu _B are core concepts in fuzzy logic for defining the abnormal state of the system and the degree of execution of the emergency handling measures. For example, when the water quality detects a contaminant over-standard, the system will determine the severity of the contaminant over-standard by μ _A and match the most appropriate emergency response measure by μ _B, such as closing a valve or activating a filtration system.

The operation of min in the model shows that the execution strength of the emergency response depends on the matching degree of the abnormal state and the response rule. Only when the abnormal state reaches a certain severity will the system perform the corresponding enforcement measures.

Through the combination of dynamic fault detection and fuzzy logic emergency response, the system can realize rapid and accurate exception handling in a complex environment, and ensure stable and efficient operation of an irrigation system.

Referring to fig. 2, a schematic structural diagram of an intelligent monitoring and adjusting reclaimed water irrigation device according to an embodiment of the present application includes:

the deployment unit 21 is used for deploying a sensor network, and the sensor network comprises a water quality sensor, a flow sensor and a pressure sensor;

the monitoring unit 22 is used for monitoring irrigation system parameters in real time by the sensor network and sending the parameters to the intelligent controller;

The transmission unit 23 is used for uploading the parameters to the cloud server by the intelligent controller;

The analysis unit 24 is used for analyzing the parameters through an intelligent control algorithm by the cloud server and dynamically adjusting water resource allocation;

and the receiving unit 25 is used for receiving the adjustment instruction of the cloud server by the intelligent controller and automatically adjusting the irrigation system parameters.

Referring to fig. 3, an embodiment of the present application further provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and capable of running on the processor, wherein the processor 320 implements any one of the above-mentioned methods for intelligently monitoring and adjusting the irrigation of reclaimed water when executing the computer program 311.

Since the electronic device described in this embodiment is a device for implementing the intelligent monitoring and adjusting device for secondary water irrigation according to the embodiment of the present application, based on the method described in this embodiment, those skilled in the art can understand the specific implementation of the electronic device and various modifications thereof, so how the electronic device implements the method in this embodiment of the present application will not be described in detail herein, and only those devices for implementing the method in this embodiment of the present application will belong to the scope of protection intended by the present application.

In a specific implementation, any implementation manner of the embodiment corresponding to the first aspect may be implemented when the computer program 311 is executed by a processor.

In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-readable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

Embodiments of the present application also provide a computer program product comprising computer software instructions that, when run on a processing device, cause the processing device to perform the flow of the intelligent monitoring and regulation reclaimed water irrigation method in the corresponding embodiment of fig. 1.

The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may 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 may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). Computer readable storage media can be any available media that can be stored by a computer or data storage devices such as servers, data centers, etc. that contain an integration of one or more available media. Usable media may be magnetic media (e.g., floppy disks, hard disks, magnetic tape), optical media (e.g., DVD), or semiconductor media (e.g., solid State Disk (SSD)) or the like.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of 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.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. The storage medium includes a U disk, a removable hard disk, a Read-only memory (ROM), a random access memory (RandomAccess Memory, RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.

The foregoing embodiments are merely for illustrating the technical solution of the present application, but not for limiting the same, and although the present application has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art that modifications may be made to the technical solution described in the foregoing embodiments or equivalents may be substituted for parts of the technical features thereof, and that such modifications or substitutions do not depart from the spirit and scope of the technical solution of the embodiments of the present application in essence.

While preferred embodiments of the present description have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the disclosure.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present specification without departing from the spirit or scope of the specification. Thus, if such modifications and variations of the present specification fall within the scope of the claims and the equivalents thereof, the present specification is also intended to include such modifications and variations.

Claims

1. A method for reclaimed water irrigation 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 method for reclaimed water irrigation with intelligent monitoring and regulation according to claim 1, characterized in that the deployment of the sensor network comprises:

The set of sensor nodes is S = (X ₁ , Y ₁ ), (X ₂ , Y ₂ ), ..., (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 sensors 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 areas; _δa is whether each key area has been covered; w _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:

Where, (X _c , Y _c ) represents the coordinates of the i-th sensor;

Cover all key areas, that is, in each key area Ra _, at least one sensor node _Si satisfies:

d(S _i ,R _a )≤d _max

Where d _max is the effective coverage radius of the sensor.

3. The intelligent monitoring and regulating reclaimed water irrigation method according to claim 2, characterized in that the weight w _i of the sensor is 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 mutual information between sensors S _i and S _j ; α is the adjustment coefficient;

The calculation formula of mutual information I(S _i ,S _j ) is:

Where p( _xi , _xj ) is the joint probability distribution of the data collected by sensors _Si and _Sj ; p( _xi ) and p( _xj ) are their respective marginal probability distributions.

4. The method for reclaimed water irrigation with intelligent monitoring and regulation according to claim 1 is characterized in that the intelligent controller performs a data fusion operation before uploading the parameters to the cloud server, including:

Assume that the value collected by each sensor _Si at time t is _Si (t), and the data fusion function is expressed as:

Where, _Si (t) is the collected value of sensor _Si at time t; β and ε are weight coefficients, which control the influence of direct fusion and spatiotemporal correlation terms respectively; _γij is the spatiotemporal correlation between sensors _Si and _Sj ; Δt is the time delay, which indicates the influence of the data of the previous time step on the current data;

The spatiotemporal correlation γ _ij is expressed as:

Where H(S _i ) and H(S _j ) are the entropies of sensor S _i and sensor S _j , respectively.

5. The method for reclaimed water irrigation with intelligent monitoring and regulation according to claim 1 is characterized in that the cloud server analyzes parameters through an intelligent control algorithm and dynamically adjusts water resource allocation, including:

Use a recurrent neural network to predict the future state _Xt+1 , the formula is:

In the formula, is the next state _Xt+1 predicted based on the historical time series data; f( _Xt ) is the state transfer function; W is the number of time steps; _Wstep is the weight of the time step; g(Xt _-step ) is the state at the historical moment t-step; _Xt 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; _Xt is the system state vector; _Yt is the sensor data vector; _Kt is the adaptive gain matrix; H is the observation matrix;

In order to optimize water resource allocation, the optimal operation O _opt is solved to maximize the water resource utilization benefit u _water (t) and minimize the operation adjustment cost C _adjust (O _o ). The optimization objective function is:

Where 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, which represents the resource consumption required to implement a specific operation O _o .

6. The method for reclaimed water irrigation with intelligent monitoring and regulation according to claim 5, characterized in that the adaptive gain matrix K _t is determined based on the following formula:

K _t -P _t ·H ^T ·(H·P _t ·H ^T +R _t ) ^-1

Where _Pt is the covariance matrix of the system state; _Rt is the covariance matrix of the measurement noise.

7. The method for reclaimed water irrigation with intelligent monitoring and regulation 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 target value set; 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 by comprising:

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, wherein when the computer program is executed by a processor, the intelligent monitoring and regulating reclaimed water irrigation method according to any one of claims 1 to 7 is implemented.