Cable channel detection method and system based on distributed optical fiber sensing technology

Abstract

The invention provides a cable channel detection method and system based on a distributed optical fiber sensing technology, and relates to the technical field of cable detection, and the method comprises the steps: configuring a monitoring region and an uncovered region according to distribution coordinates and monitoring precision; a distributed optical fiber sensor is used for cable monitoring to establish a monitoring data set; carrying out collaborative anomaly identification on the monitoring data set, and establishing a first anomaly identification result; inputting the monitoring data set into a distance-temperature interpolation prediction network, executing interpolation prediction of an uncovered area, performing fault risk prediction by using an interpolation prediction result, and establishing a second anomaly identification result; and after carrying out anomaly fusion on the first anomaly identification result and the second anomaly identification result, reporting that the cable is abnormal. According to the invention, the technical problems that a monitoring blind area exists and an uncovered area cannot be effectively detected due to the fact that a traditional detection method cannot comprehensively cover all monitoring areas can be solved, the problem of the monitoring blind area can be effectively eliminated, and all-area and blind-spot-free abnormal monitoring and fault early warning are realized.

Description

Technical Field

[0001] The present application relates to the field of cable detection technology, and in particular to a cable channel detection method and system based on distributed optical fiber sensing technology. Background Art

[0002] Distributed fiber optic sensing technology has been widely used in the field of cable monitoring in recent years. This technology uses optical fiber as a sensing medium and utilizes the scattering effects inside the optical fiber (such as Rayleigh scattering, Brillouin scattering, etc.) to achieve continuous monitoring of the cable channel. Compared with traditional point sensors, distributed fiber optic sensing technology has higher spatial resolution and real-time monitoring capabilities, and can obtain temperature, stress, vibration and other information over long distances, providing more comprehensive monitoring coverage.

[0003] However, although distributed fiber optic sensing technology can provide a wide monitoring range, it still faces some challenges in actual application scenarios, especially in cable systems. Some areas may have blind spots that cannot be effectively monitored due to improper sensor deployment, environmental influences, or equipment configuration. These monitoring blind spots may have potential fault hazards. If not discovered in time, it will cause equipment damage or shutdown, thereby increasing operation and maintenance costs and the risk of system failure. Summary of the invention

[0004] The purpose of this application is to provide a cable channel detection method and system based on distributed optical fiber sensing technology, so as to solve the technical problem that the traditional cable channel detection method based on distributed optical fiber sensing technology fails to fully cover all monitoring areas, resulting in the existence of monitoring blind spots and the inability to effectively detect uncovered areas.

[0005] In view of the above problems, the present application provides a cable channel detection method and system based on distributed optical fiber sensing technology.

[0006] In the first aspect, the present application provides a cable channel detection method based on distributed optical fiber sensing technology, which is implemented by a cable channel detection system based on distributed optical fiber sensing technology, including: obtaining the distribution coordinates of the distributed optical fiber sensor, and configuring the monitoring area and the uncovered area according to the distribution coordinates and the monitoring accuracy; using the distributed optical fiber sensor to perform cable monitoring and establish a monitoring data set, wherein the monitoring data set includes temperature data, vibration data, and stress data, and the monitoring data set has a monitoring location identifier; using a fault identification channel to perform collaborative anomaly identification of the monitoring data set and establish a first anomaly identification result; inputting the monitoring data set into a distance-temperature interpolation prediction network, performing interpolation prediction of the uncovered area, and establishing an interpolation prediction result; using the interpolation prediction result to predict fault risk and establish a second anomaly identification result; after anomaly fusion of the first anomaly identification result and the second anomaly identification result, reporting a cable anomaly.

[0007] Optionally, the cable channel detection method based on distributed optical fiber sensing technology further includes: using the dynamic weight optimization hierarchy of the distance-temperature interpolation prediction network to perform dynamic weight calculation of interpolation points based on distance and temperature, as follows: ;in, Characterization based on known points Predicted unknown points The dynamic weight of Characterizing unknown points With known points The distance Characterization The location of the point, Characterizes the spatial distance smoothing parameter, is the distance exponential factor, Characterizing known points The temperature, Characterizes the average temperature of known points within the neighborhood window, is the smoothing parameter of the temperature difference, is the total number of known points, is the index of any known point; interpolation prediction based on the monitoring data set is performed according to the dynamic weight calculation result of the interpolation point: ;in, is the interpolation prediction feature, For the The feature vectors of known points, , is the stress characteristic value, is the vibration characteristic value.

[0008] Optionally, the cable channel detection method based on distributed optical fiber sensing technology further includes: performing fault risk prediction through a fault probability prediction model as follows: ;in, Characterizing unknown points The probability of failure, Characterize the interpolation prediction characteristic mode, is the modulus normalization parameter, Characterizing interpolation prediction features and their neighborhood average features The inner product of is the inner product normalization parameter, Represents historical changes, Normalize the parameters for historical changes; according to the unknown points The failure probability generates a second abnormality identification result.

[0009] Optionally, the cable channel detection method based on distributed fiber optic sensing technology also includes: after classifying the monitoring data set based on the monitoring location identifier and the acquisition time of the monitoring data set through the preprocessing layer in the fault identification channel, performing outlier extraction to establish a preprocessing data set; using the feature extraction layer in the fault identification channel to extract the change rate, peak value, and window abnormality features of the preprocessing data set to establish a feature extraction data set; performing feature space correlation analysis based on the feature extraction data set through the spatial collaborative analysis layer to establish a first collaborative abnormality identification result; performing feature time correlation analysis based on the feature extraction data set through the time collaborative analysis layer to establish a second collaborative abnormality identification result; after fusing the first collaborative abnormality identification result and the second collaborative abnormality identification result, outputting the first abnormality identification result.

[0010] Optionally, the cable channel detection method based on distributed fiber optic sensing technology also includes: obtaining an abnormality fusion result, and obtaining an abnormality type, abnormality position and abnormal value information based on the abnormality fusion result; obtaining the current working parameters of the cable, and generating first auxiliary verification information based on the working parameters; obtaining the location environment information of the cable, and generating second auxiliary verification information according to the location environment information; using the abnormality type, the abnormal position, the abnormal value information, the first auxiliary verification information, and the second auxiliary verification information to identify the abnormality trigger level; and using the abnormality trigger level identification result to report the cable abnormality.

[0011] Optionally, the cable channel detection method based on distributed optical fiber sensing technology also includes: obtaining model information and usage information of the distributed optical fiber sensor; identifying accuracy loss based on the model information and the usage information, and establishing an accuracy loss identification result; reconstructing monitoring accuracy based on the accuracy loss identification result and the model information, and using the reconstructed monitoring accuracy to configure monitoring areas and uncovered areas.

[0012] Optionally, the cable channel detection method based on distributed optical fiber sensing technology also includes: establishing a cumulative weighted coefficient of anomalies; when a cable at any position is abnormal and has not been repaired, accumulating the cable anomalies according to the cumulative weighted coefficient and establishing a cumulative result; and managing the cable anomalies according to the cumulative result.

[0013] In the second aspect, the present application also provides a cable channel detection system based on distributed optical fiber sensing technology, which is used to execute a cable channel detection method based on distributed optical fiber sensing technology as described in the first aspect, including: an area configuration module, which is used to obtain the distribution coordinates of the distributed optical fiber sensor, and configure the monitoring area and the uncovered area according to the distribution coordinates and the monitoring accuracy; a monitoring data establishment module, which is used to use the distributed optical fiber sensor to monitor the cable and establish a monitoring data set, wherein the monitoring data set includes temperature data, vibration data, and stress data, and the monitoring data set is marked with a monitoring location; a first abnormality identification module, which is used to use the fault identification channel to perform collaborative abnormality identification of the monitoring data set and establish a first abnormality identification result; an interpolation prediction module, which is used to input the monitoring data set into a distance-temperature interpolation prediction network, perform interpolation prediction of the uncovered area, and establish an interpolation prediction result; a second abnormality identification module, which is used to use the interpolation prediction result to predict the fault risk and establish a second abnormality identification result; an abnormality fusion module, which is used to perform abnormal fusion on the first abnormality identification result and the second abnormality identification result, and then report the cable abnormality.

[0014] One or more technical solutions provided in this application have at least the following technical effects or advantages: By acquiring the distribution coordinates of the distributed optical fiber sensor, the monitoring area and the uncovered area are configured according to the distribution coordinates and the monitoring accuracy; then the distributed optical fiber sensor is used to monitor the cable and a monitoring data set is established, wherein the monitoring data set includes temperature data, vibration data, and stress data, and the monitoring data set has a monitoring location identifier; then the fault identification channel is used to perform collaborative abnormality identification of the monitoring data set and establish a first abnormality identification result; on the other hand, the monitoring data set is input into the distance-temperature interpolation prediction network, and the interpolation prediction of the uncovered area is performed to establish an interpolation prediction result; the interpolation prediction result is further used to predict the fault risk and establish a second abnormality identification result; finally, the first abnormality identification result and the second abnormality identification result are abnormally fused and the cable abnormality is reported; the problem of monitoring blind spots in cable channel detection can be effectively eliminated, and potential abnormalities in uncovered areas can be discovered in a timely manner, thereby achieving abnormal monitoring and fault warning in the entire area without blind spots, and ensuring the safe and stable operation of cable equipment.

[0015] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0017] Figure 1 A schematic diagram of a process of a cable channel detection method based on distributed optical fiber sensing technology for this application; Figure 2 A schematic diagram of a process for establishing a first abnormality identification result in a cable channel detection method based on distributed optical fiber sensing technology in the present application; Figure 3 This is a structural schematic diagram of a cable channel detection system based on distributed optical fiber sensing technology for this application.

[0018] Description of reference numerals: Area configuration module 01, monitoring data establishment module 02, first anomaly identification module 03, interpolation prediction module 04, second anomaly identification module 05, anomaly fusion module 06. DETAILED DESCRIPTION

[0019] The present application provides a cable channel detection method and system based on distributed optical fiber sensing technology, which solves the technical problem that the traditional cable channel detection method based on distributed optical fiber sensing technology fails to fully cover all monitoring areas, resulting in the existence of monitoring blind spots and inability to effectively detect uncovered areas. It can effectively eliminate the monitoring blind spot problem in cable channel detection and promptly discover potential abnormalities in uncovered areas, thereby realizing full-area, blind-spot-free abnormal monitoring and fault warning, ensuring the safe and stable operation of cable equipment.

[0020] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0021] For example, please refer to the attached Figure 1 The present application provides a cable channel detection method based on distributed optical fiber sensing technology, which is applied to a cable channel detection system based on distributed optical fiber sensing technology, and specifically includes the following steps: S100: Obtain distribution coordinates of distributed optical fiber sensors, and configure monitoring areas and uncovered areas according to the distribution coordinates and monitoring accuracy.

[0022] Furthermore, step S100 of the present application also includes: S110: Acquire the model information and usage information of the distributed optical fiber sensor; S120: Identify the accuracy loss according to the model information and the usage information, and establish an accuracy loss identification result; S130: Reconstruct the monitoring accuracy based on the accuracy loss identification result and the model information, and use the reconstructed monitoring accuracy to configure the monitoring area and the uncovered area.

[0023] Specifically, first, the model information, usage information and location coordinates of all distributed optical fiber sensors in the distributed optical fiber sensor are obtained, wherein the model information includes the sensor type, sensitivity range, measurement accuracy, applicable environment, etc., which are helpful to understand the performance and applicable scope of the sensor; the usage information includes the installation time, working environment (such as temperature, humidity, electromagnetic interference, etc.), whether it has been calibrated, whether it has been maintained, etc., which can reflect the actual use of the sensor and the change of sensing accuracy; the distribution coordinates refer to the spatial position coordinates of the sensor, indicating its specific position in the cable channel or equipment. Through these coordinates, the monitoring coverage area of ​​the sensor can be clarified, and data support can be provided for subsequent regional configuration.

[0024] Next, the accuracy loss is identified based on the model information and the usage information, that is, based on the model information and usage information of the sensor, the factors that may cause the accuracy loss are analyzed, such as the aging of the optical fiber caused by long-term use, the impact of temperature changes on sensor performance, and the long-term non-maintenance of the equipment. Based on these factors, statistical methods or machine learning algorithms are used to identify sensors with accuracy loss and the degree of impact. For example, according to the usage of the sensor, key features that may affect the accuracy loss (such as usage time, temperature fluctuations, environmental interference, sensor model, etc.) are selected, and then the regression analysis method is used to train the regression model in combination with historical data or experimental data, and the trained regression model is used to predict the accuracy loss of each sensor. The model will output the corresponding accuracy loss value according to the input features (such as the working environment of the sensor, the length of use, etc.), and establish the accuracy loss identification result. Through regression analysis, a quantitative evaluation of the accuracy loss can be provided for each sensor, and the monitoring accuracy of which sensors has changed can be understood in real time, providing a basis for optimizing the configuration of the monitoring area.

[0025] Then, the monitoring accuracy of each sensor is reconstructed according to the accuracy loss identification result and the model information, wherein each distributed optical fiber sensor sets an initial monitoring accuracy when it is installed. This accuracy is usually provided by the manufacturer of the sensor and is obtained based on its specifications and test results. The initial monitoring accuracy is usually the accuracy value under ideal conditions, indicating the optimal accuracy that the sensor can achieve without any external interference; then, the initial monitoring accuracy of each sensor is subtracted from the accuracy loss identification result to obtain the actual monitoring accuracy. The reconstructed actual monitoring accuracy reflects the accuracy of the sensor in the actual working environment. The monitoring area and the uncovered area are further configured using the reconstructed actual monitoring accuracy and the distributed coordinates of the distributed optical fiber sensor. First, according to the actual monitoring accuracy of each sensor, the range of its effective monitoring area is calculated. The higher the accuracy, the larger the area that the sensor can monitor. For example, a sensor with a smaller accuracy loss can monitor a larger cable area, while a sensor with a larger accuracy loss may only be suitable for monitoring a smaller area; then, based on the accuracy and distribution coordinates of the sensor, the circular or polygonal monitoring area of ​​each sensor is calculated. For example, if the monitoring accuracy of the sensor is r, the monitoring area of ​​the sensor is a circular area with a radius of r and a sensor position as the center. On the other hand, by calculating the monitoring areas of all sensors and combining them with the global layout of the cable channel, areas that are not monitored by any sensor are identified, called uncovered areas. Uncovered areas are usually blind spots in the cable channel or areas with low sensor accuracy, which cannot be effectively detected by existing sensors.

[0026] By configuring the monitoring area and uncovered area in combination with the actual monitoring accuracy of the distributed optical fiber sensor, the monitoring blind area can be effectively identified and support can be provided for the effective detection of subsequent monitoring blind areas.

[0027] S200: Use the distributed optical fiber sensor to perform cable monitoring and establish a monitoring data set, where the monitoring data set includes temperature data, vibration data, and stress data, and the monitoring data set carries a monitoring location identifier.

[0028] Specifically, distributed fiber optic sensors are deployed along the cable line. These sensors can monitor the entire cable in real time and transmit the collected raw data to the central processing system in real time through the sensor network or data acquisition module to obtain a monitoring data set, wherein the monitoring data set includes temperature data, vibration data, and stress data. The temperature data is used to identify the temperature changes in the cable channel and analyze overheating, especially when the cable is heavily loaded; the vibration data can identify the situation where the cable is subjected to external physical interference, such as mechanical vibration, equipment vibration, or abnormal vibration of the cable itself due to improper operation; the stress data is used to identify the stress condition of the cable and detect stress problems such as stretching and compression that may occur in the cable during long-term use; wherein each data record carries a monitoring location identifier to clarify the specific location of the data point in the cable system. This location identifier can be defined based on the sensor's deployment coordinates, physical distance, or cable segment number.

[0029] S300: Using the fault identification channel to perform collaborative anomaly identification on the monitoring data set to establish a first anomaly identification result.

[0030] Further, if Figure 2 As shown, step S300 of the present application also includes: S310: After the monitoring data set is classified based on the monitoring location identifier and the acquisition time of the monitoring data set by the preprocessing layer in the fault identification channel, outlier extraction is performed to establish a preprocessing data set; S320: The change rate, peak value, and window abnormality feature extraction of the preprocessing data set are performed using the feature extraction layer in the fault identification channel to establish a feature extraction data set; S330: The feature space correlation analysis based on the feature extraction data set is performed by the spatial collaborative analysis layer to establish a first collaborative abnormality identification result; S340: The feature time correlation analysis based on the feature extraction data set is performed by the temporal collaborative analysis layer to establish a second collaborative abnormality identification result. S350: After fusing the first collaborative abnormality identification result and the second collaborative abnormality identification result, the first abnormality identification result is output.

[0031] Specifically, first, through the preprocessing layer in the fault identification channel, the monitoring data set is classified according to the monitoring location identifier and the acquisition time of the monitoring data set, that is, according to the monitoring location identifier of each data point, the data set is grouped by location, each location can represent a different part of the cable, or a different sensor location, and classification can help determine which areas of the equipment may have abnormalities; by classifying the monitoring data according to the acquisition time, the data fluctuations in different time periods can be identified, and then help analyze the anomalies in time; through the combined classification of time and space, the monitoring data set can be divided into multiple data subsets, each data subset represents the cable status within a specific location and time range, which is convenient for detailed analysis of different areas and time periods. Then, outliers are extracted from multiple data subsets. Outliers refer to data points that deviate from the normal data trend, which may indicate cable failures or potential problems, including extreme data exceeding the preset threshold (such as temperature exceeding the safety range), abnormal data fluctuations (such as drastic changes in vibration sensor data, indicating that the cable is subjected to severe impact or mechanical damage), data that is stable for a long time (such as stress data that remains unchanged for a long time, indicating that the sensor may be faulty), etc. Through classification and outlier extraction, effective abnormal monitoring data is extracted to form a new preprocessing data set.

[0032] Then, the feature extraction layer in the fault identification channel extracts the change rate, peak value, and window anomaly features of the preprocessed data set, wherein the change rate refers to the amplitude of change between a data point and the data points before and after it. By calculating the change rate of temperature, stress or vibration, it is possible to identify whether the cable has experienced drastic fluctuations within a certain period of time, including temperature change rate (identifying cable temperature fluctuations, too fast temperature changes may indicate a fault), vibration change rate (sudden vibration changes may indicate that the cable is impacted or damaged by external forces) and stress change rate (excessive stress changes may indicate that the cable is unevenly stressed or mechanically damaged); a peak value refers to the highest value in a piece of data, usually representing an extreme manifestation of an abnormal state, including temperature peak value (if the temperature value exceeds the set threshold within a certain period of time, it may mean that the equipment is overheated), vibration peak value (abnormal vibration peak value may indicate that the cable has been subjected to excessive mechanical shock, which may cause damage) and stress peak value (peak stress changes may indicate that the cable is subjected to excessive stress and is at risk of damage); a window anomaly refers to an abnormal fluctuation within a specific time period. The data window usually refers to a set time period or a fixed-length data interval. The statistics (such as mean, variance, etc.) within the interval are calculated and compared with the expected value to identify whether the data is abnormal. For example, for each monitoring parameter, a sliding window (for example, 30 seconds, 1 minute, etc.) is used to calculate the mean, variance, standard deviation and other statistics of the data in the window, and compared with the preset normal range. By comparing the statistics of each window with the set threshold, it is detected whether there is an abnormality, including temperature window abnormality (abnormal temperature fluctuations within a specific time period may indicate that the cable has an overheating problem), vibration window abnormality (abnormal vibration within a time window may reflect that the cable has a mechanical failure or is disturbed by external forces) and stress window abnormality (if the stress data fluctuates too much within a time window, it may indicate that the cable is unevenly stressed or has a potential failure); by calculating features such as the rate of change, peak value and window abnormality, a new feature extraction data set is established. The data set contains the feature values ​​of all sensors at different monitoring positions, providing data support for subsequent abnormality identification.

[0033] Furthermore, the feature extraction data set is subjected to feature spatial correlation analysis through the spatial collaborative analysis layer. Through the spatial collaborative analysis, the correlation relationship between different monitoring points (sensors) is identified, that is, whether multiple sensors show similar abnormal characteristics at the same time, or whether there is a concentrated abnormal pattern in the same spatial area. Each record in the data set contains the characteristics of the monitoring data (such as temperature change rate, vibration peak, stress window anomaly, etc.), and each feature has a corresponding monitoring location identifier. The spatial collaborative analysis determines the synergy between different sensors by calculating the correlation or similarity between these feature values. For example, a correlation coefficient (such as the Pearson correlation coefficient) is used to measure the spatial correlation between sensors. A higher correlation may mean that these sensors are in the same fault area. For adjacent sensors or sensors in the same area, the similarity between these sensor features can be calculated to determine whether they jointly indicate a potential fault. Based on the results of spatial correlation analysis, determine whether there is a spatially concentrated abnormal pattern. If the abnormal values ​​of multiple sensors appear in the same area and these anomalies show coordinated changes in space, a potential spatial anomaly can be identified and a first coordinated anomaly identification result can be generated. The first coordinated anomaly identification result can mark the abnormal area with spatial correlation in the cable channel. This area may indicate that the cable has some common fault or abnormality and requires the attention of operation and maintenance personnel. For example, if multiple temperature sensors and stress sensors show abnormal fluctuations at the same time in a certain area, this may mean that the cables in the area are overheated or under excessive stress.

[0034] On the other hand, the feature extraction data set is subjected to feature time correlation analysis through the time collaborative analysis layer. Through the time collaborative analysis, the correlation between the time series data of multiple monitoring points is identified, and the data is analyzed whether abnormalities occur synchronously in time, so that persistent faults, short-term sudden faults or long-term trend changes can be identified; wherein, the timestamp of each data point and the monitoring characteristics (such as temperature, vibration, stress, etc.) together constitute the time series data. By analyzing these time series data, abnormal patterns in the time dimension can be identified. Time series analysis methods, such as autocorrelation function, can be used to analyze the synchronization between time series data and calculate the abnormal change trend within a time period. For example, whether monitoring data such as temperature and stress occur synchronously in a certain time period. Whether there is a drastic change in the time point, or whether it continues to exceed the normal range for a period of time; if multiple sensors are abnormal in the same time period, or the abnormal fluctuations in different time periods have similar patterns, a time anomaly can be identified and a second collaborative anomaly identification result can be generated. The second collaborative anomaly identification result can identify those areas or sensors that show consistent abnormal trends in time. These time anomalies may indicate that there are continuous or sudden fault problems in the cable system. For example, if multiple sensors (such as temperature, vibration, stress, etc.) show synchronous abnormal fluctuations in a certain time period, the time period will be identified as a potential fault period, and the second collaborative anomaly identification result will be generated, and the possible fault type will be inferred.

[0035] Finally, the first collaborative anomaly recognition result (based on spatial correlation) is fused with the second collaborative anomaly recognition result (based on temporal correlation). For example, for each anomaly recognition point (area or time period), different weights can be assigned to spatial anomalies and temporal anomalies according to the priority of spatial and temporal anomalies in actual applications. The first collaborative anomaly recognition result and the second collaborative anomaly recognition result are weightedly calculated according to the weight configuration result, and the first anomaly recognition result is output.

[0036] By integrating the anomaly recognition results of space and time, the feature extraction data set can be comprehensively analyzed from both spatial and temporal dimensions, so as to accurately calibrate the fault area and fault time of the cable, and provide accurate decision support for subsequent operation and maintenance.

[0037] S400: Inputting the monitoring data set into a distance-temperature interpolation prediction network, performing interpolation prediction of the uncovered area, and establishing an interpolation prediction result.

[0038] Furthermore, step S400 of the present application also includes: S410: Calculate the dynamic weight of the interpolation point based on distance and temperature using the dynamic weight optimization level of the distance-temperature interpolation prediction network, as follows: ;in, Characterization based on known points Predicted unknown points The dynamic weight of Characterizing unknown points With known points The distance Characterization The location of the point, Characterizes the spatial distance smoothing parameter, is the distance exponential factor, Characterizing known points The temperature, Characterizes the average temperature of known points within the neighborhood window, is the smoothing parameter of the temperature difference, is the total number of known points, is the index of any known point.

[0039] Specifically, in the distance-temperature interpolation prediction network, the dynamic weight optimization layer is used to calculate the dynamic weights of the interpolation points. This process adjusts the weights of the interpolation points in the uncovered area based on factors such as distance and temperature. That is, the dynamic weight of each interpolation point is calculated according to the formula and the dynamic weight optimization layer of the network. The weight is determined by the distance and temperature information of the known points. The weight of the interpolation point reflects its similarity with the known data. The interpolation calculation is performed through the characteristic values ​​of the known data points (such as temperature, stress, vibration, etc.) and the calculated weights to fill in the data in the uncovered area to improve the accuracy and reliability of the interpolation prediction.

[0040] In the interpolation point weight calculation formula, Characterization based on known points Predicted unknown points The dynamic weight of the known point Forecast point The weight is dynamically adjusted by considering the distance and temperature difference. The closer the distance or the smaller the temperature difference, the greater the influence of the known point on the unknown point. Characterizing unknown points With known points Distance (spatial position distance); Characterization The location of the point, Characterizes the spatial distance smoothing parameter, which is used to control the influence of distance on weight. It can adjust the speed at which weight decays with increasing distance, thereby affecting the accuracy of interpolation. The influence of distant points on the interpolation result will be rapidly attenuated, and the larger This will make the points farther away still have a greater impact on the interpolation; is the distance exponential factor, Characterizing known points The temperature, Characterizes the average temperature of the known points in the neighborhood window, that is, the average temperature of all known points in a certain time window. This value is used to measure the overall temperature level of the cable area and as a benchmark for comparison with the temperature difference of the known points; is the smoothing parameter of the temperature difference, which is used to control the influence of the temperature difference on the interpolation result. Will make the temperature difference less affected, smaller This will increase the impact of temperature differences; is the total number of known points, It is the index of any known point, indicating the unique identification of each known point in the interpolation calculation.

[0041] S420: performing interpolation prediction based on the monitoring data set according to the calculation result of the dynamic weight of the interpolation point; ;in, is the interpolation prediction feature, For the The feature vectors of known points, , is the stress characteristic value, is the vibration characteristic value.

[0042] Specifically, the monitoring data set is then weighted according to the dynamic weight calculation results of the interpolation points to obtain the interpolation prediction results to fill the data of the uncovered area. The key to the interpolation prediction is to integrate the characteristics of the known points by calculating the weight of each interpolation point, so as to predict the characteristics of the uncovered area (such as temperature, stress, vibration, etc.).

[0043] In the interpolation prediction calculation function, To interpolate the predicted features, the predicted results are obtained by weighted averaging the features of known points, including temperature eigenvalues, vibration eigenvalues, and stress eigenvalues; For the The feature vector of a known point contains various monitoring data of the point (such as temperature, stress, vibration, etc.). , is the stress characteristic value, is the vibration characteristic value; that is, the characteristics of the unknown points are predicted by weighted average according to the dynamic weight of the interpolation point and the characteristics of the known points. By weighted average of the characteristics of the known points (such as temperature, stress, vibration, etc.), various characteristic values ​​of the unknown points can be accurately predicted, and the missing data of the uncovered areas can be filled, thereby achieving effective detection of the uncovered areas.

[0044] S500: Utilize the interpolation prediction result to perform fault risk prediction and establish a second abnormality identification result.

[0045] Furthermore, step S500 of the present application also includes: S510: Failure risk prediction is performed using a failure probability prediction model as follows: ;in, Characterizing unknown points The probability of failure, Characterize the interpolation prediction characteristic mode, is the modulus normalization parameter, Characterizing interpolation prediction features and their neighborhood average features The inner product of is the inner product normalization parameter, Represents historical changes, Normalize the parameters for historical changes; S520: According to the unknown points The failure probability generates a second abnormality identification result.

[0046] Specifically, a fault probability prediction function is constructed. The fault probability prediction function calculates the fault probability of unknown points by combining interpolation prediction features, historical changes, neighborhood average features and other data to generate the second anomaly recognition result. In the fault probability prediction function, Characterizing unknown points The greater the failure probability, the higher the failure risk of the unknown point. Characterizes the interpolation prediction feature modulus, which is a modulus normalization parameter, indicating the modulus normalization of the interpolation prediction feature. Since different features may have different dimensions and ranges, modulus normalization helps to eliminate dimensional differences, so that each feature can be fairly compared in the calculation; Characterizing interpolation prediction features and their neighborhood average features The inner product reflects the similarity between the interpolation prediction feature and the neighborhood average feature, which can reveal the similarity and correlation of unknown points in space. is the inner product normalization parameter, that is, in order to eliminate the influence of the characteristic mode, the inner product result is normalized; Represents historical changes and indicates unknown points The historical change trend and abnormal degree of the unknown point is the difference between the historical characteristic value of the unknown point and the average value of the historical characteristic value of the neighboring point. It can reflect whether there is a major change or a precursor to a fault in the cable system. Normalize the parameters for historical variation.

[0047] Then, the fault probability prediction function is used to predict the fault risk of the interpolation prediction result to obtain several unknown points. The failure probability of The fault probability is used as the second abnormality identification result. By generating the second abnormality identification result, efficient abnormality prediction of uncovered areas can be achieved, potential abnormalities in uncovered areas can be discovered in time, and the monitoring blind area problem in cable channel detection can be effectively eliminated.

[0048] S600: After performing abnormal fusion on the first abnormality recognition result and the second abnormality recognition result, a cable abnormality is reported.

[0049] Furthermore, step S600 of the present application also includes: S610: Obtain the abnormal fusion result, and obtain the abnormal type, abnormal position and abnormal value information based on the abnormal fusion result; S620: Obtain the current working parameters of the cable, and generate first auxiliary verification information based on the working parameters; S630: Obtain the location environment information of the cable, and generate second auxiliary verification information according to the location environment information; S640: Use the abnormal type, the abnormal position, the abnormal value information, the first auxiliary verification information, and the second auxiliary verification information to identify the abnormal trigger level; S650: Report the cable abnormality using the abnormal trigger level identification result.

[0050] Specifically, first, the first abnormality recognition result and the second abnormality recognition result are subjected to abnormal fusion, that is, the abnormality recognition results of the monitored area and the uncovered area are integrated into a comprehensive abnormality recognition result of the cable channel area to obtain an abnormality fusion result; then, abnormal feature extraction is performed based on the abnormality fusion result to obtain the abnormality type (such as overheating abnormality), abnormality location and abnormality value (such as abnormal temperature) information.

[0051] Then, the current working parameters of the cable are obtained, including but not limited to load, voltage, etc. These parameters can reflect the current working state of the cable and help to determine whether the cable is within the normal working range. For example, load refers to the current or power load of the cable. Too high a load may cause a cable failure; voltage refers to the voltage at both ends of the cable. Excessive voltage fluctuation may indicate that the cable is faulty; then, by analyzing the working parameters of the cable, the first auxiliary verification information is generated. This information is usually used to confirm whether the cable is in a normal working state. If the working parameters exceed the normal range, it means that the cable may be faulty or abnormal. For example, if the load is higher than the safe range that the cable can withstand, a load abnormality verification information can be generated. On the other hand, the location environment information of the cable is obtained, where the environment information has an important impact on its working state, including but not limited to ambient temperature (ambient temperature affects the heat dissipation and load bearing capacity of the cable), humidity (high humidity environment may accelerate the aging of the cable), external mechanical interference, etc.; then the second auxiliary verification information is generated according to the location environment information. For example, if the cable is installed in an environment with high temperature, humidity or large mechanical vibration, this may accelerate the aging of the cable or increase the probability of failure.

[0052] Next, an evaluation is performed based on the abnormal type, abnormal location, abnormal value information, the first auxiliary verification information, and the second auxiliary verification information, and different weights are assigned according to the importance of each abnormal factor. Then, each data is comprehensively scored through a weighted scoring method to determine the abnormal trigger level; finally, the cable abnormality is reported based on the abnormal trigger level. By evaluating the abnormal type, abnormal location, abnormal value information, the first auxiliary verification information, and the second auxiliary verification information, the abnormal trigger level of the cable system can be accurately determined, so that the cable monitoring system can provide accurate responses and early warnings when facing various abnormalities.

[0053] Furthermore, step S600 of the present application also includes: S660: Establishing a cumulative weighted coefficient of abnormality; S670: When a cable at any position is abnormal and has not been repaired, the cable abnormality is accumulated according to the cumulative weighted coefficient and a cumulative result is established; S680: Cable abnormality management is performed according to the cumulative result.

[0054] Specifically, first, establish the cumulative weighted coefficient of the abnormality. The weighted coefficient reflects the severity of the abnormality, which is usually determined by factors such as the type of abnormality, the location of the abnormality, and the value of the abnormality. Each time an abnormality occurs, a weight value is assigned according to its trigger level and the type of abnormality. It can be set according to the actual situation. The cumulative weighted coefficient is the accumulation of the weighted coefficient each time the abnormality is triggered. That is, when an abnormality occurs at a certain position of the cable, the weighted coefficient of the abnormality will be recorded and added to the total weighted coefficient of the position. Then, if the cable at any position is abnormal and has not been repaired, that is, the abnormal state continues to be unprocessed, the cable abnormality is accumulated according to the cumulative weighted coefficient of the position, that is, the abnormalities of all cable positions are recorded and the weighted coefficients are accumulated. The cumulative weighted coefficients of all positions form a cumulative result, and the result is used to determine whether each position needs emergency processing. Finally, different cumulative weighted coefficient thresholds are set according to the working environment, importance, and workload of the cable. When the cumulative weighted coefficient reaches the threshold, it means that the cable has a continuous abnormal risk and needs to be repaired or replaced.

[0055] In summary, the cable channel detection method based on distributed optical fiber sensing technology provided by the present application has the following technical effects: By acquiring the distribution coordinates of the distributed optical fiber sensor, the monitoring area and the uncovered area are configured according to the distribution coordinates and the monitoring accuracy; then the distributed optical fiber sensor is used to monitor the cable and a monitoring data set is established, wherein the monitoring data set includes temperature data, vibration data, and stress data, and the monitoring data set has a monitoring location identifier; then the fault identification channel is used to perform collaborative abnormality identification of the monitoring data set and establish a first abnormality identification result; on the other hand, the monitoring data set is input into the distance-temperature interpolation prediction network, and the interpolation prediction of the uncovered area is performed to establish an interpolation prediction result; the interpolation prediction result is further used to predict the fault risk and establish a second abnormality identification result; finally, the first abnormality identification result and the second abnormality identification result are abnormally fused and the cable abnormality is reported; the problem of monitoring blind spots in cable channel detection can be effectively eliminated, and potential abnormalities in uncovered areas can be discovered in a timely manner, thereby achieving abnormal monitoring and fault warning in the entire area without blind spots, and ensuring the safe and stable operation of cable equipment.

[0056] Embodiment 2, based on the same inventive concept as the cable channel detection method based on distributed optical fiber sensing technology in the previous embodiment, this application also provides a cable channel detection system based on distributed optical fiber sensing technology, please refer to the attached Figure 3 ,include: The area configuration module 01 is used to obtain the distribution coordinates of the distributed optical fiber sensor, and configure the monitoring area and the uncovered area according to the distribution coordinates and the monitoring accuracy; the monitoring data establishment module 02 is used to use the distributed optical fiber sensor to perform cable monitoring and establish a monitoring data set, wherein the monitoring data set includes temperature data, vibration data, and stress data, and the monitoring data set is provided with a monitoring location identifier; the first abnormality identification module 03 is used to use the fault identification channel to perform collaborative abnormality identification of the monitoring data set and establish a first abnormality identification result; the interpolation prediction module 04 is used to input the monitoring data set into the distance-temperature interpolation prediction network, perform interpolation prediction of the uncovered area, and establish an interpolation prediction result; the second abnormality identification module 05 is used to use the interpolation prediction result to perform fault risk prediction and establish a second abnormality identification result; the abnormality fusion module 06 is used to perform abnormal fusion on the first abnormality identification result and the second abnormality identification result, and then report the cable abnormality.

[0057] Furthermore, the cable channel detection system based on distributed optical fiber sensing technology is also used to: utilize the dynamic weight optimization hierarchy of the distance-temperature interpolation prediction network to perform dynamic weight calculation of interpolation points based on distance and temperature, as follows: ;in, Characterization based on known points Predicted unknown points The dynamic weight of Characterizing unknown points With known points The distance Characterization The location of the point, Characterizes the spatial distance smoothing parameter, is the distance exponential factor, Characterizing known points The temperature, Characterizes the average temperature of known points within the neighborhood window, is the smoothing parameter of the temperature difference, is the total number of known points, is the index of any known point; interpolation prediction based on the monitoring data set is performed according to the dynamic weight calculation result of the interpolation point: ;in, is the interpolation prediction feature, For the The feature vectors of known points, , is the stress characteristic value, is the vibration characteristic value.

[0058] Furthermore, the cable channel detection system based on distributed optical fiber sensing technology is also used to: predict fault risks through a fault probability prediction model, as follows: ;in, Characterizing unknown points The probability of failure, Characterize the interpolation prediction characteristic mode, is the modulus normalization parameter, Characterizing interpolation prediction features and their neighborhood average features The inner product of is the inner product normalization parameter, Represents historical changes, Normalize the parameters for historical changes; according to the unknown points The failure probability generates a second abnormality identification result.

[0059] Furthermore, the cable channel detection system based on distributed fiber optic sensing technology is also used for: after classifying the monitoring data set based on the monitoring location identifier and the acquisition time of the monitoring data set through the preprocessing layer in the fault identification channel, performing outlier extraction to establish a preprocessing data set; using the feature extraction layer in the fault identification channel to extract the change rate, peak value, and window abnormality features of the preprocessing data set to establish a feature extraction data set; performing feature space correlation analysis based on the feature extraction data set through the spatial collaborative analysis layer to establish a first collaborative abnormality identification result; performing feature time correlation analysis based on the feature extraction data set through the time collaborative analysis layer to establish a second collaborative abnormality identification result; after fusing the first collaborative abnormality identification result and the second collaborative abnormality identification result, outputting the first abnormality identification result.

[0060] Furthermore, the cable channel detection system based on distributed optical fiber sensing technology is also used to: obtain anomaly fusion results, and obtain anomaly type, anomaly position and anomaly value information based on the anomaly fusion results; obtain current working parameters of the cable, and generate first auxiliary verification information based on the working parameters; obtain location environment information of the cable, and generate second auxiliary verification information according to the location environment information; use the anomaly type, the anomaly position, the anomaly value information, the first auxiliary verification information, and the second auxiliary verification information to identify anomaly trigger levels; and use the anomaly trigger level identification results to report cable anomalies.

[0061] Furthermore, the cable channel detection system based on distributed optical fiber sensing technology is also used to: obtain model information and usage information of the distributed optical fiber sensor; identify accuracy loss based on the model information and the usage information, and establish an accuracy loss identification result; reconstruct monitoring accuracy based on the accuracy loss identification result and the model information, and use the reconstructed monitoring accuracy to configure the monitoring area and the uncovered area.

[0062] Furthermore, the cable channel detection system based on distributed optical fiber sensing technology is also used to: establish a cumulative weighted coefficient of anomalies; when a cable at any position is abnormal and has not been repaired, the cable anomalies are accumulated according to the cumulative weighted coefficient to establish a cumulative result; and the cable anomaly management is performed according to the cumulative result.

[0063] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The cable channel detection method based on distributed optical fiber sensing technology and the specific examples in the aforementioned embodiment 1 are also applicable to a cable channel detection system based on distributed optical fiber sensing technology in this embodiment. Through the aforementioned detailed description of a cable channel detection method based on distributed optical fiber sensing technology, those skilled in the art can clearly know a cable channel detection system based on distributed optical fiber sensing technology in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0064] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0065] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A cable channel detection method based on distributed optical fiber sensing technology, characterized in that: Methods include: Obtaining distribution coordinates of distributed optical fiber sensors, and configuring monitoring areas and uncovered areas according to the distribution coordinates and monitoring accuracy; Using the distributed optical fiber sensor to monitor the cable, establishing a monitoring data set, wherein the monitoring data set includes temperature data, vibration data, and stress data, and the monitoring data set is provided with a monitoring location identifier; Using the fault identification channel to perform collaborative anomaly identification of the monitoring data set to establish a first anomaly identification result; Inputting the monitoring data set into the distance-temperature interpolation prediction network, performing interpolation prediction of the uncovered area, and establishing an interpolation prediction result; Using the interpolation prediction result to perform fault risk prediction and establish a second abnormality identification result; After abnormal fusion of the first abnormal recognition result and the second abnormal recognition result, a cable abnormality is reported.

2. The cable channel detection method based on distributed optical fiber sensing technology as claimed in claim 1, characterized in that: The step of inputting the monitoring data set into a distance-temperature interpolation prediction network, performing interpolation prediction of the uncovered area, and establishing an interpolation prediction result includes: The dynamic weight optimization level of the distance-temperature interpolation prediction network is used to calculate the dynamic weight of the interpolation points based on distance and temperature, as follows: ； in, Characterization based on known points Predicted unknown points The dynamic weight of Characterizing unknown points With known points The distance Characterization The location of the point, Characterizes the spatial distance smoothing parameter, is the distance exponential factor, Characterizing known points The temperature, Characterizes the average temperature of known points within the neighborhood window, is the smoothing parameter of the temperature difference, is the total number of known points, is the index of any known point; According to the calculation results of the dynamic weights of the interpolation points, an interpolation prediction based on the monitoring data set is performed: ； in, is the interpolation prediction feature, For the The feature vectors of known points, , is the stress characteristic value, is the vibration characteristic value.

3. The cable channel detection method based on distributed optical fiber sensing technology as claimed in claim 2, characterized in that: The method of using the interpolation prediction result to perform fault risk prediction and establish a second abnormality identification result includes: Failure risk prediction is performed through the failure probability prediction model as follows: ； in, Characterizing unknown points The probability of failure, Characterize the interpolation prediction characteristic mode, is the modulus normalization parameter, Characterizing interpolation prediction features and their neighborhood average features The inner product of is the inner product normalization parameter, Represents historical changes, Normalize parameters for historical changes; According to the unknown point The failure probability generates a second abnormality identification result.

4. The cable channel detection method based on distributed optical fiber sensing technology according to claim 1, characterized in that: The using the fault identification channel to perform collaborative anomaly identification of the monitoring data set to establish a first anomaly identification result includes: After classifying the monitoring data set based on the monitoring location identifier and the acquisition time of the monitoring data set through the preprocessing layer in the fault identification channel, performing outlier extraction and establishing a preprocessing data set; Using the feature extraction layer in the fault identification channel to extract the change rate, peak value, and window abnormality features of the preprocessed data set, and establish a feature extraction data set; Performing feature space correlation analysis based on the feature extraction data set through a spatial collaborative analysis layer to establish a first collaborative anomaly recognition result; Performing feature time correlation analysis based on the feature extraction data set through a time collaborative analysis layer to establish a second collaborative anomaly recognition result; After the first collaborative anomaly recognition result and the second collaborative anomaly recognition result are merged, a first anomaly recognition result is output.

5. The cable channel detection method based on distributed optical fiber sensing technology according to claim 1, characterized in that: After performing abnormal fusion on the first abnormal recognition result and the second abnormal recognition result, the method includes: Acquire an abnormal fusion result, and acquire abnormal type, abnormal position and abnormal value information based on the abnormal fusion result; Acquire current working parameters of the cable, and generate first auxiliary verification information based on the working parameters; Acquire location environment information of the cable, and generate second auxiliary verification information according to the location environment information; Identify an abnormality trigger level using the abnormality type, the abnormality location, the abnormal value information, the first auxiliary verification information, and the second auxiliary verification information; The abnormal trigger level identification result is used to report the cable abnormality.

6. The cable channel detection method based on distributed optical fiber sensing technology according to claim 1, characterized in that: The configuring the monitoring area and the uncovered area according to the distribution coordinates and the monitoring accuracy includes: Obtaining model information and usage information of the distributed optical fiber sensor; Perform precision loss identification according to the model information and the usage information, and establish a precision loss identification result; The monitoring accuracy is reconstructed based on the accuracy loss identification result and the model information, and the monitoring area and the uncovered area are configured using the reconstructed monitoring accuracy.

7. The cable channel detection method based on distributed optical fiber sensing technology according to claim 1, characterized in that: The method also includes: Establishing cumulative weighting coefficients for anomalies; When a cable at any position is abnormal and has not been repaired, the cable abnormality is accumulated according to the cumulative weighted coefficient to establish a cumulative result; Cable abnormality management is performed according to the accumulated results.

8. A cable channel detection system based on distributed optical fiber sensing technology, characterized in that: The steps for implementing the cable channel detection method based on distributed optical fiber sensing technology as described in any one of claims 1 to 7 include: An area configuration module, used to obtain the distribution coordinates of the distributed optical fiber sensor, and configure the monitoring area and the uncovered area according to the distribution coordinates and the monitoring accuracy; A monitoring data establishment module, used to use the distributed optical fiber sensor to perform cable monitoring and establish a monitoring data set, wherein the monitoring data set includes temperature data, vibration data, and stress data, and the monitoring data set has a monitoring location identifier; A first anomaly identification module, configured to use a fault identification channel to perform collaborative anomaly identification of the monitoring data set and establish a first anomaly identification result; An interpolation prediction module, used for inputting the monitoring data set into a distance-temperature interpolation prediction network, performing interpolation prediction of the uncovered area, and establishing an interpolation prediction result; A second abnormality identification module, used to use the interpolation prediction result to perform fault risk prediction and establish a second abnormality identification result; The abnormality fusion module is used to report the cable abnormality after abnormality fusion of the first abnormality recognition result and the second abnormality recognition result.

Images