Intelligent pipe network management system based on Internet of Things technology

Abstract

The invention discloses an intelligent pipe network management system based on the Internet of Things technology, and relates to the technical field of data management. Pressure bearing capacity and water pressure data of a pipeline are collected in real time through stress and pressure sensors, and whether water flow exceeds a pipeline safety range or not is accurately assessed by combining pipeline pressure bearing capacity monitoring, frequency analysis and risk assessment; based on the data, the risk division module divides risks into high, medium and low levels, and takes targeted management measures; and for medium-risk conditions, the maintenance module reduces the pipeline fracture risk by predicting and dynamically adjusting the starting frequency of the water pump and the opening degree of the valve, and effectively prevents secondary pollution and water quality decline, thereby ensuring safe and stable operation of the water supply system.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a smart pipe network management system based on Internet of Things technology. Background Art

[0002] Smart pipe network management based on IoT technology refers to the use of IoT technology to intelligently monitor and manage the operation of urban pipe networks (such as water, electricity, gas, heating, etc.). IoT embeds sensors, smart meters and communication modules in pipe network equipment and facilities, so that all kinds of data on pipe network operation can be collected in real time and transmitted to a centralized management system.

[0003] Through the smart pipe network management system, managers can not only remotely monitor and control the pipe network, but also predict the failures and risks of the pipe network through big data analysis and artificial intelligence technology, and optimize the maintenance and scheduling of the pipe network. For example, in the water pipe network, the system can analyze the risk of water leakage based on real-time data, automatically adjust the water flow, and even predict equipment failures in advance and notify relevant personnel for maintenance. In this way, the smart pipe network not only improves the efficiency of resource utilization, but also greatly reduces human operational errors and emergency response time, and enhances the reliability and sustainable development capabilities of the pipe network system.

[0004] The prior art has the following deficiencies: Although the water pipe network system can optimize water pressure and flow when automatically adjusting water flow, excessive automatic adjustment may cause water pipes to burst. In some rare cases, the automatic adjustment of the system may cause drastic fluctuations in water flow, exceeding the maximum pressure of the pipe design, causing pipe bursts or equipment damage, especially when the pipe network is aging or improperly maintained. In addition, pipe ruptures may cause secondary pollution, causing pollutants and bacteria to enter the water supply system, endangering public health, causing a sharp decline in water quality, and possibly leading to water source pollution and large-scale health crises. Summary of the invention

[0005] The purpose of the present invention is to provide a smart pipe network management system based on Internet of Things technology to solve the shortcomings of the background technology.

[0006] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a smart pipe network management system based on Internet of Things technology, including a data acquisition module, a pipeline pressure bearing capacity monitoring module, a water pressure fluctuation analysis module, a risk assessment module, a risk classification module and a maintenance module; Data acquisition module: by installing stress sensors at different positions of the pipeline, it is used to obtain the actual pressure bearing capacity data of the pipeline in real time, and by laying pressure sensors in the pipeline, it is used to collect the water pressure data of each monitoring point in real time; Pipeline pressure bearing capacity monitoring module: monitors the actual pressure bearing capacity of each section of pipeline in real time based on the actual pressure bearing capacity data of pipeline obtained in real time, and evaluates the stability of pipeline pressure bearing capacity by analyzing the maximum load fluctuation of pipeline under different operating environments; Water pressure fluctuation analysis module: If the pipeline pressure bearing capacity is stable, the frequency and amplitude characteristics of water pressure fluctuations are extracted through the Fourier transform algorithm to evaluate whether the water flow is within the pipeline pressure range; Risk assessment module: Based on the stability of the pipeline's pressure bearing capacity and the characteristics of dynamic water pressure changes, the risk of water flow regulation exceeding the pipeline's safety range is assessed; Risk classification module: Based on the assessment results, the risk of water flow regulation exceeding the pipeline safety range is divided into high-risk regulation, medium-risk regulation and low-risk regulation, and corresponding management is carried out; Maintenance module: For medium-risk regulation, further prediction is made on the risk of water flow regulation exceeding the pipeline safety range within a fixed time period, and the pump start-up frequency and valve opening speed are dynamically adjusted according to the prediction results to reduce the risk of pipeline rupture.

[0007] Preferably, in the pipeline pressure bearing capacity monitoring module, the pipeline load fluctuation situation in different time periods is analyzed to generate a pipeline load fluctuation index, and the pipeline load fluctuation index is obtained by: Collect and organize the water pressure fluctuation data x(t) of the pipeline, where t is time and x(t) is the water pressure value corresponding to time point t; calculate the local maximum and local minimum of the signal, calculate the upper and lower envelopes u(t) and l(t) of the signal through the local maximum and minimum, and calculate the average value of the envelope , the expression is: ; Extract the intrinsic mode function IMF of the signal until the signal is decomposed into several IMF components and a residual signal, and obtain several IMF components through EMD decomposition and a residual signal r(t), for each IMF component , calculate its amplitude and energy, and calculate the maximum value of the IMF component and minimum value Get the amplitude , the expression is: ; Energy is calculated by the sum of squares, expressed as: ; Where T is the total duration of the signal; frequency characteristics By calculating its main frequency, the IMF component is transformed into the frequency domain using Fourier transform to obtain the spectrum , the expression is: ; The amplitude, energy and frequency of each IMF are combined to obtain the pipeline load fluctuation index, which is expressed as: ; In the formula, ECK is the pipeline load fluctuation index, where is the weight coefficient.

[0008] Preferably, in the water pressure fluctuation analysis module, a water pressure fluctuation frequency anomaly index is generated by analyzing the frequency characteristics of the water pressure fluctuation. The method for obtaining the water pressure fluctuation frequency anomaly index is: The time series data x(s) of water pressure is obtained from the water pipe network, which represents the change of water pressure at time s. The time domain signal x(s) of water pressure is converted into the frequency domain signal X(f) through Fourier transform, so as to analyze the intensity of different frequency components in the signal; the Fourier transform formula is: ; Where X(f) is the complex number representation of the frequency domain signal, representing the amplitude and phase of each frequency f, x(s) is the time domain signal of water pressure, f is the frequency, j is the imaginary unit, and s is the time. Through Fourier transform, the frequency domain signal X(f) is obtained, which contains the amplitude and phase of the signal at different frequencies. The amplitude spectrum, that is, the amplitude of the frequency domain signal, is extracted from the result of Fourier transform, and the deviation between the actual frequency spectrum and the expected frequency spectrum is calculated. , the expression is: ; In the formula, is the expected frequency spectrum, and the water pressure fluctuation frequency anomaly index is calculated. The expression is: ; In the formula, is the maximum value of frequency, It is the water pressure fluctuation frequency anomaly index.

[0009] Preferably, in the risk assessment module, the risk of water flow regulation exceeding the pipeline safety range is assessed based on the stability of the pipeline pressure bearing capacity and the dynamic water pressure change characteristics, specifically: The pipeline load fluctuation index and the water pressure fluctuation frequency anomaly index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the risk value label of water flow regulation exceeding the pipeline safety range as the prediction target, and takes minimizing the sum of prediction errors of all risk value labels of water flow regulation exceeding the pipeline safety range as the training target. The machine learning model is trained until the sum of prediction errors converges and the model training is stopped. The risk value of water flow regulation exceeding the pipeline safety range is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0010] Preferably, in the risk classification module, the risk of water flow regulation exceeding the pipeline safety range is classified into high-risk regulation, medium-risk regulation and low-risk regulation according to the evaluation results; The risk value of the water flow regulation exceeding the pipeline safety range is compared with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the risk value of the water flow regulation exceeding the pipeline safety range is compared with the first standard threshold and the second standard threshold respectively; If the risk value of the water flow regulation exceeding the pipeline safety range is greater than the second standard threshold, it means that the risk of the water flow regulation exceeding the pipeline safety range is high, and a first-level warning signal is generated at this time, and the risk of the water flow regulation exceeding the pipeline safety range is classified as high-risk regulation; If the risk value of water flow regulation exceeding the pipeline safety range is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the risk of water flow regulation exceeding the pipeline safety range is at a medium level. At this time, a secondary warning signal is generated, and the risk of water flow regulation exceeding the pipeline safety range is classified as medium risk regulation; If the risk value of water flow regulation exceeding the pipeline safety range is less than the first standard threshold, it means that the risk of water flow regulation exceeding the pipeline safety range is low. At this time, a third-level warning signal is generated, and the risk of water flow regulation exceeding the pipeline safety range is classified as low-risk regulation.

[0011] Preferably, in the maintenance module, for medium-risk regulation, the risk of water flow regulation exceeding the pipeline safety range within a fixed time period is further predicted, and the water pump start-up frequency and valve opening speed are dynamically adjusted according to the prediction results, specifically: For medium-risk regulation, the water flow regulation risk value of the time series is set to R(m), where m represents the time step, and the formula is: ;in, is the predicted future risk value, f is the risk value prediction function, is the historical risk value, and n is the total number of historical risk values.

[0012] Preferably, the starting frequency of the water pump is set to be proportional to the risk value of the water flow regulation. A high risk value requires reducing the starting frequency of the water pump to reduce pipeline pressure fluctuations. The formula is expressed as: ;in, is the starting frequency of the water pump, α is an adjustment constant, which indicates the relationship between the risk value and the starting frequency of the water pump; the valve opening speed affects the water flow rate and pressure fluctuation in the pipeline. When the risk value is high, the adjustment formula of the valve opening speed is: ;in, is the valve opening speed, and β is an adjustment constant that represents the relationship between the risk value and the valve opening speed.

[0013] In the above technical solution, the technical effects and advantages provided by the present invention are: 1. The present invention collects pipeline pressure bearing capacity and water pressure data in real time, and combines multi-module analysis (such as pipeline pressure bearing capacity monitoring, frequency analysis and risk assessment). The system can accurately assess the stability of pipeline pressure bearing capacity and whether the water flow exceeds the pipeline safety range. Through the machine learning model combined with the pipeline load fluctuation index and the water pressure fluctuation frequency abnormality index, the water flow regulation risk can be accurately predicted and classified, thereby optimizing the management of the pipeline network and preventing the occurrence of water pipe rupture and secondary pollution.

[0014] 2. The present invention predicts medium-risk regulation and dynamically adjusts the pump start-up frequency and valve opening speed, effectively reducing the risk of pipeline rupture. The risk management mechanism divides the risk of water flow regulation exceeding the pipeline safety range into three levels: high, medium, and low, generates early warning signals and takes corresponding control measures to ensure that the pipe network system maintains safe and stable operation during the automatic adjustment process, avoiding safety hazards caused by excessive adjustment or aging of the pipe network. The present invention significantly improves the safety, reliability, and intelligence level of the water pipe network, which is of great significance to ensuring public health and water quality safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0016] Figure 1 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0018] For examples, see Figure 1 As shown, the smart pipe network management system based on the Internet of Things technology described in this embodiment includes a data acquisition module, a pipeline pressure bearing capacity monitoring module, a water pressure fluctuation analysis module, a risk assessment module, a risk classification module and a maintenance module; Data acquisition module: by installing stress sensors at different positions of the pipeline, it is used to obtain the actual pressure bearing capacity data of the pipeline in real time, and by laying pressure sensors in the pipeline, it is used to collect the water pressure data of each monitoring point in real time; Pipeline pressure bearing capacity monitoring module: monitors the actual pressure bearing capacity of each section of pipeline in real time based on the actual pressure bearing capacity data of pipeline obtained in real time, and evaluates the stability of pipeline pressure bearing capacity by analyzing the maximum load fluctuation of pipeline under different operating environments; Water pressure fluctuation analysis module: If the pipeline pressure bearing capacity is stable, the frequency and amplitude characteristics of water pressure fluctuations are extracted through the Fourier transform algorithm to evaluate whether the water flow is within the pipeline pressure range; Risk assessment module: Based on the stability of the pipeline's pressure bearing capacity and the characteristics of dynamic water pressure changes, the risk of water flow regulation exceeding the pipeline's safety range is assessed; Risk classification module: Based on the assessment results, the risk of water flow regulation exceeding the pipeline safety range is divided into high-risk regulation, medium-risk regulation and low-risk regulation, and corresponding management is carried out; Maintenance module: For medium-risk regulation, further prediction is made on the risk of water flow regulation exceeding the pipeline safety range within a fixed time period, and the pump start-up frequency and valve opening speed are dynamically adjusted according to the prediction results to reduce the risk of pipeline rupture.

[0019] In the data acquisition module, stress sensors are installed at key locations of the pipeline (such as pipe joints, elbows, corners of pipeline sections, etc.) to monitor the stress changes of the pipeline in real time. It calculates the actual pressure bearing capacity of the pipeline by detecting the strain changes when the pipeline is stressed. The stress sensor can sense the stress of the pipeline under the influence of factors such as water flow load, external pressure changes, and pipeline aging, thereby helping to assess whether there is a potential risk of overload or excessive pressure in the pipeline.

[0020] Stress sensors detect tiny deformations inside or on the surface of the pipeline and convert them into strain signals. The strain signal is transmitted to the central control system through the sensor, and the system analyzes the strain changes to calculate the current stress level of the pipeline. Based on these data, the system can determine whether the pipeline is within the design load range. If it exceeds the load limit, it will sound an alarm or automatically adjust the water flow to avoid pipeline rupture or leakage. Stress sensors are usually installed in places where the pipeline is subjected to greater stress, such as: pipe elbows or connection points, which are easily affected by water flow fluctuations, friction and external pressure. High-pressure areas, such as water pump outlets, trunk pipelines, etc.

[0021] Pressure sensors are used to monitor water pressure changes at different monitoring points in the pipeline in real time. These monitoring points can be distributed in various areas of the pipeline, especially in locations where water consumption varies greatly, flow fluctuates significantly, or the pipeline is relatively fragile. Pressure sensors can provide real-time data on the water pressure inside the pipeline, helping to analyze whether the pipeline is over-pressurized or whether the water flow is abnormal, and prevent pipeline bursts or leaks caused by excessive water pressure.

[0022] Pressure sensors usually use piezoresistive, piezoelectric or capacitive principles to sense the water pressure inside the pipe. These sensors convert the water pressure in the pipe into an electrical signal and transmit it to the monitoring system. The system can determine the working status of the pipeline through real-time analysis of water pressure data. If the system finds that the water pressure is close to or exceeds the designed pressure range of the pipeline, the system will automatically issue an early warning to prompt the operator to take measures, such as adjusting the water flow or activating a backup pipeline. Pressure sensors can be installed at multiple monitoring points in the pipeline network to fully understand the changes in water pressure. Typical installation locations include: important nodes such as water source inlet, pump station outlet or water tower outlet. The water pressure fluctuates greatly at the end of the pipeline, especially in the end area far away from the center. High-pressure areas of the pipeline network or pipe sections that are subject to heavy loads.

[0023] By deploying stress sensors and pressure sensors at the same time, the system can monitor the operation status of the pipeline in real time. These data can be integrated into a unified monitoring platform for the following aspects: Real-time pipeline pressure bearing capacity monitoring: The stress sensor provides data on the actual pressure bearing capacity of the pipeline, while the pressure sensor provides data on the current water pressure of the pipeline. The combination of the two can achieve comprehensive monitoring of whether the pipeline is overloaded and real-time assessment of whether the pipeline is within the designed pressure range.

[0024] Dynamic water flow regulation: Based on the collected data, the system can determine whether changes in water flow will cause excessive water pressure in the pipe. If it detects that the water pressure fluctuates too much or the stress is close to the critical point, the system will automatically adjust the water flow or take other measures to avoid damage or bursting of the pipe.

[0025] Risk warning and fault prediction: Based on stress and pressure data, the system can analyze the pressure fluctuation pattern of the pipeline under different operating conditions and predict potential fault risks in advance. For example, if the pipeline is under too high pressure, the risk of pipeline burst may be predicted in advance, so that measures can be taken in advance to avoid accidents.

[0026] Data analysis and maintenance optimization: The historical data collected by sensors provides an important basis for later pipeline maintenance. By analyzing the pressure bearing capacity of the pipeline and the trend of water pressure fluctuations, maintenance personnel can evaluate the degree of pipeline aging, local damage and other problems, and perform preventive maintenance before problems occur, thereby reducing the occurrence of unexpected accidents.

[0027] Pipeline pressure bearing capacity monitoring module: monitors the actual pressure bearing capacity of each section of pipeline in real time based on the actual pressure bearing capacity data of the pipeline obtained in real time, and evaluates the stability of the pipeline pressure bearing capacity by analyzing the maximum load fluctuation of the pipeline under different operating environments.

[0028] Based on the data collected by the sensors, the system continuously calculates and evaluates the pressure bearing capacity of each section of the pipeline. The assessment of pressure bearing capacity is mainly based on: Pipeline material and thickness: The theoretical pressure bearing capacity is calculated based on the material of the pipeline (such as steel, cast iron, plastic, etc.) and the thickness of the pipeline. Environmental factors: Such factors as climate change, soil pressure, terrain factors, etc., will also affect the pressure bearing capacity of the pipeline. Historical data comparison: Compare with the historical operation data of the pipeline to determine whether the pipeline is within the normal load range. Pressure bearing status assessment: The system monitors the pressure bearing capacity of each section of the pipeline in real time through the set safety pressure bearing standards. If the pressure bearing capacity of a section of the pipeline is lower than the safety threshold, the system will automatically issue an alarm to remind the operation and maintenance personnel to check or adjust.

[0029] The load on the pipeline will fluctuate according to factors such as water flow, water demand, and pipeline network scheduling. For example, increased water consumption during peak hours in the morning and evening may cause a momentary increase in pipeline pressure; load fluctuations may also occur when the water pump is started or stopped. After collecting water pressure data, by analyzing the changing trends of these water pressure data, especially the frequency and amplitude of pressure fluctuations, the system can identify whether the pipeline often experiences excessive load fluctuations. If the load fluctuations on the pipeline are too large, it may cause fatigue, aging or damage to the pipeline material, increasing the risk of pipeline rupture. The system can use advanced data analysis methods (such as Fourier transform, time domain analysis, frequency domain analysis, etc.) to process the water pressure fluctuation data and extract the characteristics of load fluctuations.

[0030] The stability of the pipeline's pressure bearing capacity is calculated by conducting statistical analysis on pipeline load fluctuations in different time periods. The key indicators for stability assessment include: Pressure bearing capacity fluctuation amplitude: The greater the amplitude of change in the pipeline's pressure bearing capacity, the worse the stability, indicating that the pipeline has been under excessive pressure for a long time, which may cause structural damage. Frequency and period: The frequency and period of load fluctuations are also key factors in assessing stability. Frequent and drastic fluctuations mean that the pipeline is under unstable loads for a long time and is prone to fatigue. Duration: Assess the duration of load fluctuations that exceed the pipeline's design pressure bearing capacity. If the duration is too long, it may aggravate pipeline fatigue damage and cause pipeline rupture.

[0031] After analyzing the pipeline load fluctuations in different time periods, the pipeline load fluctuation index is generated. The pipeline load fluctuation index is obtained as follows: Collect and organize pipeline water pressure fluctuation data, which are usually time series data, indicating the changes in water pressure at different locations in the pipeline within a certain period of time. Filter or denoise the original data to remove external noise interference and ensure accurate analysis results.

[0032] Set the original signal to x(t), where t is time and x(t) is the water pressure value corresponding to time point t; calculate the local maximum and local minimum of the signal. Calculate the upper and lower envelopes u(t) and l(t) of the signal through the local maximum and minimum. Calculate the average value of the envelope , the expression is: . Extract an intrinsic mode function IMF of the signal: ; If h(t) satisfies the definition of IMF (i.e.: 1) the number of zero crossing points and extreme points of the signal is equal or differs by 1; 2) the local average of the envelope is zero), then stop; otherwise, repeat the above steps until the conditions are met.

[0033] Repeat the steps until the signal is decomposed into several IMF components and a residual signal. and a residual signal r(t). For each IMF component , calculate its amplitude and energy, and calculate the maximum value of the IMF component and minimum value , and get the amplitude , the expression is: ; Energy is calculated by the sum of squares, expressed as: ; Where T is the total duration of the signal.

[0034] The frequency characteristics of each IMF component can be obtained by analyzing its spectrum. Common frequency analysis methods include Fourier transform or wavelet transform. Frequency characteristics It can be represented by calculating its main frequency. For example, the IMF component is transformed into the frequency domain using Fourier transform to obtain the spectrum , the expression is: ; The amplitude, energy and frequency of each IMF are combined to obtain the pipeline load fluctuation index, which is expressed as: ; In the formula, ECK is the pipeline load fluctuation index, where is the weight coefficient (usually set through experiments or experience).

[0035] When the pipeline load fluctuation index is large, it usually means that the pipeline pressure bearing capacity is highly unstable. This is because when the load fluctuation index is large, the amplitude and frequency of water pressure changes are large, which may cause the pipeline to frequently withstand severe water pressure fluctuations. Such fluctuations will accelerate pipeline fatigue and aging, and increase the risk of pipeline rupture. Especially when the pipeline is aged or improperly maintained, excessive fluctuations may cause damage to the pipeline structure and even cause serious problems such as water pipe bursts, thereby affecting the stability and safety of the water supply system.

[0036] On the contrary, when the pipeline load fluctuation index is small, it means that the water pressure changes more smoothly and the pipeline pressure bearing capacity is more stable. In this case, the fluctuation of water flow and water pressure is within the safe range of pipeline design and will not cause excessive pressure shock to the pipeline. Smaller fluctuations help maintain the long-term operation stability of the pipeline and reduce fatigue damage to the pipeline, thereby extending the service life of the pipeline, reducing maintenance costs, and effectively ensuring the safety and reliability of the water supply system.

[0037] Water pressure fluctuation analysis module: If the pipeline's pressure bearing capacity is stable, the frequency and amplitude characteristics of the water pressure fluctuation are extracted through the Fourier transform algorithm to evaluate whether the water flow is within the pipeline's pressure bearing range.

[0038] By placing pressure sensors in the pipeline, water pressure data at each monitoring point can be obtained in real time. These data are usually stored in the form of time series. The water pressure data is processed by denoising and removing outliers to ensure the accuracy and effectiveness of the data during the analysis process. For example, filters can be used to remove high-frequency noise and smooth the signal.

[0039] Fourier transform is a mathematical method that converts time domain signals into frequency domain signals. Through Fourier transform, the time series signal x(s) of water pressure can be converted into a frequency domain signal X(f), that is, the amplitude and phase information of each frequency component, s is time, and the expression is: ; Where f is the frequency, x(s) is the time domain signal, and X(f) is the frequency domain signal.

[0040] The result X(f) after Fourier transformation can show the amplitude of each frequency component, indicating the strength of the signal at different frequencies. The amplitude spectrum of water pressure fluctuation can reveal the intensity of water flow fluctuation. The result of Fourier transformation can also provide the main frequency of fluctuation, which helps to identify periodic or irregular fluctuations of water flow. If the frequency component matches the design frequency of the pipeline, it means that the water flow fluctuation is within the pressure range of the pipeline.

[0041] By analyzing the amplitude of water pressure fluctuations, it is evaluated whether the pressure of the water flow exceeds the design pressure range of the pipeline. If the fluctuation amplitude of water pressure is too large, it may lead to the risk of pipeline rupture. Comparison of frequency and pipeline characteristics: By comparing the frequency characteristics with the natural frequency of the pipeline design, it is determined whether there is resonance. The resonant frequency will amplify the water flow fluctuations and increase the risk of pipeline rupture.

[0042] The water pressure fluctuation frequency anomaly index is generated by analyzing the frequency characteristics of water pressure fluctuations. The method for obtaining the water pressure fluctuation frequency anomaly index is as follows: The time series data of water pressure obtained from the water pipe network is usually the data x(s) collected regularly by the pressure sensor, which represents the change of water pressure in time s. The time domain signal x(s) of water pressure is converted into the frequency domain signal X(f) through Fourier transform, so as to analyze the intensity of different frequency components in the signal; the Fourier transform formula is: ; Where X(f) is the complex representation of the frequency domain signal, representing the amplitude and phase of each frequency f, x(s) is the time domain signal of water pressure, f is the frequency, and the unit is Hertz (Hz). j is the imaginary unit, and s is the time. Through Fourier transform, we can get the frequency domain signal X(f), which contains the amplitude and phase of the signal at different frequencies. From the result of Fourier transform, we can extract the amplitude spectrum, that is, the amplitude of the frequency domain signal , the expression is: ; where ℜ[X(f)] and ℑ[X(f)] are the real and imaginary parts of the frequency domain signal X(f), respectively.

[0043] Under normal circumstances, the frequency of water pressure fluctuations in the pipeline should fall within a certain range. If the frequency spectrum of the water pressure signal exceeds the predetermined range, these frequency components are considered abnormal. Calculate the deviation between the actual frequency spectrum and the expected frequency spectrum , the expression is: ; In the formula, is the expected frequency spectrum, and the water pressure fluctuation frequency anomaly index is calculated. The expression is: ; In the formula, is the maximum value of frequency, It is the water pressure fluctuation frequency anomaly index.

[0044] The larger the water pressure fluctuation frequency anomaly index (FAI), the more drastic the change in the water pressure fluctuation frequency, which usually means that the fluctuation of the water flow exceeds the pressure range of the pipeline design. This drastic frequency fluctuation may be caused by structural problems in the pipeline, improper valve operation, pump station failure, etc. The increase in the frequency anomaly index means that the fluctuation frequency of the water flow pressure exceeds the normal fluctuation range, which may cause the pressure in the pipeline to be too high or too low instantly, increasing the risk of pipeline rupture, leakage or equipment damage. Therefore, a large frequency anomaly index usually indicates that the pipeline's pressure bearing capacity has failed to adapt to the current changes in water flow, and there is a potential risk of pipeline rupture.

[0045] On the contrary, the smaller the water pressure fluctuation frequency anomaly index is, the more stable the water flow fluctuation is, and the frequency change is in line with the pressure bearing capacity of the pipeline design. This usually means that the pipeline is operating normally, the water flow changes are within a reasonable range, and the amplitude and frequency of pressure fluctuations do not exceed the pressure bearing capacity of the pipeline. When the frequency anomaly index is small, the pressure bearing capacity of the pipeline is stable, the water flow regulation and system operation are relatively smooth, and abnormal situations such as pipeline rupture are unlikely to occur. Therefore, a smaller frequency anomaly index usually indicates that the water flow is within the pressure bearing range of the pipeline and the system operation is in a safe state.

[0046] Risk assessment module: Based on the stability of the pipeline's pressure bearing capacity and the characteristics of dynamic water pressure changes, the risk of water flow regulation exceeding the pipeline's safety range is assessed.

[0047] The pipeline load fluctuation index and the water pressure fluctuation frequency anomaly index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the risk value label of water flow regulation exceeding the pipeline safety range as the prediction target, and takes minimizing the sum of prediction errors of all risk value labels of water flow regulation exceeding the pipeline safety range as the training target. The machine learning model is trained until the sum of prediction errors converges and the model training is stopped. The risk value of water flow regulation exceeding the pipeline safety range is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0048] The method for obtaining the risk value of water flow regulation exceeding the pipeline safety range is as follows: from the comprehensive feature vector training data of the trained machine learning model, the corresponding function expression is obtained: ; In the formula, is the output function of the model, ECK is the pipeline load fluctuation index, FAI is the water pressure fluctuation frequency anomaly index, The risk value for water flow regulation exceeding the safety range of the pipeline.

[0049] Risk classification module: Based on the assessment results, the risk of water flow regulation exceeding the pipeline safety range is divided into high-risk regulation, medium-risk regulation and low-risk regulation, and corresponding management is carried out.

[0050] The risk value of the water flow regulation exceeding the pipeline safety range is compared with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the risk value of the water flow regulation exceeding the pipeline safety range is compared with the first standard threshold and the second standard threshold respectively; If the risk value of the water flow regulation exceeding the pipeline safety range is greater than the second standard threshold, it means that the risk of the water flow regulation exceeding the pipeline safety range is high, and a first-level warning signal is generated at this time, and the risk of the water flow regulation exceeding the pipeline safety range is classified as high-risk regulation; If the risk value of water flow regulation exceeding the pipeline safety range is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the risk of water flow regulation exceeding the pipeline safety range is at a medium level. At this time, a secondary warning signal is generated, and the risk of water flow regulation exceeding the pipeline safety range is classified as medium risk regulation; If the risk value of water flow regulation exceeding the pipeline safety range is less than the first standard threshold, it means that the risk of water flow regulation exceeding the pipeline safety range is low. At this time, a third-level warning signal is generated, and the risk of water flow regulation exceeding the pipeline safety range is classified as low-risk regulation.

[0051] It should be noted here that the importance of the first-level warning signal is greater than that of the second-level warning signal, and the importance of the second-level warning signal is greater than that of the third-level warning signal. Relevant personnel can take corresponding management measures according to different warning signal levels.

[0052] High-risk regulation management requires the immediate activation of the emergency warning system to pass information to relevant managers and technicians, triggering a first-level warning signal and requiring prompt action. Conduct a quick inspection of the relevant area, and the monitoring system comprehensively evaluates the real-time status and water flow characteristics of the pipeline to determine whether there is a risk of pipeline rupture or other equipment failure. Temporarily stop or slowly reduce water flow regulation to reduce pressure on the pipeline. Set control limits for maximum allowable water flow and pressure fluctuations to prevent further system imbalance or equipment damage. Conduct emergency inspections of pipelines and equipment to check for signs of structural damage, equipment failure or overload operation. Dispatch maintenance personnel to perform troubleshooting and repair work to prevent possible pipeline rupture or leakage. Strengthen the monitoring and inspection frequency of pipelines, use remote monitoring technology to grasp the operating status of pipelines in real time, and respond quickly to abnormal situations. Optimize water flow regulation strategies and use intelligent regulation systems to ensure that pipelines operate within a safe water flow and pressure range.

[0053] Medium-risk regulation management needs to trigger a secondary warning to notify relevant personnel to pay attention to the operating status of the pipeline, especially water pressure fluctuations and load changes. According to the risk value, set the inspection frequency of pipelines and equipment to improve the sensitivity of detection. Improve the accuracy of pipeline monitoring, analyze water flow fluctuations through real-time monitoring data, and identify potential risks in a timely manner. Use frequency anomaly detection algorithms and pipeline pressure bearing capacity assessment models for dynamic monitoring to warn of unstable trends in pipelines in advance. Optimize water flow regulation strategies to avoid excessive fluctuations and ensure that pipelines operate within the medium risk range. Use intelligent algorithms to adjust the start-up frequency of water pumps and the speed of valve opening and closing to ensure that water flow fluctuations do not cause stress overload in pipelines. Strengthen daily inspections and pipeline maintenance, and regularly inspect key parts to ensure that there are no potential structural problems. Regularly inspect equipment, clean up debris in pipelines, and check pipeline sealing and aging.

[0054] Low-risk regulation management needs to trigger a third-level warning. The system reminds managers to pay attention to the status of water flow regulation, but no emergency response is required. Emphasize regular monitoring to ensure that there are no hidden dangers that gradually accumulate during long-term operation. Regularly perform health checks on pipelines to ensure that the fluctuation frequency of water flow and load fluctuations are within the normal range. Continuously monitor the actual pressure bearing capacity of the pipeline and the fluctuation of water flow, and use data analysis and prediction models to ensure that the pipeline operation is within the safety boundary. During the operation of the system, implement mild optimization, such as adjusting the optimal control range of water flow to avoid small-scale fluctuations affecting the long-term stability of the system. Encourage the gradual implementation of new regulation technologies or system upgrades under low-risk conditions to improve the flexibility and intelligence level of overall management. Regularly summarize and analyze all sensor data to ensure that there are no potential risk points. Establish a good data recording and analysis mechanism to support possible optimization and improvement in the future. Continuously improve the water flow regulation model through the data feedback mechanism, and use new regulation strategies in the water flow regulation process.

[0055] Maintenance module: For medium-risk regulation, further prediction is made on the risk of water flow regulation exceeding the pipeline safety range within a fixed time period, and the pump start-up frequency and valve opening speed are dynamically adjusted according to the prediction results to reduce the risk of pipeline rupture.

[0056] For medium-risk regulation, it is necessary to make time series predictions based on the risk value of historical water flow regulation exceeding the pipeline safety range, recorded as R(m). Use a simple regression model, or a more advanced autoregressive integrated moving average (ARIMA) model, long short-term memory (LSTM) model, etc. to predict future risk values. Set the water flow regulation risk value of the time series to R(m), where m represents the time step, and the formula is: ;in, is the predicted future risk value, and f is the risk value prediction function, which can be any machine learning algorithm (such as linear regression, ARIMA, LSTM, etc.). is the historical risk value, and n is the total number of historical risk values. By predicting the future risk value, the pump start frequency and valve opening speed can be dynamically adjusted. The goal is to control the water flow so that it always remains within the pressure bearing capacity of the pipeline and avoid pipeline overload caused by water flow fluctuations.

[0057] The starting frequency of the water pump is proportional to the risk value of water flow regulation. A high risk value requires reducing the starting frequency of the water pump to reduce pipeline pressure fluctuations. The formula is: ;in, is the pump start frequency, expressed in number of starts / time, and α is a regulation constant that indicates the relationship between the risk value and the pump start frequency. For a higher predicted risk value, the pump start frequency should be reduced to avoid excessive fluctuations in pipeline pressure caused by over-frequent starts.

[0058] The valve opening speed affects the water flow rate and pressure fluctuation in the pipeline. When the risk value is high, the valve opening speed should be controlled in a slower range to avoid excessive water pressure fluctuations that lead to drastic fluctuations in pipeline pressure. The adjustment formula for the valve opening speed is: ;in, is the valve opening speed, the unit is valve opening degree / unit time, β is an adjustment constant, which represents the relationship between the risk value and the valve opening speed.

[0059] In this embodiment, multiple modules work together to ensure the safe operation of the pipeline network. First, by installing stress and pressure sensors at key locations of the pipeline, the pressure bearing capacity and water pressure data of the pipeline are collected in real time. The pipeline pressure bearing capacity monitoring module analyzes the data in real time, evaluates the stability of the pipeline's pressure bearing capacity, and extracts the frequency and amplitude characteristics of water pressure fluctuations through Fourier transform to further determine whether the water flow is within the safety range of the pipeline. The risk assessment module evaluates whether the water flow regulation exceeds the safety range of the pipeline based on the pressure bearing capacity and water pressure changes, and divides it into high, medium and low risks for management in combination with the risk classification module. For medium-risk regulation, the maintenance module dynamically adjusts the water pump start-up frequency and valve opening by predicting water flow risks to reduce the risk of pipeline rupture.

[0060] 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.

[0061] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0062] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the 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.

Claims

1. A smart pipe network management system based on Internet of Things technology, characterized by: It includes data acquisition module, pipeline pressure bearing capacity monitoring module, water pressure fluctuation analysis module, risk assessment module, risk classification module and maintenance module; Data acquisition module: by installing stress sensors at different positions of the pipeline, it is used to obtain the actual pressure bearing capacity data of the pipeline in real time, and by laying pressure sensors in the pipeline, it is used to collect the water pressure data of each monitoring point in real time; Pipeline pressure bearing capacity monitoring module: monitors the actual pressure bearing capacity of each section of pipeline in real time based on the actual pressure bearing capacity data of pipeline obtained in real time, and evaluates the stability of pipeline pressure bearing capacity by analyzing the maximum load fluctuation of pipeline under different operating environments; Water pressure fluctuation analysis module: If the pipeline pressure bearing capacity is stable, the frequency and amplitude characteristics of water pressure fluctuations are extracted through the Fourier transform algorithm to evaluate whether the water flow is within the pipeline pressure range; Risk assessment module: Based on the stability of the pipeline's pressure bearing capacity and the characteristics of dynamic water pressure changes, the risk of water flow regulation exceeding the pipeline's safety range is assessed; Risk classification module: Based on the assessment results, the risk of water flow regulation exceeding the pipeline safety range is divided into high-risk regulation, medium-risk regulation and low-risk regulation, and corresponding management is carried out; Maintenance module: For medium-risk regulation, further prediction is made on the risk of water flow regulation exceeding the pipeline safety range within a fixed time period, and the pump start-up frequency and valve opening speed are dynamically adjusted according to the prediction results to reduce the risk of pipeline rupture.

2. According to claim 1, a smart pipe network management system based on Internet of Things technology is characterized by: In the pipeline pressure bearing capacity monitoring module, the pipeline load fluctuation situation in different time periods is analyzed to generate the pipeline load fluctuation index. The method for obtaining the pipeline load fluctuation index is as follows: Collect and organize the water pressure fluctuation data x(t) of the pipeline, where t is time and x(t) is the water pressure value corresponding to time point t; calculate the local maximum and local minimum of the signal, calculate the upper and lower envelopes u(t) and l(t) of the signal through the local maximum and minimum, and calculate the average value of the envelope , the expression is: ; Extract the intrinsic mode function IMF of the signal until the signal is decomposed into several IMF components and a residual signal, and obtain several IMF components through EMD decomposition and a residual signal r(t), for each IMF component , calculate its amplitude and energy, and calculate the maximum value of the IMF component and minimum value Get the amplitude , the expression is: ; Energy is calculated by the sum of squares, expressed as: ; Where T is the total duration of the signal; frequency characteristics By calculating its main frequency, the IMF component is transformed into the frequency domain using Fourier transform to obtain the spectrum , the expression is: ; The amplitude, energy and frequency of each IMF are combined to obtain the pipeline load fluctuation index, which is expressed as: ; In the formula, ECK is the pipeline load fluctuation index, where is the weight coefficient.

3. According to claim 2, a smart pipe network management system based on Internet of Things technology is characterized by: In the water pressure fluctuation analysis module, the water pressure fluctuation frequency anomaly index is generated by analyzing the frequency characteristics of the water pressure fluctuation. The method for obtaining the water pressure fluctuation frequency anomaly index is as follows: The time series data x(s) of water pressure is obtained from the water pipe network, which represents the change of water pressure at time s. The time domain signal x(s) of water pressure is converted into the frequency domain signal X(f) through Fourier transform, so as to analyze the intensity of different frequency components in the signal; the Fourier transform formula is: ; Where X(f) is the complex number representation of the frequency domain signal, representing the amplitude and phase of each frequency f, x(s) is the time domain signal of water pressure, f is the frequency, j is the imaginary unit, and s is the time. Through Fourier transform, the frequency domain signal X(f) is obtained, which contains the amplitude and phase of the signal at different frequencies. The amplitude spectrum, that is, the amplitude of the frequency domain signal, is extracted from the result of Fourier transform, and the deviation between the actual frequency spectrum and the expected frequency spectrum is calculated. , the expression is: ; In the formula, is the expected frequency spectrum, and the water pressure fluctuation frequency anomaly index is calculated. The expression is: ; In the formula, is the maximum value of frequency, It is the water pressure fluctuation frequency anomaly index.

4. According to claim 3, a smart pipe network management system based on Internet of Things technology is characterized by: In the risk assessment module, the risk of water flow regulation exceeding the pipeline safety range is assessed based on the stability of the pipeline's pressure bearing capacity and the dynamic water pressure change characteristics. Specifically: The pipeline load fluctuation index and the water pressure fluctuation frequency anomaly index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the risk value label of water flow regulation exceeding the pipeline safety range as the prediction target, and takes minimizing the sum of prediction errors of all risk value labels of water flow regulation exceeding the pipeline safety range as the training target. The machine learning model is trained until the sum of prediction errors converges and the model training is stopped. The risk value of water flow regulation exceeding the pipeline safety range is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

5. According to claim 4, a smart pipe network management system based on Internet of Things technology is characterized by: In the risk classification module, the risk of water flow regulation exceeding the pipeline safety range is divided into high-risk regulation, medium-risk regulation and low-risk regulation according to the assessment results; The risk value of the water flow regulation exceeding the pipeline safety range is compared with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the risk value of the water flow regulation exceeding the pipeline safety range is compared with the first standard threshold and the second standard threshold respectively; If the risk value of the water flow regulation exceeding the pipeline safety range is greater than the second standard threshold, it means that the risk of the water flow regulation exceeding the pipeline safety range is high, and a first-level warning signal is generated at this time, and the risk of the water flow regulation exceeding the pipeline safety range is classified as high-risk regulation; If the risk value of water flow regulation exceeding the pipeline safety range is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the risk of water flow regulation exceeding the pipeline safety range is at a medium level. At this time, a secondary warning signal is generated, and the risk of water flow regulation exceeding the pipeline safety range is classified as medium risk regulation; If the risk value of water flow regulation exceeding the pipeline safety range is less than the first standard threshold, it means that the risk of water flow regulation exceeding the pipeline safety range is low. At this time, a third-level warning signal is generated, and the risk of water flow regulation exceeding the pipeline safety range is classified as low-risk regulation.

6. According to claim 1, the intelligent pipe network management system based on Internet of Things technology is characterized by: In the maintenance module, for medium-risk regulation, the risk of water flow regulation exceeding the pipeline safety range within a fixed time period is further predicted, and the pump start frequency and valve opening speed are dynamically adjusted according to the prediction results. Specifically: For medium-risk regulation, the water flow regulation risk value of the time series is set to R(m), where m represents the time step, and the formula is: ;in, is the predicted future risk value, f is the risk value prediction function, is the historical risk value, and n is the total number of historical risk values.

7. The intelligent pipe network management system based on Internet of Things technology according to claim 6 is characterized by: The starting frequency of the water pump is proportional to the risk value of water flow regulation. A high risk value requires reducing the starting frequency of the water pump to reduce pipeline pressure fluctuations. The formula is: ;in, is the starting frequency of the water pump, α is an adjustment constant, which indicates the relationship between the risk value and the starting frequency of the water pump; the valve opening speed affects the water flow rate and pressure fluctuation in the pipeline. When the risk value is high, the adjustment formula of the valve opening speed is: ;in, is the valve opening speed, and β is an adjustment constant that represents the relationship between the risk value and the valve opening speed.

Images