Irrigation monitoring system for grass original ecological restoration

Abstract

The invention relates to the technical field of grassland restoration, in particular to an irrigation monitoring system for grassland original ecological restoration, which comprises an irrigation data collection and analysis module, an irrigation demand prediction module, an irrigation strategy intelligent adjustment module, an irrigation equipment state monitoring module and an equipment fault automatic troubleshooting module. A sensor network is deployed to collect data, and the collected data is preprocessed, so that the accuracy of the data is improved; the irrigation demand is predicted by using the prediction model, and manual intervention is reduced; the irrigation strategy is automatically adjusted according to the predicted irrigation requirement, and automatic management of irrigation is achieved; the state parameters of the irrigation equipment are monitored in real time, so that safety accidents caused by equipment faults can be avoided; by using the Bayesian theorem and combining the early warning signal and the equipment state parameters monitored in real time, the fault reason is positioned, so that measures can be taken immediately. The method is used for solving the technical problem that the monitoring management level of current grassland recovery is not high.

Description

Technical Field

[0001] The invention relates to the technical field of grassland restoration, and in particular to an irrigation monitoring system for grassland ecological restoration. Background Art

[0002] In the current grassland restoration monitoring and management, the following problems still exist: the low intelligence level of irrigation demand prediction and the lack of intelligent irrigation demand prediction means make it impossible for irrigation management to accurately predict and adjust according to the real-time changes of grassland ecology, which may lead to waste or shortage of irrigation resources; irrigation strategy adjustment relies on manual experience. Traditional irrigation strategy adjustment mainly relies on manual experience and judgment, lacking an automated and intelligent adjustment mechanism, which makes it difficult for irrigation management to adapt to the complexity and variability of grassland ecology, affecting irrigation efficiency and effect; irrigation equipment status monitoring is not timely. The operating status of irrigation equipment is crucial to the stability and reliability of the irrigation system, but traditional monitoring methods often have lags, making it difficult to detect equipment failures or abnormal conditions in time, which may lead to problems such as irrigation interruption or waste of water resources; equipment fault troubleshooting is time-consuming and inefficient. When irrigation equipment fails, traditional troubleshooting methods often take a long time and need to rely on the experience and skills of professionals, which not only affects the normal operation of the irrigation system, but also increases the maintenance cost and time cost. Therefore, a series of targeted methods are urgently needed to deal with these problems in order to improve the monitoring and management level of grassland restoration. Summary of the invention

[0003] The purpose of the present invention is to solve the problems in the background technology and to propose an irrigation monitoring system for grassland ecological restoration.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions: An irrigation monitoring system for grassland ecological restoration, comprising: an irrigation data collection and analysis module, an irrigation demand prediction module, an irrigation strategy intelligent adjustment module, an irrigation equipment status monitoring module, and an equipment fault automatic troubleshooting module; Irrigation data collection and analysis module: deploy a sensor network in the grassland ecological restoration area to collect original soil moisture values ​​and NDVI values; pre-process the collected original soil moisture values ​​and NDVI values ​​to obtain soil moisture data sets and vegetation growth status data sets; the pre-processing includes denoising and truncation processing; Irrigation demand prediction module: further analyze and process the soil moisture data set and the vegetation growth status data set to obtain fusion features; use the support vector machine algorithm to establish an irrigation prediction model to predict irrigation demand; Irrigation strategy intelligent adjustment module: automatically adjusts the irrigation strategy according to the irrigation demand predicted by the irrigation prediction model; the irrigation strategy includes irrigation water volume, irrigation frequency and irrigation method; Irrigation equipment status monitoring module: real-time monitoring of irrigation equipment status parameters and analysis of irrigation equipment status parameters; if an abnormal equipment status is detected, an early warning signal is immediately issued; the irrigation equipment status parameters include current, voltage, water pressure and flow; Automatic equipment fault troubleshooting module: Using Bayesian theorem, combined with early warning signals and real-time monitoring of irrigation equipment status parameters, it automatically analyzes possible fault causes of irrigation equipment.

[0005] It should be noted that the application object of the irrigation monitoring system for grassland ecological restoration in the present invention can be the field of grassland ecological restoration. Specifically, it can be used to conduct a comprehensive analysis of soil moisture and vegetation growth status data. Through multiple core links such as irrigation data collection and analysis, irrigation demand prediction, intelligent adjustment of irrigation strategies, irrigation equipment status monitoring, and automatic troubleshooting of equipment failures, efficient management and intelligent decision-making of grassland irrigation can be achieved; at the same time, the system also promotes the efficiency and quality of grassland ecological restoration, and effectively improves the monitoring and management level of grassland ecological environment.

[0006] Furthermore, the irrigation data collection and analysis module deploys a sensor network in the grassland ecological restoration area, and the process of collecting the original soil moisture value and NDVI value includes: Set the grassland ecological restoration area as a flat area , and divided into Sub-areas ;in, Indicates that the plane area The number of sub-regions divided, Indicates that the plane area The sub-region index, and ; In each sub-area Uniform deployment within Soil moisture sensors, the original soil moisture value measured by the soil moisture sensor is ;in, Indicates the index of the soil moisture sensor, Represents each sub-region The number of soil moisture sensors uniformly deployed within ; For flat areas , the plane area Split into Vegetation monitoring sub-areas ;in, Indicates that the plane area The number of segmented vegetation monitoring sub-areas, Indicates that the plane area The index of the segmented vegetation monitoring sub-area, and ; In each vegetation monitoring sub-area The number of internal deployments is NDVI sensor and get the original NDVI value measured by the NDVI sensor ;in, represents the index of the NDVI sensor, and ; It is understandable that the NDVI sensor is a sensor that evaluates vegetation coverage based on the measurement principle of the difference in plant reflectance of visible light and near-infrared light. It has broad application prospects and important scientific value in agriculture, forestry, ecological environment monitoring and other fields.

[0007] Furthermore, the irrigation data collection and analysis module preprocesses the collected original soil moisture values ​​and NDVI values ​​to obtain a soil moisture data set and a vegetation growth status data set, including the following process: The raw soil moisture value measured by the soil moisture sensor , use mean filtering method for denoising: define the filter window size as , then the soil moisture value after denoising is for: , where Indicates the filter window index; when or When , boundary processing is performed; It is understandable that when the window slides to the boundary of the original data, that is, when the starting position of the window is less than 1 (the left boundary of the window exceeds the data range) or the ending position of the window is greater than (The right edge of the window exceeds the data range), there is a problem, because the window no longer contains complete original data, and the average calculation cannot be performed directly. The valid data in the window can be used for the average calculation, and the part beyond the edge is ignored; For the raw NDVI values ​​measured by the NDVI sensor Since the range of NDVI value is [-1, 1], if the original NDVI value If it is greater than 1 or less than -1, truncation is used to obtain the truncated NDVI value. ,Right now ; The preprocessed soil moisture values ​​are aggregated into a soil moisture dataset At the same time, the preprocessed NDVI values ​​are used to construct a vegetation growth status dataset for vegetation growth status assessment. ; The soil moisture dataset and vegetation growth status dataset Integrate into a unified data center Above; the data middle platform is used to store the pre-processed data.

[0008] Furthermore, the irrigation demand prediction module further analyzes and processes the soil moisture data set and the vegetation growth status data set to obtain fusion features; the support vector machine algorithm is used to establish an irrigation prediction model. The process of predicting irrigation demand includes: Extract soil moisture dataset from the data center and vegetation growth status dataset ; The soil moisture dataset and vegetation growth status dataset Perform polynomial feature mapping separately: , In the formula, represents the highest degree of a polynomial, The polynomial eigenvectors representing soil moisture and vegetation growth conditions respectively; The principal component analysis method is used to reduce the dimension and fuse the polynomial feature vectors of the mapped soil moisture and vegetation growth conditions to obtain the fusion feature ; The specific process is as follows: Step 1: Use the polynomial kernel function to calculate the similarity of the polynomial eigenvectors of soil moisture and vegetation growth conditions in the kernel space: , In the formula, represents the similarity measure between two polynomial eigenvectors in kernel space; represents the kernel matrix; The inner product of the polynomial eigenvectors representing soil moisture and vegetation growth conditions; is a constant term used to adjust the shape and range of the kernel function; Step 2: Kernel matrix Centralize: Calculate the mean vector of the kernel matrix and ,in express All 1 vector of ; centralized kernel matrix , where express The matrix of all 1s, is the transpose of the matrix; Step 3: Centralize the kernel matrix Perform eigenvalue decomposition to obtain the eigenvalues ​​and corresponding eigenvectors: , where represents the matrix of eigenvectors, is a diagonal matrix whose diagonal elements are the kernel matrix The characteristic value of Step 4: According to the contribution of the eigenvalue (i.e., the size of the eigenvalue), select the principal component with higher contribution as the retained feature; the higher the contribution, the stronger the explanatory power of the principal component for the data; Step 5: Project the data sets of soil moisture and vegetation growth conditions into the low-dimensional space composed of the selected principal components to obtain soil moisture characteristics. and vegetation growth characteristics ; Wherein, it can be realized by calculating the inner product of the data set of soil moisture and vegetation growth condition and the polynomial characteristic vector of the selected soil moisture and vegetation growth condition; Step 6: Use the weighted fusion method to fuse the soil moisture characteristics and vegetation growth characteristics to obtain the fusion characteristics : , where They are respectively expressed as the weights corresponding to the soil moisture characteristics and the vegetation growth condition characteristics; The fusion features As input features for irrigation prediction models; Irrigation needs As the prediction target value of the irrigation prediction model; wherein the irrigation demand includes whether irrigation is needed, the amount of irrigation, etc., and the irrigation demand corresponds to the input characteristics of the irrigation prediction model; Then there is an optimization objective to optimize the irrigation prediction model and minimize the prediction error of irrigation demand: , In the formula, is the Grarange multiplier; is the slack variable; is the penalty parameter; represents the input feature index, Indicates the difference from The input feature index of Indicates the number of input features; represents the kernel function; Among them, the constraints of the optimization objective are: ; The decision function is obtained by optimizing the irrigation prediction model. : , where is a sign function used to map a value to 1 or -1. If the expression in the brackets is positive, then The function returns 1 if the expression in the brackets is negative. The function returns -1; represents the bias term. In support vector machines and other linear models, the bias term is used to adjust the position of the decision boundary to better fit the training data. The decision function is regarded as the prediction result of the irrigation prediction model, that is, the predicted irrigation demand. .

[0009] Furthermore, the process of the irrigation strategy intelligent adjustment module automatically adjusting the irrigation strategy according to the irrigation demand predicted by the irrigation prediction model includes: Irrigation demand forecasted by irrigation forecast model , set the maximum irrigation water volume of the irrigation equipment to The minimum irrigation water volume is and the initial irrigation frequency ;when When , the irrigation frequency is reduced, and the reduction ratio is defined as , get the new irrigation frequency ;when When , the irrigation frequency is increased, and the increase ratio is defined as , get the new irrigation frequency ; For irrigation water , the irrigation water volume per unit time of the irrigation equipment is marked as , then the irrigation water volume is ; At the same time, the irrigation method is adjusted according to soil moisture and vegetation growth conditions; among them, irrigation methods include sprinkler irrigation, flood irrigation, infiltration irrigation, micro-sprinkler irrigation, etc.

[0010] Furthermore, the irrigation equipment status monitoring module monitors the irrigation equipment status parameters in real time and analyzes the irrigation equipment status parameters; if an abnormal equipment status is detected, the process of immediately sending an early warning signal includes: Install sensor components on irrigation equipment to monitor irrigation equipment status parameters in real time; Preset the current range for normal operation of irrigation equipment and voltage range , respectively calculate the current deviation and voltage deviation ; Assume that there is a relationship between water pressure and flow , for the measured water pressure value and flow value , calculate the flow deviation ;in, represent the mean current and voltage respectively, Indicates the parameter index, represents the proportionality coefficient; Based on the calculated current deviation, voltage deviation and flow deviation, a current deviation threshold, a voltage deviation threshold and a flow deviation threshold are set respectively. If the current deviation is greater than the current deviation threshold, the current is determined to be abnormal. If the voltage deviation is greater than the voltage deviation threshold, the voltage is determined to be abnormal. If the flow deviation is greater than the flow deviation threshold, the flow is determined to be abnormal. When any state parameter of current, voltage and flow is judged to be abnormal, an early warning signal will be issued immediately.

[0011] Furthermore, the automatic troubleshooting module for equipment failures uses the Bayesian theorem and combines the early warning signals and the real-time monitored irrigation equipment status parameters to automatically analyze the possible causes of failures of the irrigation equipment. The process includes: Sort out the fault causes of irrigation equipment from the logs and get a set of fault causes ; Get early warning signals and irrigation equipment status parameters ; According to Bayes' theorem formula , In the formula, Indicates the cause of the fault The prior probability of occurrence can be obtained based on historical fault data statistics, where Indicates the fault cause index; Indicates the cause of the fault Warning signs appear below and irrigation equipment status parameters probability; Indicates a warning signal and irrigation equipment status parameters The probability of Calculated, Indicates the number of fault causes; Calculate each failure cause The posterior probability , get the most probable fault cause , which is the most likely cause of irrigation equipment failure; The most likely cause of irrigation equipment failure and its related irrigation equipment status parameters are sent to maintenance personnel.

[0012] Compared with the existing technology, the present invention provides an irrigation monitoring system and method for grassland ecological restoration, which has the following advantages: 1. The present invention can collect soil moisture and NDVI values ​​in real time and accurately by deploying sensor networks in grassland ecological restoration areas, providing a reliable data basis for subsequent irrigation decisions; by denoising and truncating the original data, data errors are effectively reduced, and the accuracy and availability of the data set are improved; by integrating the processed soil moisture data set and vegetation growth status data set into a unified data platform, centralized management and efficient use of data are facilitated, providing convenience for subsequent data analysis; 2. The present invention uses a support vector machine algorithm to establish an irrigation prediction model, which can predict irrigation demand based on soil moisture and vegetation growth data, thereby realizing intelligent prediction of irrigation demand; by predicting irrigation demand, irrigation time and water volume can be reasonably arranged to avoid over-irrigation or under-irrigation, thereby improving irrigation efficiency and water resource utilization; by automatically adjusting irrigation strategies, including irrigation water volume, irrigation frequency and irrigation method, according to the irrigation demand predicted by the irrigation prediction model, flexible adjustment of irrigation strategies is realized, which is helpful to promote the restoration and development of grassland ecology; 3. The present invention can timely detect equipment failure or abnormal conditions by real-time monitoring of irrigation equipment status parameters, including current, voltage, water pressure and flow. When an abnormal equipment status is detected, an early warning signal is immediately issued, which helps to avoid problems such as irrigation interruption or waste of water resources caused by equipment failure. At the same time, equipment failure can be timely detected and handled to improve the reliability and stability of irrigation equipment. By utilizing Bayes' theorem and combining early warning signals with real-time monitored irrigation equipment status parameters, the present invention automatically analyzes possible causes of irrigation equipment failures, which helps to quickly locate the fault point, and reduces the time and cost of manual troubleshooting by automatically troubleshooting, thereby improving maintenance efficiency.

[0013] In summary, the present invention constitutes an intelligent, efficient and safe system through five links: irrigation data collection and analysis, irrigation demand prediction, irrigation strategy adjustment, equipment status monitoring and automatic troubleshooting of equipment faults, ensuring the efficient and stable operation of a subsequent irrigation monitoring system for grassland ecological restoration. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a module diagram of an irrigation monitoring system for grassland ecological restoration proposed by the present invention. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the implementation regulations described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] Reference Figure 1 , an irrigation monitoring system for grassland ecological restoration, the system includes an irrigation data collection and analysis module, an irrigation demand prediction module, an irrigation strategy intelligent adjustment module, an irrigation equipment status monitoring module and an equipment fault automatic troubleshooting module; Irrigation data collection and analysis module: deploy a sensor network in the grassland ecological restoration area to collect original soil moisture values ​​and NDVI values; pre-process the collected original soil moisture values ​​and NDVI values ​​to obtain soil moisture data sets and vegetation growth status data sets; the pre-processing includes denoising and truncation processing; Irrigation demand prediction module: further analyze and process the soil moisture data set and the vegetation growth status data set to obtain fusion features; use the support vector machine algorithm to establish an irrigation prediction model to predict irrigation demand; Irrigation strategy intelligent adjustment module: automatically adjusts the irrigation strategy according to the irrigation demand predicted by the irrigation prediction model; the irrigation strategy includes irrigation water volume, irrigation frequency and irrigation method; Irrigation equipment status monitoring module: real-time monitoring of irrigation equipment status parameters and analysis of irrigation equipment status parameters; if an abnormal equipment status is detected, an early warning signal is immediately issued; the irrigation equipment status parameters include current, voltage, water pressure and flow; Automatic equipment fault troubleshooting module: Using Bayesian theorem, combined with early warning signals and real-time monitoring of irrigation equipment status parameters, it automatically analyzes possible fault causes of irrigation equipment.

[0017] It should be noted that the application object of the irrigation monitoring system for grassland ecological restoration in the present invention can be the field of grassland ecological restoration. Specifically, it can be used to conduct a comprehensive analysis of soil moisture and vegetation growth status data. Through multiple core links such as irrigation data collection and analysis, irrigation demand prediction, intelligent adjustment of irrigation strategies, irrigation equipment status monitoring, and automatic troubleshooting of equipment failures, efficient management and intelligent decision-making of grassland irrigation can be achieved; at the same time, the system also promotes the efficiency and quality of grassland ecological restoration, and effectively improves the monitoring and management level of grassland ecological environment.

[0018] The irrigation data collection and analysis module deploys a sensor network in the grassland ecological restoration area to collect original soil moisture values ​​and NDVI values; the steps of preprocessing the collected original soil moisture values ​​and NDVI values ​​to obtain a soil moisture data set and a vegetation growth status data set include: Step 101: Set the grassland ecological restoration area as a plane area , and divided into Sub-areas ;in, Indicates that the plane area The number of sub-regions divided, Indicates that the plane area The sub-region index, and ; Step 102: In each sub-area Uniform deployment within Soil moisture sensors, the original soil moisture value measured by the soil moisture sensor is ;in, Indicates the index of the soil moisture sensor, Represents each sub-region The number of soil moisture sensors uniformly deployed within ; Step 103: For the plane area , the plane area Split into Vegetation monitoring sub-areas ;in, Indicates that the plane area The number of segmented vegetation monitoring sub-areas, Indicates that the plane area The index of the segmented vegetation monitoring sub-area, and ; Step 104: In each vegetation monitoring sub-area The number of internal deployments is NDVI sensor and get the original NDVI value measured by the NDVI sensor ;in, represents the index of the NDVI sensor, and ; In step 104, the NDVI sensor is a sensor that evaluates vegetation coverage based on the measurement principle of the difference in plant reflectance of visible light and near-infrared light. It has broad application prospects and important scientific value in the fields of agriculture, forestry, and ecological environment monitoring; Step 105: the original soil moisture value measured by the soil moisture sensor , use mean filtering method for denoising: define the filter window size as , then the soil moisture value after denoising is for: , where Indicates the filter window index; when or When , boundary processing is performed; In step 105, when the window slides to the boundary of the original data, that is, when the starting position of the window is less than 1 (the left boundary of the window exceeds the data range) or the ending position of the window is greater than (The right edge of the window exceeds the data range), there is a problem, because the window no longer contains complete original data, and the average calculation cannot be performed directly. The valid data in the window can be used for the average calculation, and the part beyond the edge is ignored; Step 106: The original NDVI value measured by the NDVI sensor Since the range of NDVI value is [-1, 1], if the original NDVI value If it is greater than 1 or less than -1, truncation is used to obtain the truncated NDVI value. ,Right now ; Step 107: Collect the preprocessed soil moisture values ​​into a soil moisture data set At the same time, the preprocessed NDVI values ​​are used to construct a vegetation growth status dataset for vegetation growth status assessment. ; Step 108: The soil moisture dataset and vegetation growth status dataset Integrate into a unified data center Above; the data middle platform is used to store the pre-processed data.

[0019] The irrigation demand prediction module further analyzes and processes the soil moisture data set and the vegetation growth status data set to obtain fusion features; the support vector machine algorithm is used to establish an irrigation prediction model. The steps for predicting irrigation demand include: Step 201: Extract soil moisture data set from the data center and vegetation growth status dataset ; Step 202: The soil moisture dataset and vegetation growth status dataset Perform polynomial feature mapping separately: , In the formula, represents the highest degree of a polynomial, The polynomial eigenvectors representing soil moisture and vegetation growth conditions respectively; Step 203: Use principal component analysis to perform dimension reduction and feature fusion processing on the polynomial feature vectors of the mapped soil moisture and vegetation growth conditions to obtain fusion features. , wherein the specific steps are as follows: Step 1: Use the polynomial kernel function to calculate the similarity of the polynomial eigenvectors of soil moisture and vegetation growth conditions in the kernel space: , In the formula, represents the similarity measure between two polynomial eigenvectors in kernel space; represents the kernel matrix; The inner product of the polynomial eigenvectors representing soil moisture and vegetation growth conditions; is a constant term used to adjust the shape and range of the kernel function; Step 2: Kernel matrix Centralize: Calculate the mean vector of the kernel matrix and ,in express All 1 vector of ; centralized kernel matrix , where express The matrix of all 1s, is the transpose of the matrix; Step 3: Centralize the kernel matrix Perform eigenvalue decomposition to obtain the eigenvalues ​​and corresponding eigenvectors: , where represents the matrix of eigenvectors, is a diagonal matrix whose diagonal elements are the kernel matrix The characteristic value of Step 4: According to the contribution of the eigenvalue (i.e., the size of the eigenvalue), select the principal component with higher contribution as the retained feature; the higher the contribution, the stronger the explanatory power of the principal component for the data; Step 5: Project the data sets of soil moisture and vegetation growth conditions into the low-dimensional space composed of the selected principal components to obtain soil moisture characteristics. and vegetation growth characteristics ; Wherein, it can be realized by calculating the inner product of the data set of soil moisture and vegetation growth condition and the polynomial characteristic vector of the selected soil moisture and vegetation growth condition; Step 6: Use the weighted fusion method to fuse the soil moisture characteristics and vegetation growth characteristics to obtain the fusion characteristics : , where They are respectively expressed as the weights corresponding to the soil moisture characteristics and the vegetation growth condition characteristics; Step 204: Fusion features As input features for irrigation prediction models; Step 205: Irrigation requirements As the prediction target value of the irrigation prediction model; In step 205, the irrigation demand includes whether irrigation is needed, the amount of irrigation, etc., and the irrigation demand corresponds to the input characteristics of the irrigation prediction model; Step 206: The irrigation prediction model is optimized with an optimization objective to minimize the prediction error of irrigation demand: , In the formula, is the Grarange multiplier; is the slack variable; is the penalty parameter; represents the input feature index, Indicates the difference from The input feature index of Indicates the number of input features; represents the kernel function; Among them, the constraints of the optimization objective are: ; Step 207: Obtain a decision function by optimizing the irrigation prediction model : , where is a sign function used to map a value to 1 or -1. If the expression in the brackets is positive, then The function returns 1 if the expression in the brackets is negative. The function returns -1; represents the bias term. In support vector machines and other linear models, the bias term is used to adjust the position of the decision boundary to better fit the training data. The decision function is regarded as the prediction result of the irrigation prediction model, that is, the predicted irrigation demand. .

[0020] The irrigation strategy intelligent adjustment module automatically adjusts the irrigation strategy according to the irrigation demand predicted by the irrigation prediction model, including the following steps: Step 301: Irrigation demand predicted by an irrigation prediction model , set the maximum irrigation water volume of the irrigation equipment to The minimum irrigation water volume is and the initial irrigation frequency ;when When , the irrigation frequency is reduced, and the reduction ratio is defined as , get the new irrigation frequency ;when When , the irrigation frequency is increased, and the increase ratio is defined as , get the new irrigation frequency ; Step 302: Irrigation water volume , the irrigation water volume per unit time of the irrigation equipment is marked as , then the irrigation water volume is ; At the same time, the irrigation method is adjusted according to the soil moisture and vegetation growth conditions; the irrigation methods include sprinkler irrigation, flood irrigation, infiltration irrigation, micro-sprinkler irrigation, etc.; For example, the specific steps to automatically adjust the irrigation strategy based on the predicted irrigation demand are as follows: Step 1: Forecast irrigation demand: Assume that the irrigation demand predicted by the irrigation forecasting model is Cubic meters / day; Step 2: Set the maximum irrigation water volume for the irrigation equipment Cubic meters / day; Step 3: Adjust irrigation frequency: Initial irrigation frequency times / day; if it is decided to reduce the irrigation frequency by 10%, that is According to the formula , new irrigation frequency times / day; Step 4: Adjust the irrigation water volume: Assume that the irrigation water volume per unit time of the irrigation equipment is Cubic meters / time; irrigation water volume Cubic meters / day; Step 5: Adjust the irrigation method according to soil moisture and vegetation growth conditions: When soil moisture is low and vegetation growth is slow, drip irrigation is used; assuming the probability of using drip irrigation is (satisfy the conditions), otherwise (Conditions not met).

[0021] The irrigation equipment status monitoring module monitors the irrigation equipment status parameters in real time and analyzes the irrigation equipment status parameters; if an abnormal equipment status is detected, the steps of immediately sending an early warning signal include: Step 401: Install a sensor assembly on the irrigation equipment to monitor the state parameters of the irrigation equipment in real time; Step 402: Preset the current range of the irrigation equipment when it is working normally and voltage range , respectively calculate the current deviation and voltage deviation ; Assume that there is a relationship between water pressure and flow , for the measured water pressure value and flow value , calculate the flow deviation ;in, represent the mean current and voltage respectively, Indicates the parameter index, represents the proportionality coefficient; Step 403: based on the calculated current deviation, voltage deviation and flow deviation, respectively set a current deviation threshold, a voltage deviation threshold and a flow deviation threshold; if the current deviation is greater than the current deviation threshold, determine that the current is abnormal; if the voltage deviation is greater than the voltage deviation threshold, determine that the voltage is abnormal; if the flow deviation is greater than the flow deviation threshold, determine that the flow is abnormal; Step 404: When any state parameter among current, voltage and flow is determined to be abnormal, an early warning signal is immediately issued.

[0022] The automatic troubleshooting module for equipment failures uses the Bayesian theorem and combines early warning signals with real-time monitoring of irrigation equipment status parameters to automatically analyze the possible causes of irrigation equipment failures. The steps include: Step 501: sort out the fault causes of the irrigation equipment from the log to obtain a set of fault causes ; Step 502: Obtaining an early warning signal and irrigation equipment status parameters ; Step 503: According to the Bayesian theorem formula , In the formula, Indicates the cause of the fault The prior probability of occurrence can be obtained based on historical fault data statistics, where Indicates the fault cause index; Indicates the cause of the fault Warning signs appear below and irrigation equipment status parameters probability; Indicates a warning signal and irrigation equipment status parameters The probability of Calculated, Indicates the number of fault causes; Step 504: Calculate each fault cause The posterior probability , get the most probable fault cause , which is the most likely cause of irrigation equipment failure; Step 505: The most likely cause of the irrigation equipment failure and its related irrigation equipment status parameters are sent to maintenance personnel.

[0023] In the embodiment of the present invention, by deploying a sensor network, soil moisture and vegetation growth status data in the grassland ecological restoration area can be comprehensively collected. By adopting the mean filtering method to perform denoising on the soil moisture data, the accuracy of the data is ensured. By truncating the NDVI value, the influence of data anomalies on subsequent analysis is avoided. By integrating the preprocessed data into a unified data platform, subsequent data analysis and utilization are facilitated. By performing polynomial feature mapping and principal component analysis on the soil moisture data set and the vegetation growth status data set, fusion features are obtained, and the accuracy of irrigation demand prediction is improved. By using the support vector machine algorithm to establish an irrigation prediction model, intelligent prediction of irrigation demand is realized, and manual intervention is reduced. According to the irrigation demand predicted by the irrigation prediction model, the irrigation strategy is automatically adjusted, and automatic management of irrigation is realized. By installing sensor components, the state parameters of the irrigation equipment are monitored in real time, and the normal operation of the equipment is ensured. When the state parameters of the equipment are abnormal, an early warning signal is immediately issued, which is helpful to timely discover and handle equipment failures. By utilizing the Bayesian theorem and combining the early warning signal with the state parameters of the irrigation equipment monitored in real time, the cause of the failure can be quickly located, thereby reducing the time and cost of manual troubleshooting. In summary, the present invention solves the problem that the current monitoring and management level of grassland restoration is not high. In actual situations, more data and context information may be needed to make specific decisions and optimize solutions.

[0024] In addition, the formulas involved in the above are all calculated by removing dimensions and taking their numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The proportional coefficient in the formula and the various preset thresholds in the analysis process are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data; the size of the proportional coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the proportional coefficient depends on the amount of sample data and the preliminary setting of the corresponding processing coefficient for each group of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0025] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically based on the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0026] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0027] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0028] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks 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 processor, 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.

[0029] 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.

[0030] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0031] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other; Finally: The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An irrigation monitoring system for grassland ecological restoration, characterized in that: It includes irrigation data collection and analysis module, irrigation demand prediction module, irrigation strategy intelligent adjustment module, irrigation equipment status monitoring module and equipment fault automatic troubleshooting module; Irrigation data collection and analysis module: Deploy a sensor network in the grassland ecological restoration area to collect raw soil moisture values ​​and NDVI values; Preprocessing the collected original soil moisture values ​​and NDVI values ​​to obtain soil moisture data set and vegetation growth status data set; the preprocessing includes denoising and truncation processing; Irrigation demand prediction module: further analyze and process the soil moisture data set and the vegetation growth status data set to obtain fusion features; use the support vector machine algorithm to establish an irrigation prediction model to predict irrigation demand; Irrigation strategy intelligent adjustment module: automatically adjusts the irrigation strategy according to the irrigation demand predicted by the irrigation prediction model; the irrigation strategy includes irrigation water volume, irrigation frequency and irrigation method; Irrigation equipment status monitoring module: real-time monitoring of irrigation equipment status parameters and analysis of irrigation equipment status parameters; if an abnormal equipment status is detected, an early warning signal is immediately issued; the irrigation equipment status parameters include current, voltage, water pressure and flow; Automatic equipment fault troubleshooting module: Using Bayesian theorem, combined with early warning signals and real-time monitoring of irrigation equipment status parameters, it automatically analyzes possible fault causes of irrigation equipment.

2. The irrigation monitoring system for grassland ecological restoration according to claim 1, characterized in that: The irrigation data collection and analysis module deploys a sensor network in the grassland ecological restoration area. The process of collecting original soil moisture values ​​and NDVI values ​​includes: Set the grassland ecological restoration area as a flat area , and divided into Sub-areas ;in, Indicates that the plane area The number of sub-regions divided, Indicates that the plane area The sub-region index, and ; In each sub-area Uniform deployment within Soil moisture sensors, the original soil moisture value measured by the soil moisture sensor is ;in, Indicates the index of the soil moisture sensor, Represents each sub-region The number of soil moisture sensors uniformly deployed within ; For flat areas , the plane area Split into Vegetation monitoring sub-areas ;in, Indicates that the plane area The number of segmented vegetation monitoring sub-areas, Indicates that the plane area The index of the segmented vegetation monitoring sub-area, and ; In each vegetation monitoring sub-area The number of internal deployments is NDVI sensor and get the original NDVI value measured by the NDVI sensor ;in, represents the index of the NDVI sensor, and .

3. The irrigation monitoring system for grassland ecological restoration according to claim 2 is characterized in that: The irrigation data collection and analysis module preprocesses the collected original soil moisture values ​​and NDVI values ​​to obtain the soil moisture data set and vegetation growth status data set. The process includes: The raw soil moisture value measured by the soil moisture sensor , use mean filtering method for denoising: define the filter window size as , then the soil moisture value after denoising is for: , where Indicates the filter window index; when or When , boundary processing is performed; For the raw NDVI values ​​measured by the NDVI sensor Since the range of NDVI value is [-1, 1], if the original NDVI value If it is greater than 1 or less than -1, truncation is used to obtain the truncated NDVI value. ,Right now ; The preprocessed soil moisture values ​​are aggregated into a soil moisture dataset At the same time, the preprocessed NDVI values ​​are used to construct a vegetation growth status dataset for vegetation growth status assessment. ; The soil moisture dataset and vegetation growth status dataset Integrate into a unified data center Above; the data middle platform is used to store the pre-processed data.

4. The irrigation monitoring system for grassland ecological restoration according to claim 3 is characterized in that: The irrigation demand prediction module further analyzes and processes the soil moisture dataset and the vegetation growth status dataset to obtain fusion features; The irrigation forecasting model is established using the support vector machine algorithm. The process of forecasting irrigation demand includes: Extract soil moisture dataset from the data center and vegetation growth status dataset ; The soil moisture dataset and vegetation growth status dataset Perform polynomial feature mapping separately: , In the formula, represents the highest degree of a polynomial, The polynomial eigenvectors representing soil moisture and vegetation growth conditions respectively; The principal component analysis method is used to reduce the dimension and fuse the polynomial feature vectors of the mapped soil moisture and vegetation growth conditions to obtain the fusion feature ; The fusion features As input features for irrigation prediction models; Irrigation needs As the prediction target value of the irrigation prediction model; Then there is an optimization objective to optimize the irrigation prediction model and minimize the prediction error of irrigation demand: ， In the formula, is the Grarange multiplier; is the slack variable; is the penalty parameter; represents the input feature index, Indicates the difference from The input feature index of Indicates the number of input features; represents the kernel function; Among them, the constraints of the optimization objective are: ； The decision function is obtained by optimizing the irrigation prediction model. : , where is a symbolic function; represents the bias term; where the decision function is regarded as the prediction result of the irrigation prediction model, that is, the predicted irrigation demand .

5. The irrigation monitoring system for grassland ecological restoration according to claim 4 is characterized in that: The irrigation strategy intelligent adjustment module automatically adjusts the irrigation strategy according to the irrigation demand predicted by the irrigation prediction model. The process includes: Irrigation demand forecasted by irrigation forecast model , set the maximum irrigation water volume of the irrigation equipment to The minimum irrigation water volume is and the initial irrigation frequency ;when When , the irrigation frequency is reduced, and the reduction ratio is defined as , get the new irrigation frequency ;when When , the irrigation frequency is increased, and the increase ratio is defined as , get the new irrigation frequency ; For irrigation water , the irrigation water volume per unit time of the irrigation equipment is marked as , then the irrigation water volume is ; At the same time, the irrigation method is adjusted according to soil moisture and vegetation growth conditions.

6. The irrigation monitoring system for grassland ecological restoration according to claim 1, characterized in that: The irrigation equipment status monitoring module monitors the status parameters of the irrigation equipment in real time and analyzes the status parameters of the irrigation equipment; if an abnormal equipment status is detected, the process of immediately sending an early warning signal includes: Install sensor components on irrigation equipment to monitor irrigation equipment status parameters in real time; Preset the current range for normal operation of irrigation equipment and voltage range , respectively calculate the current deviation and voltage deviation ; Assume that there is a relationship between water pressure and flow , for the measured water pressure value and flow value , calculate the flow deviation ;in, represent the mean current and voltage respectively, Indicates the parameter index, represents the proportionality coefficient; Based on the calculated current deviation, voltage deviation and flow deviation, a current deviation threshold, a voltage deviation threshold and a flow deviation threshold are set respectively. If the current deviation is greater than the current deviation threshold, the current is determined to be abnormal. If the voltage deviation is greater than the voltage deviation threshold, the voltage is determined to be abnormal. If the flow deviation is greater than the flow deviation threshold, the flow is determined to be abnormal. When any state parameter of current, voltage and flow is judged to be abnormal, an early warning signal will be issued immediately.

7. The irrigation monitoring system for grassland ecological restoration according to claim 6, characterized in that: The equipment fault automatic troubleshooting module uses Bayesian theorem and combines early warning signals and real-time monitoring of irrigation equipment status parameters to automatically analyze the possible causes of irrigation equipment failures. The process includes: Sort out the fault causes of irrigation equipment from the logs and get a set of fault causes ; Get early warning signals and irrigation equipment status parameters ; According to Bayes' theorem formula , In the formula, Indicates the cause of the fault The prior probability of occurrence is Indicates the fault cause index; Indicates the cause of the fault Warning signs appear below and irrigation equipment status parameters probability; Indicates a warning signal and irrigation equipment status parameters probability; Calculate each failure cause The posterior probability , get the most probable fault cause , which is the most likely cause of irrigation equipment failure; The most likely cause of irrigation equipment failure and its related irrigation equipment status parameters are sent to maintenance personnel.

Images