Pipeline monitoring system and pipeline monitoring methods

Abstract

This application discloses a pipeline monitoring system and method, relating to the field of water conservancy engineering technology. The system includes: data acquisition devices installed on the inner wall concrete protective layer of a prestressed steel cylinder pipeline to collect pipeline data; a hybrid transmission network obtained by combining LoRa and NB-IoT technologies based on regional signal transmission characteristics; and the transmission of multi-dimensional monitoring parameters to a cloud analysis platform for pipeline health assessment. This application overcomes the bottleneck of underground scene data acquisition by using multi-parameter coupled sensing of the data acquisition device and piezoelectric energy acquisition technology, acquiring rich multi-dimensional data; reliable data transmission in complex underground environments is achieved based on dynamically switched clustered wireless networks; and the cloud analysis platform, based on multi-dimensional monitoring parameters and integrating a multi-modal analysis engine, provides a full life-cycle health status profile for the pipeline, improving the accuracy of pipeline monitoring.

Description

Technical Field

[0001] This application relates to the field of water conservancy engineering technology, and in particular to a pipeline monitoring system and pipeline monitoring method. Background Technology

[0002] Prestressed concrete cylinder pipes (PCCPs), as a core material for long-distance water conveyance projects since the mid-20th century, are widely used globally in major infrastructure projects such as urban water supply, inter-basin water transfer, nuclear power plant cooling water systems, and agricultural irrigation due to their high pressure resistance, durability, and economy. However, with increasing service life, the risk of structural failure due to material aging, environmental corrosion, and abnormal loads is becoming increasingly prominent for PCCPs. Typical defects include hydrogen embrittlement fracture of prestressed steel wires (especially in sulfur-containing soils or areas with stray current interference), carbonization and spalling of the concrete protective layer, and electrochemical corrosion perforation of the steel cylinder. These damages are characterized by their high degree of concealment and non-linear development; once a pipe rupture accident occurs, it will lead to a leakage of thousands of cubic meters per hour, causing a chain reaction of disasters such as urban water outages, road collapses, and ecological pollution.

[0003] However, existing monitoring systems rely on point sensors such as vibration optical fibers and strain gauges, which can only acquire a single physical quantity and cannot capture the coupling effect of stress redistribution and corrosion leakage. The underground burial depth of 3-5 meters makes wired power supply difficult, while battery-powered equipment has a short lifespan and high replacement costs, resulting in low accuracy of pipeline monitoring. Summary of the Invention

[0004] The main purpose of this application is to provide a pipeline monitoring system and pipeline monitoring method, which aims to solve the technical problem of low monitoring accuracy in existing pipeline monitoring methods.

[0005] To achieve the above objectives, this application proposes a pipeline monitoring system, which includes data acquisition equipment, a hybrid transmission network, and a cloud analysis platform;

[0006] The data acquisition device is used to acquire data from the prestressed steel cylinder concrete pipe and send the obtained multi-dimensional monitoring parameters to the hybrid transmission network. The data acquisition device is installed in the inner wall concrete protective layer of the prestressed steel cylinder concrete pipe.

[0007] The hybrid transmission network is used to transmit the multi-dimensional monitoring parameters to the cloud analysis platform. The hybrid transmission network is obtained by combining LoRa technology and NB-IoT technology according to the regional signal transmission characteristics.

[0008] The cloud-based analytics platform is used to analyze the multi-dimensional monitoring parameters and obtain health assessment results.

[0009] In one embodiment, the data acquisition device includes a multi-sensor layer, an energy harvesting layer, and a protective communication layer;

[0010] The data acquisition device is also used to acquire data from the prestressed steel cylinder concrete pipe through the multi-sensor layer to obtain multi-dimensional sensing data, which includes at least one of pipe wall circumferential stress distribution, leakage humidity, vibration spectrum, and temperature.

[0011] The data acquisition device is also used to capture energy from the prestressed steel cylinder concrete pipe through the energy acquisition layer to obtain energy data;

[0012] The data acquisition device is also used to transmit the multi-dimensional sensing data and the energy data to the hybrid transmission network through the protective communication layer.

[0013] In one embodiment, the data acquisition device is further configured to shut down the multi-sensor layer and the energy acquisition layer when the vibration spectrum is detected to be continuously lower than a preset lower limit threshold within a consecutive preset time period.

[0014] The data acquisition device is also used to activate the multi-sensor layer and the energy acquisition layer at a preset frequency when the vibration spectrum is detected to be between the preset lower limit threshold and the preset upper limit threshold within a continuous preset time period.

[0015] The data acquisition device is also used to activate the multi-sensor layer and the energy acquisition layer when the vibration spectrum is detected to be greater than the preset upper limit threshold.

[0016] In one embodiment, the cloud analysis platform is further used to perform multi-dimensional feature identification on the multi-dimensional monitoring parameters, distinguish the preset fluctuation features from the actual leakage features, and obtain the leakage risk probability value.

[0017] The cloud-based analysis platform is also used to extract time series data from the multi-dimensional monitoring parameters and determine the trend of pipeline health changes based on the time series.

[0018] The cloud-based analysis platform is also used to determine the stress wave signal caused by the damage from the multi-dimensional monitoring parameters, thereby obtaining hidden damage.

[0019] The cloud-based analysis platform is also used to conduct pipeline health assessments based on the leakage risk probability value, the pipeline health change trend, and the hidden damage, and to obtain health assessment results.

[0020] In one embodiment, the cloud-based analysis platform is further configured to generate a health report based on the health assessment result when the health assessment result is greater than a preset first health threshold. The health report includes a stress distribution heatmap and a corrosion rate trend map.

[0021] The cloud-based analysis platform is also used to increase the data acquisition frequency of the data acquisition device and to mark the area of ​​the prestressed steel cylinder concrete pipe corresponding to the health assessment result when the health assessment result is less than the preset first health threshold and greater than the preset second health threshold.

[0022] The cloud-based analysis platform is also used to reduce the pressure value of the substance transmitted by the prestressed steel cylinder concrete pipe and activate the audible and visual alarm device in the maintenance area corresponding to the prestressed steel cylinder concrete pipe when the health assessment result is less than the preset second health threshold and greater than the preset third health threshold.

[0023] The cloud-based analysis platform is also used to shut down the prestressed steel cylinder concrete pipeline when the health assessment result is less than the preset third health threshold, and to generate an optimal emergency repair path based on real-time traffic conditions and preset pipeline topology, and send the optimal emergency repair path to the user terminal for pipeline emergency repair.

[0024] Furthermore, to achieve the above objectives, this application also proposes a pipeline monitoring method, which is applied to a pipeline monitoring system, the pipeline monitoring system including data acquisition equipment, a hybrid transmission network, and a cloud analysis platform; the method includes:

[0025] The data acquisition device collects data from the prestressed steel cylinder concrete pipe and sends the obtained multi-dimensional monitoring parameters to the hybrid transmission network. The data acquisition device is installed on the inner wall concrete protective layer of the prestressed steel cylinder concrete pipe.

[0026] The hybrid transmission network transmits the multi-dimensional monitoring parameters to the cloud analysis platform. The hybrid transmission network is obtained by combining LoRa technology and NB-IoT technology according to the regional signal transmission characteristics.

[0027] The cloud-based analytics platform analyzes the multi-dimensional monitoring parameters to obtain health assessment results.

[0028] In one embodiment, the data acquisition device includes a multi-sensor layer, an energy harvesting layer, and a protective communication layer;

[0029] The data acquisition device collects data from the prestressed steel cylinder concrete pipe and sends the obtained multi-dimensional monitoring parameters to the hybrid transmission network. The step of installing the data acquisition device on the inner wall concrete protective layer of the prestressed steel cylinder concrete pipe includes:

[0030] The data acquisition device collects data from the prestressed steel cylinder concrete pipe through the multi-sensor layer to obtain multi-dimensional sensing data, which includes at least one of pipe wall circumferential stress distribution, leakage humidity, vibration spectrum, and temperature.

[0031] The data acquisition device captures energy from the prestressed steel cylinder concrete pipe through the energy acquisition layer to obtain energy data;

[0032] The data acquisition device transmits the multi-dimensional sensing data and the energy data to the hybrid transmission network through the protective communication layer.

[0033] In one embodiment, before the step of the data acquisition device acquiring data from the prestressed steel cylinder concrete pipe through the multi-sensor layer to obtain multi-dimensional sensor data, the method further includes:

[0034] When the data acquisition device detects that the vibration spectrum is continuously lower than a preset lower limit threshold for a continuous preset time period, it shuts down the multi-sensor layer and the energy acquisition layer.

[0035] When the data acquisition device detects that the vibration spectrum is between the preset lower limit threshold and the preset upper limit threshold within a continuous preset time period, it activates the multi-sensor layer and the energy acquisition layer at a preset frequency.

[0036] When the data acquisition device detects that the vibration spectrum is greater than the preset upper limit threshold, it activates the multi-sensor layer and the energy acquisition layer.

[0037] In one embodiment, the step of the cloud-based analytics platform analyzing the multi-dimensional monitoring parameters to obtain health assessment results includes:

[0038] The cloud-based analysis platform performs multi-dimensional feature identification on the multi-dimensional monitoring parameters, distinguishes between preset fluctuation features and actual leakage features, and obtains leakage risk probability values.

[0039] The cloud-based analysis platform extracts time series data from the multi-dimensional monitoring parameters and determines the trend of pipeline health changes based on the time series.

[0040] The cloud-based analysis platform determines the stress wave signal caused by the damage from the multi-dimensional monitoring parameters, thereby obtaining the hidden damage.

[0041] The cloud-based analysis platform performs a pipeline health assessment based on the leakage risk probability value, the pipeline health change trend, and the hidden damage, and obtains the health assessment results.

[0042] In one embodiment, after the cloud-based analysis platform performs a pipeline health assessment based on the leakage risk probability value, the pipeline health change trend, and the hidden damage, and obtains the health assessment results, the platform further includes:

[0043] When the health assessment result is greater than a preset first health threshold, the cloud analysis platform generates a health report based on the health assessment result. The health report includes a stress distribution heat map and a corrosion rate trend map.

[0044] When the health assessment result is less than the preset first health threshold and greater than the preset second health threshold, the cloud analysis platform increases the data acquisition frequency of the data acquisition device and marks the area of ​​the prestressed steel cylinder concrete pipe corresponding to the health assessment result.

[0045] When the health assessment result is less than the preset second health threshold and greater than the preset third health threshold, the cloud analysis platform reduces the pressure value of the material transmitted by the prestressed steel cylinder concrete pipe and activates the audible and visual alarm device in the maintenance area corresponding to the prestressed steel cylinder concrete pipe.

[0046] When the health assessment result is less than the preset third health threshold, the cloud analysis platform shuts down the prestressed steel cylinder concrete pipeline, generates an optimal emergency repair path based on real-time traffic conditions and preset pipeline topology, and sends the optimal emergency repair path to the user terminal for pipeline emergency repair.

[0047] This application provides a pipeline monitoring system that collects data from the pipeline using data acquisition devices installed in the inner concrete protective layer of a prestressed steel cylinder pipeline. A hybrid transmission network is obtained by combining LoRa and NB-IoT technologies based on regional signal transmission characteristics, transmitting multi-dimensional monitoring parameters to a cloud analysis platform. The data is then analyzed to obtain pipeline health assessment results. This application overcomes the bottleneck of underground scene data acquisition by using multi-parameter coupled sensing of the data acquisition device and piezoelectric energy acquisition technology, acquiring rich multi-dimensional data. A clustered wireless network based on dynamic switching between LoRa and NB-IoT enables reliable data transmission in complex underground environments. The cloud analysis platform, based on multi-dimensional monitoring parameters and integrating a multi-modal analysis engine, provides a full life-cycle health status profile of the pipeline, improving the accuracy of pipeline monitoring. Attached Figure Description

[0048] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0049] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a schematic diagram of the architecture of the pipeline monitoring system provided in Embodiment 1 of this application;

[0051] Figure 2 This is a schematic diagram of the data acquisition equipment architecture in Embodiment 2 of the pipeline monitoring system of this application;

[0052] Figure 3 This is a schematic flowchart of an embodiment of the pipeline monitoring method of this application;

[0053] Figure 4 This is a schematic diagram of the process provided in Embodiment 2 of the pipeline monitoring method of this application.

[0054] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0055] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0056] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0057] The main solution of this application embodiment is as follows: the pipeline monitoring system includes a data acquisition device, a hybrid transmission network, and a cloud analysis platform; the data acquisition device is used to acquire data from the prestressed steel cylinder concrete pipeline and send the obtained multi-dimensional monitoring parameters to the hybrid transmission network, and the data acquisition device is installed in the inner wall concrete protective layer of the prestressed steel cylinder concrete pipeline; the hybrid transmission network is used to transmit the multi-dimensional monitoring parameters to the cloud analysis platform, and the hybrid transmission network is obtained by combining LoRa technology and NB-IoT technology according to the regional signal transmission characteristics; the cloud analysis platform is used to analyze the multi-dimensional monitoring parameters to obtain health assessment results.

[0058] However, existing monitoring systems rely on point sensors such as vibration optical fibers and strain gauges, which can only acquire a single physical quantity and cannot capture the coupling effect of stress redistribution and corrosion leakage. The underground burial depth of 3-5 meters makes wired power supply difficult, while battery-powered equipment has a short lifespan and high replacement costs, resulting in low accuracy of pipeline monitoring.

[0059] This application provides a solution that collects data from a prestressed steel cylinder concrete pipeline by installing a data acquisition device on the inner wall concrete protective layer. Based on the regional signal transmission characteristics, LoRa and NB-IoT technologies are combined to obtain a hybrid transmission network, transmitting multi-dimensional monitoring parameters to a cloud analysis platform. The data is then analyzed to obtain pipeline health assessment results. By leveraging multi-parameter coupled sensing of the data acquisition device and combining it with piezoelectric energy acquisition technology to overcome the bottleneck of underground scene data collection, rich multi-dimensional data is acquired. A clustered wireless network based on dynamic switching between LoRa and NB-IoT enables reliable data transmission in complex underground environments. The cloud analysis platform, based on multi-dimensional monitoring parameters and integrating a multi-modal analysis engine, provides a full lifecycle health status profile for the pipeline, improving the accuracy of pipeline monitoring.

[0060] It should be noted that the implementing entity in this embodiment can be a pipeline monitoring system, including data acquisition equipment, a hybrid transmission network, and a cloud analysis platform.

[0061] Based on this, the embodiments of this application provide a pipeline monitoring system, referring to... Figure 1 , Figure 1 This is a schematic diagram of the architecture of the first embodiment of the pipeline monitoring system of this application.

[0062] In this embodiment, the pipeline monitoring system includes data acquisition equipment, a hybrid transmission network, and a cloud analysis platform;

[0063] The data acquisition device is used to acquire data from the prestressed steel cylinder concrete pipe and send the obtained multi-dimensional monitoring parameters to the hybrid transmission network. The data acquisition device is installed in the inner wall concrete protective layer of the prestressed steel cylinder concrete pipe.

[0064] It should be noted that this system adopts a three-layer distributed architecture of "perception layer - transmission layer - decision layer," forming a closed-loop management system for the entire process from data acquisition and transmission to intelligent analysis. Its core design concept lies in "edge perception - collaborative computing - dynamic optimization." The data acquisition device of the perception layer can be composed of an array of intelligent monitoring chips embedded in the concrete protective layer of the PCCP inner wall. The array of chips can be configured according to actual conditions. For example, each chip can cover a 1.5m pipe section, with adjacent chips spaced ≤0.5m apart, forming a high-density monitoring network with a spatial resolution of 0.3m². The combination of the chips and the concrete protective layer of the PCCP inner wall ensures the synchronization of strain between the chips and the pipe body while avoiding stress concentration. The embedded intelligent monitoring chip adopts a four-layer flexible PCB stacked architecture, achieving a high degree of integration of sensing, power supply, and protection functions through modular design, adapting to the curved structure and harsh working conditions of the PCCP pipe inner wall. Data is collected from the PCCP pipe through this data acquisition device, and the obtained multi-dimensional monitoring parameters are sent to the hybrid transmission network for transmission.

[0065] The hybrid transmission network is used to transmit the multi-dimensional monitoring parameters to the cloud analysis platform. The hybrid transmission network is obtained by combining LoRa technology and NB-IoT technology according to the regional signal transmission characteristics.

[0066] Understandably, the hybrid transmission network at the transport layer is a clustered wireless network based on dynamic switching between LoRa and NB-IoT, enabling reliable data transmission in complex underground environments. Chip communication employs a hybrid networking strategy. Both LoRa and NB-IoT are low-power wide-area network (LPWAN) technologies, but LoRa offers advantages such as strong penetration, long-distance transmission, and strong anti-interference capabilities, while NB-IoT boasts wide-area coverage, high-speed transmission, large connection capacity, and strong compatibility. In the communication protocol design, NB-IoT and LoRa hybrid networking are dynamically switched for different scenarios, including urban areas, suburbs, and underground environments. Based on the advantages of each technology, NB-IoT is prioritized in open suburban areas or densely populated areas, relying on operator base stations to achieve high-frequency, low-latency data backhaul and wide-area coverage. In urban areas with severe signal obstruction, such as underground utility tunnels or remote locations, LoRa is switched to, using forward error correction and frequency hopping technologies to resist multipath interference and ensure a packet loss rate of <2%.

[0067] It should be noted that a clustered data aggregation approach can also be used for multi-dimensional monitoring parameters. Each cluster consists of 10 monitoring chips, and nodes within the cluster upload data to the edge gateway via the TDMA protocol. The gateway uses an improved LZ4 algorithm to compress the data and employs a CRC-16 cyclic redundancy check algorithm and selective retransmission mechanism to control the packet loss rate to <2%. Furthermore, in the data preprocessing stage, the edge gateway uses an improved CEEMDAN algorithm to perform noise mode decomposition on the acceleration signal, separating environmental noise such as subway vibration and electromagnetic interference, and suppressing temperature drift errors from stress sensors. It also integrates time-domain statistics (stress mean, variance, kurtosis) and spatial correlation features (humidity gradient, stress difference) to extract regional features, reducing data transmission volume while improving model convergence speed and classification accuracy, providing a high signal-to-noise ratio input for intelligent early warning.

[0068] The cloud-based analytics platform is used to analyze the multi-dimensional monitoring parameters and obtain health assessment results.

[0069] Understandably, the decision-making layer is a cloud-based analytics platform deployed in the cloud, consisting of a machine learning engine and a visualization terminal. The machine learning engine, based on data transmitted from the chip, integrates a multimodal analysis engine to analyze multi-dimensional monitoring parameters, while the visualization terminal displays the health assessment results. By utilizing random forests and digital twin models, it achieves a leap from "single-point alarm" to "system-level risk projection," providing a full lifecycle health profile for the PCCP pipeline.

[0070] In this embodiment, the cloud analysis platform is also used to perform multi-dimensional feature recognition on the multi-dimensional monitoring parameters, distinguish the preset fluctuation features from the actual leakage features, and obtain the leakage risk probability value.

[0071] It should be noted that a large amount of historical fault data covering typical events such as wire breakage, leakage, and corrosion was collected in advance, and intelligent analysis was performed using a multi-algorithm fusion engine. The random forest classifier, through the construction of multiple decision trees and parallel voting, performs feature recognition on 128-dimensional features such as stress mutation rate, humidity spatial gradient, and vibration frequency domain energy, accurately distinguishing the periodic pressure oscillations caused by water hammer effect from the continuous negative pressure fluctuations of actual leakage, and outputting the leakage risk probability.

[0072] The cloud-based analysis platform is also used to extract time series data from the multi-dimensional monitoring parameters and determine the trend of pipeline health changes based on the time series.

[0073] Understandably, the Long Short-Term Memory Time Series Prediction Model (LSTM) is based on a recurrent neural network architecture and dynamically adjusts the temporal correlation of pipeline health monitoring data through a triple gating mechanism of forget gate, input gate, and output gate. The model constructs a multidimensional time series by extracting historical sensor data using a sliding window. After standardization and outlier removal preprocessing in the input layer, the hidden layer LSTM units extract nonlinear features within the time step and suppress overfitting. During the training phase, the Adam optimizer minimizes the mean square error, dynamically controlling the number of iterations, and finally outputs continuous predictions of the Pipeline Health Index (PHI) for a preset future time period (e.g., 30 minutes), forming a trend of pipeline health changes. By capturing the decay gradient and abrupt inflection points of the PHI sequence, this model can identify latent risks such as the propagation of microcracks in prestressed steel wires and the accumulation of fatigue damage in concrete in advance.

[0074] The cloud-based analysis platform is also used to determine the stress wave signal caused by the damage from the multi-dimensional monitoring parameters, thereby obtaining hidden damage.

[0075] It should be understood that the damage location engine employs a time-of-flight (TOF) method, using a distributed sensor array to capture stress wave signals triggered by damage for precise location. When a pipeline ruptures or leaks, the stress wave released instantaneously within the structure propagates along the pipe wall as a longitudinal wave. MEMS sensors deployed at key nodes of the pipe simultaneously record the arrival time of the wavefront, calculating the time difference Δt between adjacent sensors based on wave velocity calibration values. Using a hyperbolic intersection algorithm, the spatial coordinates of the stress wave source are analyzed using a set of time-of-flight equations composed of three or more sensors, achieving a location accuracy within 1% of the pipe section length. This method overcomes the limitations of traditional single-point monitoring, inverting the damage location through wavefield propagation characteristics and simultaneously using frequency domain coherence analysis to suppress environmental vibration noise, enabling non-contact dynamic tracking of hidden underground damage.

[0076] The cloud-based analysis platform is also used to conduct pipeline health assessments based on the leakage risk probability value, the pipeline health change trend, and the hidden damage, and to obtain health assessment results.

[0077] In this embodiment, the cloud analysis platform is also used to generate a health report based on the health assessment result when the health assessment result is greater than a preset first health threshold. The health report includes a stress distribution heat map and a corrosion rate trend map.

[0078] It is worth noting that this embodiment constructs a complete early warning chain from data to decision through a two-stage collaboration of "machine learning modeling - dynamic response control," and establishes a four-level early warning mechanism in the dynamic response control stage. When the PHI value is greater than the preset first health threshold (for example, above 0.8 in the normal level), the system automatically archives the data and generates a health report based on the health assessment results, including a stress distribution heatmap and corrosion rate trend.

[0079] The cloud-based analysis platform is also used to increase the data acquisition frequency of the data acquisition device and to mark the area of ​​the prestressed steel cylinder concrete pipe corresponding to the health assessment result when the health assessment result is less than the preset first health threshold and greater than the preset second health threshold.

[0080] It is understandable that when the health assessment result is less than a preset first health threshold and greater than a preset second health threshold (for example, when the PHI drops to a concern level of 0.6 to 0.8), the data acquisition frequency of the data acquisition device is increased, high-frequency data acquisition is immediately started, and customized inspection instructions are pushed to the mobile terminal. At the same time, a yellow warning area is marked on the GIS platform.

[0081] The cloud-based analysis platform is also used to reduce the pressure value of the substance transmitted by the prestressed steel cylinder concrete pipe and activate the audible and visual alarm device in the maintenance area corresponding to the prestressed steel cylinder concrete pipe when the health assessment result is less than the preset second health threshold and greater than the preset third health threshold.

[0082] It should be understood that when the health assessment result is less than the preset second health threshold and greater than the preset third health threshold (for example, when PHI enters the warning level of 0.4 to 0.6), the audible and visual alarm device in the underground maintenance well is activated, and the Supervisory Control and Data Acquisition (SCADA) system is depressurized in conjunction with the system.

[0083] The cloud-based analysis platform is also used to shut down the prestressed steel cylinder concrete pipeline when the health assessment result is less than the preset third health threshold, and to generate an optimal emergency repair path based on real-time traffic conditions and preset pipeline topology, and send the optimal emergency repair path to the user terminal for pipeline emergency repair.

[0084] Understandably, when the health assessment result is less than the preset third health threshold (for example, when PHI falls below the 0.4 emergency threshold), the system will close the upstream and downstream electric valves of the damaged pipeline section within 30 seconds, generate the optimal repair route by combining real-time traffic conditions and pipeline topology, and push a complete plan including the excavation scope, spare parts list and safety plan to the emergency command center.

[0085] It is worth noting that, in order to improve adaptability, the system uses a 7-day sliding window to dynamically calculate the PHI mean μ and standard deviation σ, sets the threshold for normal level to μ+1.5σ and the threshold for emergency level to μ-2σ, and introduces temperature and humidity as covariates for seasonal correction. When the false alarm rate exceeds 5% for 30 consecutive days, the incremental learning algorithm is automatically triggered to update the model parameters, ultimately forming a closed-loop decision chain from feature analysis, simulation verification, graded response to dynamic optimization, thereby upgrading the cross-scale risk management capabilities.

[0086] In this embodiment, data is collected from the pipeline using a data acquisition device installed in the inner concrete protective layer of the prestressed steel cylinder pipeline. A hybrid transmission network is obtained by combining LoRa and NB-IoT technologies based on the regional signal transmission characteristics, transmitting multi-dimensional monitoring parameters to the cloud analysis platform. The data is then analyzed to obtain the pipeline's health assessment results. This embodiment overcomes the bottleneck of underground scene data acquisition by using multi-parameter coupled sensing of the data acquisition device and piezoelectric energy acquisition technology, collecting rich multi-dimensional data. A clustered wireless network based on dynamic switching between LoRa and NB-IoT enables reliable data transmission in complex underground environments. The cloud analysis platform, based on multi-dimensional monitoring parameters and integrating a multi-modal analysis engine, provides a full lifecycle health status profile for the pipeline, improving the accuracy of pipeline monitoring.

[0087] Based on the first embodiment of the above system, a second embodiment of the pipeline monitoring system of this application is proposed, with reference to... Figure 2 , Figure 2 This is a schematic diagram of the architecture of the data acquisition equipment in Embodiment 2 of the pipeline monitoring system of this application.

[0088] In this embodiment, the data acquisition device includes a multi-sensor layer, an energy harvesting layer, and a protective communication layer;

[0089] Understandably, the embedded intelligent monitoring chip adopts a four-layer flexible PCB stacked architecture, achieving a high degree of integration of sensing, power supply, and protection functions through modular design, adapting to the curved structure and harsh operating conditions of the PCCP pipeline inner wall. The structural design is divided into three layers: a multi-sensor layer, an energy harvesting layer, and a protection and communication layer.

[0090] The data acquisition device is also used to acquire data from the prestressed steel cylinder concrete pipe through the multi-sensor layer to obtain multi-dimensional sensing data, which includes at least one of pipe wall circumferential stress distribution, leakage humidity, vibration spectrum, and temperature.

[0091] It should be understood that the top layer of the chip is equipped with a MEMS sensor array, including a piezoresistive stress sensor that is directly attached to the circumferential prestressed steel wire to monitor the circumferential stress distribution of the pipe wall caused by wire breakage in real time; a nanoporous humidity sensor that detects the humidity gradient caused by leakage through impedance changes and monitors the leakage humidity; a triaxial accelerometer that captures water hammer impact and external mechanical vibration to obtain the vibration spectrum; and a wide temperature range temperature sensor that monitors temperature changes and pipe deformation caused by freeze-thaw cycles, and is connected to the central control unit to ensure signal synchronization and anti-interference.

[0092] The data acquisition device is also used to capture energy from the prestressed steel cylinder concrete pipe through the energy acquisition layer to obtain energy data;

[0093] Understandably, the middle energy harvesting layer integrates a low-power MCU (microcontroller), signal conditioning circuitry, and piezoelectric energy management module, while also embedding a piezoelectric cantilever beam array to capture energy using fluid turbulence vibration.

[0094] The data acquisition device is also used to transmit the multi-dimensional sensing data and the energy data to the hybrid transmission network through the protective communication layer.

[0095] It should be understood that the bottom protective communication layer is a supercapacitor energy storage unit and a LoRa or NB-IoT communication module. The surface is coated with a 50μm aluminum nitride ceramic layer, the edges are laser sealed, and the interior is filled with flexible silicone gel buffer material, which can withstand ±10% tensile strain caused by tube deformation.

[0096] In this embodiment, the data acquisition device is further configured to shut down the multi-sensor layer and the energy acquisition layer when the vibration spectrum is detected to be continuously less than a preset lower limit threshold within a consecutive preset time period.

[0097] It is worth noting that the low-power architecture of the chip in this embodiment achieves energy efficiency optimization through a dual strategy of dynamic power management and intelligent data compression. The dynamic power management adopts a three-level power mode adaptive switching mechanism. When the vibration spectrum is detected to be continuously lower than the preset lower limit threshold for a continuous preset time period (for example, no vibration energy > 1mJ is detected for 10 consecutive minutes), a deep sleep mode is adopted, shutting down all sensors and communication modules, and only maintaining the real-time clock operation.

[0098] The data acquisition device is also used to activate the multi-sensor layer and the energy acquisition layer at a preset frequency when the vibration spectrum is detected to be between the preset lower limit threshold and the preset upper limit threshold within a continuous preset time period.

[0099] It is understood that when the vibration spectrum is detected to be between the preset lower limit threshold and the preset upper limit threshold within a continuous preset time period (for example, the vibration energy is greater than 1mJ and less than 10mJ), the default working state is adopted, the stress and humidity sensors are polled at a frequency of 1Hz, and the accelerometer is in the threshold detection state (trigger sensitivity 0.5mJ).

[0100] The data acquisition device is also used to activate the multi-sensor layer and the energy acquisition layer when the vibration spectrum is detected to be greater than the preset upper limit threshold.

[0101] It should be understood that when the vibration spectrum is detected to be greater than the preset upper limit threshold (for example, when the vibration energy is detected to be >10mJ), the range of the vibration spectrum corresponds to water hammer impact or external construction vibration. The triaxial accelerometer, humidity sensor, temperature sensor and stress sensor are immediately activated, and resources are dynamically allocated through a priority scheduling algorithm to ensure complete acquisition of key data.

[0102] It should be noted that energy efficiency optimization can also be achieved through data compression strategies. The data compression algorithm deploys an improved wavelet packet transform (WPT) compression engine at the node end, achieving signal feature preservation and data volume reduction through joint time-frequency domain analysis. The edge gateway uses the LZ77 algorithm to perform secondary optimization on the compressed data stream, reducing the overall data volume and lowering transmission power consumption. This design, through an event-driven, hierarchical compression, and on-demand transmission collaborative mechanism, enables the chip to achieve annual energy consumption fully covered by the piezoelectric self-powered system under typical operating conditions where the daily activation time is <5%, achieving long-term maintenance-free operation in underground scenarios.

[0103] In this embodiment, the data acquisition device consists of a three-layer structure: a multi-sensor layer, an energy acquisition layer, and a protection and communication layer. A modular design achieves a high degree of integration of sensing, power supply, and protection functions, adapting to the curved surface structure and harsh operating conditions of the PCCP pipeline inner wall. The data acquisition device utilizes a dynamic power management adaptive switching mechanism to switch between deep sleep mode, steady-state monitoring mode, and full-parameter acquisition mode, thereby optimizing energy efficiency.

[0104] Reference Figure 3 This application provides a pipeline monitoring system and a pipeline monitoring method. Figure 3 This is a flowchart illustrating the first embodiment of the pipeline monitoring method of this application. The pipeline monitoring method is applied to a pipeline monitoring system, which includes data acquisition equipment, a hybrid transmission network, and a cloud analysis platform; the method includes steps S10~S30:

[0105] Step S10: The data acquisition device acquires data from the prestressed steel cylinder concrete pipe and sends the obtained multi-dimensional monitoring parameters to the hybrid transmission network. The data acquisition device is installed on the inner wall concrete protective layer of the prestressed steel cylinder concrete pipe.

[0106] It should be noted that this system adopts a three-layer distributed architecture of "perception layer - transmission layer - decision layer," forming a closed-loop management system for the entire process from data acquisition and transmission to intelligent analysis. Its core design concept lies in "edge perception - collaborative computing - dynamic optimization." The data acquisition device of the perception layer can be composed of an array of intelligent monitoring chips embedded in the concrete protective layer of the PCCP inner wall. The array of chips can be configured according to actual conditions. For example, each chip can cover a 1.5m pipe section, with adjacent chips spaced ≤0.5m apart, forming a high-density monitoring network with a spatial resolution of 0.3m². The combination of the chips and the concrete protective layer of the PCCP inner wall ensures the synchronization of strain between the chips and the pipe body while avoiding stress concentration. The embedded intelligent monitoring chip adopts a four-layer flexible PCB stacked architecture, achieving a high degree of integration of sensing, power supply, and protection functions through modular design, adapting to the curved structure and harsh working conditions of the PCCP pipe inner wall. Data is collected from the PCCP pipe through this data acquisition device, and the obtained multi-dimensional monitoring parameters are sent to the hybrid transmission network for transmission.

[0107] In step S20, the hybrid transmission network transmits the multi-dimensional monitoring parameters to the cloud analysis platform. The hybrid transmission network is obtained by combining LoRa technology and NB-IoT technology according to the regional signal transmission characteristics.

[0108] Understandably, the hybrid transmission network at the transport layer is a clustered wireless network based on dynamic switching between LoRa and NB-IoT, enabling reliable data transmission in complex underground environments. Chip communication employs a hybrid networking strategy. Both LoRa and NB-IoT are low-power wide-area network (LPWAN) technologies, but LoRa offers advantages such as strong penetration, long-distance transmission, and strong anti-interference capabilities, while NB-IoT boasts wide-area coverage, high-speed transmission, large connection capacity, and strong compatibility. In the communication protocol design, NB-IoT and LoRa hybrid networking are dynamically switched for different scenarios, including urban areas, suburbs, and underground environments. Based on the advantages of each technology, NB-IoT is prioritized in open suburban areas or densely populated areas, relying on operator base stations to achieve high-frequency, low-latency data backhaul and wide-area coverage. In urban areas with severe signal obstruction, such as underground utility tunnels or remote locations, LoRa is switched to, using forward error correction and frequency hopping technologies to resist multipath interference and ensure a packet loss rate of <2%.

[0109] It should be noted that a clustered data aggregation approach can also be used for multi-dimensional monitoring parameters. Each cluster consists of 10 monitoring chips, and nodes within the cluster upload data to the edge gateway via the TDMA protocol. The gateway uses an improved LZ4 algorithm to compress the data and employs a CRC-16 cyclic redundancy check algorithm and selective retransmission mechanism to control the packet loss rate to <2%. Furthermore, in the data preprocessing stage, the edge gateway uses an improved CEEMDAN algorithm to perform noise mode decomposition on the acceleration signal, separating environmental noise such as subway vibration and electromagnetic interference, and suppressing temperature drift errors from stress sensors. It also integrates time-domain statistics (stress mean, variance, kurtosis) and spatial correlation features (humidity gradient, stress difference) to extract regional features, reducing data transmission volume while improving model convergence speed and classification accuracy, providing a high signal-to-noise ratio input for intelligent early warning.

[0110] In step S30, the cloud-based analysis platform analyzes the multi-dimensional monitoring parameters to obtain health assessment results.

[0111] Understandably, the decision-making layer is a cloud-based analytics platform deployed in the cloud, consisting of a machine learning engine and a visualization terminal. The machine learning engine, based on data transmitted from the chip, integrates a multimodal analysis engine to analyze multi-dimensional monitoring parameters, while the visualization terminal displays the health assessment results. By utilizing random forests and digital twin models, it achieves a leap from "single-point alarm" to "system-level risk projection," providing a full lifecycle health profile for the PCCP pipeline.

[0112] In this embodiment, step S30 further includes steps S301 to S304:

[0113] In step S301, the cloud analysis platform performs multi-dimensional feature identification on the multi-dimensional monitoring parameters, distinguishes the preset fluctuation characteristics from the actual leakage characteristics, and obtains the leakage risk probability value.

[0114] It should be noted that a large amount of historical fault data covering typical events such as wire breakage, leakage, and corrosion was collected in advance, and intelligent analysis was performed using a multi-algorithm fusion engine. The random forest classifier, through the construction of multiple decision trees and parallel voting, performs feature recognition on 128-dimensional features such as stress mutation rate, humidity spatial gradient, and vibration frequency domain energy, accurately distinguishing the periodic pressure oscillations caused by water hammer effect from the continuous negative pressure fluctuations of actual leakage, and outputting the leakage risk probability.

[0115] In step S302, the cloud analysis platform extracts time series data from the multi-dimensional monitoring parameters and determines the trend of pipeline health changes based on the time series.

[0116] Understandably, the Long Short-Term Memory Time Series Prediction Model (LSTM) is based on a recurrent neural network architecture and dynamically adjusts the temporal correlation of pipeline health monitoring data through a triple gating mechanism of forget gate, input gate, and output gate. The model constructs a multidimensional time series by extracting historical sensor data using a sliding window. After standardization and outlier removal preprocessing in the input layer, the hidden layer LSTM units extract nonlinear features within the time step and suppress overfitting. During the training phase, the Adam optimizer minimizes the mean square error, dynamically controlling the number of iterations, and finally outputs continuous predictions of the Pipeline Health Index (PHI) for a preset future time period (e.g., 30 minutes), forming a trend of pipeline health changes. By capturing the decay gradient and abrupt inflection points of the PHI sequence, this model can identify latent risks such as the propagation of microcracks in prestressed steel wires and the accumulation of fatigue damage in concrete in advance.

[0117] In step S303, the cloud-based analysis platform determines the stress wave signal caused by the damage from the multi-dimensional monitoring parameters to obtain the hidden damage.

[0118] It should be understood that the damage location engine employs a time-of-flight (TOF) method, using a distributed sensor array to capture stress wave signals triggered by damage for precise location. When a pipeline ruptures or leaks, the stress wave released instantaneously within the structure propagates along the pipe wall as a longitudinal wave. MEMS sensors deployed at key nodes of the pipe simultaneously record the arrival time of the wavefront, calculating the time difference Δt between adjacent sensors based on wave velocity calibration values. Using a hyperbolic intersection algorithm, the spatial coordinates of the stress wave source are analyzed using a set of time-of-flight equations composed of three or more sensors, achieving a location accuracy within 1% of the pipe section length. This method overcomes the limitations of traditional single-point monitoring, inverting the damage location through wavefield propagation characteristics and simultaneously using frequency domain coherence analysis to suppress environmental vibration noise, enabling non-contact dynamic tracking of hidden underground damage.

[0119] In step S304, the cloud-based analysis platform performs a pipeline health assessment based on the leakage risk probability value, the pipeline health change trend, and the hidden damage, and obtains the health assessment results.

[0120] In this embodiment, based on chip-transmitted data, a multimodal analysis engine is integrated: a random forest classifier determines the trend of pipeline health changes by performing time series extraction; an STM network determines the stress wave signal caused by damage, obtaining hidden damage; and a damage localization engine achieves non-contact dynamic tracking and precise location of hidden underground damage through time-difference localization.

[0121] In this embodiment, after step S304, steps S305 to S308 are also included:

[0122] In step S305, when the health assessment result is greater than a preset first health threshold, the cloud analysis platform generates a health report based on the health assessment result. The health report includes a stress distribution heat map and a corrosion rate trend map.

[0123] It is worth noting that this embodiment constructs a complete early warning chain from data to decision through a two-stage collaboration of "machine learning modeling - dynamic response control," and establishes a four-level early warning mechanism in the dynamic response control stage. When the PHI value is greater than the preset first health threshold (for example, above 0.8 in the normal level), the system automatically archives the data and generates a health report based on the health assessment results, including a stress distribution heatmap and corrosion rate trend.

[0124] In step S306, when the health assessment result is less than the preset first health threshold and greater than the preset second health threshold, the cloud analysis platform increases the data acquisition frequency of the data acquisition device and marks the area of ​​the prestressed steel cylinder concrete pipe corresponding to the health assessment result with an early warning.

[0125] It is understandable that when the health assessment result is less than a preset first health threshold and greater than a preset second health threshold (for example, when the PHI drops to a concern level of 0.6 to 0.8), the data acquisition frequency of the data acquisition device is increased, high-frequency data acquisition is immediately started, and customized inspection instructions are pushed to the mobile terminal. At the same time, a yellow warning area is marked on the GIS platform.

[0126] In step S307, when the health assessment result is less than the preset second health threshold and greater than the preset third health threshold, the cloud analysis platform reduces the pressure value of the substance transmitted by the prestressed steel cylinder concrete pipe and activates the audible and visual alarm device in the maintenance area corresponding to the prestressed steel cylinder concrete pipe.

[0127] It should be understood that when the health assessment result is less than the preset second health threshold and greater than the preset third health threshold (for example, when PHI enters the warning level of 0.4 to 0.6), the audible and visual alarm device in the underground maintenance well is activated, and the Supervisory Control and Data Acquisition (SCADA) system is depressurized in conjunction with the system.

[0128] In step S308, when the health assessment result is less than the preset third health threshold, the cloud analysis platform shuts down the prestressed steel cylinder concrete pipeline, generates an optimal emergency repair path based on real-time traffic conditions and preset pipeline topology, and sends the optimal emergency repair path to the user terminal for pipeline emergency repair.

[0129] Understandably, when the health assessment result is less than the preset third health threshold (for example, when PHI falls below the 0.4 emergency threshold), the system will close the upstream and downstream electric valves of the damaged pipeline section within 30 seconds, generate the optimal repair route by combining real-time traffic conditions and pipeline topology, and push a complete plan including the excavation scope, spare parts list and safety plan to the emergency command center.

[0130] It is worth noting that, in order to improve adaptability, the system uses a 7-day sliding window to dynamically calculate the PHI mean μ and standard deviation σ, sets the threshold for normal level to μ+1.5σ and the threshold for emergency level to μ-2σ, and introduces temperature and humidity as covariates for seasonal correction. When the false alarm rate exceeds 5% for 30 consecutive days, the incremental learning algorithm is automatically triggered to update the model parameters, ultimately forming a closed-loop decision chain from feature analysis, simulation verification, graded response to dynamic optimization, thereby upgrading the cross-scale risk management capabilities.

[0131] In this implementation, a complete early warning chain from data to decision is constructed through a two-stage synergy of machine learning modeling and dynamic response control. Based on health assessment results, dynamic evaluation is performed, triggering a four-level progressive response to effectively suppress the risk of sudden leaks and spread.

[0132] In this embodiment, data is collected from the pipeline using a data acquisition device installed in the inner concrete protective layer of the prestressed steel cylinder pipeline. A hybrid transmission network is obtained by combining LoRa and NB-IoT technologies based on the regional signal transmission characteristics, transmitting multi-dimensional monitoring parameters to the cloud analysis platform. The data is then analyzed to obtain the pipeline's health assessment results. This embodiment overcomes the bottleneck of underground scene data acquisition by using multi-parameter coupled sensing of the data acquisition device and piezoelectric energy acquisition technology, collecting rich multi-dimensional data. A clustered wireless network based on dynamic switching between LoRa and NB-IoT enables reliable data transmission in complex underground environments. The cloud analysis platform, based on multi-dimensional monitoring parameters and integrating a multi-modal analysis engine, provides a full lifecycle health status profile for the pipeline, improving the accuracy of pipeline monitoring.

[0133] Reference Figure 4 , Figure 4 This is a flowchart illustrating the second embodiment of the pipeline monitoring method of this application. Based on the first embodiment described above, a second embodiment of the pipeline monitoring method of this application is proposed.

[0134] In this embodiment, the data acquisition device includes a multi-sensor layer, an energy harvesting layer, and a protective communication layer. Step S10 further includes steps S101 to S103:

[0135] Step S101: The data acquisition device acquires data from the prestressed steel cylinder concrete pipe through the multi-sensor layer to obtain multi-dimensional sensing data. The multi-dimensional sensing data includes at least one of the following: pipe wall circumferential stress distribution, leakage humidity, vibration spectrum, and temperature.

[0136] Understandably, the embedded intelligent monitoring chip adopts a four-layer flexible PCB stacked architecture, achieving a high degree of integration of sensing, power supply, and protection functions through modular design, adapting to the curved structure and harsh operating conditions of the PCCP pipeline inner wall. The structural design is divided into three layers: a multi-sensor layer, an energy harvesting layer, and a protection and communication layer.

[0137] It should be understood that the top layer of the chip is equipped with a MEMS sensor array, including a piezoresistive stress sensor that is directly attached to the circumferential prestressed steel wire to monitor the circumferential stress distribution of the pipe wall caused by wire breakage in real time; a nanoporous humidity sensor that detects the humidity gradient caused by leakage through impedance changes and monitors the leakage humidity; a triaxial accelerometer that captures water hammer impact and external mechanical vibration to obtain the vibration spectrum; and a wide temperature range temperature sensor that monitors temperature changes and pipe deformation caused by freeze-thaw cycles, and is connected to the central control unit to ensure signal synchronization and anti-interference.

[0138] In step S102, the data acquisition device captures energy from the prestressed steel cylinder concrete pipe through the energy acquisition layer to obtain energy data.

[0139] Understandably, the middle energy harvesting layer integrates a low-power MCU (microcontroller), signal conditioning circuitry, and piezoelectric energy management module, while also embedding a piezoelectric cantilever beam array to capture energy using fluid turbulence vibration.

[0140] In step S103, the data acquisition device transmits the multi-dimensional sensing data and the energy data to the hybrid transmission network through the protective communication layer.

[0141] It should be understood that the bottom protective communication layer is a supercapacitor energy storage unit and a LoRa or NB-IoT communication module. The surface is coated with a 50μm aluminum nitride ceramic layer, the edges are laser sealed, and the interior is filled with flexible silicone gel buffer material, which can withstand ±10% tensile strain caused by tube deformation.

[0142] In this embodiment, before step S101, steps S01 to S03 are also included:

[0143] Step S01: When the data acquisition device detects that the vibration spectrum is continuously less than the preset lower limit threshold for a continuous preset time period, it shuts down the multi-sensor layer and the energy acquisition layer.

[0144] It is worth noting that the low-power architecture of the chip in this embodiment achieves energy efficiency optimization through a dual strategy of dynamic power management and intelligent data compression. The dynamic power management adopts a three-level power mode adaptive switching mechanism. When the vibration spectrum is detected to be continuously lower than the preset lower limit threshold for a continuous preset time period (for example, no vibration energy > 1mJ is detected for 10 consecutive minutes), a deep sleep mode is adopted, shutting down all sensors and communication modules, and only maintaining the real-time clock operation.

[0145] Step S02: When the data acquisition device detects that the vibration spectrum is between the preset lower limit threshold and the preset upper limit threshold within a continuous preset time period, it activates the multi-sensor layer and the energy acquisition layer at a preset frequency.

[0146] It is understood that when the vibration spectrum is detected to be between the preset lower limit threshold and the preset upper limit threshold within a continuous preset time period (for example, the vibration energy is greater than 1mJ and less than 10mJ), the default working state is adopted, the stress and humidity sensors are polled at a frequency of 1Hz, and the accelerometer is in the threshold detection state (trigger sensitivity 0.5mJ).

[0147] Step S03: When the data acquisition device detects that the vibration spectrum is greater than the preset upper limit threshold, it activates the multi-sensor layer and the energy acquisition layer.

[0148] It should be understood that when the vibration spectrum is detected to be greater than the preset upper limit threshold (for example, when the vibration energy is detected to be >10mJ), the range of the vibration spectrum corresponds to water hammer impact or external construction vibration. The triaxial accelerometer, humidity sensor, temperature sensor and stress sensor are immediately activated, and resources are dynamically allocated through a priority scheduling algorithm to ensure complete acquisition of key data.

[0149] It should be noted that energy efficiency optimization can also be achieved through data compression strategies. The data compression algorithm deploys an improved wavelet packet transform (WPT) compression engine at the node end, achieving signal feature preservation and data volume reduction through joint time-frequency domain analysis. The edge gateway uses the LZ77 algorithm to perform secondary optimization on the compressed data stream, reducing the overall data volume and lowering transmission power consumption. This design, through an event-driven, hierarchical compression, and on-demand transmission collaborative mechanism, enables the chip to achieve annual energy consumption fully covered by the piezoelectric self-powered system under typical operating conditions where the daily activation time is <5%, achieving long-term maintenance-free operation in underground scenarios.

[0150] In this embodiment, the data acquisition device consists of a three-layer structure: a multi-sensor layer, an energy acquisition layer, and a protection and communication layer. A modular design achieves a high degree of integration of sensing, power supply, and protection functions, adapting to the curved surface structure and harsh operating conditions of the PCCP pipeline inner wall. The data acquisition device utilizes a dynamic power management adaptive switching mechanism to switch between deep sleep mode, steady-state monitoring mode, and full-parameter acquisition mode, thereby optimizing energy efficiency.

[0151] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the pipeline monitoring system and pipeline monitoring method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0152] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A pipeline monitoring system, characterized in that, The pipeline monitoring system includes data acquisition equipment, a hybrid transmission network, and a cloud analysis platform; The data acquisition device is used to acquire data from the prestressed steel cylinder concrete pipe and send the obtained multi-dimensional monitoring parameters to the hybrid transmission network. The data acquisition device is installed in the inner wall concrete protective layer of the prestressed steel cylinder concrete pipe. The hybrid transmission network is used to transmit the multi-dimensional monitoring parameters to the cloud analysis platform. The hybrid transmission network is obtained by combining LoRa and NB-IoT technologies according to the regional signal transmission characteristics. It is a clustered wireless network based on dynamic switching between LoRa and NB-IoT. The cloud-based analysis platform is used to analyze the multi-dimensional monitoring parameters to obtain health assessment results; The cloud analytics platform is also used for: Multi-dimensional feature identification is performed on the multi-dimensional monitoring parameters to distinguish between preset fluctuation features and actual leakage features, thereby obtaining leakage risk probability values. The multi-dimensional monitoring parameters are extracted into time series, and the trend of pipeline health changes is determined based on the time series. The stress wave signal induced by the damage is determined from the multi-dimensional monitoring parameters to obtain the hidden damage; Based on the leakage risk probability value, the pipeline health change trend, and the hidden damage, a pipeline health assessment is conducted to obtain the health assessment results.

2. The system as described in claim 1, characterized in that, The data acquisition device includes a multi-sensor layer, an energy harvesting layer, and a protective communication layer; The data acquisition device is also used to acquire data from the prestressed steel cylinder concrete pipe through the multi-sensor layer to obtain multi-dimensional sensing data, which includes at least one of pipe wall circumferential stress distribution, leakage humidity, vibration spectrum, and temperature. The data acquisition device is also used to capture energy from the prestressed steel cylinder concrete pipe through the energy acquisition layer to obtain energy data; The data acquisition device is also used to transmit the multi-dimensional sensing data and the energy data to the hybrid transmission network through the protective communication layer.

3. The system as described in claim 2, characterized in that, The data acquisition device is also used to shut down the multi-sensor layer and the energy acquisition layer when the vibration spectrum is detected to be continuously less than a preset lower limit threshold within a continuous preset time period. The data acquisition device is also used to activate the multi-sensor layer and the energy acquisition layer at a preset frequency when the vibration spectrum is detected to be between the preset lower limit threshold and the preset upper limit threshold within a continuous preset time period. The data acquisition device is also used to activate the multi-sensor layer and the energy acquisition layer when the vibration spectrum is detected to be greater than the preset upper limit threshold.

4. The system as described in claim 1, characterized in that, The cloud-based analysis platform is also used to generate a health report based on the health assessment result when the health assessment result is greater than a preset first health threshold. The health report includes a stress distribution heat map and a corrosion rate trend map. The cloud-based analysis platform is also used to increase the data acquisition frequency of the data acquisition device and to mark the area of ​​the prestressed steel cylinder concrete pipe corresponding to the health assessment result when the health assessment result is less than the preset first health threshold and greater than the preset second health threshold. The cloud-based analysis platform is also used to reduce the pressure value of the substance transmitted by the prestressed steel cylinder concrete pipe and activate the audible and visual alarm device in the maintenance area corresponding to the prestressed steel cylinder concrete pipe when the health assessment result is less than the preset second health threshold and greater than the preset third health threshold. The cloud-based analysis platform is also used to shut down the prestressed steel cylinder concrete pipeline when the health assessment result is less than the preset third health threshold, and to generate an optimal emergency repair path based on real-time traffic conditions and preset pipeline topology, and send the optimal emergency repair path to the user terminal for pipeline emergency repair.

5. A pipeline monitoring method, characterized in that, The method is applied to a pipeline monitoring system, which includes data acquisition equipment, a hybrid transmission network, and a cloud analysis platform; the method includes: The data acquisition device collects data from the prestressed steel cylinder concrete pipe and sends the obtained multi-dimensional monitoring parameters to the hybrid transmission network. The data acquisition device is installed on the inner wall concrete protective layer of the prestressed steel cylinder concrete pipe. The hybrid transmission network transmits the multi-dimensional monitoring parameters to the cloud analysis platform. The hybrid transmission network is obtained by combining LoRa and NB-IoT technologies according to the regional signal transmission characteristics. It is a clustered wireless network based on dynamic switching between LoRa and NB-IoT. The cloud-based analytics platform analyzes the multi-dimensional monitoring parameters to obtain health assessment results; The cloud-based analytics platform analyzes the multi-dimensional monitoring parameters to obtain health assessment results, including the following steps: The cloud-based analysis platform performs multi-dimensional feature identification on the multi-dimensional monitoring parameters, distinguishes between preset fluctuation features and actual leakage features, and obtains leakage risk probability values. The cloud-based analysis platform extracts time series data from the multi-dimensional monitoring parameters and determines the trend of pipeline health changes based on the time series. The cloud-based analysis platform determines the stress wave signal caused by the damage from the multi-dimensional monitoring parameters, thereby obtaining the hidden damage. The cloud-based analysis platform performs a pipeline health assessment based on the leakage risk probability value, the pipeline health change trend, and the hidden damage, and obtains the health assessment results.

6. The method as described in claim 5, characterized in that, The data acquisition device includes a multi-sensor layer, an energy harvesting layer, and a protective communication layer; The data acquisition device collects data from the prestressed steel cylinder concrete pipe and sends the obtained multi-dimensional monitoring parameters to the hybrid transmission network. The step of installing the data acquisition device on the inner wall concrete protective layer of the prestressed steel cylinder concrete pipe includes: The data acquisition device collects data from the prestressed steel cylinder concrete pipe through the multi-sensor layer to obtain multi-dimensional sensing data, which includes at least one of pipe wall circumferential stress distribution, leakage humidity, vibration spectrum, and temperature. The data acquisition device captures energy from the prestressed steel cylinder concrete pipe through the energy acquisition layer to obtain energy data; The data acquisition device transmits the multi-dimensional sensing data and the energy data to the hybrid transmission network through the protective communication layer.

7. The method as described in claim 6, characterized in that, Before the step of the data acquisition device acquiring data from the prestressed steel cylinder concrete pipe through the multi-sensor layer to obtain multi-dimensional sensor data, the method further includes: When the data acquisition device detects that the vibration spectrum is continuously lower than a preset lower limit threshold for a continuous preset time period, it shuts down the multi-sensor layer and the energy acquisition layer. When the data acquisition device detects that the vibration spectrum is between the preset lower limit threshold and the preset upper limit threshold within a continuous preset time period, it activates the multi-sensor layer and the energy acquisition layer at a preset frequency. When the data acquisition device detects that the vibration spectrum is greater than the preset upper limit threshold, it activates the multi-sensor layer and the energy acquisition layer.

8. The method as described in claim 6, characterized in that, After the cloud-based analysis platform performs a pipeline health assessment based on the leakage risk probability value, the pipeline health change trend, and the hidden damage, and obtains the health assessment results, it further includes: When the health assessment result is greater than a preset first health threshold, the cloud analysis platform generates a health report based on the health assessment result. The health report includes a stress distribution heat map and a corrosion rate trend map. When the health assessment result is less than the preset first health threshold and greater than the preset second health threshold, the cloud analysis platform increases the data acquisition frequency of the data acquisition device and marks the area of ​​the prestressed steel cylinder concrete pipe corresponding to the health assessment result. When the health assessment result is less than the preset second health threshold and greater than the preset third health threshold, the cloud analysis platform reduces the pressure value of the material transmitted by the prestressed steel cylinder concrete pipe and activates the audible and visual alarm device in the maintenance area corresponding to the prestressed steel cylinder concrete pipe. When the health assessment result is less than the preset third health threshold, the cloud analysis platform shuts down the prestressed steel cylinder concrete pipeline, generates an optimal emergency repair path based on real-time traffic conditions and preset pipeline topology, and sends the optimal emergency repair path to the user terminal for pipeline emergency repair.

Images