Pipe lining stability analysis and health monitoring system for urban water supply pipe network

Abstract

The invention discloses a pipe liner stability analysis and health monitoring system for an urban water supply pipe network, and particularly relates to the field of water supply pipe network health monitoring, which comprises the following steps: a data acquisition module acquires three-axis vibration data and adds a timestamp and a topological label; the signal separation module extracts independent components of turbulence and structural vibration; the modal offset labeling module calculates an energy coupling ratio and identifies an offset modal; the stability attenuation evaluation module compares the reference data through the transfer function matrix to quantify the rigidity loss and converts the rigidity loss into a pipe liner stability attenuation rate; the synchronous association module analyzes the time sequence characteristics and marks synchronous association nodes; the pipe lining degradation traceability module constructs a traceability path tree and converts the traceability path tree into a decision result with geographic coordinates; the system can effectively distinguish fluid disturbance and structural abnormity, performs pipe lining degradation monitoring and traceability, realizes visual early warning, and ensures long-term stable operation of a water supply pipe network.

Description

Technical Field

[0001] The present invention relates to the technical field of water supply network monitoring. More specifically, the present invention relates to a pipe lining stability analysis and health monitoring system for urban water supply networks. Background Art

[0002] Since the pipes in urban water supply networks operate underground for a long time, their structural health is significantly affected by the changes in surrounding rock stress. Affected by factors such as the relaxation of in-situ stress, the change of groundwater seepage pressure, or periodic loads (such as earthquakes, construction disturbances, etc.), the surrounding rock will cause millimeter-level elastic deformation of the pipes. This deformation not only changes the geometric parameters of the pipes but also affects the stability attenuation of the pipe lining layer, thereby changing the internal natural vibration modes, especially the standing wave mode in the low-frequency band. However, the existing pipe lining health monitoring technologies mainly rely on traditional methods such as laboratory testing or empirical judgment. Such traditional methods require sampling or even shutting down the water supply network for testing, making it difficult to ensure the timeliness and adaptability of the testing. Especially in the scenario of large-scale systems such as urban water supply networks, the traditional testing methods show great inadaptability.

[0003] In addition, the existing water supply network health monitoring technologies often adopt a decentralized sensor layout and perform anomaly alarms based on single signal characteristics, without being able to provide a clear traceability of pipe lining deterioration.

[0004] To solve the above problems, a technical solution is provided now. Summary of the Invention

[0005] To overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a pipe lining stability analysis and health monitoring system for urban water supply networks to solve the problems raised in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solutions: A pipe lining stability analysis and health monitoring system for urban water supply networks includes a data acquisition module, a signal separation module, a modal offset annotation module, a stability attenuation evaluation module, a synchronization association module, and a pipe lining deterioration traceability module: The data acquisition module acquires three-axis vibration raw waveform data containing timestamps, and outputs the data to the signal separation module after attaching timestamps and topological labels; The signal separation module calculates the independent component projection directions of the turbulent component and the structural vibration component, and outputs the separated turbulent noise signal and structural vibration signal; The modal offset annotation module extracts the amplitude spectrum energy of the vibration mode, calculates the percentage of the energy in each direction in the total energy, constructs an energy coupling ratio matrix, and marks the response offset mode; The stability decay evaluation module applies a variable-direction mechanical excitation wave at the modal shift marking pipeline node to calculate the transfer function matrix, compares it with the preset initial reference matrix at each frequency point, and extracts the phase difference data to quantify the stability decay of the pipe lining; The synchronous correlation module maps the energy coupling ratio matrix and the pipe lining stability decay to the graph node features, analyzes the temporal evolution of the modal parameters, captures synchronous events and marks the synchronous correlation nodes; The pipe lining deterioration traceability module constructs a traceability tree structure including the main path and alternative branches, and converts the verified traceability path tree into a decision result with geographical coordinate annotations.

[0007] In a preferred embodiment, collecting the original three-axis vibration waveform data with timestamps and outputting the data to the signal separation module after attaching timestamps and topological labels specifically includes: Install three-axis low-frequency acceleration sensors along the axial direction of the inner wall of the pipeline in the water supply network at preset intervals to collect the original three-axis vibration waveform data with timestamps; At the same time, collect the surrounding rock strain data at the same acquisition frequency as the original vibration waveform data; According to the longitude and latitude coordinates of the sensor installation position and the pipeline node number, establish a spatial position-sensor identification mapping relationship table, and output the standardized vibration data stream with topological labels; Encode the calibrated three-axis vibration data into double-precision floating-point format according to the axial, circumferential, and radial components, and output it to the signal separation module after attaching timestamps and topological labels.

[0008] In a preferred embodiment, it is characterized in that calculating the independent component projection directions of the turbulent component and the structural vibration component and outputting the separated turbulent noise signal and structural vibration signal specifically includes: Perform time window segmentation on the input standardized vibration data stream, use the Hamming window function to eliminate spectral leakage, and output the time-domain signal frame sequence with an overlap rate; Introduce the kurtosis statistic as a weight factor in the FastICA objective function, use the non-Gaussianity measure as the separation criterion, and calculate the independent component projection directions of the turbulent component and the structural vibration component; Iteratively update the demixing matrix through the fixed-point algorithm, and terminate when the change rate of the Frobenius norm of the mixing matrix between adjacent iterations is lower than the convergence threshold, and output the separated turbulent noise signal and structural vibration signal; Calculate the autocorrelation peak decay rate of the structural vibration component. If the amplitude decay rates of the main peak and the secondary peak reach below the set minimum decay rate threshold, it is determined as a valid modal signal; Recombine the structural vibration components of the valid modal signals according to the time-domain frame sequence, attach the separation confidence label and output it to the modal shift annotation module, and discard the invalid separation data that does not meet the standard.

[0009] In a preferred embodiment, calculating the percentage of energy in each direction in the total energy by extracting the amplitude spectrum energy of the vibration mode, constructing an energy coupling ratio matrix, and marking the response offset mode specifically include: Perform frequency-domain decomposition on the input structural vibration signal, extract the amplitude spectrum energy of the axial, circumferential, and radial vibration modes using the frequency-domain subspace method, and output the modal energy density distribution curves in each direction; Integrate the axial, circumferential, and radial modal energies within a set frequency band respectively, calculate the percentage of energy in each direction in the total energy, and generate a three-degree-of-freedom energy percentage vector; Based on the sensor topology index table of the acquisition module, perform feature fusion on the energy percentage vectors of adjacent nodes, and construct a three-dimensional matrix containing the axial-circumferential, circumferential-radial, and axial-radial energy coupling ratios; Based on the sliding time window, statistically calculate the mean and variance of the historical energy ratios of each node. If the current coupling ratio deviates from the mean by more than the set dynamic threshold, mark the modal offset and record the offset direction; Encode the modal offset mark and the corresponding energy coupling ratio matrix into a structured data stream, append the time stamp and topological label, and then output it to the stability decay evaluation module.

[0010] In a preferred embodiment, applying a variable-direction mechanical excitation wave at the modal offset mark pipeline node to calculate the transfer function matrix, comparing it with the preset initial reference matrix point by point in frequency, and extracting the phase difference data to quantify the stability decay of the pipe lining specifically include: Apply a variable-direction mechanical excitation wave at the pipeline node corresponding to the modal offset mark, synchronously record the vibration velocity and excitation force data corresponding to each frequency point, and calculate the complex ratio of the vibration velocity to the excitation force through Fourier transform to form a transfer function matrix; Calculate the current transfer function matrix, compare it with the preset initial reference matrix point by point in frequency, extract the phase lag of the transfer function, and generate a curve of the phase difference varying with frequency; Based on the elastic wave propagation theory, establish a stiffness-phase mapping model for the physical relationship between the propagation phase difference and the axial stiffness, and quantify the stiffness loss of the current axial stiffness relative to the initial reference according to the phase difference; Convert the stiffness loss quantization value into an expression of the stability response deterioration attenuation of the pipe lining structure under frequency-domain excitation, and generate an equivalent pipe lining stability decay rate; Send the modal offset pipeline node with an equivalent pipe lining stability decay rate greater than or equal to the set equivalent pipe lining stability decay rate threshold to the synchronous correlation module.

[0011] In a preferred embodiment, mapping the energy coupling ratio matrix and the pipe lining stability decay to the graph node features, analyzing the temporal evolution of the modal parameters, capturing synchronous events, and marking the synchronous correlation nodes specifically include: Map the energy coupling ratio matrix and the transfer function matrix into graph node features, define the edge connection relationship based on the sensor topology index table, and initialize the edge weights; Dynamically adjust the edge weights according to the temporal covariance of the energy coupling ratio between nodes, use the sliding window Pearson correlation coefficient to quantify the vibration propagation path intensity, and generate a dynamic adjacency matrix; Overlay a time dimension sliding window on the dynamic adjacency matrix, apply a spectral graph convolution kernel to extract spatial features, and combine a gated recurrent unit to capture the temporal evolution law of modal parameters; Calculate the cosine similarity of the change in the modal energy ratio between adjacent nodes within a set time window. If the average similarity of a continuously set number of windows exceeds a preset threshold, it is determined as a synchronization event and the synchronized associated nodes are marked; Encode the synchronized associated node clusters and their topological connection relationships into a regional number list, and transmit it to the pipe lining deterioration traceability module after attaching a confidence score.

[0012] In a preferred embodiment, constructing a traceability tree-like structure including a main path and alternative branches, and converting the verified traceability path tree into a decision result with geographical coordinate annotations specifically includes: Align the synchronized associated node clusters with the surrounding rock strain historical data according to the acquisition timestamps; Based on the backpropagation confidence weighted algorithm, iteratively calculate the posterior probability of each node as the source of pipe lining deterioration on the pipeline topology graph, and output a heat map of the pipe lining deterioration source probability distribution; Search for the maximum probability propagation path according to the heat map of the pipe lining deterioration source probability distribution, and construct a tree-like structure including a main path and alternative branches; Calculate the entropy value of the tree-like path branches. If the entropy value of the main path is lower than the average entropy value of the branches and the confidence gradient descent rate meets the preset smoothness micro interval, it is determined that the path converges effectively; Convert the verified traceability path tree into a decision result with geographical coordinate annotations, trigger an early warning signal, and push it to the visualization interface of the operation and maintenance platform.

[0013] In a preferred embodiment, the triggering of the early warning signal and pushing it to the visualization interface of the operation and maintenance platform specifically includes: After receiving the early warning signal, the water supply network operation and maintenance platform marks the source node in red on the visualization interface based on the decision result. The main path continuously passes through the associated nodes with a solid line, and the alternative branch paths are marked with a dashed line to indicate the secondary impact area.

[0014] The technical effects and advantages of a pipe lining stability analysis and health monitoring system for urban water supply networks according to the present invention: The signal separation module optimizes the non-Gaussianity metric based on the independent component analysis method to efficiently separate the turbulent noise and the structural vibration signal. The modal shift annotation module calculates the proportion of vibration energy, constructs an energy coupling ratio matrix, and identifies the response mode shift characteristics. The stability decay evaluation module uses a variable-direction mechanical excitation wave and combines transfer function matrix analysis to quantitatively evaluate the stiffness loss, and then generates the stability decay rate of the equivalent pipe lining. The synchronous correlation module constructs a synchronous event marking mechanism based on the temporal evolution law of vibration modes, captures the spatial correlation characteristics for traceability analysis. The pipe lining deterioration traceability module constructs a traceability tree structure, combines geographical coordinate information, and generates a visual decision result, providing accurate and efficient early warning means for the health monitoring of the pipe lining of the water supply pipeline.

[0015] The system can effectively distinguish high-frequency fluid disturbances, capture low-frequency abnormal disturbances of the pipe lining structure, monitor and trace the deterioration of the pipe lining of the water supply pipeline, and at the same time achieve visual early warning to ensure the long-term stable operation of the water supply network. Brief Description of the Drawings

[0016] Figure 1 This is a schematic structural diagram of a pipe lining stability analysis and health monitoring system for urban water supply networks according to the present invention. Detailed Embodiments

[0017] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0018] Embodiment 1 Figure 1 A pipe lining stability analysis and health monitoring system for urban water supply networks according to the present invention is provided, including a data acquisition module, a signal separation module, a modal shift annotation module, a stability decay evaluation module, a synchronous correlation module, and a pipe lining deterioration traceability module: The data acquisition module acquires the original three-axis vibration waveform data containing time stamps, and outputs the data to the signal separation module after attaching time stamps and topological tags; The signal separation module calculates the independent component projection directions of the turbulent component and the structural vibration component, and outputs the separated turbulent noise signal and structural vibration signal; The modal shift annotation module extracts the amplitude spectrum energy of the vibration mode, calculates the percentage of the energy in each direction in the total energy, constructs an energy coupling ratio matrix, and marks the response offset mode; The stability decay evaluation module applies a variable-direction mechanical excitation wave at the modal shift marking pipeline node to calculate the transfer function matrix, compares it with the preset initial reference matrix at each frequency point, extracts the phase difference data, and quantifies the stability decay of the pipe lining. The synchronous correlation module maps the energy coupling ratio matrix and the pipe lining stability decay to the graph node features, analyzes the temporal evolution of the modal parameters, captures synchronous events, and marks the synchronous correlation nodes. The pipe lining deterioration traceability module constructs a traceability tree structure including the main path and alternative branches, and converts the verified traceability path tree into a decision result with geographical coordinate annotations.

[0019] Collect the raw triaxial vibration waveform data containing timestamps, attach timestamps and topological labels to the data, and output it to the signal separation module.

[0020] Install triaxial low-frequency acceleration sensors along the inner wall axis of the water supply pipeline at preset intervals, and collect the raw triaxial vibration waveform data containing timestamps by aligning them with the axial (X), circumferential (Y), and radial (Z) directions of the pipeline respectively. Use a GNSS surveying instrument to record the longitude and latitude coordinates of each sensor, with a required accuracy better than ±0.5 meters, and establish a high-precision position index.

[0021] At the same time, collect the surrounding rock strain data at the same acquisition frequency as the raw vibration waveform data. The vibration data and the strain data use a unified clock synchronization protocol (IEEE 1588 PTP) to ensure that the timestamp error does not exceed 1 ms to avoid phase shift caused by data alignment error.

[0022] According to the longitude and latitude coordinates of the sensor installation location and the pipeline node number, construct a spatial position-sensor identification mapping table, store it using hash indexing, and output a standardized vibration data stream with topological labels. Encode the calibrated triaxial vibration data into double-precision floating-point format according to the axial, circumferential, and radial components. At the same time, preprocess the data, use band-pass filtering to remove environmental noise, encapsulate the vibration data according to information such as acquisition time, pipeline node number, and topological label to form a complete time-series data stream, and output it to the signal separation module.

[0023] Calculate the independent component projection directions of the turbulent component and the structural vibration component, and output the separated turbulent noise signal and structural vibration signal.

[0024] Segment the input standardized vibration data stream to ensure that each window contains sufficient time-domain information for frequency-domain analysis. Apply a Hamming window function to each time window to eliminate spectral leakage, and use a 50% window overlap rate to output a time-domain signal frame sequence with overlapping rates for smooth frame-to-frame transition.

[0025] In pipeline vibration analysis, the signal is usually composed of the superposition of the water flow turbulence component and the pipeline structure vibration component. The kurtosis statistic is introduced as a non-Gaussian weight factor in the FastICA objective function to enhance the signal separation effect.

[0026] Among them, kurtosis measures the non-Gaussianity of the signal. A high-kurtosis signal has sharp peaks, indicating fewer strong burst signals (mechanical resonance, shock vibration), and a low-kurtosis signal is close to the Gaussian distribution, indicating more random noise (turbulence noise). Introducing kurtosis can make the algorithm more inclined to separate components with higher kurtosis and suppress components close to Gaussian noise.

[0027] Taking the suppression of non-Gaussianity measure as the separation criterion, the projection directions of independent components are defined to calculate the turbulence component and the structure vibration component.

[0028] The demixing matrix is iteratively updated by the fixed-point algorithm and terminated when the change rate of the Frobenius norm of the mixing matrix between adjacent iterations is lower than the convergence threshold. The separated turbulence noise signal and structure vibration signal are output. The specific process is as follows: The formula for iteratively updating the demixing matrix by the fixed-point algorithm is:

[0029] In the formula, is the separation vector at the t-th iteration, is the objective function, which is set as and is used to measure the non-Gaussianity of the signal, is the gradient of the objective function, a is the independent variable of the function, is set as , is the transposed vector of, represents the mathematical expectation operation, is the normalization matrix of the input time-domain signal frame sequence.

[0030] Based on the separation vectors in adjacent iteration steps, the demixing matrix is constructed, and the change rate of the Frobenius norm of the demixing matrix is calculated :

[0031] In the formula, is the Frobenius norm of the demixing matrix at the t-th iteration. It is set that when is less than , the algorithm is considered to converge, the iteration is terminated, and the separated turbulence noise signal and structure vibration signal are output.

[0032] Calculate the autocorrelation peak decay rate of the structural vibration components (calculated by the decay amount of the window length of the original peak after component extraction). If the amplitude decay rates of the main peak and the secondary peak reach below the set minimum decay rate thresholds (specifically set according to the peak ratio of the decomposed components, with the default main peak decay rate threshold being 50% and the secondary peak decay rate threshold being 70%), it is determined as an effective modal signal.

[0033] Recombine the verified structural vibration signals according to the time-domain frame sequence to restore the continuous time-series signals, attach the separation confidence tags, and then output them to the modal energy analysis module, discarding the invalid separation data that does not meet the standards. The calculation method of the separation confidence tag is the complement of the mean value of the autocorrelation peak decay rate of the vibration components.

[0034] Extract the amplitude spectrum energy of the vibration modes, calculate the percentage of the energy in each direction in the total energy, construct the energy coupling ratio matrix, and mark the response offset modes.

[0035] Perform frequency-domain decomposition on the input structural vibration signals. By performing a fast Fourier transform (FFT) on the signals, extract the frequency-domain components of the signals, and then construct the frequency-domain subspace. In the frequency-domain subspace, decompose according to three different vibration directions: axial, circumferential, and radial, and extract the amplitude spectrum of each mode respectively. The amplitude spectrum represents the vibration intensity in different frequency ranges. By calculating the energy density of these modes, obtain the energy distribution of the vibration signal in each direction, plot the frequency-domain energy spectrum of each modal direction as an energy density distribution curve, and provide the energy distribution in each direction in different frequency bands.

[0036] Integrate the axial, circumferential, and radial modal energies within the set frequency band respectively. The frequency bands in each direction are dynamically set according to the pipeline material and geometric parameters. Specifically, the measured natural frequencies in each direction through the tapping experiment ±15% are used as the frequency band boundaries to ensure that more than 95% of the effective modal energy is covered. Calculate the percentage of the energy in each direction in the total energy, and generate a three-degree-of-freedom energy ratio vector (that is, combine the energy ratios of the axial, circumferential, and radial directions into a three-dimensional vector).

[0037] According to the pipeline layout and sensor positions, use the topological index table to define the relative position relationship between the sensors. Each sensor is associated with information such as the geographical location and node number through its number. Perform feature fusion on the energy ratio vectors of adjacent nodes to construct a three-dimensional matrix R containing the axial-circumferential, circumferential-radial, and axial-radial energy coupling ratios, specifically: , where, , , are the axial, circumferential, and radial modal energies respectively, and the matrix element , , Axial - circumferential, circumferential - radial, and axial - radial coupling ratios respectively.

[0038] Based on the sliding time window, the mean and variance of the historical energy ratio of each node are statistically calculated. If the current coupling ratio deviates from the mean by more than the set dynamic threshold (dynamically set based on pipeline materials and geometric parameters, default set to 30% to monitor sudden changes in the energy coupling ratio), if the sudden change in the energy coupling ratio in a certain area exceeds 30%, it may be that the local bending of the pipeline or the stable deterioration of the pipe lining marks the modal response shift and records the shift direction.

[0039] Encode the modal response shift mark and the corresponding energy coupling ratio matrix into a structured data stream, and output it to the stability decay evaluation module after attaching the time stamp and topological label.

[0040] Apply a variable - direction mechanical excitation wave at the pipeline node marked by the modal response shift to calculate the transfer function matrix, compare it with the preset initial reference matrix point by point in frequency, and extract the phase - difference data to quantify the stiffness loss.

[0041] Apply mechanical excitation waves in the shift direction at the pipeline nodes corresponding to the modal shift marks. These excitation waves cover different frequency points of the pipeline to simulate the different load effects of the external environment on the pipeline. Synchronously record the vibration velocity and excitation force data corresponding to each frequency point, calculate the complex ratio of the vibration velocity and excitation force through Fourier transform to form a transfer function matrix, where the rows of the transfer function matrix correspond to frequency points, and the three columns respectively store the complex values of the axial, circumferential, and radial directions.

[0042] Calculate the current transfer function matrix, compare it with the preset initial reference matrix point by point in frequency, extract the phase - lag amount of the transfer function, and generate a curve of the phase difference varying with frequency. Among them, in the initial stage of pipeline operation (when the pipeline is in a non - damaged state), repeat the above - mentioned frequency - sweep experiment to obtain the reference data of the complex ratio of the vibration velocity and excitation force, construct the initial transfer function matrix by taking the mean value after repeated measurements, and store the axial phase reference curve for the reference data.

[0043] Through the preset stiffness - phase mapping model, calculate the loss percentage of the current axial stiffness relative to the initial reference. Among them, according to the theory of elastic wave propagation in the pipeline in the stiffness - phase mapping model, the physical relationship between the phase difference and the axial stiffness is that the phase difference is inversely proportional to the square root of the frequency and directly proportional to the stiffness loss amount. Integrate the phase - difference curve in the set frequency band (consistent with the set frequency bands in each direction in the modal shift annotation module) and deduce the stiffness loss amount. The specific expression is:

[0044] In the formula, is the stiffness loss amount, 、 They are the measured actual phase and the reference phase at frequency f respectively, and f1 and f2 are the upper and lower limits of the set frequency band range respectively.

[0045] Unify and normalize the response deterioration degrees corresponding to different stiffness loss amounts, and finally output the standardized equivalent lining stability attenuation rate between 0 and 1. Send the deterioration mode offset pipeline node whose lining stability attenuation rate exceeds the set threshold to the synchronous correlation module through the threshold comparison method.

[0046] Map the energy coupling ratio matrix and the lining stability attenuation to graph node features, analyze the time series evolution of modal parameters, capture synchronous events and mark synchronous correlation nodes.

[0047] Construct a node feature vector based on the transfer function of the energy coupling ratio matrix and the lining stability attenuation rate. Set the feature dimensions to include the axial - circumferential coupling ratio, circumferential - radial coupling ratio, axial - radial coupling ratio and the corresponding lining stability attenuation rate values. Define the edge connection relationship according to the sensor topology index table of the acquisition module, and initialize the edge weight as the reciprocal of the Euclidean distance between nodes.

[0048] Calculate the sliding window covariance of the node energy coupling ratio vectors at consecutive moments, use the Pearson correlation coefficient to measure the vibration propagation path strength between nodes, superimpose a time - dimension sliding window on the constructed dynamic adjacency matrix, extract spatial features using a spectral graph convolution kernel, and calculate the node state change rate.

[0049] Combine a gated recurrent unit to process time - series data and extract the time - series evolution trend of modal energy.

[0050] Calculate the cosine similarity of the change in modal energy ratio between adjacent nodes within a set time window. If the average similarity of consecutive set numbers of windows exceeds a preset threshold (specifically set according to the modal energy size, default set to 85%), it is determined as a synchronous event and mark the synchronous correlation nodes.

[0051] Encode the synchronous correlation node cluster and its topological connection relationship into a region number list, and after attaching a confidence score (the confidence score is obtained from the comprehensive operation of the adjacent window similarity and the initialized edge weight), transmit it to the lining deterioration traceability module.

[0052] Construct a traceability tree - like structure including the main path and alternative branches, and convert the verified traceability path tree into a decision result with geographical coordinate annotations.

[0053] For the synchronous correlation node cluster dataset and the surrounding rock strain history data received by the lining deterioration traceability module, use the linear interpolation method to align the time of data with different sampling rates to ensure that all data points are arranged in a unified time series to form a complete time - series dataset.

[0054] Based on the adjacency matrix structure of the pipeline topology diagram, initially assign a uniformly distributed prior probability of the initial pipe lining deterioration source to all nodes. If there are historical fault records, adjust the initial weights according to the node fault frequencies.

[0055] Adopt the backpropagation confidence weighted algorithm for iterative optimization. Each iteration includes two processes: forward propagation and backward correction. In the forward propagation stage, along the direction of the medium flow, evaluate the physical attenuation effect of the deformation propagation according to the pipe segment length, support point density, and material attenuation coefficient, and update the confidence of the downstream nodes probabilistically. The value range of the attenuation coefficient is default set to 0.8 to 0.95, and the specific value is dynamically set according to the non-destructive testing report of the pipe lining.

[0056] In the backward correction stage, combine the current modal energy ratio outliers, convert the measurement data into likelihood probabilities through the Bayesian formula, model the measurement error using the Gamma distribution, and perform reverse probability correction on the confidence of the upstream nodes.

[0057] Introduce a time decay factor during the iterative process, assign an exponential weight to the historical confidence data, and ensure the dominant role of the new measurement data in the probability distribution. After 3 to 5 iterations, output the posterior probability distribution of the pipe lining deterioration source at each node, forming a probability density field presented in the form of a heat map.

[0058] In the probability distribution heat map, select the node with the maximum posterior probability as the starting point of the main tracing path, adopt the dynamic programming method to search for the maximum probability propagation path, and construct a tree-like structure including the main path and alternative branches.

[0059] Conduct information entropy analysis on the generated tree-like path, calculate the Shannon entropy values of the main path and each branch path to quantify the path uncertainty. The entropy value of the main path is obtained by accumulating the logarithmic weighted sum of the confidence of the path nodes, and the average entropy value of the branches is the arithmetic mean of the entropy values of all branch paths.

[0060] At the same time, extract the confidence sequence of the main path nodes, calculate the change rate of the confidence gradient between adjacent nodes, and analyze whether its fluctuation range meets the preset smoothness threshold. The convergence verification needs to simultaneously meet that the entropy value of the main path is lower than 80% of the average entropy value of the branches, and the fluctuation amplitude of the confidence gradient does not exceed plus or minus 15%.

[0061] If the verification fails, automatically trigger a new round of iterative calculation until the convergence condition is met or the maximum number of iterations is reached. Through the dual constraint mechanism of entropy value and gradient, ensure the physical rationality and statistical significance of the tracing path.

[0062] Convert the verified tracing path tree into a decision result with geographical coordinate annotations, trigger an early warning signal and push it to the visualization interface of the operation and maintenance platform.

[0063] After the water supply network operation and maintenance platform receives a warning signal, based on the decision result, the source node is marked in red on the visualization interface, the main path continuously runs through the associated nodes with a solid line, and the alternative branch paths are marked with a dashed line to indicate the secondary impact area.

[0064] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

[0065] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using 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 processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0066] Those of ordinary skill in the art can realize that the modules and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0067] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices, and modules described above can refer to the corresponding processes in the foregoing method embodiments and will not be repeated here.

[0068] In several embodiments provided by this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or modules can be in electrical, mechanical, or other forms.

[0069] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules. They can be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0070] In addition, in each embodiment of this application, the functional modules can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0071] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of this application. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs and other various media that can store program codes.

[0072] As described above, this is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0073] Finally, the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A pipe lining stability analysis and health monitoring system for urban water supply networks, characterized in that: It includes data acquisition module, signal separation module, modal offset annotation module, stability attenuation assessment module, synchronous correlation module and pipe lining degradation traceability module: The data acquisition module collects the original waveform data of the three-axis vibration including the time stamp, and outputs the data to the signal separation module after adding the time stamp and the topological label; The signal separation module calculates the independent component projection directions of the turbulence component and the structural vibration component, and outputs the separated turbulence noise signal and structural vibration signal; The modal offset annotation module extracts the amplitude spectrum energy of the vibration mode, calculates the percentage of energy in each direction to the total energy, constructs the energy coupling ratio matrix and marks the response offset mode; The stability attenuation assessment module applies a variable-direction mechanical excitation wave to the modal offset marked pipeline node to calculate the transfer function matrix, compares it with the preset initial reference matrix frequency point by frequency point, and extracts phase difference data to quantify the stability attenuation of the pipe lining; The synchronous correlation module maps the energy coupling ratio matrix and the lining stability attenuation into graph node features, analyzes the temporal evolution of modal parameters, captures synchronous events and marks synchronous correlation nodes; The pipe lining degradation traceability module constructs a traceability tree structure consisting of a main path and alternative branches, and converts the verified traceability path tree into a decision result with geographic coordinate annotations.

2. According to claim 1, a pipe lining stability analysis and health monitoring system for urban water supply network is characterized in that: Collect the original triaxial vibration waveform data including timestamps, add timestamps and topological labels to the data and output them to the signal separation module, which specifically includes: A triaxial low-frequency acceleration sensor is installed at a preset interval along the inner wall of the pipe of the water supply network to collect triaxial vibration raw waveform data including time stamps; At the same time, the surrounding rock strain data is collected at the same collection frequency as the original vibration waveform data; According to the latitude and longitude coordinates of the sensor installation location and the pipeline node number, a spatial location-sensor identification mapping relationship table is established, and a standardized vibration data stream with topological labels is output; The calibrated three-axis vibration data are encoded into double-precision floating point format according to the axial, circumferential and radial components, and then output to the signal separation module after adding timestamps and topological labels.

3. The pipe lining stability analysis and health monitoring system for urban water supply network according to claim 2 is characterized in that: Calculate the independent component projection direction of the turbulence component and the structural vibration component, and output the separated turbulence noise signal and structural vibration signal, specifically including: The input standardized vibration data stream is divided into time windows, the spectral leakage is eliminated by using the Hamming window function, and a time domain signal frame sequence with overlapping rate is output; The kurtosis statistic is introduced as a weight factor in the FastICA objective function, and the non-Gaussianity measure is used as a separation criterion to calculate the independent component projection directions of the turbulence component and the structural vibration component. The unmixing matrix is ​​iteratively updated through a fixed point algorithm, and the algorithm is terminated when the rate of change of the Frobenius norm of the mixing matrix of adjacent iterations is lower than the convergence threshold, and the separated turbulence noise signal and structural vibration signal are output; Calculate the autocorrelation peak attenuation rate of the structural vibration component. If the attenuation rate of the main peak and the secondary peak amplitude reaches below the set minimum attenuation rate threshold, it is determined to be a valid modal signal. The structural vibration components of the effective modal signal are reorganized according to the time domain frame sequence, attached with separation confidence labels and output to the modal shift annotation module, and the invalid separation data that does not meet the standards is discarded.

4. The pipe lining stability analysis and health monitoring system for urban water supply network according to claim 3 is characterized in that: Extract the amplitude spectrum energy of the vibration mode and calculate the percentage of energy in each direction to the total energy, construct the energy coupling ratio matrix and mark the response offset mode. Specifically include: The input structural vibration signal is decomposed in the frequency domain, and the amplitude spectrum energy of the axial, circumferential and radial vibration modes is extracted using the frequency domain subspace method, and the modal energy density distribution curves in each direction are output; Integrate the axial, circumferential and radial modal energies within the set frequency band, calculate the percentage of energy in each direction to the total energy, and generate the three-degree-of-freedom energy proportion vector; Based on the sensor topology index table of the acquisition module, the energy share vectors of adjacent nodes are feature fused to construct a three-dimensional matrix containing axial-annular, annular-radial, and axial-radial energy coupling ratios; The mean and variance of the historical energy ratio of each node are counted based on the sliding time window. If the current coupling ratio deviates from the mean by more than the set dynamic threshold, the mode shift is marked and the shift direction is recorded. The modal shift markers and the corresponding energy coupling ratio matrix are encoded into a structured data stream, which is then output to the stability decay assessment module after being attached with timestamps and topological labels.

5. The pipe lining stability analysis and health monitoring system for urban water supply network according to claim 4 is characterized in that: Apply variable directional mechanical excitation waves to the modal offset marked pipeline nodes to calculate the transfer function matrix, compare it with the preset initial reference matrix frequency point by frequency point, and extract phase difference data to quantify the attenuation of the pipe lining stability. Specifically include: Apply a variable-direction mechanical excitation wave at the pipeline node corresponding to the modal shift mark, synchronously record the vibration velocity and excitation force data corresponding to each frequency point, calculate the complex ratio of the vibration velocity and the excitation force through Fourier transform, and form a transfer function matrix; Calculate the current transfer function matrix and compare it with the preset initial reference matrix at each frequency point, extract the phase lag of the transfer function, and generate a curve of phase difference changing with frequency; Based on the elastic wave propagation theory, a stiffness-phase mapping model is established to show the physical relationship between the propagation phase difference and the axial stiffness. The stiffness loss of the current axial stiffness relative to the initial reference is quantified according to the phase difference. The quantified value of stiffness loss is converted into the attenuation expression of stability response degradation of the pipe lining structure under frequency domain excitation, and the equivalent pipe lining stability attenuation rate is generated; The modal offset pipeline nodes whose equivalent pipe lining stability decay rate is greater than or equal to the set equivalent pipe lining stability decay rate threshold are sent to the synchronous association module.

6. The pipe lining stability analysis and health monitoring system for urban water supply network according to claim 5, characterized in that: The energy coupling ratio matrix and the lining stability attenuation are mapped into graph node features, the temporal evolution of modal parameters is analyzed, synchronous events are captured, and synchronous associated nodes are marked, including: The energy coupling ratio matrix and the transfer function matrix are mapped into graph node features, and the edge connection relationship is defined and the edge weight is initialized based on the sensor topology index table; The edge weights are dynamically adjusted according to the temporal covariance of the energy coupling ratio between nodes, and the sliding window Pearson correlation coefficient is used to quantify the intensity of the vibration propagation path to generate a dynamic adjacency matrix. A sliding window of time dimension is superimposed on the dynamic adjacency matrix, and the spectral convolution kernel is applied to extract spatial features, and the gated recurrent unit is combined to capture the temporal evolution law of modal parameters; Calculate the cosine similarity of the modal energy ratio changes of adjacent nodes within a set time window. If the mean similarity of a set number of consecutive windows exceeds a preset threshold, it is determined to be a synchronization event and the synchronization-related nodes are marked. The synchronously associated node clusters and their topological connection relationships are encoded as a list of area numbers and transmitted to the pipe lining degradation traceability module after adding confidence scores.

7. A pipe lining stability analysis and health monitoring system for urban water supply pipe networks according to claim 6, characterized in that: Construct a traceability tree structure containing the main path and alternative branches, and convert the verified traceability path tree into a decision result with geographic coordinates. Specifically, it includes: Align the synchronous associated node cluster with the surrounding rock strain history data according to the acquisition timestamp; Based on the back-propagation confidence weighted algorithm, the posterior probability of each node as the source of pipe lining degradation is iteratively calculated on the pipeline topology map, and the probability distribution heat map of the pipe lining degradation source is output; According to the probability distribution heat map of the pipe lining degradation source, the maximum probability propagation path is searched, and a tree structure including the main path and alternative branches is constructed; Calculate the tree path branch entropy value. If the main path entropy value is lower than the branch average entropy value and the confidence gradient descent rate meets the preset smoothness micro interval, the path convergence is determined to be effective. The verified traceability path tree is converted into a decision result with geographic coordinate annotations, triggering an early warning signal and pushing it to the visual interface of the operation and maintenance platform.

8. The pipe lining stability analysis and health monitoring system for urban water supply network according to claim 7, characterized in that: The triggering of the early warning signal and pushing it to the visual interface of the operation and maintenance platform specifically includes: After receiving the early warning signal, the water supply network operation and maintenance platform marks the source node in red in the visualization interface based on the decision results. The main path uses a solid line to continuously run through the related nodes, and the alternative branch path uses a dotted line to mark the secondary impact area.

Images