Pipeline insulation monitoring system and method based on wireless passive sensor

Abstract

The invention relates to the technical field of insulation monitoring, and discloses a pipeline insulation monitoring system and method based on a wireless passive sensor, and the system comprises a sensor assembly which comprises a wireless passive electromagnetic sensor; the processing unit collects a reflected signal set for noise elimination; the judgment unit compares the reflected signal set after noise elimination with a standard signal range to judge the signal type; when the suspected abnormal signal is determined, grouping the reflected signal set to determine whether the reflected signal set is an abnormal signal; when the signal is judged to be the abnormal signal, identifying unit abnormal data, and determining whether the characteristic vector judges whether the abnormal data is the same defect or not; and the early warning unit determines a defect weight according to an identification result and determines a pipeline insulation monitoring result. According to the invention, the efficiency of pipeline insulation monitoring is improved, the risks of manual intervention and misjudgment are reduced, and the safe operation of the pipeline is ensured.

Description

Technical Field

[0001] This application relates to the technical field of insulation monitoring, and more specifically, to a pipeline insulation monitoring system and method based on wireless passive sensors. Background Art

[0002] As one of the important infrastructure facilities, pipelines play a crucial role in many fields such as industrial production and energy transmission. Especially for pipelines for transporting oil, gas, etc., they operate in complex environments for a long time and are subject to multiple effects such as corrosion, wear, and environmental pressure for a long time. The insulation performance of pipelines is one of the key factors to ensure the structural safety and normal function of pipelines. As the service life of pipelines increases, the insulation materials of pipelines may age, be damaged, or have other defects. These defects not only affect the normal use of pipelines but also may pose threats to the environment and personnel safety. Therefore, pipeline insulation monitoring has become an important task to ensure the safe operation of pipeline systems.

[0003] Currently, the monitoring methods for pipeline insulation mainly rely on manual inspections, regular maintenance, and some simple physical testing methods. However, these traditional methods have many limitations. First of all, manual inspections often rely on the experience and judgment of inspectors, with certain errors and risks of missed inspections; secondly, conventional physical detection methods (such as current methods, magnetic methods, etc.) usually require shutdown for maintenance or drilling for sampling, the process is cumbersome and cannot achieve real-time monitoring, and may damage the pipeline itself. Especially in some scenarios with complex environments, hidden pipeline locations, or difficult access, the existing detection technologies are difficult to provide continuous, real-time, and efficient monitoring results. Summary of the Invention

[0004] In view of this, this application proposes a pipeline insulation monitoring system and method based on wireless passive sensors, aiming to solve the problems in current pipeline insulation monitoring that manual detection is time-consuming and laborious, monitoring is likely to cause secondary damage to pipelines, and the reliability of monitoring results is poor.

[0005] In a first aspect, the present application proposes a pipeline insulation monitoring system based on wireless passive sensors, including: a sensor assembly including a plurality of wireless passive electromagnetic sensors, wherein a rectifying antenna is provided in the wireless passive electromagnetic sensor, and the rectifying antenna is used to capture external radio frequency signals and collect a set of reflected signals; a processing unit configured to remove noise from each reflected signal in the set of reflected signals collected by the sensor assembly; a judging unit configured to compare the set of reflected signals after noise removal with a standard signal range, and judge the signal type according to the comparison result, where the signal type includes an abnormal signal, a suspected abnormal signal, and a non-abnormal signal; when the judging unit determines that the set of reflected signals is a suspected abnormal signal, the judging unit groups the set of reflected signals and obtains an abnormal factor of the set of reflected signals according to the grouped data, and determines whether the set of reflected signals is an abnormal signal according to the abnormal factor; an identifying unit configured to, when the judging unit determines that the set of reflected signals is an abnormal signal, extract abnormal data from the set of reflected signals, determine a feature vector of each abnormal data, and judge whether the abnormal data is the same defect according to the feature vector; and an early warning unit configured to determine a defect weight according to the identification result of the identifying unit and determine a pipeline insulation monitoring result according to the defect weight.

[0006] Optionally, when the judging unit compares the set of reflected signals after noise removal with the standard signal range and judges the signal type according to the comparison result, it includes: obtaining initial standard reflected data corresponding to the set of reflected signals; collecting the previous non-abnormal record corresponding to the set of reflected signals, and extracting the corresponding non-abnormal historical set of reflected signals from the previous non-abnormal record; comparing the non-abnormal historical set of reflected signals with the initial standard reflected data, and generating a standard signal range according to the numerical size relationship in the comparison result, where the standard signal range includes a left boundary value and a right boundary value; when all the reflected signals in the set of reflected signals are not within the standard signal range, determining that the set of reflected signals is an abnormal signal; when all the reflected signals in the set of reflected signals are within the standard signal range, determining that the set of reflected signals is a non-abnormal signal; and when there is at least one reflected signal within the standard signal range and at least one reflected signal not within the standard signal range in the set of reflected signals, determining that the set of reflected signals is a suspected abnormal signal.

[0007] Optionally, when the judging unit groups the set of reflected signals, obtains an abnormal factor of the set of reflected signals according to the grouped data, and determines whether the set of reflected signals is an abnormal signal according to the abnormal factor, it includes: listing the reflected signals in the set of reflected signals that are greater than the right boundary of the standard signal range in a first data group; listing the reflected signals in the set of reflected signals that are within the standard signal range in a second data group; listing the reflected signals in the set of reflected signals that are less than the left boundary of the standard signal range in a third data group; and obtaining an abnormal factor according to the first data group, the second data group, and the third data group;

[0008]

[0009] Wherein, Y represents the anomaly factor, E1 represents the average reflection amplitude of the reflection signals in the first data set, E2 represents the average reflection amplitude of the reflection signals in the second data set, E3 represents the average reflection amplitude of the reflection signals in the third data set, n1 represents the number of reflection signals in the first data set, n2 represents the number of reflection signals in the second data set, and n3 represents the number of reflection signals in the third data set;

[0010] When the anomaly factor is greater than the anomaly factor threshold, it is determined that the reflection signal set is an abnormal signal; when the anomaly factor is less than or equal to the anomaly factor threshold, it is determined that the reflection signal set is a non-abnormal signal.

[0011] Optionally, the pipeline insulation monitoring system based on the wireless passive sensor further includes: an acquisition unit configured to acquire pipeline information and determine the scanning operation speed of the sensor assembly according to the pipeline information, where the pipeline information includes the pipeline diameter, the pipeline usage duration, the external environment temperature of the pipeline, and the external environment humidity of the pipeline.

[0012] Optionally, when the acquisition unit determines the scanning operation speed of the sensor assembly according to the pipeline information, it includes:

[0013]

[0014] Wherein, V represents the scanning operation speed, V0 represents the basic scanning operation speed, D0 represents the reference pipeline diameter, D represents the pipeline diameter to be monitored, T0 represents the suitable temperature of the pipeline, H0 represents the suitable humidity of the pipeline, L0 represents the reference usage duration of the pipeline, T represents the external environment temperature of the pipeline, H represents the external environment humidity of the pipeline, and L represents the usage duration of the pipeline.

[0015] Optionally, when the processing unit performs noise rejection on each reflection signal in the reflection signal set, it includes: performing discrete wavelet transform using the multi-wavelet Daubechies 4, decomposing the reflection signal into 4 layers of wavelet decomposition to obtain approximation coefficients and detail coefficients: using the soft threshold method to perform threshold denoising on the detail coefficients, and setting the threshold to 2 times the standard deviation of the signal noise; using the denoised coefficients to perform inverse wavelet transform to reconstruct the denoised signal and obtain the reflection signal after noise rejection.

[0016] Optionally, when the recognition unit extracts abnormal data from the reflected signal set, determines the feature vector of each abnormal data, and determines whether the abnormal data is the same defect according to the feature vector, it includes: taking the data that is not within the standard signal range in the reflected signal set as abnormal data, determining the feature vector of each abnormal data, where the feature vector includes the reflection frequency, reflection amplitude, and reflection duration of each abnormal data; performing standard score Z-score normalization processing on the feature vector; determining the initial neighborhood radius through the k-distance graph, and determining the minimum point number threshold MinPts to be 6; scanning all points, and determining the points with the number of points in the neighborhood greater than or equal to MinPts as core points; starting from each core point, checking the points in the neighborhood of the core point; if the points in the neighborhood of the core point are core points, continue to expand the cluster; if the points in the neighborhood of the core point are border points, add the border points to the current cluster; if a point is not in the neighborhood of the core point and does not form a cluster with other points, it is marked as a noise point; when the number of core points is 1, it is determined that the abnormal data is the same defect.

[0017] Optionally, the pipeline insulation monitoring result includes insulation defect assessment; when the early warning unit determines the defect weight according to the recognition result of the recognition unit and determines the pipeline insulation monitoring result according to the defect weight, it includes: when the abnormal data is the same defect, determining the defect weight to be 1; when the abnormal data is different defects, determining the defect weight of each defect based on the location importance model; the insulation defect assessment is obtained by the following formula:

[0018]

[0019] where Q represents the insulation defect assessment, Eij represents the reflection amplitude of the j-th abnormal data in the i-th defect, Ai represents the defect weight of the i-th defect, n represents the number of defect types, and m represents the number of abnormal data in the i-th defect.

[0020] Optionally, the early warning unit is further configured to: determine the difference between the insulation defect assessment and the assessment threshold as the assessment difference; determine the early warning level according to the assessment difference, and the early warning level is inversely proportional to the assessment difference.

[0021] Second aspect, a pipeline insulation monitoring method based on a wireless passive sensor is provided, including: based on the set of reflected signals collected by the sensor assembly, removing noise from each reflected signal in the set of reflected signals; the sensor assembly includes a plurality of wireless passive electromagnetic sensors, and a rectifying antenna is arranged in the wireless passive electromagnetic sensor, and the rectifying antenna is used to capture external radio frequency signals and collect the set of reflected signals; comparing the set of reflected signals after noise removal with a standard signal range, and judging the signal type according to the comparison result, and the signal type includes an abnormal signal, a suspected abnormal signal and a non-abnormal signal; when the set of reflected signals is a suspected abnormal signal, grouping the set of reflected signals, and obtaining an abnormal factor of the set of reflected signals according to the grouped data, and judging whether the set of reflected signals is an abnormal signal according to the abnormal factor; when the set of reflected signals is an abnormal signal, extracting abnormal data of the set of reflected signals, determining a feature vector of each abnormal data, and judging a defect identification result of the abnormal data according to the feature vector; the defect identification result includes: whether the abnormal data is the same defect; determining a defect weight according to the defect identification result, and determining a pipeline insulation monitoring result according to the defect weight.

[0022] Third aspect, a pipeline insulation monitoring device based on a wireless passive sensor is provided, including a memory and a processor; the memory is used to store computer execution instructions, and the processor is connected to the memory through a bus; when the pipeline insulation monitoring device based on a wireless passive sensor runs, the processor executes the computer execution instructions stored in the memory, so that the pipeline insulation monitoring device based on a wireless passive sensor executes the pipeline insulation monitoring method described in the second aspect.

[0023] The pipeline insulation monitoring device based on a wireless passive sensor can be a network device or a part of a device in the network device, such as a chip system in the network device. The chip system is used to support the network device to implement the functions involved in the first aspect and any one of its possible implementation manners. For example, obtaining, determining, and sending the data and / or information involved in the pipeline insulation monitoring method based on a wireless passive sensor described above. The chip system includes a chip, and may also include other discrete devices or circuit structures.

[0024] Fourth aspect, a computer-readable storage medium is provided, and the computer-readable storage medium includes computer execution instructions. When the computer execution instructions run on a computer, the computer executes the pipeline insulation monitoring method described in the second aspect.

[0025] In a fifth aspect, a computer program product is further provided. The computer program product includes computer instructions which, when running on a pipeline insulation monitoring device based on a wireless passive sensor, cause the pipeline insulation monitoring device based on the wireless passive sensor to execute the pipeline insulation monitoring method based on the wireless passive sensor as described in the second aspect above.

[0026] It should be noted that the above computer instructions may be stored in whole or in part on a computer-readable storage medium. Among them, the computer-readable storage medium may be packaged together with the processor of the pipeline insulation monitoring device based on the wireless passive sensor, or may be separately packaged from the processor of the pipeline insulation monitoring device based on the wireless passive sensor. The embodiments of the present application do not limit this.

[0027] For the descriptions of the second aspect, the third aspect, the fourth aspect, and the fifth aspect in the present application, reference may be made to the detailed description of the first aspect.

[0028] In the embodiments of the present application, the name of the above pipeline insulation monitoring device based on the wireless passive sensor does not limit the device or the functional module itself. In actual implementation, these devices or functional modules may appear under other names. For example, the receiving unit may also be called a receiving module, a receiver, etc. As long as the functions of each device or functional module are similar to those of the present application and fall within the scope of the claims of the present application and their equivalent technologies.

[0029] The present application provides a pipeline insulation monitoring system and method through wireless passive sensors, which solves the limitations in traditional monitoring methods. The wireless passive electromagnetic sensor captures and reflects signals using an external radio frequency signal for acquisition, and can continuously monitor the insulation state of the pipeline without contacting the pipeline, avoiding the complexity and potential risks of shutdown and drilling for sampling in traditional detection methods. Through the processing unit, noise elimination, abnormal signal determination, and defect grouping analysis are performed on the reflected signals, improving the accuracy and precision of detection. Especially in the judgment of signal types and the analysis of abnormal data feature vectors, through defect identification and evaluation, a reliable basis is provided for the real-time monitoring and early warning of the pipeline insulation condition. The efficiency of pipeline insulation monitoring is improved, the risk of manual intervention and misjudgment is reduced, and the safe operation of the pipeline is ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to limit the present application. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0031] Figure 1Block diagram of a pipeline insulation monitoring system based on a wireless passive sensor provided by an embodiment of the present application;

[0032] Figure 2 Flow block diagram of a pipeline insulation monitoring method based on a wireless passive sensor provided by an embodiment of the present application;

[0033] Figure 3 Block diagram of a pipeline insulation monitoring device based on a wireless passive sensor provided by an embodiment of the present application. Detailed implementation manners

[0034] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. Hereinafter, the present application will be described in detail with reference to the drawings and in conjunction with the embodiments.

[0035] In some embodiments of the present application, referring to Figure 1 as shown, a pipeline insulation monitoring system based on a wireless passive sensor includes: a sensor assembly, a processing unit, a judgment unit, an identification unit, and an early warning unit, wherein,

[0036] The sensor assembly includes a plurality of wireless passive electromagnetic sensors, and a rectifying antenna is arranged in the wireless passive electromagnetic sensor. The rectifying antenna is used to capture external radio frequency signals and collect a set of reflected signals.

[0037] The processing unit is configured to perform noise removal on each reflected signal in the set of reflected signals based on the set of reflected signals collected by the sensor assembly.

[0038] The judgment unit is configured to compare the set of reflected signals after noise removal with a standard signal range, and judge the signal type according to the comparison result. The signal types include abnormal signals, suspected abnormal signals, and non-abnormal signals. When the judgment unit determines that the set of reflected signals is a suspected abnormal signal, the judgment unit groups the set of reflected signals, and obtains an abnormal factor of the set of reflected signals according to the grouped data, and determines whether the set of reflected signals is an abnormal signal according to the abnormal factor.

[0039] The identification unit is configured to, when the judgment unit determines that the set of reflected signals is an abnormal signal, the identification unit extracts abnormal data from the set of reflected signals, determines a feature vector of each abnormal data, and judges whether the abnormal data is the same defect according to the feature vector.

[0040] The warning unit is configured to determine the defect weight according to the recognition result of the recognition unit, and determine the pipeline insulation monitoring result according to the defect weight. That is, the defect weight is determined according to the recognition result of the recognition unit to obtain the insulation defect assessment, and a warning is issued according to the insulation defect assessment.

[0041] Optionally, the pipeline insulation monitoring system based on wireless passive sensors further includes: an acquisition unit configured to acquire pipeline information and determine the scanning operation speed of the sensor assembly according to the pipeline information, where the pipeline information includes the pipeline diameter (which can also be referred to as the pipeline size), the pipeline usage duration (which can also be referred to as the service life), the external environment temperature of the pipeline, and the external environment humidity of the pipeline.

[0042] Specifically, the sensor assembly consists of multiple wireless passive electromagnetic sensors. Each sensor is provided with a rectifying antenna that converts the captured radio frequency signal into electrical energy and emits an electromagnetic signal, and receives the reflected signal. The acquisition unit acquires the relevant information of the pipeline, including the size of the pipeline, the service life, the external environment temperature and humidity, etc. The scanning speed of the sensor is dynamically adjusted according to these factors to ensure the accuracy of the monitoring data. The scanning speed is the speed at which the sensor assembly moves along the pipeline diameter direction. The processing unit removes noise from the reflected signals collected by the sensor assembly. Since the sensors form a wrapped form around the pipeline periphery, there is signal interference between multiple sensors. These interferences are removed through signal processing (such as filtering, denoising, etc.) to ensure the purity of a single reflected signal. The judgment unit analyzes the set of reflected signals after noise removal by comparing with the standard signal range to judge the signal type. The signal types include abnormal signals, suspected abnormal signals, and non-abnormal signals. If a signal is determined to be a suspected abnormal signal, the judgment unit will further analyze these signals, group them, and calculate the abnormal factor. According to the calculation result of the abnormal factor, it is judged whether the signal is an abnormal signal. After the judgment unit determines the abnormal signal, the recognition unit extracts the abnormal data from the set of reflected signals and calculates the feature vector for each abnormal data. The feature vector includes parameters such as the reflection frequency, amplitude, and duration of the signal. Through these feature vectors, it is analyzed and judged whether the abnormal signals are caused by the same defect. If multiple abnormal signals have similar feature vectors, it can be inferred that they are caused by the same defect. The warning unit further analyzes the severity of the defect through the recognition result output by the recognition unit and issues a warning according to the evaluation value of the defect.

[0043] It is understandable that the insulation state of the pipeline is collected in real time, and the reflected signals are dynamically adjusted and processed to ensure that abnormal signals can be captured in a timely manner, avoiding the lag of traditional manual inspection and regular maintenance methods. Through intelligent processing such as noise removal, signal classification, and abnormal factor calculation of the reflected signals, the accuracy of signal analysis is improved, and the possibility of misjudgment and missed judgment is reduced. Through feature vector extraction and analysis, it is accurately determined whether the abnormal signals originate from the same defect, and the nature of the defect is classified, providing effective guidance for subsequent pipeline maintenance and repair. Through pipeline insulation monitoring and early warning, an early warning is issued in a timely manner when there is an insulation problem in the pipeline, effectively reducing the risk of pipeline failures caused by insulation defects, thereby ensuring the safe and stable operation of the pipeline system. The use of wireless passive sensors enables pipeline monitoring in complex, concealed, or inaccessible environments, avoiding contact problems in traditional methods and improving the flexibility and comprehensiveness of monitoring.

[0044] In some embodiments of the present application, when the acquisition unit determines the scanning operation speed of the sensor assembly according to pipeline information, it includes:

[0045]

[0046] Wherein, V represents the scanning operation speed, V0 represents the basic scanning operation speed, D0 represents the reference pipeline diameter, D represents the diameter of the pipeline to be monitored, T0 represents the suitable temperature of the pipeline, H0 represents the suitable humidity of the pipeline, L0 represents the reference service life of the pipeline (i.e., the reference service life of the pipeline), T represents the external environment temperature of the pipeline, H represents the external environment humidity of the pipeline, and L represents the service life of the pipeline (i.e., the service life of the pipeline to be monitored).

[0047] It is understandable that by real-time sensing and evaluating the external environment of the pipeline, the scanning operation speed of the sensor assembly is dynamically adjusted. The scanning speed of the sensor directly affects the acquisition accuracy of signals and the real-time performance of data processing. Especially under different pipeline conditions, factors such as temperature, humidity, and pipeline diameter will cause changes in the electromagnetic wave propagation characteristics, thereby affecting the quality of the reflected signals. By adjusting the scanning speed according to parameters such as the size, environmental temperature and humidity, and service life of the pipeline, it can better adapt to different environmental conditions and improve the accuracy of monitoring. Considering the influence of external environmental factors (such as temperature, humidity, etc.) on signal transmission, the scanning speed is adjusted in real time to cope with environmental changes and reduce signal errors or losses caused by external environmental fluctuations.

[0048] In some embodiments of the present application, when the processing unit performs noise removal on each reflected signal in the reflected signal set, it includes:

[0049] Perform a discrete wavelet transform using Daubechies 4 wavelets, decompose the reflected signal into 4 levels of wavelets to obtain approximation coefficients and detail coefficients: Use the soft threshold method to perform threshold denoising on the detail coefficients, and set the threshold to 2 times the standard deviation of the signal noise. Use the denoised coefficients to perform an inverse wavelet transform to reconstruct the denoised signal and obtain the reflected signal after removing the noise.

[0050] It can be understood that the different frequency components of the signal are separated to identify and remove noise. Through soft threshold denoising, the signal can be smoothed, over-denoising can be avoided, and the detail components in the signal can be retained. Through the multi-level analysis of wavelet transform, the multi-scale characteristics of the signal can be captured to better adapt to the time-varying nature of the signal.

[0051] In some embodiments of the present application, when the determination unit compares the set of reflected signals after removing noise with the standard signal range, it includes:

[0052] The determination unit obtains the initial standard reflection data corresponding to the position of the set of reflected signals.

[0053] The determination unit collects the previous non-abnormal record corresponding to the position of the set of reflected signals, and extracts the corresponding set of non-abnormal historical reflected signals from the previous non-abnormal record.

[0054] The determination unit compares the set of non-abnormal historical reflected signals with the initial standard reflection data, and generates a standard signal range according to the numerical size relationship in the comparison result, where the standard signal range includes a left boundary value and a right boundary value.

[0055] In some embodiments of the present application, when the determination unit determines the signal type according to the comparison result, it includes: When none of the reflected signals in the set of reflected signals are within the standard signal range, the determination unit determines that the set of reflected signals is an abnormal signal. When all the reflected signals in the set of reflected signals are within the standard signal range, the determination unit determines that the set of reflected signals is a non-abnormal signal. When there is at least one reflected signal in the set of reflected signals that is within the standard signal range and at least one reflected signal that is not within the standard signal range, it is determined that the set of reflected signals is a suspected abnormal signal.

[0056] That is to say, when one or more reflected signals in the set of reflected signals are within the standard signal range and one or more reflected signals are not within the standard signal range, the determination unit determines that the set of reflected signals is a suspected abnormal signal.

[0057] Specifically, the determination unit compares the set of reflected signals after removing noise with the standard signal range, obtains the initial standard reflection amplitude data corresponding to the position of the set of reflected signals by comparing the reflection amplitudes of the reflected signals, and extracts the corresponding set of non-abnormal historical reflection amplitude signals from the previous non-abnormal record to obtain the standard signal amplitude range.

[0058] It is understandable that by comparing the reflected signal with historical data and initial standard data, judgments are made based on the historical state of the pipeline, reducing the possibility of misjudgment. Using the previous non-abnormal record as a reference, the standard signal range is dynamically adjusted according to the historical data of the pipeline operation status to adapt to changes under different pipeline states. The reflected signal is compared with the standard signal range in real time, and a response is made in a timely manner at the early stage when the pipeline shows abnormalities, thereby improving the response speed of the pipeline monitoring system. Through a detailed comparison mechanism, abnormal signals, non-abnormal signals, and suspected abnormal signals are effectively distinguished, thereby helping to further identify and locate the severity of pipeline defects and avoiding missed judgments and misjudgments.

[0059] In some embodiments of the present application, when the judgment unit groups the reflected signal set and obtains the abnormal factor of the reflected signal set based on the grouped data, it includes: The judgment unit includes the reflected signals in the reflected signal set that are greater than the right boundary of the standard signal range in the first data group. The judgment unit includes the reflected signals in the reflected signal set that are within the standard signal range in the second data group. The judgment unit includes the reflected signals in the reflected signal set that are less than the left boundary of the standard signal range in the third data group.

[0060] An abnormal factor is obtained based on the first data group, the second data group, and the third data group.

[0061]

[0062] Wherein, Y represents the abnormal factor, E1 represents the average reflection amplitude of the reflected signals in the first data group, E2 represents the average reflection amplitude of the reflected signals in the second data group, E3 represents the average reflection amplitude of the reflected signals in the third data group, n1 represents the number of reflected signals in the first data group, n2 represents the number of reflected signals in the second data group, and n3 represents the number of reflected signals in the third data group.

[0063] In some embodiments of the present application, when the judgment unit determines whether the reflected signal set is an abnormal signal according to the abnormal factor, it includes: The judgment unit compares the abnormal factor with the abnormal factor threshold, and determines whether the reflected signal set is an abnormal signal according to the comparison result.

[0064] Specifically, when the abnormal factor is greater than the abnormal factor threshold, the judgment unit determines that the reflected signal set is an abnormal signal. When the abnormal factor is less than or equal to the abnormal factor threshold, the judgment unit determines that the reflected signal set is a non-abnormal signal.

[0065] Specifically, the first data set contains reflected signals with values greater than the right boundary of the standard signal range. These signals indicate excessive reflections occurring locally in the pipeline, which are caused by increased reflections due to pipeline damage or severe aging of the insulation layer. The second data set contains reflected signals with values within the standard signal range, which reflect the normal reflection characteristics of the pipeline, meaning that the insulation performance of the pipeline is in a normal state. The third data set contains reflected signals with values less than the left boundary of the standard signal range. These signals reflect pipeline damage or partial absence of the insulation layer, resulting in smaller reflected signals. When the anomaly factor Y is greater than the anomaly factor threshold, the reflected signal set is determined to be an abnormal signal, indicating that there are relatively serious insulation defects in the pipeline and subsequent inspections or maintenance are required. When the anomaly factor Y is less than or equal to the anomaly factor threshold, the reflected signal set is determined to be a non-abnormal signal, indicating that the state of the pipeline insulation layer is normal and the signal fluctuations are within a reasonable range.

[0066] It can be understood that by dividing the reflected signals into three groups and calculating based on the reflection intensity of each group, the reflected signals can be analyzed more precisely, avoiding misjudgments that may be caused by a single signal range. The method of calculating the anomaly factor by grouping can more carefully identify the damage degree of different parts of the pipeline. It can not only capture anomalies with overly strong signals (which may be damage or aging), but also identify anomalies with overly weak signals (which may be local insulation failure). Based on the comparison mechanism of the anomaly factor threshold, it can quickly respond to the state of the pipeline during real-time monitoring, timely detect potential insulation defects, and avoid the expansion of problems. The setting of the anomaly factor threshold can be adjusted according to the characteristics of different pipelines and operating environments, achieving adaptation to various pipeline monitoring requirements.

[0067] In some embodiments of the present application, when the recognition unit extracts abnormal data from the reflected signal set, determines the feature vector of each abnormal data, and determines whether the abnormal data is the same defect according to the feature vector, it includes: the recognition unit uses the data that is not within the standard signal range in the reflected signal set as abnormal data, determines the feature vector of each abnormal data, and the feature vector includes the reflection frequency, reflection amplitude, and reflection duration of each abnormal data.

[0068] Perform standard score (Z-score) normalization processing on the feature vector.

[0069] Determine the initial neighborhood radius through the k-distance graph and determine the minimum number of points threshold (MinPts) to be 6.

[0070] Scan all points and determine that the points with the number of points in the neighborhood greater than or equal to MinPts are core points.

[0071] Starting from each core point, check the points within the neighborhood of the core point; if the points in the neighborhood of the core point are core points, continue to expand the cluster; if the points in the neighborhood of the core point are border points, add the border points to the current cluster; if a point is not within the neighborhood of a core point and does not form a cluster with other points, it is marked as a noise point; when the core point is 1, determine that the abnormal data is the same defect.

[0072] That is to say, starting from each core point, check the points within its neighborhood. If the points in the neighborhood are core points, continue to expand the cluster. If the points in the neighborhood are border points, add them to the current cluster. If a point is not within the neighborhood of any core point and cannot form a cluster with other points, it is marked as a noise point.

[0073] When the core point is 1, the recognition unit determines that the abnormal data is the same defect.

[0074] In some embodiments of the present application, the pipeline insulation monitoring result includes insulation defect evaluation; when the early warning unit determines the defect weight according to the recognition result of the recognition unit and determines the pipeline insulation monitoring result according to the defect weight, it includes: when the recognition unit determines that the abnormal data is the same defect, the early warning unit determines that the defect weight is 1. When the recognition unit determines that the abnormal data is different defects, the early warning unit determines the defect weight of each defect based on the position importance model.

[0075] The insulation defect evaluation is obtained by the following formula:

[0076]

[0077] Where Q represents the insulation defect evaluation, Eij represents the reflection amplitude of the j-th abnormal data in the i-th defect, Ai represents the defect weight of the i-th defect, n represents the number of defect types, and m represents the number of abnormal data in the i-th defect.

[0078] In some embodiments of the present application, the early warning unit is further configured to:

[0079] Determine the difference between the insulation defect evaluation and the evaluation threshold as the evaluation difference; determine the early warning level according to the evaluation difference, and the early warning level is inversely proportional to the evaluation difference.

[0080] That is to say, when the early warning unit gives an early warning according to the insulation defect evaluation, it includes:

[0081] The early warning unit compares the insulation defect evaluation with the evaluation threshold to obtain the evaluation difference. The evaluation difference is the difference between the insulation defect evaluation and the evaluation threshold. The early warning unit determines the early warning level according to the evaluation difference, and the early warning level is inversely proportional to the evaluation difference.

[0082] It can be understood that the initial neighborhood radius is determined by the k-distance graph, and this radius defines the similarity range between two points. The k-distance graph helps identify local dense regions by calculating the distance from each data point to its k-th nearest neighbor. After determining the initial neighborhood radius on the k-distance graph, the DBSCAN algorithm is used for clustering data points. This algorithm determines whether a point belongs to the same cluster based on the density of the point. If the number of points within the neighborhood of a certain point is greater than or equal to MinPts (the minimum number of points threshold), then this point is regarded as a core point. If a point is within the neighborhood of a core point but does not itself constitute a core point, then it is a boundary point. Points that cannot be attributed to any core point are regarded as noise. After clustering is completed, the recognition unit checks the points in each cluster. If the points in the cluster are all manifestations of the same defect, then it is determined to be the same defect; if the points belong to different clusters, then it indicates different defects. When the recognition unit determines that the abnormal data is the same defect, the defect weight is 1. If it is determined to be different defects, the warning unit assigns a weight to each defect according to the location importance model. The location importance model assigns weights according to the defect location factors of the pipeline, and defects in key parts will have higher weights.

[0083] Specifically, the warning unit obtains historical defect data and constructs a historical data set based on the historical defect data; the warning unit samples the historical data set according to a preset ratio to obtain a training subset and a test subset. The warning unit obtains a neural network model and iteratively trains the neural network model according to the training subset, evaluates the iteratively trained neural network model according to the test subset, and obtains the location importance model.

[0084] It can be understood that through feature vector extraction and Z-score normalization processing, the scale differences of different features are eliminated to ensure that the clustering algorithm can accurately identify various types of defects in the pipeline. At the same time, the DBSCAN algorithm clusters according to density, effectively distinguishing the same defect from different defects and avoiding misjudgment. The defect assessment is comprehensively calculated based on multiple factors such as reflection amplitude and defect location, and the assessment result of the defect is adjusted in real time according to the specific situation of the pipeline, providing assessment data that better meets the actual needs. By comparing with a preset threshold, the warning level is automatically generated according to the defect assessment. The warning can not only respond efficiently to potential problems but also provide reasonable warning prompts according to the severity of the defect. It realizes real-time monitoring of the pipeline condition, quickly conducts data analysis and clustering when abnormalities are found, improves the efficiency and accuracy of pipeline monitoring, and reduces the dependence on manual detection.

[0085] In the above embodiments, the pipeline insulation monitoring system using wireless passive sensors solves the limitations in traditional monitoring methods. The wireless passive electromagnetic sensor captures and reflects external radio frequency signals to collect signals, enabling continuous monitoring of the pipeline insulation status without contacting the pipeline, avoiding the complexity and potential risks of shutdown and drilling for sampling in traditional detection methods. Through the data processing unit, noise elimination, abnormal signal determination, and defect grouping analysis are performed on the reflected signals, improving the accuracy and precision of detection. Especially in the judgment of signal types and the analysis of abnormal data feature vectors, through defect identification and evaluation, a reliable basis is provided for the real-time monitoring and early warning of the pipeline insulation status. The efficiency of pipeline insulation monitoring is improved, the risk of manual intervention and misjudgment is reduced, and the safe operation of the pipeline is ensured.

[0086] In some embodiments, as Figure 2 shown, the embodiments of the present application further provide a pipeline insulation monitoring method based on wireless passive sensors, which is applied to the Figure 1 above-mentioned pipeline insulation monitoring system based on wireless passive sensors, and includes:

[0087] S201. Based on the set of reflected signals collected by the sensor assembly, noise elimination is performed on each reflected signal in the set of reflected signals.

[0088] Among them, the sensor assembly includes a plurality of wireless passive electromagnetic sensors, and a rectifying antenna is arranged in the wireless passive electromagnetic sensor, and the rectifying antenna is used to capture external radio frequency signals and collect the set of reflected signals.

[0089] S202. Compare the set of reflected signals after noise elimination with the standard signal range, and judge the signal type according to the comparison result.

[0090] Among them, the signal types include abnormal signals, suspected abnormal signals, and non-abnormal signals.

[0091] When the set of reflected signals is a suspected abnormal signal, the set of reflected signals is grouped, and an abnormal factor of the set of reflected signals is obtained according to the grouped data, and it is judged whether the set of reflected signals is an abnormal signal according to the abnormal factor.

[0092] S203. When the set of reflected signals is an abnormal signal, extract the abnormal data of the set of reflected signals, determine the feature vector of each abnormal data, and judge the defect identification result of the abnormal data according to the feature vector.

[0093] Among them, the defect identification result includes: whether the abnormal data is the same defect.

[0094] S204. Determine the defect weight according to the defect identification result, and determine the pipeline insulation monitoring result according to the defect weight.

[0095] In some embodiments of the present application, in the above S202, the reflected signal set after removing noise is compared with the standard signal range, and the signal type is determined according to the comparison result, including:

[0096] Obtain the initial standard reflection data corresponding to the position of the reflected signal set; collect the previous non-abnormal record corresponding to the position of the reflected signal set, and extract the corresponding non-abnormal historical reflected signal set from the previous non-abnormal record; compare the non-abnormal historical reflected signal set with the initial standard reflection data, and generate a standard signal range according to the numerical size relationship in the comparison result, where the standard signal range includes a left boundary value and a right boundary value; when none of the reflected signals in the reflected signal set are within the standard signal range, determine that the reflected signal set is an abnormal signal; when all the reflected signals in the reflected signal set are within the standard signal range, determine that the reflected signal set is a non-abnormal signal; when there is at least one reflected signal in the reflected signal set that is within the standard signal range and at least one reflected signal that is not within the standard signal range, determine that the reflected signal set is a suspected abnormal signal.

[0097] In some embodiments of the present application, in the above S202, the reflected signal set is grouped, and an abnormality factor of the reflected signal set is obtained according to the grouped data, and it is determined whether the reflected signal set is an abnormal signal according to the abnormality factor, including: listing the reflected signals in the reflected signal set that are greater than the right boundary of the standard signal range into the first data group; listing the reflected signals in the reflected signal set that are within the standard signal range into the second data group; listing the reflected signals in the reflected signal set that are less than the left boundary of the standard signal range into the third data group; obtaining an abnormality factor according to the first data group, the second data group, and the third data group;

[0098]

[0099] Where Y represents the abnormality factor, E1 represents the average reflection amplitude of the reflected signals in the first data group, E2 represents the average reflection amplitude of the reflected signals in the second data group, E3 represents the average reflection amplitude of the reflected signals in the third data group, n1 represents the number of reflected signals in the first data group, n2 represents the number of reflected signals in the second data group, and n3 represents the number of reflected signals in the third data group;

[0100] When the abnormality factor is greater than the abnormality factor threshold, determine that the reflected signal set is an abnormal signal; when the abnormality factor is less than or equal to the abnormality factor threshold, determine that the reflected signal set is a non-abnormal signal.

[0101] In some embodiments of the present application, the method further includes: collecting pipeline information and determining the scanning operation speed of the sensor assembly according to the pipeline information.

[0102] Among them, the pipeline information includes the pipeline diameter, the pipeline usage duration, the external environment temperature of the pipeline, and the external environment humidity of the pipeline.

[0103] In some embodiments of the present application, the above-mentioned determining the scanning operation speed of the sensor assembly according to the pipeline information includes:

[0104]

[0105] Among them, V represents the scanning operation speed, V0 represents the basic scanning operation speed, D0 represents the reference pipeline diameter, D represents the pipeline diameter to be monitored, T0 represents the suitable temperature of the pipeline, H0 represents the suitable humidity of the pipeline, L0 represents the reference usage duration of the pipeline, T represents the external environment temperature of the pipeline, H represents the external environment humidity of the pipeline, and L represents the pipeline usage duration.

[0106] In some embodiments of the present application, in the above S201, removing noise from each reflection signal in the reflection signal set includes: performing discrete wavelet transform using Daubechies 4 wavelet, decomposing the reflection signal into 4 layers of wavelet to obtain approximation coefficients and detail coefficients; using the soft threshold method to perform threshold denoising on the detail coefficients, and setting the threshold to 2 times the standard deviation of the signal noise; using the denoised coefficients to perform inverse wavelet transform to reconstruct the denoised signal, and obtaining the reflection signal after removing noise.

[0107] In some embodiments of the present application, in the above S203, extracting abnormal data from the reflection signal set, determining the feature vector of each abnormal data, and judging the defect recognition result of the abnormal data according to the feature vector includes: taking the data that is not within the standard signal range in the reflection signal set as abnormal data, determining the feature vector of each abnormal data, and the feature vector includes the reflection frequency, reflection amplitude, and reflection duration of each abnormal data; performing Z-score standardization processing on the feature vector; determining the initial neighborhood radius through the k-distance graph, and determining MinPts as 6; scanning all points, and determining the points with the number of points in the neighborhood greater than or equal to MinPts as core points; starting from each core point, checking the points in the neighborhood of the core point; if the points in the neighborhood of the core point are core points, continue to expand the cluster; if the points in the neighborhood of the core point are boundary points, add the boundary points to the current cluster; if a point is not in the neighborhood of the core point and does not form a cluster with other points, it is marked as a noise point; when the core point is 1, it is determined that the abnormal data is the same defect.

[0108] In some embodiments of the present application, in the above S204, determining the defect weight according to the defect recognition result, and determining the pipeline insulation monitoring result according to the defect weight includes: when the abnormal data is the same defect, determining the defect weight as 1; when the abnormal data is different defects, determining the defect weight of each defect based on the position importance model; the insulation defect evaluation is calculated through the following formula:

[0109]

[0110] Among them, Q represents the insulation defect assessment, Eij represents the reflection amplitude of the j-th abnormal data in the i-th defect, Ai represents the defect weight of the i-th defect, n represents the number of defect types, and m represents the number of abnormal data in the i-th defect.

[0111] In some embodiments of the present application, the method further includes:

[0112] Determine the difference between the insulation defect assessment and the assessment threshold as the assessment difference; determine the warning level according to the assessment difference, and the warning level is inversely proportional to the assessment difference.

[0113] The above mainly introduces the solution provided by the embodiments of the present application from the perspective of the method. To implement the above functions, it includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving the hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0114] The embodiments of the present application can divide the functional modules of the pipeline insulation monitoring device based on wireless passive sensors according to the above method examples. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. Optionally, the division of modules in the embodiments of the present application is illustrative, only a logical function division, and there can be other division methods in actual implementation.

[0115] As Figure 3 shown, it is a schematic structural diagram of a pipeline insulation monitoring device based on wireless passive sensors provided by an embodiment of the present application. Figure 3 The pipeline insulation monitoring device based on wireless passive sensors shown includes: a communication unit 301 and a processing unit 302;

[0116] The communication unit 301 is used to collect a set of reflection signals based on the sensor component.

[0117] The processing unit 302 is used to remove noise from each reflection signal in the set of reflection signals collected based on the sensor component.

[0118] Among them, the sensor component includes a number of wireless passive electromagnetic sensors. A rectifying antenna is provided inside the wireless passive electromagnetic sensor, and the rectifying antenna is used to capture external radio frequency signals and collect a set of reflected signals.

[0119] The processing unit 302 is further configured to compare the set of reflected signals after removing noise with a standard signal range, and determine the signal type according to the comparison result.

[0120] Among them, the signal types include abnormal signals, suspected abnormal signals, and non-abnormal signals.

[0121] When the set of reflected signals is a suspected abnormal signal, group the set of reflected signals, obtain the abnormal factor of the set of reflected signals according to the grouped data, and determine whether the set of reflected signals is an abnormal signal according to the abnormal factor.

[0122] The processing unit 302 is further configured to, when the set of reflected signals is an abnormal signal, extract the abnormal data of the set of reflected signals, determine the feature vector of each abnormal data, and judge the defect identification result of the abnormal data according to the feature vector.

[0123] Among them, the defect identification result includes: whether the abnormal data is the same defect.

[0124] The processing unit 302 is further configured to determine the defect weight according to the defect identification result, and determine the pipeline insulation monitoring result according to the defect weight.

[0125] In some embodiments of the present application, the processing unit 302 is specifically configured to:

[0126] Obtain the initial standard reflection data corresponding to the set of reflected signals; collect the previous non-abnormal record corresponding to the set of reflected signals, and extract the corresponding non-abnormal historical reflection signal set from the previous non-abnormal record; compare the non-abnormal historical reflection signal set with the initial standard reflection data, and generate a standard signal range according to the numerical size relationship in the comparison result, where the standard signal range includes a left boundary value and a right boundary value; when all the reflected signals in the set of reflected signals are not within the standard signal range, determine that the set of reflected signals is an abnormal signal; when all the reflected signals in the set of reflected signals are within the standard signal range, determine that the set of reflected signals is a non-abnormal signal; when there is at least one reflected signal within the standard signal range and at least one reflected signal not within the standard signal range in the set of reflected signals, determine that the set of reflected signals is a suspected abnormal signal.

[0127] In some embodiments of the present application, the processing unit 302 is specifically configured to:

[0128] The reflected signals in the reflected signal set that are greater than the right boundary of the standard signal range are included in the first data set; the reflected signals in the reflected signal set that are within the standard signal range are included in the second data set; the reflected signals in the reflected signal set that are less than the left boundary of the standard signal range are included in the third data set; an anomaly factor is obtained based on the first data set, the second data set, and the third data set;

[0129]

[0130] Where Y represents the anomaly factor, E1 represents the average reflection amplitude of the reflected signals in the first data set, E2 represents the average reflection amplitude of the reflected signals in the second data set, E3 represents the average reflection amplitude of the reflected signals in the third data set, n1 represents the number of reflected signals in the first data set, n2 represents the number of reflected signals in the second data set, and n3 represents the number of reflected signals in the third data set;

[0131] When the anomaly factor is greater than the anomaly factor threshold, it is determined that the reflected signal set is an abnormal signal; when the anomaly factor is less than or equal to the anomaly factor threshold, it is determined that the reflected signal set is a non-abnormal signal.

[0132] In some embodiments of the present application, the communication unit 301 is further configured to collect pipeline information. The processing unit 302 is further configured to determine the scanning operation speed of the sensor assembly according to the pipeline information.

[0133] Where the pipeline information includes the pipeline diameter, the pipeline usage duration, the external environment temperature of the pipeline, and the external environment humidity of the pipeline.

[0134] In some embodiments of the present application, the processing unit 302 is specifically configured to:

[0135]

[0136] Where V represents the scanning operation speed, V0 represents the basic scanning operation speed, D0 represents the reference pipeline diameter, D represents the pipeline diameter to be monitored, T0 represents the suitable temperature of the pipeline, H0 represents the suitable humidity of the pipeline, L0 represents the reference usage duration of the pipeline, T represents the external environment temperature of the pipeline, H represents the external environment humidity of the pipeline, and L represents the pipeline usage duration.

[0137] In some embodiments of the present application, the processing unit 302 is specifically configured to:

[0138] Perform discrete wavelet transform using Daubechies 4 wavelet, decompose the reflected signal into 4 layers of wavelet to obtain the approximation coefficient and the detail coefficient: use the soft threshold method to perform threshold denoising on the detail coefficient, and set the threshold to 2 times the standard deviation of the signal noise; use the denoised coefficient to perform inverse wavelet transform to reconstruct the denoised signal and obtain the reflected signal after removing the noise.

[0139] In some embodiments of the present application, the processing unit 302 is specifically configured to:

[0140] Regarding the data that is not within the standard signal range in the reflected signal concentration as abnormal data, determine the feature vector of each abnormal data, where the feature vector includes the reflection frequency, reflection amplitude, and reflection duration of each abnormal data; perform Z-score normalization processing on the feature vector; determine the initial neighborhood radius through the k-distance graph, and determine that MinPts is 6; scan all points, and determine that the points with the number of points in the neighborhood greater than or equal to MinPts are core points; starting from each core point, check the points in the neighborhood of the core point; if the points in the neighborhood of the core point are core points, continue to expand the cluster; if the points in the neighborhood of the core point are border points, add the border points to the current cluster; if a point is not in the neighborhood of a core point and does not form a cluster with other points, it is marked as a noise point; when there is 1 core point, determine that the abnormal data is the same defect.

[0141] In some embodiments of the present application, the processing unit 302 is specifically configured to:

[0142] When the abnormal data is the same defect, determine that the defect weight is 1; when the abnormal data is different defects, determine the defect weight of each defect based on the position importance model; the insulation defect evaluation is obtained by calculating with the following formula:

[0143]

[0144] where Q represents the insulation defect evaluation, Eij represents the reflection amplitude of the j-th abnormal data in the i-th defect, Ai represents the defect weight of the i-th defect, n represents the number of defect types, and m represents the number of abnormal data in the i-th defect.

[0145] In some embodiments of the present application, the processing unit 302 is further configured to:

[0146] Determine the difference between the insulation defect evaluation and the evaluation threshold as the evaluation difference; determine the early warning level according to the evaluation difference, and the early warning level is inversely proportional to the evaluation difference.

[0147] The embodiments of the present application further provide a computer-readable storage medium, where the computer-readable storage medium includes computer-executable instructions. When the computer-executable instructions run on a computer, the computer is enabled to execute the pipeline insulation monitoring method based on a wireless passive sensor provided in the above embodiments.

[0148] The embodiments of the present application further provide a computer program product. The computer program product can be directly loaded into a memory and contains software code. After being loaded and executed by a computer, the computer program product can implement the pipeline insulation monitoring method based on a wireless passive sensor provided in the above embodiments. Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that they can still modify or equivalently replace the technical solutions of the present invention, and these modifications or equivalent replacements do not make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present invention.

[0149] For the system provided in the above embodiments, only the division of the above function modules is used as an example for illustration. In actual applications, the above functions can be allocated to different function modules according to needs, that is, the modules or steps in the embodiments of the present invention can be further decomposed or combined. For example, the modules in the above embodiments can be combined into one module, or further split into multiple sub-modules to complete all or part of the functions described above. For the names of the modules and steps involved in the embodiments of the present invention, they are only used to distinguish each module or step and are not regarded as an improper limitation of the present invention.

[0150] Those skilled in the art should be able to realize that the modules and method steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. The programs corresponding to the software modules and method steps can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically erasable programmable ROM, register, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field. To clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in the form of electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

Claims

1. A pipeline insulation monitoring system based on wireless passive sensors, characterized in that: include: The sensor assembly includes a plurality of wireless passive electromagnetic sensors, wherein a rectifying antenna is provided inside the wireless passive electromagnetic sensor, and the rectifying antenna is used to capture external radio frequency signals and collect reflected signal sets; a processing unit configured to perform noise removal on each reflection signal in the reflection signal set based on the reflection signal set collected by the sensor assembly; A judgment unit is configured to compare the reflection signal set after noise removal with the standard signal range, and judge the signal type according to the comparison result, wherein the signal type includes an abnormal signal, a suspected abnormal signal, and a non-abnormal signal; when the judgment unit determines that the reflection signal set is the suspected abnormal signal, the judgment unit groups the reflection signal set, obtains the abnormal factor of the reflection signal set according to the grouped data, and judges whether the reflection signal set is an abnormal signal according to the abnormal factor; an identification unit configured to extract abnormal data of the reflection signal set, determine a feature vector of each abnormal data, and determine whether the abnormal data are the same defect according to the feature vector when the determination unit determines that the reflection signal set is an abnormal signal; The early warning unit is configured to determine a defect weight according to the identification result of the identification unit, and determine a pipeline insulation monitoring result according to the defect weight.

2. The pipeline insulation monitoring system based on wireless passive sensor according to claim 1 is characterized in that: The judgment unit compares the reflected signal set after noise removal with the standard signal range, and judges the signal type according to the comparison result, including: Acquiring initial standard reflection data at a position corresponding to the reflection signal set; Collecting the last non-abnormal record at a position corresponding to the reflection signal set, and extracting the corresponding non-abnormal historical reflection signal set from the last non-abnormal record; Comparing the non-abnormal historical reflection signal set with the initial standard reflection data, and generating a standard signal range according to the numerical value relationship in the comparison result, wherein the standard signal range includes a left boundary value and a right boundary value; When none of the reflected signals in the reflected signal set is within the standard signal range, determining that the reflected signal set is the abnormal signal; When all reflected signals in the reflected signal set are within the standard signal range, determining that the reflected signal set is the non-abnormal signal; When there is at least one reflection signal in the reflection signal set that is within the standard signal range and there is at least one reflection signal that is not within the standard signal range, the reflection signal set is determined to be the suspected abnormal signal.

3. The pipeline insulation monitoring system based on wireless passive sensor according to claim 2 is characterized in that: The judging unit groups the reflection signal set, obtains an abnormality factor of the reflection signal set according to the grouped data, and judges whether the reflection signal set is an abnormal signal according to the abnormality factor, including: Adding the reflected signals in the reflected signal set that are greater than the right boundary of the standard signal range into the first data group; Adding the reflected signals in the reflected signal set that are within the standard signal range into a second data group; Adding the reflected signals in the reflected signal set that are smaller than the left boundary of the standard signal range into a third data group; Obtaining the abnormal factor according to the first data group, the second data group and the third data group; Wherein, Y represents an abnormal factor, E1 represents an average reflection amplitude of the reflection signal in the first data group, E2 represents an average reflection amplitude of the reflection signal in the second data group, E3 represents an average reflection amplitude of the reflection signal in the third data group, n1 represents the number of reflection signals in the first data group, n2 represents the number of reflection signals in the second data group, and n3 represents the number of reflection signals in the third data group; When the abnormal factor is greater than the abnormal factor threshold, the reflection signal set is determined to be an abnormal signal; when the abnormal factor is less than or equal to the abnormal factor threshold, the reflection signal set is determined to be a non-abnormal signal.

4. The pipeline insulation monitoring system based on wireless passive sensor according to claim 1 is characterized in that: Also includes: The collecting unit is configured to collect pipeline information and determine the scanning operation speed of the sensor component according to the pipeline information. The pipeline information includes pipeline diameter, pipeline usage time, ambient temperature outside the pipeline, and ambient humidity outside the pipeline.

5. The pipeline insulation monitoring system based on wireless passive sensor according to claim 4 is characterized in that: When the acquisition unit determines the scanning operation speed of the sensor component according to the pipeline information, it includes: Among them, V represents the scanning operation speed, V0 represents the basic scanning operation speed, D0 represents the reference pipeline diameter, D represents the diameter of the pipeline to be monitored, T0 represents the suitable temperature of the pipeline, H0 represents the suitable humidity of the pipeline, L0 represents the reference usage time of the pipeline, T represents the ambient temperature outside the pipeline, H represents the ambient humidity outside the pipeline, and L represents the usage time of the pipeline.

6. The pipeline insulation monitoring system based on wireless passive sensor according to claim 1 is characterized in that: When the processing unit performs noise removal on each reflected signal in the reflected signal set, it includes: Daubechies 4 wavelets are used for discrete wavelet transform, and the reflection signal is decomposed by 4 layers of wavelets to obtain approximation coefficients and detail coefficients: Using a soft threshold method, threshold denoising is performed on the detail coefficient, and the threshold is set to twice the standard deviation of the signal noise; The denoised coefficients are used to perform inverse wavelet transform, reconstruct the denoised signal, and obtain the reflected signal after noise removal.

7. The pipeline insulation monitoring system based on wireless passive sensor according to claim 1 is characterized in that: The identification unit extracts abnormal data of the reflection signal set, determines a feature vector of each abnormal data, and judges whether the abnormal data are the same defect according to the feature vector, including: Taking the data in the reflection signal set that is not within the standard signal range as abnormal data, and determining a feature vector of each of the abnormal data, wherein the feature vector includes a reflection frequency, a reflection amplitude, and a reflection duration of each of the abnormal data; Performing Z-score standardization processing on the feature vector; The initialization neighborhood radius is determined through the k-distance graph, and the minimum point count threshold MinPts is determined to be 6; Scan all points and determine the points whose number of points in the neighborhood is greater than or equal to the MinPts as core points; Starting from each core point, check the points in the neighborhood of the core point; if the point in the neighborhood of the core point is a core point, continue to expand the cluster; if the point in the neighborhood of the core point is a boundary point, add the boundary point to the current cluster; if a point is not a point in the neighborhood of the core point and does not form a cluster with other points, it is marked as a noise point; When the core point is 1, it is determined that the abnormal data are the same defect.

8. The pipeline insulation monitoring system based on wireless passive sensor according to claim 7 is characterized in that: The pipeline insulation monitoring result includes an insulation defect assessment; the early warning unit determines a defect weight according to the identification result of the identification unit, and determines the pipeline insulation monitoring result according to the defect weight, including: When the abnormal data are the same defect, the defect weight is determined to be 1; When the abnormal data are different defects, determining a defect weight of each defect based on a position importance model; The insulation defect assessment is calculated by the following formula: Wherein, Q represents insulation defect evaluation, Eij represents the reflection amplitude of the jth abnormal data in the i-th defect, Ai represents the defect weight of the i-th defect, n represents the number of defect types, and m represents the number of abnormal data in the i-th defect.

9. The pipeline insulation monitoring system based on wireless passive sensor according to claim 8 is characterized in that: The early warning unit is further configured to: Determining a difference between the insulation defect assessment and an assessment threshold as an assessment difference; A warning level is determined according to the evaluation difference, and the warning level is in inverse proportion to the evaluation difference.

10. A pipeline insulation monitoring method based on wireless passive sensor, characterized in that: include: Based on the reflection signal set collected by the sensor component, noise is removed from each reflection signal in the reflection signal set; the sensor component includes a plurality of wireless passive electromagnetic sensors, and a rectifying antenna is arranged in the wireless passive electromagnetic sensor, and the rectifying antenna is used to capture external radio frequency signals and collect the reflection signal set; Compare the reflection signal set after noise removal with the standard signal range, and judge the signal type according to the comparison result, wherein the signal type includes abnormal signal, suspected abnormal signal and non-abnormal signal; when the reflection signal set is the suspected abnormal signal, group the reflection signal set, and obtain the abnormal factor of the reflection signal set according to the grouped data, and judge whether the reflection signal set is an abnormal signal according to the abnormal factor; When the reflection signal set is an abnormal signal, extracting abnormal data of the reflection signal set, determining a feature vector of each abnormal data, and judging a defect recognition result of the abnormal data according to the feature vector; The defect identification result includes: whether the abnormal data are the same defect; A defect weight is determined according to the defect identification result, and a pipeline insulation monitoring result is determined according to the defect weight.

Images