Water conservancy project real-time monitoring management method based on sensor network

Abstract

The invention discloses a water conservancy project real-time monitoring management method based on a sensor network, and relates to the field of water conservancy projects, and the method comprises the following steps: obtaining pipeline nodes in a to-be-detected region, marking each pipeline node to construct a water conservancy project data set, obtaining maintenance demand data corresponding to the pipeline nodes, and obtaining a water conservancy project data set; the maintenance demand data comprises a pipeline corrosion rate, a pipeline fatigue life and a crack growth rate; constructing a maintenance priority evaluation model based on a machine learning algorithm according to the maintenance demand data, and generating a maintenance priority; and according to the generated maintenance priorities, performing descending sorting on the pipeline nodes, and generating a maintenance priority sorting table. According to the method and the device, the maintenance priority sorting table is generated, so that the problems of errors and human resource waste caused by manual operation are solved.

Description

Technical Field

[0001] The present application relates to the field of water conservancy projects, and more specifically, to a real-time monitoring and management method for water conservancy projects based on a sensor network. Background Art

[0002] Sensor networks are key infrastructure for urban economic and social development and play a vital role. They provide data support for data analysis by real-time monitoring, sensing and collecting various information in the network coverage area. Sensor networks are a kind of computer network composed of many automatic devices distributed in space, which can effectively analyze and process data.

[0003] In water conservancy projects, sensor networks are of great significance for hydrological monitoring and reservoir water level monitoring. The sensor network monitors the real-time data around it and sends the monitored information to the server through the network after processing. In addition, the sensor network can automatically control and process data, significantly reducing the dependence on manual operation, thereby reducing the consumption of human resources. Through automated data processing, the efficiency of data collection is improved, the data errors caused by manual operation are effectively reduced, the reliability of data is improved, and the environmental changes are responded to in real time to provide accurate information.

[0004] The above disclosed technical solutions have at least the following technical problems:

[0005] Traditional sensor network monitoring data needs to be manually screened to identify critical areas that need maintenance. However, manual screening is not only extremely time-consuming, but also unable to automatically analyze and prioritize according to severity, which greatly reduces work efficiency, resulting in extended maintenance response time and missed critical maintenance windows. The manual screening process is easily affected by human errors, leading to neglect and misjudgment of critical areas, thus affecting the accuracy and timeliness of maintenance.

[0006] Therefore, an optimized real-time monitoring and management method for water conservancy projects based on sensor networks is desired.

[0007] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0008] In order to solve the above technical problems, this application is proposed. The embodiment of this application provides a real-time monitoring and management method for water conservancy projects based on a sensor network, which collects data around pipeline nodes, processes and analyzes the data, generates a maintenance priority ranking table, and updates the data and maintenance priority ranking table in real time to solve the problem of errors caused by manual operation, reduce human resource consumption and reduce maintenance costs.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] A real-time monitoring and management method for water conservancy projects based on a sensor network includes: obtaining pipeline nodes in a test area, labeling each pipeline node to construct a water conservancy project data set, obtaining maintenance demand data corresponding to the pipeline nodes, and the maintenance demand data including pipeline corrosion rate, pipeline fatigue life and crack growth rate; constructing a maintenance priority evaluation model based on a machine learning algorithm according to the maintenance demand data, generating a maintenance priority, sorting the pipeline nodes in descending order according to the generated maintenance priority, and generating a maintenance priority sorting table.

[0011] In a preferred embodiment, the maintenance requirement data includes pipeline corrosion rate, pipeline fatigue life and crack growth rate.

[0012] In a preferred embodiment, the specific method for obtaining the pipeline corrosion rate is as follows: obtain the material category of each node, and prepare the material samples to be tested of the corresponding material category respectively; select the material samples to be tested, and measure the initial weight, thickness and surface area of ​​the material samples; put the material samples into a specified pipeline corrosion environment, and after a period of time, take out and clean the material samples, and measure the weight of the material samples after drying; calculate the weight of the material lost within a period of time according to the initial weight of the material sample and the weight of the material sample after the experiment; and obtain the pipeline corrosion rate through a preset pipeline corrosion rate formula according to the weight of the material lost within a period of time, the time the material is in the corrosive environment and the surface area of ​​the material.

[0013] In a preferred embodiment, the specific method for obtaining the fatigue life of the pipeline is as follows: obtaining the stress of the pipeline material under test conditions through a stress sensor; recording the maximum stress and the minimum stress in each cycle during the loading cycle of the pipeline material; obtaining the stress amplitude based on the maximum stress and the minimum stress during the material loading cycle and based on a preset stress amplitude formula; obtaining the material constant through a tensile test; and calculating the pipeline fatigue life based on the stress amplitude and the pipeline material constant and using a preset pipeline fatigue life calculation formula.

[0014] In a preferred embodiment, the specific method for obtaining the crack growth rate is as follows: testing the material through a fatigue testing machine, recording the crack length, width and far-field stress before and after the material experiment, and calculating the range of the stress intensity factor and the maximum stress intensity factor; increasing the opening displacement of the crack tip by applying a load, recording the opening displacement of the crack tip, and obtaining the fracture toughness of the material by measuring the stress intensity factor value during crack growth; obtaining the material constant through a tensile test; and obtaining the crack growth rate through a preset crack growth model Forman formula based on the range of the stress intensity factor, the maximum stress intensity factor, the fracture toughness of the material and the material constant.

[0015] In a preferred embodiment, the maintenance demand data constructs a maintenance priority assessment model based on a machine learning algorithm to generate a maintenance priority, specifically: through the pipeline corrosion rate, pipeline fatigue life and crack growth rate, a pipeline maintenance assessment model is established based on machine learning to obtain the maintenance priority.

[0016] In a preferred embodiment, the pipeline nodes are sorted in descending order according to the generated maintenance priority to generate a maintenance priority sorting table, specifically: each pipeline node is taken as a whole, and the pipeline data around the pipeline node is collected; based on the collected data, the status data of a single node is corrected; the corrected node data is used to calculate the maintenance priority of each node, and the maintenance priority sorting table is generated based on the calculated maintenance priority.

[0017] The technical effects and advantages of the real-time monitoring and management method of water conservancy projects based on sensor networks of the present invention are as follows:

[0018] 1. Real-time data acquisition and accurate decision-making. The present invention can obtain the status data of pipeline nodes in real time through the sensor network, including pipeline corrosion rate, pipeline fatigue life and crack growth rate. Through this real-time monitoring, the maintenance management of water conservancy projects becomes more efficient and accurate. Combined with machine learning algorithms, a comprehensive assessment of maintenance needs is conducted, providing a powerful decision-making support tool for project managers. Data-driven analysis and models can more objectively assess maintenance needs, significantly reduce the deviation caused by manual operations, and thus improve the accuracy of decision-making.

[0019] 2. Dynamic maintenance priority adjustment. The present invention can correct pipeline node data in real time by tracking pipeline fatigue life, corrosion rate and crack growth rate over a long period of time, recalculate maintenance priority based on the corrected data, and update the maintenance priority sorting form to ensure the continued effectiveness of the maintenance plan. This method improves the maintenance efficiency and scientificity of water conservancy projects, reduces maintenance costs, enhances system reliability, and optimizes resource allocation, making maintenance work more targeted.

[0020] 3. Improve system stability and prevention capabilities: The real-time monitoring and data processing mechanism of the present invention significantly improves the stability and prevention capabilities of the system. By continuously tracking the status of the pipeline, potential hidden dangers and abnormal changes can be discovered in a timely manner, and preventive measures can be taken in advance, thereby reducing the risk of sudden failures. The system also has predictive analysis capabilities. Based on historical data and real-time monitoring information, it can predict future maintenance needs and arrange maintenance work in advance. This forward-looking management method not only reduces the frequency of emergency repairs, but also reduces downtime caused by pipeline failures, thereby ensuring the continuous operation and safety of water conservancy projects and further optimizing resource utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a structural schematic diagram of the real-time monitoring and management method of water conservancy projects based on sensor networks of the present invention. DETAILED DESCRIPTION

[0022] 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 described embodiments 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.

[0023] Embodiment 1, Figure 1 The present invention provides a real-time monitoring and management method for water conservancy projects based on a sensor network, comprising the following steps:

[0024] S1, obtain the pipeline nodes in the area to be tested, label each pipeline node to construct a water conservancy project data set, and obtain the maintenance demand data corresponding to the pipeline node, wherein the maintenance demand data includes pipeline corrosion assessment, pipeline fatigue assessment and crack growth rate assessment.

[0025] In modern society, water conservancy projects are an important part of social life. However, water conservancy projects involve too wide an area and insufficient human resources, which leads to regional omissions. The emergence of sensor networks solves this problem. However, new problems arise. When multiple nodes are damaged, manual operation is required to determine whether the node should be maintained first.

[0026] In this embodiment, sensors are placed at the pipeline nodes to be tested, and a unique number is assigned to each pipeline node. The sensors continuously collect data related to the pipeline, such as flow, temperature, and pressure. The acquired data is transmitted to the data storage center through the network, and the acquired data is integrated with the information of the pipeline nodes to construct a water conservancy project data set. The data set contains basic information of the pipeline nodes and real-time monitoring data.

[0027] In this embodiment, the sensor network node composition and functions include:

[0028] The sensing unit is responsible for collecting information about the surrounding environment. The sensing unit converts these environmental quantities into electrical signals or digital signals through sensors;

[0029] The processing unit analyzes and processes the data collected by the sensor unit, such as filtering, correcting, summarizing and interpreting;

[0030] The communication unit is responsible for transmitting data between the sensor node and other nodes or between the sensor node and the central system.

[0031] In this embodiment, the maintenance requirement data corresponding to the pipeline node is obtained, specifically:

[0032] Pipeline corrosion rate assessment. The corrosion rate is a key indicator to measure the corrosion rate of a material in a given environment. It represents the weight of material lost by a single area of ​​the pipeline over a period of time. It is used to evaluate the corrosion resistance of the material and help predict the service life and maintenance needs of the pipeline.

[0033] The specific method for obtaining the pipeline corrosion rate is as follows:

[0034] Select the material sample to be tested, and measure the initial weight, thickness and surface area of ​​the material sample;

[0035] Put the sample into the specified pipeline corrosion environment, take it out and clean it after a period of time, let it dry and measure the weight;

[0036] The pipeline corrosion rate is obtained through the pipeline corrosion rate formula;

[0037] The actual thickness loss of the pipeline is calculated based on the pipeline corrosion rate, and the actual thickness is calculated based on the original thickness.

[0038] The specific calculation formula of the pipeline corrosion rate is as follows:

[0039]

[0040] The specific calculation formula for the actual thickness of the pipeline is as follows:

[0041] d=d0-C·t

[0042] Where C is the pipeline corrosion rate, W is the weight of material lost over a period of time, A is the surface area of ​​a single measurement, t is the time, d is the actual thickness, d0 is the initial thickness, and the corrosion rate C is expressed in millimeters per year (mm / year).

[0043] It should be noted that the corrosion rate is positively correlated with the weight of material lost over a period of time. The greater the weight of material lost over a period of time, the higher the corrosion rate and the higher the maintenance frequency of the pipeline. As pipeline corrosion continues, the thickness of the pipeline becomes thinner, the bearing capacity of the pipeline decreases, and the risk of pipeline leakage and rupture increases under high-pressure environments. By calculating the thickness of the pipeline, personnel can be planned and arranged in advance to perform maintenance work on the pipeline, reducing maintenance costs, reducing risks, and ensuring the stability and safety of the pipeline during use.

[0044] Pipeline fatigue life assessment, the selection and use of pipeline materials are closely related to the subsequent pipeline maintenance frequency. By evaluating the pipeline fatigue life and improving the selection of pipeline materials, the reliability of the pipeline system can be improved and the risk factor can be reduced, thereby reducing the pipeline maintenance frequency and maintenance costs. The pipeline uses the SN curve to calculate the fatigue life.

[0045] The specific method for obtaining the pipeline fatigue life is as follows:

[0046] Obtain the stress of the pipeline material under the test conditions through the stress sensor;

[0047] During the pipeline material loading cycle, record the maximum stress and minimum stress in each cycle;

[0048] According to the maximum stress and minimum stress in the material loading cycle, the stress amplitude is obtained based on the stress amplitude formula;

[0049] Obtain material constants through tensile tests;

[0050] According to the stress amplitude and pipeline material constant, the pipeline fatigue life is calculated using the preset pipeline fatigue life calculation formula.

[0051] The specific calculation formula for the pipeline fatigue life is as follows:

[0052]

[0053] The specific calculation formula of the stress amplitude is as follows:

[0054]

[0055] Where N f is the pipeline fatigue life, σ is the stress amplitude, c and m are material constants determined by tensile tests, σ ​​is the stress amplitude, σ max is the maximum stress in the cycle, σ min is the minimum stress in the cycle.

[0056] It should be noted that fatigue life refers to the number of cycles that a material can withstand under a given stress amplitude. By predicting the fatigue life of pipeline materials, pipeline maintenance work can be carried out in advance, thereby effectively reducing risks and maintenance costs. Fatigue life is inversely proportional to stress amplitude. The higher the stress amplitude, the fewer cycles the material can withstand under high stress conditions, and the higher the frequency of pipeline maintenance.

[0057] It should be noted that the SN curve is a graph used to depict the fatigue life of materials under different stress levels. It shows the relationship between the stress applied to the material and the number of cycles the material can withstand. The actual stress amplitude is adjusted according to the SN graph to extend the service life of the material, reduce maintenance costs and avoid potential risks. The stress amplitude refers to half of the difference between the maximum stress and the minimum stress experienced by the material in a loading cycle. It represents the amount of stress change that the material is subjected to in a loading cycle and reflects the intensity of the actual stress fluctuations to which the material is subjected. The larger the stress amplitude, the more drastic the stress change experienced by the material, the greater the risk of fatigue failure, and the more likely fatigue failure to occur.

[0058] Crack growth rate assessment is a prediction of pipeline service life. By evaluating the pipeline life, the pipeline damage time can be roughly predicted, and the pipeline can be maintained in advance to reduce risks and costs. By considering the combined influence of the stress intensity factor range and the maximum stress intensity factor, the Forman formula based on the material fatigue crack growth model is selected to predict the remaining service life of the pipeline.

[0059] The specific method for obtaining the crack growth rate is as follows:

[0060] Test the material using a fatigue testing machine, record the crack length, width and far-field stress before and after the material test, and calculate the range and maximum stress intensity factor of the stress intensity factor;

[0061] By applying a load to increase the opening displacement of the crack tip, the opening displacement of the crack tip is recorded, and the stress intensity factor value during crack extension is measured to obtain the fracture toughness of the material;

[0062] According to the range of stress intensity factor, maximum stress intensity factor, fracture toughness of material and material constant, the crack growth rate is obtained through the Forman formula of crack growth model.

[0063] The specific calculation formula of the crack extension model Forman is as follows:

[0064]

[0065] The specific calculation formula of the material toughness is as follows:

[0066]

[0067] In the formula is the crack growth rate, ΔK is the range of stress intensity factor, K max is the maximum stress intensity factor, K ICis the fracture toughness of the material, c, n and m are material-specific constants determined by tensile tests, P is the material fracture load, B is the material thickness, W is the material width, and Y is the geometric factor.

[0068] It should be noted that the crack propagation model is used to predict and analyze the propagation behavior of cracks in material structures. By accurately predicting the crack propagation behavior, the material structure can be effectively monitored and maintained to prevent structural collapse and select materials with excellent performance. The range of the stress intensity factor is directly related to the crack length and the shape of the material. The longer the crack length, the more concentrated the stress field at the crack tip will become, and the value of the stress intensity factor will increase accordingly.

[0069] It should be noted that there is a close relationship between the stress intensity factor and the fracture toughness of the material. Fracture toughness is a measure of the stress field strength at the crack tip and is the critical value at which the stress intensity factor reaches crack extension. Therefore, the fracture toughness of the material is an indicator of the material's ability to resist crack extension and determines the threshold at which the stress intensity factor reaches the destructive condition.

[0070] S2, constructing a maintenance priority evaluation model according to the maintenance demand data corresponding to the pipeline nodes, generating maintenance priorities, sorting the pipeline nodes in descending order according to the generated maintenance priorities, and generating a maintenance priority sorting table.

[0071] In this embodiment, a pipeline maintenance assessment model is established based on machine learning through pipeline corrosion rate, actual pipeline thickness, pipeline fatigue life and pipeline crack propagation model to obtain a maintenance priority k, and the maintenance priority of the node is determined by the maintenance priority k.

[0072] The specific calculation formula of the maintenance priority is as follows:

[0073]

[0074] Where k is the maintenance priority, is the crack growth rate, t is the actual service time, C is the corrosion rate, N f is the fatigue life.

[0075] It should be noted that the k value is a key indicator. The higher the k value, the greater the stress intensity at the crack tip, which will cause the crack to propagate faster, thereby increasing the risk of material damage and reducing the durability and safety of the material. The higher the k value, the higher the maintenance priority.

[0076] In this embodiment, the pipeline nodes are sorted in descending order according to the maintenance priority, and a maintenance priority sorting table is generated, which is specifically:

[0077] Take each pipeline node as a whole and collect pipeline data around the pipeline node;

[0078] According to the collected data, the status data of a single node is corrected;

[0079] The corrected node data is used to calculate the maintenance priority of each node, and a maintenance priority ranking table is generated based on the calculated maintenance priority.

[0080] It should be noted that a descending sort table is obtained, and nodes are maintained according to the descending sort table. When the pipeline is repaired, the system will measure the nodes in real time to obtain the latest data. Based on the latest data obtained, the sorting form is updated to ensure that the sorting form reflects the latest maintenance status and nodes, which significantly reduces the time and effort required for manual calculation and sorting, and reduces the consumption of human resources.

[0081] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0082] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0083] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0084] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0085] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0086] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A real-time monitoring and management method for water conservancy projects based on a sensor network, characterized in that: include: Obtain the pipeline nodes in the area to be tested, label each pipeline node to construct a water conservancy project data set, and obtain the maintenance demand data corresponding to the pipeline node; Building a maintenance priority evaluation model based on a machine learning algorithm according to the maintenance demand data to generate a maintenance priority; According to the generated maintenance priority, the pipeline nodes are sorted in descending order to generate a maintenance priority sorting table.

2. The real-time monitoring and management method for water conservancy projects based on sensor networks according to claim 1 is characterized in that: The maintenance requirement data includes pipeline corrosion rate, pipeline fatigue life and crack growth rate.

3. The real-time monitoring and management method for water conservancy projects based on sensor networks according to claim 2 is characterized in that: The specific method for obtaining the pipeline corrosion rate is as follows: Obtain the material category of each node and prepare the material samples to be tested of the corresponding material category; Select the material sample to be tested, and measure the initial weight, thickness and surface area of ​​the material sample; Put the material sample into a given pipeline corrosion environment. After a period of time, take out the material sample and clean it. After the material sample is dried, measure the weight. The weight of the material lost within a period of time is calculated based on the initial weight of the material sample and the weight of the material sample after the experiment; The pipeline corrosion rate is obtained by using a preset pipeline corrosion rate formula based on the weight of the material lost over a period of time, the time the material is in the corrosive environment, and the surface area of ​​the material.

4. The real-time monitoring and management method for water conservancy projects based on sensor networks according to claim 3 is characterized in that: The specific method for obtaining the pipeline fatigue life is as follows: Obtain the stress of the pipeline material under the test conditions through the stress sensor; During the pipeline material loading cycle, record the maximum stress and minimum stress in each cycle; According to the maximum stress and the minimum stress in the material loading cycle, the stress amplitude is obtained based on the preset stress amplitude formula; Obtain the pipe material constants through tensile tests; According to the stress amplitude and pipeline material constant, the pipeline fatigue life is calculated using the preset pipeline fatigue life calculation formula.

5. The real-time monitoring and management method for water conservancy projects based on sensor networks according to claim 4 is characterized in that: The specific method for obtaining the crack growth rate is as follows: Test the material using a fatigue testing machine, record the crack length, width and far-field stress before and after the material test, and calculate the range and maximum stress intensity factor of the stress intensity factor; By applying a load to increase the opening displacement of the crack tip, the opening displacement of the crack tip is recorded, and the fracture toughness of the material is obtained by measuring the stress intensity factor value during crack extension; According to the range of stress intensity factor, maximum stress intensity factor, fracture toughness of material and material constant, the crack growth rate is obtained by using the preset crack growth model Forman formula.

6. The real-time monitoring and management method for water conservancy projects based on sensor networks according to claim 5 is characterized in that: The maintenance demand data is used to construct a maintenance priority evaluation model based on a machine learning algorithm to generate maintenance priorities, specifically: Through pipeline corrosion rate, pipeline fatigue life and crack growth rate, a pipeline maintenance assessment model is established based on machine learning to obtain maintenance priority; The specific calculation formula of the maintenance priority is as follows: Where k is the maintenance priority, is the crack growth rate, t is the actual service time, C is the corrosion rate, N f is the fatigue life.

7. The real-time monitoring and management method for water conservancy projects based on sensor networks according to claim 6 is characterized in that: The pipeline nodes are sorted in descending order according to the generated maintenance priority to generate a maintenance priority sorting table, specifically: Take each pipeline node as a whole and collect pipeline data around the pipeline node; According to the collected data, the status data of a single node is corrected; The corrected node data is used to calculate the maintenance priority of each node, and a maintenance priority ranking table is generated based on the calculated maintenance priority.

8. The real-time monitoring and management method for water conservancy projects based on sensor networks according to claim 7 is characterized in that: The specific calculation formula of the pipeline corrosion rate is as follows: Where t is the time the material is in the corrosive environment, C is the corrosion rate, W is the weight of material lost over a period of time, and A is the surface area of ​​a single measurement.

9. The real-time monitoring and management method for water conservancy projects based on sensor networks according to claim 8 is characterized in that: The specific calculation formula for the pipeline fatigue life is as follows: The specific calculation formula of the stress amplitude is as follows: Where N f is the fatigue life, σ is the stress amplitude, c and m are material constants determined by tensile tests, σ ​​is the stress amplitude, σ max is the maximum stress in the cycle, σ min is the minimum stress in the cycle.

10. The sensor network-based real-time monitoring and management method for water conservancy projects according to claim 9 is characterized in that: The specific calculation formula of the crack extension model Forman is as follows: In the formula is the crack growth rate, ΔK is the range of stress intensity factor, K max is the maximum stress intensity factor, K IC is the fracture toughness of the material, and c, n and m are material-specific constants.

Images