Intelligent data acquisition and analysis method based on big data

Abstract

The invention discloses an intelligent data acquisition and analysis method based on big data, and particularly relates to the field of data analysis, comprising intelligent target data, intelligent data acquisition, controller deployment, preprocessing, data analysis and comprehensive analysis. According to the invention, accurate acquisition and analysis of key data of a pipe network system are realized through determination of intelligent target data; a high-precision sensor and an advanced data acquisition technology are adopted, so that the accuracy and reliability of data are ensured; through the comprehensive analysis model, the dynamic response, the multi-dimensional coupling relation and the material degradation process of the pipe network system are comprehensively captured, and a scientific basis is provided for the evaluation of the health state of the pipe network; the established health state evaluation model of the pipe network system realizes quantitative evaluation of the health state, can timely discover potential problems and risks, provides scientific decision support for maintenance and management of the pipe network system, and is helpful for improving the safety of the pipe network system and prolonging the service life of the pipe network system.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and more specifically, to an intelligent data collection and analysis method based on big data. Background Art

[0002] With the acceleration of urbanization, the safety and reliability of underground pipe network systems, as an important part of urban infrastructure, are increasingly valued. Pipe network systems involve multiple fields, including civil engineering, materials science, fluid mechanics, etc., and their health status is directly related to the safe operation of the city and the quality of life of residents.

[0003] At present, the monitoring and evaluation of the pipe network system mainly relies on traditional inspection and regular testing methods. These methods usually include manual inspection, regular sampling and analysis, and judgment based on experience. The operation process is roughly as follows: inspectors regularly conduct on-site inspections of the pipe network and record abnormal conditions; sample and analyze suspected problem areas to obtain more detailed data; finally, based on experience and comprehensive data analysis, evaluate the health status of the pipe network system.

[0004] However, existing technologies have many shortcomings. Manual inspections are limited by personnel experience and subjective judgment, making it difficult to fully and accurately capture the dynamic changes of the pipeline system. Although regular inspections can provide certain data support, the inspection cycle is long and the data update is slow, making it difficult to detect potential problems in a timely manner. In addition, existing technologies lack scientific and systematic analysis methods, and the assessment of the health status of the pipeline system is not accurate and comprehensive enough. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an intelligent data collection and analysis method based on big data, and solves the problems raised in the above-mentioned background technology through the following scheme.

[0006] To achieve the above object, the present invention provides the following technical solution: an intelligent data collection and analysis method based on big data, comprising:

[0007] Step 1: Intelligent target data: used to determine target data, including pipe network stress and strain data, environmental coupling data, medium operation data, and material degradation data, and collected through step 2;

[0008] Step 2: Intelligent data collection: used to collect the target data in step 1 and transmit it to step 3;

[0009] Step 3: Controller deployment: used to divide the target area and deploy controllers, manage the connection of sensors in step 2 through the controller, and pre-process the data collected in step 2 through step 4;

[0010] Step 4: Preprocessing: used to perform signal preprocessing on the data collected in step 2 and transmit it to step 5;

[0011] Step 5: Data analysis: Analyze the data transmitted in step 4 by establishing a comprehensive analysis model for pipeline network stress and strain data, a comprehensive analysis model for environmental coupling data, a comprehensive analysis model for medium operation data, and a comprehensive analysis model for material degradation data, and transmit the analysis results to step 6;

[0012] Step 6: Comprehensive analysis: Used to establish a pipeline network system health status assessment model to conduct a comprehensive analysis of the data transmitted in step 5, and establish thresholds to conduct status assessment on the target pipeline network system.

[0013] Preferably, the pipe network stress-strain data include characteristic values ​​of pipe wall deformation spectrum, cumulative displacement and periodicity of interface, bending stress distribution curve of pipe section and vibration wave propagation attenuation coefficient, which are marked as Pw, Pj, Pb and Pv respectively; the environmental coupling data include electrochemical parameters of soil-pipeline interface, groundwater seepage pressure fluctuation characteristics, surrounding building load transfer effect and geological micro-dynamic response spectrum, which are marked as Es, Eg, Eb and Em respectively; the medium operation data include fluid turbulence pulsation characteristic spectrum, pressure transient propagation law, local hydraulic factor distribution and fluid-solid coupling vibration mode, which are marked as Mf, Mp, Ml and Ms respectively; the material degradation data include pipe stress corrosion sensitivity, anti-corrosion layer impedance change law, concrete carbonization depth distribution and crack growth rate field, which are marked as Dp, Da, Dc and Dm respectively.

[0014] Preferably, the characteristic value of the pipe wall deformation spectrum is obtained by arranging fiber grating sensors every 50 meters along the outer wall of the pipeline to establish a monitoring network, the sensor sampling frequency is set to 200 Hz, the pipe wall strain data is collected in real time, the optical signal is converted into an electrical signal by a fiber optic demodulator, and then processed by FFT transformation to obtain spectrum data in the range of 0-100 Hz, and the amplitude of the main frequency point is extracted as the characteristic value, and the interface displacement accumulation and periodicity are obtained by installing an LVDT displacement sensor with an accuracy of 0.01 mm at the pipeline interface. The sensor is fixed on a stable bracket, the probe is in contact with the pipeline, and the displacement value is recorded every 5 minutes for 24 hours. After collecting data through a data collector, the data within 24 hours is calculated. The cumulative displacement is calculated by analyzing the periodic law of displacement change, and the daily variation period characteristic value is obtained. The bending stress distribution curve of the pipe section is obtained by evenly arranging 5 resistance strain gauges in the circumferential direction on the section of the pipeline every 10 meters. The strain gauges are connected to the data acquisition system through a Wheatstone bridge. The sampling frequency is set to 1Hz. The data is collected continuously for 24 hours. After obtaining the strain data, the stress value is calculated using Hooke's law, and the stress distribution curve of the pipe section is drawn. The vibration wave propagation attenuation coefficient is calculated by arranging a piezoelectric acceleration sensor every 20 meters along the pipeline, the sampling frequency is set to 1kHz, and a known vibration source is applied at the starting point of the pipeline. The vibration response of each measuring point is synchronously collected, and the wave propagation attenuation coefficient is calculated by comparing the attenuation of the vibration amplitude at different measuring points.

[0015] Preferably, the electrochemical parameters of the soil-pipeline interface are measured by burying four reference electrodes within a range of 0.5 meters around the pipeline to form a monitoring ring, collecting potential data once an hour, and measuring the soil resistivity in the depth range of 0-2 meters by a quadrupole method, and using an electrochemical workstation to measure the polarization resistance. The groundwater seepage pressure fluctuation characteristics are measured by arranging a pore water pressure sensor with a range of 0-500kPa and an accuracy of 0.1kPa every 5 meters within a range of 1 meter around the pipeline, recording the pressure value every 30 minutes, and obtaining the pressure fluctuation law and characteristic value through time series analysis. The load transfer effect of surrounding buildings is measured by arranging earth pressure boxes every 5 meters between the pipeline and the building, with a measurement range of 0-1MPa, and at the same time arranging settlement monitoring points with an accuracy of 0.1mm, recording data once an hour, and analyzing the load transfer law. The geological microdynamic response spectrum is measured by arranging a three-component seismometer at the interface between soft and hard soils with a sampling frequency of 100Hz, continuously recording geological vibration data, and obtaining characteristic periods and spectrum values ​​through spectral analysis.

[0016] Preferably, the fluid turbulence pulsation characteristic spectrum is obtained by arranging an ultrasonic flow field measurement system with 16 measuring points in the cross section of the pipeline with a sampling frequency of 1kHz, collecting the flow velocity pulsation data and performing FFT analysis to obtain a turbulence energy spectrum in the range of 0-500Hz. The pressure transient propagation law is obtained by installing a pressure sensor with a range of 0-1.6MPa every 100 meters along the pipeline with a sampling frequency of 1kHz, capturing the pressure wave propagation process through a synchronous trigger system, and calculating the attenuation characteristics. The local hydraulic factor distribution is measured by using a Doppler flowmeter in the gradually converging and expanding sections of the pipeline with a sampling frequency of 10Hz. At the same time, pressure sensors are arranged to monitor the pressure distribution and calculate the hydraulic factor. The fluid-solid coupling vibration mode is determined by arranging a three-axis acceleration sensor array at the midpoint of the suspended span section of the pipeline with a sampling frequency of 500Hz. The vibration data is processed by modal analysis software to extract vibration modal parameters.

[0017] Preferably, the stress corrosion sensitivity of the pipe is measured by selecting a measuring point every 50 meters on the pipeline surface, installing a three-electrode system at each measuring point, using an electrochemical noise meter in ZRA mode, setting the sampling frequency to 1 Hz, continuously collecting for 12 hours, measuring the potential noise range to ±10mV, the current noise range to ±100nA, and calculating the corrosion rate by calculating the noise power spectrum density, the localization index and the rolling intercept method. The stress corrosion sensitivity is comprehensively evaluated. When the localization index is greater than 0.1, it indicates a tendency to stress corrosion. The change law of the impedance of the anti-corrosion layer is determined by using a portable electrochemical workstation, setting a measuring point every 1 meter on the pipeline surface, adopting a three-electrode system, selecting Cu / CuSO4 as the reference electrode, and using a graphite rod as the auxiliary electrode. The electrochemical impedance spectroscopy test is performed, the scanning frequency range is 0.01Hz-100kHz, the excitation signal amplitude is 10mV, and the impedance modulus and phase angle in the Nyquist diagram and the Bode diagram are recorded. Each measuring point is collected 3 times and the average value is taken. The measurement environment temperature is maintained at 20±2°C, and the capacitance value of the anti-corrosion layer is obtained by equivalent circuit fitting to evaluate the anti-corrosion. Layer integrity and concrete carbonation depth distribution are measured by drilling a 20mm diameter test hole every 10 meters on the surface of the pipeline concrete protective layer, with depths of 5mm, 10mm, 15mm, 20mm, and 25mm respectively. A digital resistivity tester is used, the probe spacing is set to 5cm, the working voltage is 50V, and each depth is measured 3 times. At the same time, 1% phenolphthalein solution is sprayed at each depth, and the pH value is measured by color reaction. When pH<9, it means that carbonization has occurred. The crack growth rate field is measured by arranging 4 acoustic emission sensors per square meter in the welding joint area. The sensor uses a piezoelectric chip with a resonance frequency of 150kHz and a sensitivity greater than -65dB. The sampling rate of the data acquisition system is set to 1MHz, the pre-amplifier gain is 40dB, the event trigger threshold is set to 40dB, and the positioning accuracy is required to be ±5mm. The crack source position is determined by waveform parameter analysis and arrival time difference positioning algorithm. Continuous monitoring for 24 hours records the acoustic emission events of crack activity. The Kaiser effect is used to determine whether the crack is in an expansion state, and the crack growth rate is calculated by the event rate and energy rate.

[0018] Preferably, the localization index is specifically a standard deviation / root mean square value of each measuring point.

[0019] Preferably, step 3 divides the target area into sub-areas at a rate of 500 square meters each, with an overlap of 20%-30% between adjacent sub-areas, a width of 10-15 meters between overlapping sub-areas, a signal strength of no less than -75dBm between overlapping sub-areas, a switching trigger point of a switching threshold of -65dBm, a deployment position of the controller at the geometric center of the sub-area, an installation height of 2.5-3 meters from the ground, a communication bandwidth of 100Mbps reserved for each sub-area, and a transmission delay between sub-areas of no more than 10ms.

[0020] Preferably, step 4 eliminates environmental noise by wavelet transform or Kalman filtering, uses sliding average or exponential smoothing to process mutations, identifies abnormal points based on the 3σ principle or box plot method, and uses an interpolation algorithm to process missing data.

[0021] Preferably, the comprehensive analysis model of the pipe network stress-strain data is specifically expressed as:

[0022]

[0023] P represents the comprehensive index of stress and strain of the pipeline network, t represents the time variable, x and y represent the spatial coordinates, r represents the radial distance, α represents the fluctuation attenuation coefficient, represents the partial derivative operator.

[0024] Preferably, the environmental coupling data comprehensive analysis model is specifically expressed as:

[0025]

[0026] E represents the comprehensive index of environmental coupling, φ represents the potential function, represents the Laplace operator, n represents the normal vector, μ represents the attenuation coefficient, r represents the distance, s represents the surface parameter, and FFT represents the fast Fourier transform.

[0027] Preferably, the medium operation data comprehensive analysis model is specifically expressed as:

[0028]

[0029] M represents the comprehensive index of medium operation, Re represents the Reynolds number, ω represents the angular frequency, φi, φj represent the modal function, n represents the power index, represents the Laplace operator.

[0030] Preferably, the material degradation data comprehensive analysis model is specifically expressed as:

[0031]

[0032] D represents the comprehensive index of material degradation, σc represents the critical stress, ε represents the strain, Z represents the impedance function, k(T) represents the temperature influence coefficient, KI represents the stress intensity factor, and a represents the crack length.

[0033] Preferably, the pipeline network system health status assessment model is specifically expressed as:

[0034]

[0035] H represents the health status assessment value of the pipeline network system, and f is a multivariable nonlinear mapping function.

[0036] Preferably, the thresholds include a warning threshold, a pre-warning threshold, and a danger threshold, denoted as H1, H2, and H3, where H1 = 0.85×H max , H2 = 0.70×H max , H3 = 0.50×H max . When H > H1, it represents a healthy state; when H2 < H ≤ H1, it represents a warning state; when H3 < H ≤ H2, it represents a pre-warning state; when H ≤ H3, it represents a danger state.

[0037] Technical effects and advantages of the present invention:

[0038] The present invention defines target data through intelligent target data, providing a clear direction and focus for subsequent data collection and analysis. These target data cover multiple key aspects of the pipeline network system, helping to comprehensively evaluate the health state of the pipeline network system. Through intelligent data collection, high-precision sensors and advanced collection technologies are used to ensure the accuracy and reliability of the data. The combination of real-time collection and long-term monitoring can capture the dynamic change process of the pipeline network system. Different collection methods are adopted for different types of data, improving the pertinence and efficiency of data collection. Through controller deployment, reasonable regional division and controller deployment are carried out, realizing the effective management and control of the sensor network, ensuring the stability and real-time nature of data transmission, and providing a reliable basis for subsequent data preprocessing and analysis. Sufficient communication bandwidth is reserved and transmission delay is considered, improving the efficiency and quality of data transmission. Through preprocessing, the influence of environmental noise and mutation data on the analysis results is effectively eliminated, abnormal points and missing data are identified and processed, improving the integrity and accuracy of the data, and providing a cleaner and more accurate data set for subsequent data analysis. Through data analysis, a comprehensive analysis model is established, and different types of data are organically integrated and comprehensively analyzed to capture the dynamic response characteristics, multi-dimensional coupling relationships, complex fluid-structure coupling processes, and multi-mechanism coupling processes of material deterioration of the pipeline network system, providing a scientific and comprehensive basis for the health state assessment of the pipeline network system. Through comprehensive analysis, a health state assessment model of the pipeline network system is established, realizing the quantitative assessment of the health state of the pipeline network system. Warning thresholds, pre-warning thresholds, and danger thresholds are set, enabling the timely discovery of potential problems and risks in the pipeline network system, providing scientific decision-making support for the maintenance and management of the pipeline network system, and helping to extend the service life of the pipeline network system and improve its safety. Description of the Drawings

[0039] Figure 1 It is a schematic diagram of the overall structure of the present invention. Detailed Embodiments

[0040] 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.

[0041] refer to Figure 1 The method for intelligent data collection and analysis based on big data shown in the figure comprises the following specific steps:

[0042] Step 1: Intelligent target data: used to determine the target data, including pipeline network stress and strain data, environmental coupling data, medium operation data and material degradation data, and collected through step 2.

[0043] The stress-strain data of the pipeline network include characteristic values ​​of the pipe wall deformation spectrum, cumulative displacement and periodicity of the interface, bending stress distribution curve of the pipe section and vibration wave propagation attenuation coefficient, which are marked as Pw, Pj, Pb and Pv respectively; the environmental coupling data include electrochemical parameters of the soil-pipeline interface, groundwater seepage pressure fluctuation characteristics, surrounding building load transfer effect and geological microdynamic response spectrum, which are marked as Es, Eg, Eb and Em respectively; the medium operation data include fluid turbulence pulsation characteristic spectrum, pressure transient propagation law, local hydraulic factor distribution and fluid-solid coupling vibration mode, which are marked as Mf, Mp, Ml and Ms respectively; the material degradation data include pipe stress corrosion sensitivity, anti-corrosion layer impedance change law, concrete carbonization depth distribution and crack growth rate field, which are marked as Dp, Da, Dc and Dm respectively.

[0044] Step 2: Intelligent data collection: used to collect the target data in step 1 and transmit it to step 3.

[0045] The characteristic value of the pipe wall deformation spectrum is obtained by laying fiber optic Bragg grating sensors every 50 meters along the outer wall of the pipeline to establish a monitoring network. The sensor sampling frequency is set to 200 Hz, and the pipe wall strain data is collected in real time. The optical signal is converted into an electrical signal by a fiber optic demodulator, and then processed by FFT transformation to obtain spectrum data in the range of 0-100 Hz. The amplitude of the main frequency point is extracted as the characteristic value, and the interface displacement accumulation and periodicity are calculated by installing an LVDT displacement sensor with an accuracy of 0.01 mm at the pipeline interface. The sensor is fixed on a stable bracket, and the probe is in contact with the pipeline. The displacement value is recorded every 5 minutes for 24 hours. After collecting data through a data collector, the accumulation within 24 hours is calculated. The displacement is integrated, the periodic law of displacement change is analyzed, and the daily variation period characteristic value is obtained. The bending stress distribution curve of the pipe section is obtained by evenly arranging 5 resistance strain gauges in the circumferential direction on the section of the pipeline every 10 meters. The strain gauges are connected to the data acquisition system through a Wheatstone bridge. The sampling frequency is set to 1Hz. The data is collected continuously for 24 hours. After obtaining the strain data, the stress value is calculated using Hooke's law, and the stress distribution curve of the pipe section is drawn. The vibration wave propagation attenuation coefficient is obtained by arranging a piezoelectric acceleration sensor every 20 meters along the pipeline. The sampling frequency is set to 1kHz. A known vibration source is applied at the starting point of the pipeline. The vibration response of each measuring point is synchronously collected. The wave propagation attenuation coefficient is calculated by comparing the attenuation of the vibration amplitude at different measuring points.

[0046] The electrochemical parameters of the soil-pipeline interface are measured by burying four reference electrodes within a range of 0.5 meters around the pipeline to form a monitoring ring, collecting potential data once an hour, measuring soil resistivity in the depth range of 0-2 meters with a quadrupole method, and measuring polarization resistance using an electrochemical workstation. The groundwater seepage pressure fluctuation characteristics are measured by arranging a pore water pressure sensor with a range of 0-500kPa and an accuracy of 0.1kPa every 5 meters within a range of 1 meter around the pipeline, recording the pressure value every 30 minutes, and obtaining the pressure fluctuation law and characteristic value through time series analysis. The load transfer effect of surrounding buildings is measured by arranging earth pressure boxes every 5 meters between the pipeline and the building, with a measuring range of 0-1MPa, and arranging settlement monitoring points with an accuracy of 0.1mm, recording data once an hour, and analyzing the load transfer law. The geological microdynamic response spectrum is measured by arranging a three-component seismometer at the interface between soft and hard soils with a sampling frequency of 100Hz, continuously recording geological vibration data, and obtaining characteristic periods and spectrum values ​​through spectral analysis.

[0047] The fluid turbulence pulsation characteristic spectrum is measured by arranging an ultrasonic flow field measurement system with 16 measuring points in the cross section of the pipeline with a sampling frequency of 1kHz. After collecting the flow velocity pulsation data, FFT analysis is performed to obtain a turbulence energy spectrum within the range of 0-500Hz. The pressure transient propagation law is measured by installing a pressure sensor with a range of 0-1.6MPa every 100 meters along the pipeline with a sampling frequency of 1kHz. The pressure wave propagation process is captured by a synchronous trigger system and the attenuation characteristics are calculated. The local hydraulic factor distribution is measured by using a Doppler flowmeter in the gradually contracting and expanding sections of the pipeline with a sampling frequency of 10Hz. At the same time, pressure sensors are arranged to monitor the pressure distribution and calculate the hydraulic factor. The fluid-solid coupling vibration mode is measured by arranging a three-axis acceleration sensor array at the midpoint of the suspended span section of the pipeline with a sampling frequency of 500Hz. The vibration data is processed by modal analysis software to extract vibration modal parameters.

[0048] The stress corrosion sensitivity of the pipe is measured by selecting a measuring point every 50 meters on the pipeline surface, installing a three-electrode system at each measuring point, using an electrochemical noise meter in ZRA mode, setting the sampling frequency to 1Hz, and continuously collecting data for 12 hours. The potential noise range is ±10mV, and the current noise range is ±100nA. The corrosion rate is calculated by calculating the noise power spectrum density, localization index and rolling intercept method, and the stress corrosion sensitivity is comprehensively evaluated. When the localization index is greater than 0.1, it indicates a tendency to stress corrosion. The change law of the impedance of the anti-corrosion layer is measured by using a portable electrochemical workstation. A measuring point is arranged every 1 meter on the pipeline surface. A three-electrode system is used. Cu / CuSO4 is selected as the reference electrode, and a graphite rod is used as the auxiliary electrode. The electrochemical impedance spectroscopy test is performed. The scanning frequency range is 0.01Hz-100kHz, and the excitation signal amplitude is 10mV. The impedance modulus and phase angle in the Nyquist diagram and Bode diagram are recorded. Each measuring point is collected 3 times and the average value is taken. The measurement environment temperature is maintained at 20±2℃. The capacitance value of the anti-corrosion layer is obtained by equivalent circuit fitting to evaluate the completeness of the anti-corrosion layer. The integrity and distribution of concrete carbonation depth were measured by drilling a 20mm diameter test hole every 10 meters on the surface of the pipeline concrete protective layer, with depths of 5mm, 10mm, 15mm, 20mm, and 25mm respectively. A digital resistivity tester was used, with the probe spacing set to 5cm and the working voltage set to 50V. Each depth was measured 3 times, and 1% phenolphthalein solution was sprayed at each depth. The pH value was measured by color reaction. When pH<9, it means that carbonization has occurred. The crack growth rate field was measured by arranging 4 acoustic emission sensors per square meter in the welding joint area. The sensor used a piezoelectric chip with a resonance frequency of 150kHz and a sensitivity greater than -65dB. The sampling rate of the data acquisition system was set to 1MHz, the pre-amplifier gain was 40dB, the event trigger threshold was set to 40dB, and the positioning accuracy was required to be ±5mm. The crack source position was determined by waveform parameter analysis and arrival time difference positioning algorithm. Continuous monitoring was performed for 24 hours to record the acoustic emission events of crack activity. The Kaiser effect was used to determine whether the crack was in an expansion state, and the crack growth rate was calculated by the event rate and energy rate.

[0049] The localization index is specifically a standard deviation / root mean square value of each measuring point.

[0050] Step 3: Controller deployment: used to divide the target area and deploy the controller, manage the connection of the sensors in step 2 through the controller, and pre-process the data collected in step 2 through step 4.

[0051] The step 3 divides the target area into sub-areas at a rate of 500 square meters each, with an overlap of 20%-30% between adjacent sub-areas, a width of 10-15 meters between overlapping sub-areas, a signal strength of no less than -75dBm between overlapping sub-areas, a switching trigger point of a switching threshold of -65dBm, a deployment position of the controller at the geometric center of the sub-area, an installation height of 2.5-3 meters from the ground, a 100Mbps communication bandwidth reserved for each sub-area, and a transmission delay between sub-areas of no more than 10ms.

[0052] Step 4: Preprocessing: It is used to perform signal preprocessing on the data collected in step 2 and transmit it to step 5.

[0053] The step 4 eliminates environmental noise by wavelet transform or Kalman filtering, uses sliding average or exponential smoothing to process mutations, identifies abnormal points based on the 3σ principle or box plot method, and uses an interpolation algorithm to process missing data.

[0054] Step 5: Data analysis: Analyze the data transmitted in step 4 by establishing a comprehensive analysis model for pipeline network stress-strain data, a comprehensive analysis model for environmental coupling data, a comprehensive analysis model for medium operation data, and a comprehensive analysis model for material degradation data, and transmit the analysis results to step 6.

[0055] The comprehensive analysis model of pipeline network stress and strain data is specifically expressed as follows:

[0056]

[0057] P represents the comprehensive index of stress and strain of the pipeline network, t represents the time variable, x and y represent the spatial coordinates, r represents the radial distance, α represents the fluctuation attenuation coefficient, represents the partial derivative operator.

[0058] The comprehensive analysis model of pipeline network stress and strain data describes the dynamic evolution process of pipeline network stress and strain. The propagation characteristics of pipe wall deformation are captured by time-space domain integration. The accumulation of interface displacement uses nonlinear time terms to characterize its long-term effects. The circumferential integral reflects the distribution law of bending stress in the pipe cross section. Finally, the exponential attenuation characteristics of vibration waves during spatial propagation are considered to fully reflect the dynamic response characteristics of the pipeline network structure.

[0059] The environmental coupling data comprehensive analysis model is specifically expressed as follows:

[0060]

[0061] E represents the comprehensive index of environmental coupling, φ represents the potential function, represents the Laplace operator, n represents the normal vector, μ represents the attenuation coefficient, r represents the distance, s represents the surface parameter, and FFT represents the fast Fourier transform.

[0062] The environmental coupling data comprehensive analysis model reflects the multi-dimensional coupling relationship between environmental factors and pipeline systems. The three-dimensional Laplace operator describes the spatial distribution of the electrochemical field, the interfacial water pressure reflects the seepage effect through the normal gradient integral, the building load adopts the exponential decay model to represent the stress transfer, and the geological micro-motion is analyzed by Fourier transform to analyze its spectral characteristics, which fully considers the spatial distribution and time evolution of the environmental load.

[0063] The comprehensive analysis model of medium operation data is specifically expressed as follows:

[0064]

[0065] M represents the comprehensive index of medium operation, Re represents the Reynolds number, ω represents the angular frequency, φi, φj represent the modal function, n represents the power index, represents the Laplace operator.

[0066] The comprehensive analysis model of medium operation data describes the complex process of fluid-structure interaction. The turbulent pulsation characteristics are characterized by frequency domain integration. The time derivative of pressure transient reflects the severity of pressure fluctuation. The Laplace operator of hydraulic factor describes the spatial distribution characteristics. The modal superposition reflects the structural vibration characteristics, which fully reflects the dynamic behavior of the fluid-solid coupling system.

[0067] The material degradation data comprehensive analysis model is specifically expressed as:

[0068]

[0069] D represents the comprehensive index of material degradation, σc represents the critical stress, ε represents the strain, Z represents the impedance function, k(T) represents the temperature influence coefficient, KI represents the stress intensity factor, and a represents the crack length.

[0070] The comprehensive analysis model of material degradation data reflects the multi-mechanism coupling process of material degradation. Stress corrosion characterizes the cumulative damage through strain integration, impedance change uses time-space partial differentials to describe the dynamic characteristics, carbonization depth considers the spatial distribution of temperature effects, crack extension reflects the fracture mechanics characteristics through the double integration of stress intensity factors, and fully describes the multi-scale evolution law of material degradation.

[0071] Step 6: Comprehensive analysis: Used to establish a pipeline network system health status assessment model to conduct a comprehensive analysis of the data transmitted in step 5, and establish thresholds to conduct status assessment on the target pipeline network system.

[0072] The pipeline network system health status assessment model is specifically expressed as:

[0073] H = f(P, E, M, D) = ∫∫∫(P, E, M, exp(-D)) dx dy dt

[0074] H represents the health status evaluation value of the pipe network system, and f is a multivariable non-linear mapping function.

[0075] The health status evaluation model of the pipe network system considers the spatial (x, y) and temporal (t) dimensions through triple integration. P, E, and M are multiplied as positive indicators, and D, as a negative indicator, is transformed through an exponential function.

[0076] The thresholds include a warning threshold, a pre-warning threshold, and a danger threshold, denoted as H1, H2, and H3, where H1 = 0.85×H max , H2 = 0.70×H max , H3 = 0.50×H max , when H > H1, it indicates a healthy state; when H2 < H ≤ H1, it indicates a warning state; when H3 < H ≤ H2, it indicates a pre-warning state; when H ≤ H3, it indicates a danger state.

[0077] The present invention clarifies the target data through intelligent target data, providing a clear direction and focus for subsequent data collection and analysis. These target data cover multiple key aspects of the pipe network system, contributing to a comprehensive assessment of the health status of the pipe network system. Through intelligent data collection, high-precision sensors and advanced collection technologies are used to ensure the accuracy and reliability of the data. The combination of real-time collection and long-term monitoring can capture the dynamic change process of the pipe network system. Different collection methods are adopted for different types of data, improving the pertinence and efficiency of data collection. Through controller deployment, reasonable regional division and controller deployment are carried out, realizing the effective management and control of the sensor network, ensuring the stability and real-time nature of data transmission, and providing a reliable basis for subsequent data preprocessing and analysis. Sufficient communication bandwidth is reserved and transmission delay is considered, improving the efficiency and quality of data transmission. Through preprocessing, the influence of environmental noise and mutation data on the analysis results is effectively eliminated, abnormal points and missing data are identified and processed, improving the integrity and accuracy of the data, and providing a cleaner and more accurate data set for subsequent data analysis. Through data analysis, a comprehensive analysis model is established to organically integrate and comprehensively analyze different types of data, capturing the dynamic response characteristics, multi-dimensional coupling relationships, complex fluid-structure coupling processes, and multi-mechanism coupling processes of material deterioration in the pipe network system, providing a scientific and comprehensive basis for the health status evaluation of the pipe network system. Through comprehensive analysis, a health status evaluation model of the pipe network system is established to realize the quantitative evaluation of the health status of the pipe network system, set warning thresholds, pre-warning thresholds, and danger thresholds, be able to timely detect potential problems and risks in the pipe network system, provide scientific decision-making support for the maintenance and management of the pipe network system, and contribute to extending the service life of the pipe network system and improving its safety.

[0078] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0079] 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. An intelligent data collection and analysis method based on big data, characterized in that: include: Step 1: Intelligent target data: used to determine target data, including pipe network stress and strain data, environmental coupling data, medium operation data, and material degradation data, and collected through step 2; Step 2: Intelligent data collection: used to collect the target data in step 1 and transmit it to step 3; Step 3: Controller deployment: used to divide the target area and deploy controllers, manage the connection of sensors in step 2 through the controller, and pre-process the data collected in step 2 through step 4; Step 4: Preprocessing: used to perform signal preprocessing on the data collected in step 2 and transmit it to step 5; Step 5: Data analysis: Analyze the data transmitted in step 4 by establishing a comprehensive analysis model for pipeline network stress and strain data, a comprehensive analysis model for environmental coupling data, a comprehensive analysis model for medium operation data, and a comprehensive analysis model for material degradation data, and transmit the analysis results to step 6; Step 6: Comprehensive analysis: Used to establish a pipeline network system health status assessment model to conduct a comprehensive analysis of the data transmitted in step 5, and establish thresholds to conduct status assessment on the target pipeline network system.

2. The intelligent data collection and analysis method based on big data according to claim 1 is characterized in that: The stress-strain data of the pipeline network include the characteristic values ​​of the pipe wall deformation spectrum, the cumulative amount and periodicity of the interface displacement, the bending stress distribution curve of the pipe section and the vibration wave propagation attenuation coefficient, which are marked as Pw, Pj, Pb and Pv respectively. The environmental coupling data include the electrochemical parameters of the soil-pipeline interface, the fluctuation characteristics of the groundwater seepage pressure, the load transfer effect of the surrounding buildings and the geological micro-dynamic response spectrum, which are marked as Es, Eg, Eb and Em respectively. The medium operation data include the fluid turbulence pulsation characteristic spectrum, the pressure transient propagation law, the local hydraulic factor distribution and the fluid-solid coupling vibration mode, which are marked as Mf, Mp, Ml and Ms respectively. The material degradation data include the stress corrosion sensitivity of the pipe, the impedance change law of the anti-corrosion layer, the carbonization depth distribution of the concrete and the crack growth rate field, which are marked as Dp, Da, Dc and Dm respectively.

3. The intelligent data collection and analysis method based on big data according to claim 1 is characterized in that: The step 3 divides the target area into sub-areas at a rate of 500 square meters each, with an overlap of 20%-30% between adjacent sub-areas, a width of 10-15 meters between overlapping sub-areas, a signal strength of no less than -75dBm between overlapping sub-areas, a switching trigger point of a switching threshold of -65dBm, a deployment position of the controller at the geometric center of the sub-area, an installation height of 2.5-3 meters from the ground, a 100Mbps communication bandwidth reserved for each sub-area, and a transmission delay between sub-areas of no more than 10ms.

4. The intelligent data collection and analysis method based on big data according to claim 1 is characterized in that: The comprehensive analysis model of pipeline network stress and strain data is specifically expressed as follows: P represents the comprehensive index of pipe network stress and strain, t represents the time variable, x and y represent the spatial coordinates, r represents the radial distance, α represents the fluctuation attenuation coefficient, represents the partial derivative operator.

5. The intelligent data collection and analysis method based on big data according to claim 1 is characterized in that: The environmental coupling data comprehensive analysis model is specifically expressed as follows: E represents the comprehensive index of environmental coupling, φ represents the potential function, represents the Laplace operator, n represents the normal vector, μ represents the attenuation coefficient, r represents the distance, s represents the surface parameter, and FFT represents the fast Fourier transform.

6. The intelligent data collection and analysis method based on big data according to claim 1 is characterized by: The comprehensive analysis model of medium operation data is specifically expressed as follows: M represents the comprehensive index of medium operation, Re represents the Reynolds number, ω represents the angular frequency, φi, φj represent the modal function, n represents the power index, represents the Laplace operator.

7. The intelligent data collection and analysis method based on big data according to claim 1 is characterized in that: The material degradation data comprehensive analysis model is specifically expressed as: D represents the comprehensive index of material degradation, σc represents the critical stress, ε represents the strain, Z represents the impedance function, k(T) represents the temperature influence coefficient, KI represents the stress intensity factor, and a represents the crack length.

8. The intelligent data collection and analysis method based on big data according to claim 1 is characterized in that: The health status assessment model of the pipe network system is specifically expressed as follows: H=f(P,E,M,D)=∫∫∫(P,E,M,exp(-D))dxdydt H represents the health status assessment value of the pipeline network system, and f is a multivariable nonlinear mapping function.

9. The intelligent data collection and analysis method based on big data according to claim 1, characterized in that: The thresholds include a warning threshold, a pre-warning threshold, and a danger threshold, denoted as H1, H2, and H3, where H1 = 0.85 × H max , H2 = 0.70 × H max , H3 = 0.50 × H max , when H > H1, it indicates a healthy state; when H2 < H ≤ H1, it indicates a warning state; when H3 < H ≤ H2, it indicates a pre-warning state; when H ≤ H3, it indicates a danger state.

Images