Pipeline structure health state assessment method and system based on sensor network

Abstract

The invention discloses a pipeline structure health state assessment method and system based on a sensor network, and relates to the technical field of sensor networks, and the method comprises the steps: collecting multi-dimensional pipeline information of a target pipeline; monitoring the target pipeline through a sensor network to obtain real-time monitoring information; judging whether the real-time monitoring information conforms to a predetermined health constraint or not; if yes, an evaluation signal is sent out, health state evaluation is conducted on the target pipeline, and a real-time evaluation index is obtained; and representing the real-time health state of the target pipeline by using the real-time evaluation index. The technical problems that in the prior art, due to the fact that integration of pipeline multi-dimensional information and real-time monitoring do not depend on a sensor network, pipeline structure health state evaluation accuracy is poor, and timeliness is insufficient are solved, real-time evaluation of the pipeline structure health state based on the sensor network is achieved, and the pipeline structure health state evaluation efficiency is improved. And the accuracy and timeliness of evaluation are improved.

Description

Technical Field

[0001] This invention relates to the field of sensor network technology, and more specifically to a method and system for assessing the health status of pipeline structures based on sensor networks. Background Technology

[0002] In industrial production and infrastructure construction, pipelines serve as crucial transport carriers, and their structural health directly impacts the safe and stable operation of the system. Traditional pipeline health assessment methods largely rely on manual inspections or single-point sensor monitoring, which suffers from limited coverage, poor data timeliness, and a single assessment dimension, making it difficult to comprehensively capture potential pipeline risks. Although sensors for temperature, sound waves, and gases are increasingly being used, their deployment is scattered and lacks a systematic network. Furthermore, real-time sensor data is disconnected from static information such as pipeline structural characteristics and material properties, hindering in-depth fusion and analysis. This results in insufficient assessment accuracy and delayed early warnings, failing to meet the comprehensive and real-time requirements of pipeline health monitoring.

[0003] Existing technologies suffer from a lack of accuracy and timeliness in assessing the health status of pipeline structures due to the failure to integrate multi-dimensional pipeline information and real-time monitoring through sensor networks. Summary of the Invention

[0004] This application provides a method and system for assessing the health status of pipeline structures based on sensor networks. It addresses the technical problem that existing technologies do not rely on sensor networks to integrate multi-dimensional pipeline information and real-time monitoring, resulting in insufficient accuracy and timeliness in assessing the health status of pipeline structures.

[0005] In view of the above problems, this application provides a method and system for assessing the health status of pipeline structures based on sensor networks.

[0006] The first aspect of this application provides a method for assessing the health status of pipeline structures based on sensor networks, the method comprising:

[0007] Multidimensional pipeline information of the target pipeline is collected; the target pipeline is monitored through a sensor network to obtain real-time monitoring information; the real-time monitoring information is judged by a central platform to determine whether it meets predetermined health constraints; if it does, an evaluation signal is issued, and the health status of the target pipeline is evaluated based on the evaluation signal, in conjunction with the multidimensional pipeline information and the real-time monitoring information, to obtain a real-time evaluation index; the real-time evaluation index is used to characterize the real-time health status of the target pipeline.

[0008] A second aspect of this application provides a pipe structure health status assessment system based on sensor networks, the system comprising:

[0009] The system includes a multi-dimensional pipeline information acquisition module for collecting multi-dimensional pipeline information of the target pipeline; a real-time monitoring information acquisition module for monitoring the target pipeline through a sensor network to obtain real-time monitoring information; a health judgment module for determining whether the real-time monitoring information meets predetermined health constraints through a central platform; a real-time evaluation index acquisition module for issuing an evaluation signal if the constraints are met, and for evaluating the health status of the target pipeline based on the evaluation signal in conjunction with the multi-dimensional pipeline information and the real-time monitoring information to obtain a real-time evaluation index; and a real-time health status acquisition module for characterizing the real-time health status of the target pipeline using the real-time evaluation index.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] Multidimensional pipeline information of the target pipeline is collected; the target pipeline is monitored through a sensor network to obtain real-time monitoring information; a central platform determines whether the real-time monitoring information meets predetermined health constraints; if it does, an evaluation signal is issued, and based on the evaluation signal, in conjunction with the multidimensional pipeline information and the real-time monitoring information, the health status of the target pipeline is evaluated to obtain a real-time evaluation index; the real-time evaluation index is used to characterize the real-time health status of the target pipeline. This achieves the technical effect of realizing real-time evaluation of the health status of pipeline structures based on sensor networks, improving the accuracy and timeliness of the evaluation. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A schematic diagram of the pipeline structure health status assessment method based on sensor networks provided in this application embodiment;

[0014] Figure 2 A schematic diagram of a pipeline structure health status assessment system based on sensor networks provided in this application embodiment.

[0015] Figure labeling: Multidimensional pipeline information acquisition module 10, real-time monitoring information acquisition module 20, health judgment module 30, real-time assessment index acquisition module 40, real-time health status acquisition module 50. Detailed Implementation

[0016] This application provides a method and system for assessing the health status of pipeline structures based on sensor networks. This method addresses the technical problem that existing technologies do not rely on sensor networks to integrate multi-dimensional pipeline information and real-time monitoring, resulting in insufficient accuracy and timeliness in assessing the health status of pipeline structures.

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0018] Example 1, as Figure 1 As shown, this application provides a method for assessing the health status of pipeline structures based on sensor networks, the method comprising:

[0019] Step S100: Collect multi-dimensional pipeline information of the target pipeline.

[0020] Specifically, structural characteristic data of the target pipeline is collected through data retrieval or on-site surveys, including structural information such as pipeline dimensions, laying method, and connection type. At the same time, material property data of the pipeline is obtained through material testing reports or laboratory testing, covering material type, compressive strength, corrosion resistance, and other material-related properties. The collected structural characteristic data and material property data are integrated to form multi-dimensional pipeline information of the target pipeline, providing basic data support for subsequent health status assessment.

[0021] Step S200: Monitor the target pipeline through a sensor network to obtain real-time monitoring information.

[0022] Specifically, a sensor network consisting of distributed fiber optic acoustic sensors, distributed temperature sensors, distributed gas sensors, water level sensors, and video surveillance equipment is used to monitor the target pipeline and obtain real-time monitoring information. The distributed fiber optic acoustic sensors and distributed temperature sensors are evenly distributed along the axial direction of the target pipeline, with each point of the distributed fiber optic acoustic sensors having 10 turns of optical fiber wound around it. The distributed gas sensors include at least a first gas sensor located at the top of the pipeline manhole and a second gas sensor located at the bottom of the manhole. The water level sensors are placed in low-lying areas of the pipeline. The video surveillance equipment includes a first camera at the pipeline outlet and a second camera at the pipeline inlet. These sensor devices work together to collect information such as pipeline vibration, temperature, gas concentration, water level, and inlet / outlet status, collectively forming the real-time monitoring information.

[0023] Step S300: The central platform determines whether the real-time monitoring information meets the predetermined health constraints.

[0024] Specifically, after acquiring real-time monitoring information from the sensor network, the central platform extracts any sensing index and iterates through the real-time monitoring information to obtain any monitoring data corresponding to that index. Then, it matches the index parameter threshold corresponding to that sensing index within predetermined health constraints to determine whether the real-time parameter in the monitoring data is within that threshold range. If it is not within the threshold range, the central platform issues a first anomaly command to provide an anomaly warning for that sensing index. If it is within the threshold range, the monitoring data is processed into a time series to obtain a parameter time series. A regression test is performed on the parameter scatter plot generated based on the parameter time series to obtain a fitted curve. The target predicted parameter corresponding to the target time is obtained through the fitted curve. If the target predicted parameter is not within the index parameter threshold, a second anomaly command is issued to provide a pre-emptive anomaly warning before the target time. If the target predicted parameter is within the index parameter threshold, the real-time monitoring information is determined to meet the predetermined health constraints.

[0025] Step S400: If the conditions are met, an evaluation signal is issued, and based on the evaluation signal, the multi-dimensional pipeline information and the real-time monitoring information are used to evaluate the health status of the target pipeline to obtain a real-time evaluation index.

[0026] Specifically, when real-time monitoring information meets predetermined health constraints, the central platform sends an assessment signal. Based on this signal, a health status assessment is conducted in conjunction with multi-dimensional pipeline information and real-time monitoring information. According to the principle of maximum information coefficient, the real-time monitoring information is sequentially filtered using structural characteristic data and material property data as dependent variables to obtain structural factor data and material factor data, respectively. Then, the structural characteristic data is adjusted using the structural coefficient obtained by weighting the structural factor data with the coefficient of variation as the weight to obtain the structural characteristic index. The material property data is adjusted using the material coefficient obtained by weighting the material factor data with the coefficient of variation as the weight to obtain the material property index. Finally, the preset structure-material weight allocation is retrieved to calculate the structural characteristic index and the material property index to obtain a real-time assessment index used to characterize the pipeline health status.

[0027] Step S500: The real-time health status of the target pipeline is characterized by the real-time evaluation index.

[0028] Specifically, the calculated real-time assessment index is used as a quantitative indicator to directly characterize the real-time health status of the target pipeline. This real-time assessment index integrates the structural characteristic data, material property data, and real-time monitoring information collected by the sensor network of the target pipeline. It is formed through weighted calculation and can intuitively reflect the overall health status of the pipeline in terms of structural stability, material performance, and operating status, providing a clear and quantitative basis for pipeline maintenance and repair decisions.

[0029] In one possible implementation, step S100 further includes:

[0030] Step S110: Collect the structural characteristic data of the target pipeline.

[0031] Step S120: Collect the material property data of the target pipe.

[0032] Step S130: The structural characteristic data and the material property data constitute the multidimensional pipeline information.

[0033] Specifically, for the target pipeline, various characteristic data related to its structure are collected. These data constitute the core content of the structural characteristic data, including but not limited to dimensional parameters that reflect the pipeline's structural form (such as the pipeline's diameter, length, and wall thickness), laying methods that reflect the pipeline's installation method (such as buried laying and overhead laying), and connection forms that characterize the connection status of various parts of the pipeline (such as welded connections and flange connections). By collecting this information, complete structural characteristic data of the target pipeline is formed.

[0034] For the target pipeline, various attribute data related to the materials used are collected. These data together constitute material attribute data, including the pipeline material type (such as specific categories such as metal material, non-metal material, etc.), material compressive strength, corrosion resistance, and other information reflecting the inherent characteristics and performance of the material. By collecting this data, complete material attribute data of the target pipeline is formed, laying the foundation for subsequent combination with structural characteristic data to form multi-dimensional pipeline information.

[0035] The collected target pipeline structural characteristic data (such as pipeline size, laying method, connection type and other structure-related information) and the collected material property data (such as material type, compressive strength, corrosion resistance and other material-related property information) are integrated to form a multi-dimensional pipeline information for target pipeline health status assessment, providing comprehensive basic data support for subsequent health assessment based on real-time monitoring information.

[0036] In one possible implementation, step S200 further includes:

[0037] Step S210: The sensor network includes distributed fiber optic acoustic sensors, distributed temperature sensors, distributed gas sensors, water level sensors, and video surveillance equipment.

[0038] Step S220: The distributed fiber optic acoustic sensor and the distributed temperature sensor are both uniformly arranged along the axial direction of the target pipe, and each fiber optic acoustic sensor in the distributed fiber optic acoustic sensor is wound with 10 turns of optical fiber at the corresponding arrangement point. The distributed gas sensor includes at least a first gas sensor arranged at the top of the well in the target pipe and a second gas sensor arranged at the bottom of the well. The water level sensor is arranged in the low-lying area of ​​the target pipe. The video monitoring equipment includes a first camera arranged at the outlet of the target pipe and a second camera arranged at the inlet of the target pipe.

[0039] Specifically, the devices constituting the sensor network include distributed fiber optic acoustic sensors, distributed temperature sensors, distributed gas sensors, water level sensors, and video surveillance equipment. These different types of sensors each perform their specific functions and work together to achieve multi-dimensional monitoring of the target pipeline: distributed fiber optic acoustic sensors can capture signals such as vibration and sound waves from the pipeline; distributed temperature sensors are used to monitor temperature changes along the pipeline; distributed gas sensors can detect gas concentrations around the pipeline; water level sensors focus on monitoring water accumulation in low-lying areas of the pipeline; and video surveillance equipment records the status of the pipeline's inlets and outlets through visual images. Together, they provide comprehensive data support for obtaining real-time monitoring information of the target pipeline.

[0040] Both distributed fiber optic acoustic sensors and distributed temperature sensors are uniformly distributed along the axial direction of the target pipeline to achieve comprehensive monitoring along the pipeline. At each deployment point of the distributed fiber optic acoustic sensors, the corresponding sensor is wound with 10 turns of optical fiber, increasing the contact area between the fiber and the pipeline to improve the sensitivity of the acoustic signal acquisition. At least two distributed gas sensors are deployed at the top (first gas sensor) and bottom (second gas sensor) of the target pipeline well, respectively, to monitor the gas state at different heights within the well. Water level sensors are specifically deployed in low-lying areas of the target pipeline to accurately detect potential water accumulation. The video monitoring equipment consists of two parts: a first camera deployed at the outlet of the target pipeline and a second camera deployed at the inlet, providing real-time monitoring of the pipeline's operational status at both ends through visual monitoring of the inlet and outlet. These targeted deployment methods ensure that all types of sensors can efficiently and accurately collect relevant monitoring data from the target pipeline.

[0041] In one possible implementation, step S200 further includes:

[0042] Step S221: The sensor network is connected to the central platform via a wireless data network or a wired network and is powered by solar energy.

[0043] Specifically, the sensor network connects to the central platform via either a wireless data network or a wired network, allowing for flexible selection based on the network conditions of the pipeline's environment, ensuring stable transmission of real-time monitoring information to the central platform. Simultaneously, the sensor network is powered by solar energy. By configuring solar panels and energy storage devices at sensor deployment points, renewable energy is used to power each sensor and data transmission module. This adapts to scenarios where pipelines may be located outdoors or in remote areas, achieving an energy-saving and environmentally friendly power supply method and ensuring the long-term stable operation of the sensor network.

[0044] In one possible implementation, step S300 further includes:

[0045] Step S310: Obtain any sensing index, and traverse the real-time monitoring information to obtain any monitoring data corresponding to the arbitrary sensing index.

[0046] Step S320: Match the arbitrary sensing index with the threshold value of the arbitrary index parameter corresponding to the predetermined health constraint.

[0047] Step S330: Determine whether any real-time parameter in the arbitrary monitoring data is within the threshold of the arbitrary indicator parameter.

[0048] Step S340: If not, issue a first abnormal command and issue an abnormal warning for any sensor indicator based on the first abnormal command.

[0049] Specifically, from the real-time monitoring information transmitted from the sensor network to the central platform, any sensing indicator (such as vibration signal monitored by distributed fiber optic acoustic sensors, temperature value collected by distributed temperature sensors, gas concentration obtained by distributed gas sensors, etc.) is selected. Then, the real-time monitoring information is fully traversed to filter out the specific monitoring data corresponding to the arbitrary sensing indicator, thereby providing basic data for subsequent judgment of pipeline health status.

[0050] The central platform calls upon a pre-defined health constraint database, which stores the mapping relationship between various sensor indicators and their corresponding indicator parameter thresholds. For any acquired sensor indicator (such as the temperature monitored by a distributed temperature sensor, the gas concentration monitored by a distributed gas sensor, etc.), the database retrieval function is used to accurately match and locate the specific indicator parameter threshold (such as a specific temperature range, the upper limit of gas concentration, etc.) corresponding to the sensor indicator in the pre-defined health constraints. This provides a clear numerical reference for subsequent judgment on whether the real-time monitoring data meets health standards.

[0051] Any real-time parameter in any monitoring data obtained (such as pipeline vibration value, temperature reading, gas concentration value, etc. at a certain moment) is compared with the threshold value of any index parameter corresponding to the matched arbitrary sensing index (such as vibration safety range, normal temperature range, gas concentration limit, etc.) to determine whether the real-time parameter falls within the range limited by the threshold value of the index parameter, thereby initially determining whether the monitoring data corresponding to the sensing index meets the basic requirements for healthy pipeline operation.

[0052] When it is determined that any real-time parameter in any monitoring data is not at the corresponding threshold of any indicator parameter, the central platform immediately generates and issues a first abnormal command. This command contains the sensor indicator that has not met the standard and the specific monitoring data information. Subsequently, based on this first abnormal command, an abnormal warning is issued for the arbitrary sensor indicator through a preset early warning mechanism (such as audible and visual alarms, platform pop-ups, SMS notifications, etc.) to quickly remind relevant personnel that there is an abnormal situation in the pipeline that exceeds the health constraints in this monitoring dimension, so as to facilitate timely response measures.

[0053] In one possible implementation, step S330 further includes:

[0054] Step S331: If it is in the state, perform time-series processing on the arbitrary monitoring data to obtain the arbitrary parameter time series.

[0055] Step S332: Perform regression fitting on the arbitrary parameter scatter plot generated based on the arbitrary parameter time series to obtain an arbitrary fitted curve.

[0056] Step S333: Obtain the target prediction parameters corresponding to the target time through the arbitrary fitted curve.

[0057] Step S334: If the target prediction parameter is not at the threshold of any index parameter, issue a second abnormal command.

[0058] Step S335: Based on the second abnormal instruction, provide an early warning of abnormality for any sensor indicator before the target time.

[0059] Specifically, when it is determined that any real-time parameter in any monitoring data is at the threshold of any corresponding index parameter, the monitoring data is sorted and arranged in chronological order, and the monitoring data is associated with the corresponding time point to form an arbitrary parameter time series containing time series and corresponding parameter values, thereby presenting the change of the sensing index parameter over time.

[0060] When fitting regression to scatter plots generated from arbitrary parameter time series, the least squares method is used. This involves calculating the function parameters that minimize the sum of the squared distances from each data point in the scatter plot to the fitted curve, thus determining the curve equation that best fits the data trend and obtaining an arbitrary fitted curve. For example, if the parameter time series exhibits a linear trend, a univariate linear equation can be fitted using the least squares method; if it exhibits a nonlinear trend, a polynomial equation can be fitted, thereby accurately reflecting the changing pattern of the parameters over time.

[0061] After obtaining any fitted curve, the preset target time is substituted into the function expression of the fitted curve, and the parameter value corresponding to that time point is calculated. This parameter value is the target prediction parameter, which reflects the parameter level that the arbitrary sensing index may reach at the target time.

[0062] After obtaining the target prediction parameters corresponding to the target time, the target prediction parameters are compared with the threshold of any matched indicator parameter. If it is determined that the target prediction parameters are not within the threshold range of any indicator parameter, the central platform will generate and issue a second abnormal command. This command includes information such as the target prediction parameters, the corresponding sensor indicators, and the target time, providing a basis for subsequent proactive abnormal warnings.

[0063] Upon receiving the second abnormal command, based on the target time and any sensor indicator information contained in the command, a pre-set early warning mechanism is activated before the target time arrives, issuing a proactive abnormality warning for that arbitrary sensor indicator. Warning methods include displaying a warning prompt on the central platform interface, sending warning text messages to relevant personnel, or pushing warning notifications, to inform the pipeline in advance that an abnormality in that sensor indicator dimension may occur beyond the health constraints at the target time, allowing sufficient time for investigation and handling.

[0064] In one possible implementation, step S330 further includes:

[0065] Step S336: If the target prediction parameter is at the threshold of any indicator parameter, then the real-time monitoring information meets the predetermined health constraint.

[0066] Specifically, after obtaining the target prediction parameter, it is compared with the threshold of any matched indicator parameter. If it is determined that the target prediction parameter is within the threshold range of the arbitrary indicator parameter, it can be determined that the current real-time monitoring information meets the preset health constraints, indicating that the pipeline monitoring dimension corresponding to the arbitrary sensing indicator is in a healthy operating state from the current and predicted trends.

[0067] In one possible implementation, step S400 further includes:

[0068] Step S410: Based on the principle of maximum information coefficient, the real-time monitoring information is subjected to correlation analysis and screening with the structural characteristic data and the material property data as dependent variables in sequence to obtain structural factor data and material factor data respectively.

[0069] Step S420: Using the structural coefficients obtained by weighting the structural factor data with the coefficient of variation as weights, adjust the structural characteristic data to obtain the structural characteristic index.

[0070] Step S430: Using the material coefficient obtained by weighting the material factor data with the coefficient of variation as the weight, adjust the material property data to obtain the material property index.

[0071] Step S440: Retrieve the predetermined structure-material weight allocation to calculate the structural characteristic index and the material property index to obtain the real-time evaluation index.

[0072] Specifically, the maximum information coefficient algorithm module is invoked. This module can quantify the degree of correlation between two variables, regardless of the variable type or relationship form. When processing structural factor data, the collected target pipeline structural characteristic data (such as pipeline diameter, wall thickness, interface type, etc.) is set as the dependent variable. Then, the real-time monitoring information transmitted by the sensor network (covering various types of data such as vibration, temperature, and gas concentration) is traversed. The maximum information coefficient algorithm is used to calculate the correlation strength between each data item in the real-time monitoring information and the structural characteristic data, obtaining the corresponding information coefficient value. Next, these information coefficient values ​​are compared with a preset correlation strength threshold. Real-time monitoring data with information coefficient values ​​reaching or exceeding the threshold are filtered out and classified as structural factor data. These data can significantly reflect changes in structural characteristics. Subsequently, the same implementation logic is used to process material factor data: the target pipeline material property data (such as material composition, corrosion resistance, compressive strength, etc.) is set as the dependent variable, and the maximum information coefficient algorithm is invoked again to calculate the correlation strength of each data item in the real-time monitoring information, obtaining the information coefficient value corresponding to the material property data. Subsequently, these information coefficient values ​​are filtered based on preset correlation strength thresholds, retaining the qualified real-time monitoring data and identifying them as material factor data. This type of data can effectively reflect the state changes of material properties. Through this correlation analysis and filtering based on the principle of maximum information coefficient, data with key impacts on pipeline structure and material evaluation can be accurately extracted from complex real-time monitoring information.

[0073] For the obtained structural factor data, the coefficient of variation (CV) for each data point is calculated using the formula: CV = (Standard deviation of data ÷ Mean of data) × 100%. This quantifies the dispersion and volatility of different structural factor data. Next, the CVs of all structural factor data are normalized by dividing the CV of a specific structural factor by the sum of the CVs of all structural factor data. This yields the weight value for each structural factor, which together constitute the structural coefficient. The total weights are kept constant to reflect the relative importance of different structural factors on the pipeline structure. Subsequently, each parameter in the structural characteristic data (such as pipe diameter, wall thickness, and joint strength) is multiplied by its corresponding structural coefficient to obtain a weighted value for each parameter. Finally, all weighted values ​​are summed to obtain the structural characteristic index, which comprehensively reflects the overall characteristics of the pipeline structure. This index, through weighted adjustments, highlights factors with higher variability and more significant structural impact, making the evaluation results more consistent with reality.

[0074] For each data point in the material factor data, its coefficient of variation is calculated using the formula: Coefficient of Variation = (Standard Deviation of the data point ÷ Mean of the data point) × 100%. This measures the dispersion and magnitude of variation of each material factor data point. Next, the coefficients of variation for all material factor data are normalized. This is done by dividing the coefficient of variation of a particular material factor data point by the sum of the coefficients of variation of all material factor data points. This yields the weight corresponding to each material factor data point. These weights collectively constitute the material coefficient, ensuring that the total weights equal 1, reflecting the relative importance of different material factors on the pipeline material properties. Subsequently, each parameter in the material property data (such as the material's corrosion resistance level, compressive strength, and service life) is multiplied by its corresponding material coefficient to obtain a weighted value for each parameter. Finally, all weighted values ​​are summed. The result is the material property index, which comprehensively reflects the overall properties of the pipeline material. This index, through weighted adjustments, highlights factors with higher variability and more significant impact on material properties, making the evaluation results more accurately reflect the actual state of the pipeline material.

[0075] The system retrieves a pre-defined structure-material weight allocation scheme from the preset parameter configuration. This scheme includes the weight ratios of the structural characteristic index and the material property index. Then, the obtained structural characteristic index is multiplied by its corresponding weight, and the obtained material property index is multiplied by its corresponding weight. Finally, the two product results are added together, and the sum is the real-time evaluation index that can comprehensively reflect the health status of the target pipeline.

[0076] In one possible implementation, step S410 further includes:

[0077] Step S411: Obtain the historical pipeline database, wherein the historical pipeline database includes a historical pipeline structural characteristics database.

[0078] Step S412: Obtain the first dataset from the historical pipeline structural characteristic database, and perform mutual information analysis on the first monitoring parameter set and the first structural characteristic dataset in the first dataset to obtain the structural factor.

[0079] Step S413: Match the structural factor data corresponding to the structural factor in the real-time monitoring information.

[0080] Step S414: This includes:

[0081] Match any historical index parameter set corresponding to any sensing index in the first monitoring parameter set.

[0082] Mutual information value analysis is performed on the mapping relationship between the arbitrary historical indicator parameter set and the first structural characteristic dataset to obtain the arbitrary maximum mutual information value.

[0083] If any maximum mutual information value reaches a predetermined mutual information value limit, then the arbitrary sensing index is added to the structural factor.

[0084] Specifically, the historical pipeline database is retrieved from the database server through a preset data interface or storage path. This database is a collection of various types of historical pipeline-related data, which explicitly includes a historical pipeline structural characteristics database. This sub-database stores records related to the structural characteristics of different types of pipelines in different historical periods, providing basic data support for subsequent structural factor analysis.

[0085] The first dataset is extracted from the historical pipeline structural characteristics database. This dataset contains a first monitoring parameter set and a first structural characteristics dataset. The first monitoring parameter set is a set of relevant parameters obtained from historical pipeline monitoring, and the first structural characteristics dataset is a set of relevant data on the corresponding pipeline structural characteristics. Subsequently, mutual information analysis is used to calculate the correlation between the two datasets, and parameters in the first monitoring parameter set that have a significant correlation with the first structural characteristics dataset are selected. These parameters are then combined to form structural factors.

[0086] First, identify the specific parameter types contained in the obtained structural factors. Then, traverse the real-time monitoring information transmitted by the sensor network. Through parameter identification comparison, data type matching, and other methods, filter out the real-time monitoring data corresponding to each parameter in the structural factors from the real-time monitoring information. These filtered data are the structural factor data, thereby achieving accurate matching between structural factors and real-time monitoring information.

[0087] First, key identification information of any sensing indicator is extracted, such as indicator name, monitoring dimension, and data type. Then, based on this identification information, the first monitoring parameter set is traversed and searched. By comparing whether the identifiers of each historical indicator in the parameter set are consistent with the identifiers of any sensing indicator, all matching historical indicators are selected. Finally, these matching historical indicators are integrated to form the corresponding arbitrary historical indicator parameter set.

[0088] When performing mutual information value analysis on the mapping relationship between any historical indicator parameter set and the first structural characteristic dataset, the two datasets are first aligned to ensure that the sample size and correspondence are consistent. Then, the mutual information calculation algorithm is used to calculate the mutual information value between each indicator in the arbitrary historical indicator parameter set and each data item in the first structural characteristic dataset, thereby quantifying the correlation strength between the two. Finally, the maximum value is selected from all the calculated mutual information values ​​as the arbitrary maximum mutual information value corresponding to the mapping relationship.

[0089] The calculated maximum mutual information value is compared with the preset mutual information value limit. If the former reaches or exceeds the latter, it indicates that the arbitrary sensing index has a strong correlation with the pipeline structure characteristics. At this time, the addition mechanism is triggered to include the arbitrary sensing index into the set of structural factors to enhance the coverage and representativeness of structural factors on pipeline structure-related influencing factors.

[0090] Example 2, based on the same inventive concept as the sensor network-based pipeline structure health status assessment method in the foregoing examples, such as... Figure 2 As shown, this application provides a pipeline structure health status assessment system based on sensor networks. The system and method embodiments in this application are based on the same inventive concept. The system includes:

[0091] The multidimensional pipeline information acquisition module 10 is used to collect multidimensional pipeline information of the target pipeline.

[0092] The real-time monitoring information acquisition module 20 is used to monitor the target pipeline through a sensor network and obtain real-time monitoring information.

[0093] The health assessment module 30 is used to determine whether the real-time monitoring information meets the predetermined health constraints through the central platform.

[0094] The real-time evaluation index acquisition module 40 is used to issue an evaluation signal if the conditions are met, and to evaluate the health status of the target pipeline based on the evaluation signal in conjunction with the multi-dimensional pipeline information and the real-time monitoring information, thereby obtaining a real-time evaluation index.

[0095] The real-time health status acquisition module 50 is used to characterize the real-time health status of the target pipeline using the real-time evaluation index.

[0096] Furthermore, the system is also used to implement the following functions:

[0097] Collect structural characteristic data of the target pipeline; collect material property data of the target pipeline; the structural characteristic data and the material property data constitute the multidimensional pipeline information.

[0098] Furthermore, the system is also used to implement the following functions:

[0099] The sensor network includes distributed fiber optic acoustic sensors, distributed temperature sensors, distributed gas sensors, water level sensors, and video surveillance equipment. The distributed fiber optic acoustic sensors and the distributed temperature sensors are uniformly distributed along the axial direction of the target pipeline. Each fiber optic acoustic sensor in the distributed fiber optic acoustic sensors has 10 turns of optical fiber wound around its corresponding placement point. The distributed gas sensors include at least a first gas sensor located at the top of the well inside the target pipeline and a second gas sensor located at the bottom of the well. The water level sensors are located in low-lying areas of the target pipeline. The video surveillance equipment includes a first camera located at the outlet of the target pipeline and a second camera located at the inlet of the target pipeline.

[0100] Furthermore, the system is also used to implement the following functions:

[0101] The sensor network is connected to the central platform via a wireless data network or a wired network and is powered by solar energy.

[0102] Furthermore, the system is also used to implement the following functions:

[0103] Obtain any sensor index and traverse the real-time monitoring information to obtain any monitoring data corresponding to the arbitrary sensor index; match the arbitrary sensor index with the arbitrary index parameter threshold corresponding to the predetermined health constraint; determine whether any real-time parameter in the arbitrary monitoring data is within the arbitrary index parameter threshold; if not, issue a first abnormal command and issue an abnormal warning for the arbitrary sensor index based on the first abnormal command.

[0104] Furthermore, the system is also used to implement the following functions:

[0105] If the target time is within the specified range, the arbitrary monitoring data is processed to obtain an arbitrary parameter time series; the arbitrary parameter scatter plot generated based on the arbitrary parameter time series is fitted and regressed to obtain an arbitrary fitting curve; the target prediction parameter corresponding to the target time is obtained through the arbitrary fitting curve; if the target prediction parameter is not within the threshold of the arbitrary indicator parameter, a second abnormal command is issued; based on the second abnormal command, an early warning of anomalies is issued for the arbitrary sensing indicator before the target time.

[0106] Furthermore, the system is also used to implement the following functions:

[0107] If the target prediction parameter is within the threshold of any of the indicator parameters, then the real-time monitoring information meets the predetermined health constraints.

[0108] Furthermore, the system is also used to implement the following functions:

[0109] Based on the principle of maximum information coefficient, the real-time monitoring information is sequentially filtered using the structural characteristic data and the material property data as dependent variables to obtain structural factor data and material factor data, respectively. The structural characteristic data is then adjusted using the structural coefficient obtained by weighting the structural factor data with the coefficient of variation as the weight to obtain the structural characteristic index. Similarly, the material property data is adjusted using the material coefficient obtained by weighting the material factor data with the coefficient of variation as the weight to obtain the material property index. Finally, a predetermined structure-material weight allocation is used to calculate the structural characteristic index and the material property index to obtain the real-time evaluation index.

[0110] Furthermore, the system is also used to implement the following functions:

[0111] A historical pipeline database is acquired, including a historical pipeline structural characteristic database. A first dataset is acquired from the historical pipeline structural characteristic database, and mutual information analysis is performed on a first monitoring parameter set and a first structural characteristic dataset in the first dataset to obtain a structural factor. The structural factor data corresponding to the structural factor is matched in the real-time monitoring information. This includes: matching any historical indicator parameter set corresponding to any sensor indicator in the first monitoring parameter set; performing mutual information value analysis on the mapping relationship between the arbitrary historical indicator parameter set and the first structural characteristic dataset to obtain an arbitrary maximum mutual information value; if the arbitrary maximum mutual information value reaches a predetermined mutual information value limit, the arbitrary sensor indicator is added to the structural factor.

[0112] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0113] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0114] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A method for assessing the structural health status of pipelines based on sensor networks, characterized in that, include: Collect multi-dimensional pipeline information of the target pipeline; The target pipeline is monitored using a sensor network to obtain real-time monitoring information; The central platform determines whether the real-time monitoring information meets the predetermined health constraints. If the conditions are met, an evaluation signal is issued, and based on the evaluation signal, the multi-dimensional pipeline information and the real-time monitoring information are used to evaluate the health status of the target pipeline and obtain a real-time evaluation index. The real-time evaluation index is used to characterize the real-time health status of the target pipeline.

2. The pipeline structure health status assessment method based on sensor networks as described in claim 1, characterized in that, Collect multi-dimensional pipeline information for the target pipeline, including: Collect structural characteristic data of the target pipeline; Collect material property data of the target pipeline; The structural characteristic data and the material property data together constitute the multidimensional pipeline information.

3. The pipeline structure health status assessment method based on sensor networks as described in claim 2, characterized in that, The sensor network includes distributed fiber optic acoustic sensors, distributed temperature sensors, distributed gas sensors, water level sensors, and video surveillance equipment. The distributed fiber optic acoustic wave sensor and the distributed temperature sensor are both uniformly arranged along the axial direction of the target pipeline. Each fiber optic acoustic wave sensor in the distributed fiber optic acoustic wave sensor is wound with 10 turns of optical fiber at the corresponding arrangement point. The distributed gas sensor includes at least a first gas sensor arranged at the top of the well in the target pipeline and a second gas sensor arranged at the bottom of the well. The water level sensor is arranged in the low-lying area of ​​the target pipeline. The video monitoring equipment includes a first camera arranged at the outlet of the target pipeline and a second camera arranged at the inlet of the target pipeline.

4. The pipeline structure health status assessment method based on sensor networks as described in claim 3, characterized in that, The sensor network is connected to the central platform via a wireless data network or a wired network and is powered by solar energy.

5. The pipeline structure health status assessment method based on sensor networks as described in claim 3, characterized in that, The central platform determines whether the real-time monitoring information meets predetermined health constraints, including: Obtain any sensing index, and iterate through the real-time monitoring information to obtain any monitoring data corresponding to the arbitrary sensing index; Match the threshold of any index parameter corresponding to any sensing index in the predetermined health constraint; Determine whether any real-time parameter in any of the monitoring data is within the threshold of any of the indicator parameters; If not, issue a first abnormal command and issue an abnormal warning for any of the sensor indicators based on the first abnormal command.

6. The pipeline structure health status assessment method based on sensor networks as described in claim 5, characterized in that, After determining whether any real-time parameter in the arbitrary monitoring data is within the threshold of the arbitrary indicator parameter, the process includes: If it is in the state, the arbitrary monitoring data is processed into a time series to obtain an arbitrary parameter time series; The arbitrary parameter scatter plot generated based on the arbitrary parameter time series is fitted and regressed to obtain an arbitrary fitted curve; The target prediction parameters corresponding to the target time are obtained by using the arbitrary fitted curve. If the target prediction parameter is not at the threshold of any of the indicator parameters, a second abnormal command is issued. Based on the second abnormal instruction, an early warning of abnormality is issued for any of the sensing indicators before the target time.

7. The pipeline structure health status assessment method based on sensor networks as described in claim 6, characterized in that, If the target prediction parameter is within the threshold of any of the indicator parameters, then the real-time monitoring information meets the predetermined health constraints.

8. The pipeline structure health status assessment method based on sensor networks as described in claim 5, characterized in that, If the conditions are met, an evaluation signal is issued, and based on the evaluation signal, in conjunction with the multi-dimensional pipeline information and the real-time monitoring information, a health status assessment of the target pipeline is performed to obtain a real-time evaluation index, including: Based on the principle of maximum information coefficient, the real-time monitoring information is subjected to correlation analysis and screening with the structural characteristic data and the material property data as dependent variables in turn, to obtain structural factor data and material factor data respectively. The structural characteristic data are adjusted using the structural coefficients obtained by weighting the structural factor data with the coefficient of variation as weights to obtain the structural characteristic index. The material property data is adjusted using the material coefficient obtained by weighting the material factor data with the coefficient of variation as the weight, to obtain the material property index; The predetermined structure-material weight allocation is retrieved to calculate the structural characteristic index and the material property index, thereby obtaining the real-time evaluation index.

9. The pipeline structure health status assessment method based on sensor networks as described in claim 8, characterized in that, Based on the principle of maximum information coefficient, the real-time monitoring information is subjected to correlation analysis and filtering, with the structural characteristic data and the material property data as dependent variables, respectively, to obtain structural factor data and material factor data, including: Obtain a historical pipeline database, wherein the historical pipeline database includes a historical pipeline structural characteristics database; Obtain the first dataset from the historical pipeline structural characteristic database, and perform mutual information analysis on the first monitoring parameter set and the first structural characteristic dataset in the first dataset to obtain the structural factor; Match the structural factor data corresponding to the structural factor in the real-time monitoring information; This includes: Match any historical index parameter set corresponding to any sensor index in the first monitoring parameter set; Mutual information value analysis is performed on the mapping relationship between the arbitrary historical indicator parameter set and the first structural characteristic dataset to obtain the arbitrary maximum mutual information value; If any maximum mutual information value reaches a predetermined mutual information value limit, then the arbitrary sensing index is added to the structural factor.

10. A pipeline structure health status assessment system based on sensor networks, characterized in that, The system is used to implement the pipeline structure health status assessment method based on sensor networks as described in any one of claims 1-9, and the system comprises: The multi-dimensional pipeline information acquisition module is used to collect multi-dimensional pipeline information of the target pipeline; The real-time monitoring information acquisition module is used to monitor the target pipeline through a sensor network and obtain real-time monitoring information; The health assessment module is used to determine, through the central platform, whether the real-time monitoring information meets the predetermined health constraints. The real-time evaluation index acquisition module is used to issue an evaluation signal if the conditions are met, and to evaluate the health status of the target pipeline based on the evaluation signal in conjunction with the multi-dimensional pipeline information and the real-time monitoring information, thereby obtaining a real-time evaluation index. A real-time health status acquisition module is used to characterize the real-time health status of the target pipeline using the real-time evaluation index.

Images