Underground cable pipeline abnormity monitoring method and system

Abstract

The invention discloses an underground cable pipeline abnormity monitoring method and system, and the method comprises the following steps: S1, building a three-dimensional grid based on the regional soil distribution condition, and obtaining a collection point data set based on the three-dimensional grid and underground cable pipeline data; s2, acquiring acquisition distribution corresponding to each to-be-arranged sensor type based on the to-be-arranged sensor type and the acquisition point data set; s3, acquiring underground cable pipeline time sequence data acquired by each sensor based on acquisition distribution, and performing clustering analysis on the underground cable pipeline time sequence data to acquire abnormal data points; and S4, obtaining an abnormal position according to the abnormal data points and the collection distribution, and outputting abnormal information of the underground cable pipeline according to the abnormal position. The method has the beneficial effects that the physical position of the cable pipeline is considered, meanwhile, the soil environment characteristics are considered, the accuracy of sensor arrangement in the pipeline is improved, the abnormal data point analysis efficiency is improved, and the underground cable pipeline abnormity can be conveniently and timely checked.

Description

Technical Field

[0001] The present application relates to the technical field of underground cable anomaly monitoring, and in particular to a method and system for monitoring anomaly in underground cable pipelines. Background Art

[0002] With the acceleration of urbanization and the continuous growth of electricity demand, underground cable pipelines, as important infrastructure for urban power transmission, are directly related to the normal operation of the city and the quality of life of residents due to their safety and stability. However, due to the complex and changeable underground environment, cable pipelines are easily affected by various factors during operation, such as soil corrosion, external force damage, insulation aging, etc., which may cause changes in pipeline status and even lead to safety accidents. Therefore, real-time monitoring and abnormality detection of underground cable pipelines are particularly important.

[0003] Traditional cable pipeline monitoring methods often rely on manual inspections and regular testing. This method is not only inefficient, but also prone to missed inspections and misjudgments. In addition, manual inspections are limited by environmental and human factors, making it difficult to achieve full coverage and real-time monitoring of cable pipelines. The environment in which underground cable pipelines are located is complex and changeable, including the influence of multiple factors such as soil moisture, temperature, and pressure. These factors will affect the state of the cable pipeline. At the same time, there are many underground pipelines that are intertwined, which increases the difficulty and complexity of monitoring. And when an abnormality occurs in the cable pipeline, it is necessary to be able to quickly and accurately locate the abnormal location and transmit the information to relevant personnel in real time for processing.

[0004] Therefore, how to comprehensively and accurately monitor the status of cable pipelines and the surrounding environment, timely discover and locate potential safety hazards, and improve the operating efficiency and safety of the power system is an issue that technical personnel in this field urgently need to solve.

[0005] In the related technology, there is a method of using sensors to monitor underground cable pipelines. When the sensor collects data abnormally, the underground cable pipeline at the corresponding location is manually detected to be abnormal, or a large amount of data obtained by the sensor is processed and mined to find potential fault signs and abnormal patterns from the data. In this case, although there is no need for manual inspection, the efficiency of abnormality detection is improved. However, once the environment changes, the sensor setting is affected by the pipeline characteristics, and it is impossible to effectively distinguish or even warn of the abnormal environmental impact.

[0006] The patent "Cable Fault Detection Method Based on Artificial Neural Network", publication number: CN115795360A, publication date: March 14, 2023, specifically discloses that the method includes the following steps: S1, collect sample data when the cable fails to obtain real-time fault samples; S2, normalize the real-time fault samples to obtain normalized samples; S3, use the Dropout algorithm to improve the artificial neural network and build a cable fault detection model; S4, use the gradient descent method to train the cable fault detection model to obtain a trained cable fault detection model; S5, input the normalized samples into the trained cable fault detection model and output the fault detection results. This scheme uses artificial neural networks to train cable faults. Once the environmental state fluctuates, accurate fault detection cannot be achieved. At the same time, the output of abnormal coordinates depends on the data collection of the sensor. Once the sensor data collection is incorrect, the abnormal coordinates cannot be accurately output.

[0007] The patent "Smart Grid Operation and Maintenance System Safe Online Real-time Monitoring Method and Storage Medium", publication number: CN113253051A, publication date: May 12, 2021, specifically discloses the following methods: obtaining the road length corresponding to the underground cable project in the area and dividing the road sections; obtaining the corresponding buried time of the underground cables in each cable section; detecting the internal environmental parameters of the underground cable pipeline in each cable section; detecting the basic parameters of the outer sheath of the underground cable in each cable section; obtaining the underground cable operating parameters of each cable section in each collection time period; analyzing the buried time corresponding to the underground cable in each cable section, the internal environmental parameters of the underground cable pipeline, the basic parameters of the outer sheath of the underground cable, and the underground cable operating parameters. This solution also has high requirements for the accuracy of the sensor. Once a sensor has a problem, it is very likely to affect the final abnormality identification. Summary of the invention

[0008] The present application aims to solve the technical problem in the prior art that when a certain sensor is abnormal, it is easy to mislead the abnormal analysis. The present application provides an underground cable pipeline abnormality monitoring method and system. The early layout of sensors is associated with the environment by constructing a three-dimensional grid, and abnormal points are checked through cluster analysis of each sensor in the later stage. The abnormal position is obtained through the distribution of sensors on the three-dimensional grid, thereby avoiding a certain sensor from losing abnormal coordinates or misleading the abnormal coordinate check, thereby improving the accuracy of abnormal analysis and the efficiency of abnormal analysis.

[0009] To achieve the above-mentioned technical objectives, the present application provides a technical solution, which is a method for monitoring abnormalities in underground cable pipelines, comprising the following steps: S1: constructing a three-dimensional grid based on the regional soil distribution, and obtaining a collection point data set based on the three-dimensional grid and the underground cable pipeline data; S2: obtaining the collection distribution corresponding to each type of sensor to be deployed based on the type of sensor to be deployed and the collection point data set; S3: obtaining the underground cable pipeline time series data collected by each sensor based on the collection distribution, performing cluster analysis on the underground cable pipeline time series data, and obtaining abnormal data points; S4: obtaining the abnormal position according to the abnormal data points and the collection distribution, and outputting the underground cable pipeline abnormal information according to the abnormal position.

[0010] Furthermore, constructing a three-dimensional grid based on regional soil distribution includes: constructing a horizontal grid at preset intervals along the horizontal direction; constructing a vertical grid according to soil structure information; and constructing a three-dimensional grid with the horizontal grid and the vertical grid.

[0011] Furthermore, constructing a horizontal grid according to preset intervals in the horizontal direction includes: obtaining intervals based on expert experience, obtaining average intervals based on the horizontal underground cable pipeline layout, minimum cost and intervals, and constructing a horizontal grid using the average interval as the preset interval.

[0012] Furthermore, the acquisition of the collection point data set based on the three-dimensional grid and the underground cable pipeline data includes: obtaining a grid intersection set based on the three-dimensional grid, obtaining a layout point angle based on the pipeline shape, and obtaining a collection point data set based on the grid intersection set and the layout point angle.

[0013] Furthermore, the method of obtaining the collection distribution corresponding to each sensor type to be deployed based on the sensor type to be deployed and the collection point data set includes: obtaining the sensor type to be deployed based on the data requirements to be collected, obtaining the collection parameter characteristics corresponding to the sensor type to be deployed, and obtaining the collection distribution that meets the collection parameter characteristic requirements in the collection point data set corresponding to each sensor type to be deployed.

[0014] Furthermore, the performing of cluster analysis on the underground cable pipeline time series data to obtain abnormal data points includes: dividing the underground cable pipeline time series data into a number of subsequences containing continuous observation values ​​according to preset parameter content; performing cluster analysis on each subsequence to obtain a clustering result for each subsequence; and obtaining abnormal data points based on a distance algorithm and the clustering results.

[0015] Furthermore, obtaining the abnormal position based on the abnormal data points and the collection distribution includes: obtaining a corresponding sensor set based on each abnormal data point; obtaining a sensor position point set based on the sensor set; obtaining an abnormal area based on the sensor position point set and the collection distribution, and obtaining sensor monitoring data corresponding to the abnormal area; performing weighted averaging on the sensor monitoring data based on the relative position relationship of the sensors to obtain the abnormal position.

[0016] Furthermore, the outputting of abnormal information of the underground cable pipeline according to the abnormal position also includes: acquiring historical underground cable pipeline data, and constructing an abnormality recognition model according to the historical underground cable pipeline data; performing key feature recognition according to the sensor corresponding to the abnormal position and the underground cable pipeline time series data corresponding to the sensor, and acquiring the abnormal information of the underground cable pipeline based on the key features and the abnormality recognition model.

[0017] Furthermore, the S3 also includes: S31: obtaining the current offset physical quantity based on the historical underground cable pipeline offset data and the current regional soil distribution, and constructing an offset grid with the current offset physical quantity and the three-dimensional grid; S32: obtaining the underground cable pipeline time series data collected by each sensor based on the collection distribution, performing cluster analysis on the underground cable pipeline time series data based on the offset grid, and obtaining abnormal data points.

[0018] Furthermore, the S31 also includes: obtaining the correlation between soil distribution and offset physical quantity based on historical underground cable pipeline offset data; obtaining the current offset physical quantity according to the regional soil distribution and the correlation between soil distribution and offset physical quantity; and constructing an offset grid with the current offset physical quantity and a three-dimensional grid.

[0019] Furthermore, the S32 also includes: acquiring the underground cable pipeline time series data collected by each sensor based on the collection distribution; performing a clustering on each sensor based on the offset grid and the collection distribution; performing a secondary clustering based on the underground cable pipeline time series data collected by each sensor in the same cluster in the primary clustering; and obtaining abnormal data points based on the secondary clustering.

[0020] Furthermore, the S32 also includes: obtaining the sensor to be checked according to a preset threshold of clustering; judging whether the sensor to be checked is abnormal based on the historical underground cable pipeline monitoring data of the sensor to be checked and the current underground cable pipeline time series data, and if so, outputting the sensor abnormality information.

[0021] Furthermore, it also includes: S5: obtaining the offset grid data within a preset time segment, obtaining the offset fluctuation trend of each grid based on the offset grid data, and judging whether there is an offset anomaly in the underground cable pipeline according to the offset fluctuation trend of each grid and the grid offset threshold. If so, outputting the underground cable pipeline offset anomaly information.

[0022] Another technical solution provided by the present application is an underground cable pipeline abnormality monitoring system, which is used to implement the method as described above, including: a sensor deployment module, which constructs a three-dimensional grid based on the regional soil distribution and obtains the collection distribution corresponding to each sensor type to be deployed; a data acquisition module, which is used to obtain the underground cable pipeline time series data collected by each sensor; a data analysis module, which performs cluster analysis based on the underground cable pipeline time series data to obtain abnormal data points, and analyzes and outputs the underground cable pipeline abnormal information.

[0023] Beneficial effects of this application: 1. Construct a three-dimensional grid based on the regional soil distribution, and obtain the sensor collection point data set in combination with the pipeline information. Take into account the physical location of the cable pipeline while taking into account the soil environmental characteristics, improve the accuracy of sensor layout in the pipeline, and then improve the accuracy of underground cable pipeline time series data collection, improve the accuracy of abnormal data point analysis, and at the same time, there is no need to conduct complex misleading data investigation, improve the efficiency of abnormal data point analysis, and facilitate timely investigation of underground cable pipeline anomalies.

[0024] 2. The preset interval is obtained by using the average interval, minimum cost, and interval range, which can ensure that the horizontal grid meets the sensor layout requirements and that there must be an intersection of a horizontal grid layer and a vertical grid layer at the end point of the underground cable pipeline layout area for sensor layout, thereby avoiding errors in abnormal analysis caused by ignoring the end point data and further improving the accuracy of abnormal analysis.

[0025] 3. The data demand to be collected can be obtained according to the pipeline type. Different pipeline types may produce different anomalies. At this time, different data are required for anomaly analysis, and the corresponding sensor type to be deployed is obtained to avoid interference from unnecessary data.

[0026] 4. According to the preset parameter content, it is divided into several subsequences containing continuous observations, and each subsequence is clustered to obtain data points that deviate from the cluster center. This not only maintains uniformity in time series to avoid deviation interference caused by time series differences, but also obtains abnormal data points in the short term based on subsequence clustering of continuous observations. At the same time, abnormal analysis is performed in the long and short term to avoid mutual interference between long and short-term data, thereby improving the accuracy of data anomaly analysis.

[0027] 5. When performing cluster analysis, the default detection point of the sensor and the actual sensor detection deviation are added to compensate for the sensor detection position error. Without the need for manual correction of the sensor, abnormal data points can still be obtained through the offset difference between the three-dimensional grid and the offset grid, ensuring the accuracy of abnormal analysis while reducing the need for sensor adjustment.

[0028] 6. Through two clusterings, the spatial distribution and time series data characteristics of the sensors can be integrated to more accurately identify abnormal data points and avoid the influence of the same type of sensors with different spatial positions on abnormal data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 The present invention is a flowchart of a method for monitoring abnormalities in underground cable pipelines.

[0030] Figure 2 A schematic diagram of cluster analysis of an underground cable pipeline abnormality monitoring method for this application.

[0031] Figure 3 This is a schematic diagram of abnormal state analysis of an abnormal monitoring method for underground cable pipelines in the present application. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application is further described in detail below in conjunction with the drawings and examples. It should be understood that the specific implementation method described here is only an optimal embodiment of the present application, which is only used to explain the present application and does not limit the scope of protection of the present application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0033] like Figure 1 As shown, as the first embodiment of the present application, a method for monitoring abnormalities of underground cable pipelines includes the following steps: S1: Construct a three-dimensional grid based on the regional soil distribution, and obtain a collection point data set based on the three-dimensional grid and underground cable pipeline data; S2: based on the type of sensor to be deployed and the data set of the collection points, obtaining the collection distribution corresponding to each type of sensor to be deployed; S3: acquiring the underground cable pipeline time series data collected by each sensor based on the collection distribution, performing cluster analysis on the underground cable pipeline time series data, and obtaining abnormal data points; S4: Obtain the abnormal position according to the abnormal data points and the collection distribution, and output the abnormal information of the underground cable pipeline according to the abnormal position.

[0034] In this embodiment, a three-dimensional grid is constructed according to the regional soil distribution, and a sensor collection point data set is obtained in combination with the pipeline information. The physical position of the cable pipeline is considered while taking into account the soil environmental characteristics, thereby improving the accuracy of sensor deployment in the pipeline, thereby improving the accuracy of underground cable pipeline time series data collection, and improving the accuracy of abnormal data point analysis. At the same time, there is no need to conduct complex misleading data investigation, which improves the efficiency of abnormal data point analysis and facilitates timely investigation of underground cable pipeline anomalies.

[0035] Wherein, step S1 also includes: The area to be analyzed is obtained based on the layout of underground cable pipelines, and the soil distribution conditions of the area to be analyzed are obtained based on the area to be analyzed.

[0036] The underground cable pipeline layout at least includes the pipeline direction, pipeline length and pipeline burial depth. The underground cable pipeline layout obtains the area where the underground cable pipeline exists as the area to be analyzed, and obtains the soil distribution in the area to be analyzed as the regional soil distribution. Reduce the construction of unnecessary three-dimensional grids, avoid the deployment of unnecessary sensors while improving the accuracy of sensor deployment, reduce the monitoring cost, and reduce the collection of unnecessary underground cable pipeline time series data, reduce the amount of data for abnormal analysis, and further improve the efficiency of abnormal data point analysis.

[0037] Soil distribution at least includes soil structure information. Constructing a three-dimensional grid based on regional soil distribution includes: Grid lines are constructed based on the changes in soil structure information, and three-dimensional grids are constructed using the grid lines.

[0038] Grid lines are constructed at the locations where soil structure information changes, so that different soil structures are in different grid areas, which facilitates the subsequent investigation of the impact on the soil structure.

[0039] In some cases, soil structure information includes soil type. According to different soil types, grid layers with different spacings are constructed. In areas where the soil type varies greatly, such as the junction of soil and rock, the density of the grid layer is increased.

[0040] Generally, the underground cable pipeline layout area is usually in the form of layered filling, that is, the soil types in the horizontal direction are basically the same, and there are only differences in the soil types in the vertical direction. At this time, the three-dimensional grid is constructed based on the regional soil distribution, including: Construct a horizontal grid at preset intervals along the horizontal direction; Construct vertical grids based on soil structure information; Construct a three-dimensional grid with horizontal and vertical grids.

[0041] In the horizontal direction, along the direction and length of the cable pipeline, the area around the pipeline is divided into several horizontal grids at preset intervals; in the vertical direction, vertical grid layers of different heights are constructed according to the pipeline burial depth and soil structure. In some cases, the preset interval is the optimal sensor layout horizontal interval obtained according to expert experience, while in other cases, the construction of horizontal grids at preset intervals along the horizontal direction includes: The interval is obtained based on expert experience, the average interval is obtained based on the horizontal underground cable pipeline layout, minimum cost and interval, and the horizontal grid is constructed using the average interval as the preset interval.

[0042] According to expert experience, the minimum and maximum intervals of grid distribution in the horizontal direction are obtained to obtain the interval interval. Based on the horizontal underground cable pipeline layout, the pipeline direction and pipeline length in the horizontal direction are obtained to obtain the horizontal grid layout area. The horizontal grid that meets the average distribution is obtained with the minimum cost and interval interval. The horizontal grid layout interval is evenly divided to obtain the interval parameter set that meets the average division. The optimal interval parameter is obtained with the minimum cost and interval interval. The interval from the end point to the previous grid is the average interval parameter. It is considered that the average division is satisfied. The minimum cost is the maximum interval parameter, that is, the larger the horizontal grid spacing, the fewer sensors are laid in the horizontal direction, and the lower the cost. Conversely, the smaller the horizontal grid spacing, the more sensors are laid in the horizontal direction, and the greater the cost. The maximum average interval that meets the interval interval can be obtained with the minimum cost and interval interval, and the horizontal grid is constructed with the maximum average interval. The preset interval is obtained by combining the average interval, minimum cost and interval range, which can ensure that the horizontal grid meets the sensor layout requirements and that there must be an intersection of the horizontal grid layer and the vertical grid layer at the end point of the underground cable pipeline layout area for sensor layout, avoiding errors in abnormal analysis caused by ignoring the endpoint data and further improving the accuracy of abnormal analysis.

[0043] The data set of acquisition points based on 3D grid and underground cable pipeline data includes: A grid intersection set is obtained based on the three-dimensional grid, the layout point angle is obtained based on the pipeline shape, and the collection point data set is obtained based on the grid intersection set and the layout point angle.

[0044] The underground cable pipeline data includes at least the pipeline shape. The intersection of the horizontal grid and the vertical grid is used as the grid intersection set, and the layout point angle is subdivided according to the pipeline shape to ensure that the sensor covers all directions around the pipeline. For example, under normal circumstances, the pipeline shape is circular. In this case, it is only necessary to lay sensors at the horizontal angle, vertical angle and 45° angle of the pipeline. However, if the pipeline has a rectangular seal, the pipeline shape is rectangular, and sensors need to be laid at the horizontal angle, vertical angle, 22.5° angle, 45° angle, and 75° angle of the pipeline. According to the pipeline shape, select specific grid intersections as collection points, so as to adapt to the actual situation of different pipelines, ensure the complete coverage of pipeline information collection, and improve the accuracy of abnormal analysis.

[0045] In step S2, based on the sensor type to be deployed and the collection point data set, obtaining the collection distribution corresponding to each sensor type to be deployed includes: Based on the demand for data to be collected, the type of sensor to be deployed is obtained, the collection parameter characteristics corresponding to the sensor type to be deployed are obtained, and the collection distribution that meets the collection parameter characteristic requirements is obtained in the collection point data set corresponding to each sensor type to be deployed.

[0046] The data requirements to be collected can be obtained according to the type of pipeline. Different pipeline types may produce different anomalies. At this time, different data are required for anomaly analysis, and the corresponding sensor types to be deployed are obtained to avoid interference from unnecessary data. In this embodiment, the types of sensors to be deployed include strain gauges, vibration sensors, temperature sensors for monitoring the state of the pipeline itself, and humidity sensors and gas sensors for monitoring the pipeline environment. The distribution positions of different types of sensors are not the same. For example, strain gauges are installed on the inner wall of the pipeline to monitor the stress changes of the pipeline and prevent fractures caused by overload or fatigue. The installation position of the strain gauge is the collection point located on the inner wall of the pipeline to ensure comprehensive monitoring of the stress changes of the entire inner wall of the pipeline. The vibration sensor needs to detect vibration, and the vibration at the bends and joints of the pipeline is more severe. At this time, the installation position of the vibration sensor is the collection points located around the pipeline, evenly distributed around the pipeline, especially at the bends and joints, to detect abnormal vibrations and warn of possible mechanical failures or external interference. The temperature sensor is used to monitor the temperature changes inside the pipeline and the surrounding environment to prevent overheating or overcooling from affecting the performance of the cable. The installation location of the temperature sensor is a combination of collection points with a spacing equal to the sensing distance of the temperature sensor. Considering the influence of the ambient temperature gradient, the temperature sensor is installed near the grid point to ensure that the temperature change can be accurately captured. The installation location of the humidity sensor is a collection point located near the interface where the soil and the pipeline contact, and a collection point located in a critical water level fluctuation area to monitor soil humidity changes and prevent corrosion or short circuits caused by excessive humidity. The installation location of the gas sensor is a collection point located in an area with a risk of gas leakage, which monitors the environmental gas concentration in real time (such as detection of harmful gases such as methane and hydrogen sulfide) to ensure the safety of personnel and equipment.

[0047] In step S3, it also includes: Acquire the underground cable pipeline time series data collected by each sensor based on the collection distribution, and perform data preprocessing on the underground cable pipeline time series data; Cluster analysis is performed on the underground cable pipeline time series data after data preprocessing to obtain abnormal data points.

[0048] Among them, the data preprocessing of underground cable pipeline time series data includes: Perform data cleaning on underground cable pipeline time series data; Perform data normalization on underground cable pipeline time series data; Perform denoising on underground cable raceway time series data.

[0049] Data cleaning includes identifying and processing outliers and missing values. Data normalization is to group data into the same scale for easy comparison. The denoising process can use filtering technology to reduce or eliminate noise in the data, improve the data signal-to-noise ratio, and more accurately reflect the true state of the pipeline and its surrounding environment.

[0050] like Figure 2 As shown in the figure, cluster analysis is performed on the underground cable pipeline time series data to obtain abnormal data points including: Divide the underground cable pipeline time series data into several subsequences containing continuous observation values ​​according to the preset parameter content; Perform cluster analysis on each subsequence to obtain the clustering results of each subsequence; Abnormal data points are obtained based on the distance algorithm and clustering results.

[0051] The preset parameter content is the number of parameters contained in a preset subsequence, and the underground cable pipeline time series data is divided into several subsequences, each of which contains a fixed number of continuous observations. Determine the number of cluster centers K, apply the K-means clustering algorithm to each subsequence, and the data points of each subsequence will be assigned to K clusters to obtain the clustering results of each subsequence. It can be understood that the K-means clustering algorithm is used in this embodiment, and in the remaining embodiments, clustering algorithms such as K-medoids, DBSCAN, and OPTICS can also be used. For example, in the K-means clustering algorithm, each cluster is defined by the average value of its members, while in the K-medoids clustering algorithm, each cluster is defined by a representative point, and in the DBSCAN and OPTICS clustering algorithms, clusters are formed according to the density distribution in the data space.

[0052] In this embodiment, the clustering algorithm is K-means, and the distance algorithm is Euclidean distance. According to the clustering results, the distance from each data point to its nearest cluster center is calculated based on the Euclidean distance, and compared with the preset distance threshold. Points exceeding the preset distance threshold are regarded as abnormal data points. The preset distance threshold is the average value of the distance from all points to the cluster center plus the standard deviation. That is, at this time, the abnormal data points obtained based on the distance algorithm and the clustering results include: Based on the Euclidean distance and clustering results, the shortest distance from each data point in each subsequence to the cluster center is calculated; The preset distance threshold is obtained based on the average distance and standard deviation of each data point from each subsequence to the cluster center; The data points whose minimum distance is greater than the preset distance threshold are regarded as abnormal data points.

[0053] The collected information of each sensor is aggregated into underground cable pipeline time series data according to the time series, and then divided into several subsequences containing continuous observation values ​​according to the preset parameter content. Cluster analysis is performed on each subsequence to obtain data points that deviate from the cluster center. This not only maintains uniformity in time series to avoid deviation interference caused by time series differences, but also obtains abnormal data points in the short term based on subsequence clustering of continuous observation values. At the same time, abnormal analysis is performed in the long and short term to avoid mutual interference between long and short-term data, thereby improving the accuracy of data anomaly analysis.

[0054] The abnormal locations obtained based on abnormal data points and collection distribution include: Get the corresponding sensor according to the abnormal data point; The sensor position is obtained as the abnormal position according to the corresponding sensor and the acquisition distribution.

[0055] Each abnormal data point must correspond to a sensor that collects the data point. The corresponding sensor is obtained, and the sensor position is obtained according to the collection distribution, so as to obtain the position where the abnormality occurs as the abnormal position.

[0056] In some other embodiments, obtaining the abnormal position according to the abnormal data point and the collection distribution includes: Obtain the corresponding sensor set according to each abnormal data point; Using the sensor set to obtain a sensor position point set; The abnormal area is obtained based on the sensor location point set and the collection distribution, and the abnormal area is used as the abnormal location.

[0057] In this case, the area enclosed by the sensors corresponding to all abnormal data points is taken as the abnormal position. That is, after the abnormal data points are identified, these points are associated with the sensors to which they belong. Since each sensor has clear location information in the three-dimensional grid, the abnormal data points are combined with the location information of the sensor to preliminarily determine the abnormal area where the abnormal data points occur. This area is usually a spatial range centered on the sensor associated with the abnormal data point, which makes it easier for staff to check the abnormal position.

[0058] In this embodiment, obtaining the abnormal position according to the abnormal data point and the collection distribution also includes: Obtain sensor monitoring data corresponding to the abnormal area; Based on the relative position relationship of the sensors, the sensor monitoring data is weighted averaged to obtain the abnormal position.

[0059] After the abnormal area is initially determined, the monitoring data of all relevant sensors in the area are further utilized. These data include different types of physical quantities (such as temperature, humidity, vibration, etc.), which together reflect the comprehensive status of the abnormal area. That is, the underground cable pipeline time series data containing the monitoring data of the abnormal area is used as the sensor monitoring data corresponding to the abnormal area. Through multi-source data fusion technology, these different sources and different types of data are integrated and fused to improve the accuracy and reliability of anomaly detection. On the basis of multi-source data fusion, a three-dimensional positioning algorithm is used to calculate the precise three-dimensional coordinates of the abnormal point. The weighted average method is a simple and effective positioning method. Different weights are given to the data of each sensor according to the distance between the data points monitored by each sensor and the cluster center and the relative position relationship between them. First, the distance of each sensor data point relative to its cluster center is calculated, and then the weight of each sensor is calculated based on these distances. The weight is usually inversely proportional to the distance, that is, the closer the distance, the greater the weight of the sensor: ; in, Indicates The distance weight of each sensor, Indicates The distance from a sensor to an abnormal data point (or cluster center), Is a positive number.

[0060] Finally, the weighted average method is used to perform weighted summation on the position information (three-dimensional coordinates) of each sensor to obtain the estimated three-dimensional coordinates of the abnormal point as the abnormal position, further improving the accuracy of abnormal analysis and facilitating the staff to accurately check the abnormal points.

[0061] like Figure 3 As shown, outputting underground cable pipeline abnormal information according to the abnormal position also includes: Obtain historical underground cable pipeline data, and build an anomaly recognition model based on the historical underground cable pipeline data; Key feature recognition is performed according to the sensors corresponding to the abnormal positions and the underground cable pipeline time series data corresponding to the sensors, and the abnormal information of the underground cable pipeline is obtained based on the key features and the abnormal recognition model.

[0062] The historical underground cable pipeline data at least includes the historical underground cable pipeline abnormal data, and the data under the pipeline abnormal state is used as the underground cable pipeline abnormal data, such as monitoring data under abnormal pipeline temperature change, abnormal environmental humidity change, gas leakage, abnormal pipeline vibration, abnormal pipeline deformation, etc. The collected historical abnormal data are preprocessed, and the neural network model is trained with the preprocessed historical underground cable pipeline abnormal data to obtain an abnormal recognition model. It is understandable that the abnormal recognition model can be pre-built, and the pre-built abnormal recognition model can be directly called when an abnormal data point is found, or the abnormal recognition model can be updated with the abnormal recognition result immediately after a certain abnormal recognition is completed, so as to ensure the accuracy of the abnormal recognition model.

[0063] Key features are extracted from the positional relationship between the abnormal position and the surrounding sensors, the correlation between the abnormal position monitoring data and the surrounding sensor monitoring data, and the time series influence relationship. Key features include time series features, statistical features, and correlation features. Time series features include data change trends (such as rising, falling, and stable), change rates (i.e., the amount of data change per unit time), and periodic laws. These features are used to identify dynamic change patterns in data. Statistical features include mean, standard deviation, skewness, and kurtosis, which are used to understand the overall distribution characteristics of data. The correlation between the abnormal position monitoring data and the surrounding sensor monitoring data is extracted to extract features that can reflect this correlation, such as the correlation coefficient and mutual information between different types of sensor data. The identified key features are input into the anomaly recognition model to obtain the corresponding abnormal state. At this time, the abnormal position and abnormal state of the underground cable pipeline are output to the display terminal as the abnormal information of the underground cable pipeline, so that the staff can intuitively obtain the abnormal situation of the underground cable pipeline, so as to timely investigate and solve the abnormality.

[0064] In other cases, a three-dimensional chart of the underground cable conduit is pre-stored on the display terminal. When the abnormal position and abnormal status of the underground cable conduit are received, the display terminal performs analysis and processing, and displays the abnormal position and abnormal status on the three-dimensional chart of the underground cable conduit in an intuitive and easy-to-understand manner. When displaying, a map can be used to mark the abnormal position, a chart can be used to show the changing trend of the abnormal status, and alarm lights or sound prompts can be used to remind relevant personnel to pay attention.

[0065] As a second embodiment of the present application, step S3 further includes: S31: obtaining a current offset physical quantity based on historical underground cable pipeline offset data and soil distribution in the current area, and constructing an offset grid using the current offset physical quantity and a three-dimensional grid; S32: acquiring underground cable pipeline time series data collected by each sensor based on the collection distribution, performing cluster analysis on the underground cable pipeline time series data based on the offset grid, and acquiring abnormal data points.

[0066] In this embodiment, the current offset physical quantity that affects the offset of underground cable pipelines under the current regional soil distribution is obtained through the historical relationship between the offset influence of physical quantities on underground cables and the influence relationship between soil distribution and offset physical quantity, and the three-dimensional grid is offset-corrected based on the current offset physical quantity to obtain the corresponding offset grid. Therefore, when performing cluster analysis, the sensor default detection point and the actual sensor detection deviation are added to compensate for the sensor detection position error. Without the need for manual correction of the sensor, the abnormal data point can still be obtained through the offset difference between the three-dimensional grid and the offset grid, ensuring the accuracy of abnormal analysis while reducing the need for sensor adjustment.

[0067] Wherein, step S31 further includes: Obtain the correlation between soil distribution and displacement physical quantity based on historical underground cable pipeline displacement data; Obtain the current offset physical quantity according to the regional soil distribution and the correlation between the soil distribution and the offset physical quantity; Constructs an offset mesh using the current offset physics and the 3D mesh.

[0068] The historical underground cable pipeline offset data at least includes the historical underground cable pipeline soil distribution, the historical underground cable pipeline offset, the historical underground cable pipeline offset direction, and the historical underground cable pipeline offset time. The underground cable pipeline offset, the underground cable pipeline offset direction, and the underground cable pipeline offset time are used as offset physical quantities, and the influence of the underground cable pipeline soil distribution on the underground cable pipeline offset direction and offset is used as a weight vector. In some cases, the underground cable pipeline offset time is also affected by the different underground cable pipeline soil distribution conditions. For example, in some soil distribution conditions, the underground cable pipeline offset time is often in the rainy season. According to the historical underground cable pipeline offset data, the correlation between the soil distribution and the offset physical quantity is obtained, and the offset physical quantity under the soil distribution condition in the current area is obtained, so as to correct the deviation of the three-dimensional grid and obtain the offset grid corresponding to the three-dimensional grid of the underground cable pipeline after the offset.

[0069] Correspondingly, step S32 also includes: Acquire underground cable pipeline time series data collected by each sensor based on the collection distribution; Perform a clustering of each sensor based on the offset grid and the acquisition distribution; Perform secondary clustering based on the underground cable pipeline time series data collected by each sensor in the same cluster in the primary clustering; Abnormal data points are obtained based on secondary clustering.

[0070] The offset distribution corresponding to the acquisition distribution can be obtained through the correspondence between the offset grid and the three-dimensional grid. According to the offset distribution, the sensors that are spatially adjacent and have similar functions are classified into the same cluster, and then the underground cable pipeline time series data collected by each sensor in the same cluster are clustered twice. The steps of performing secondary clustering are as follows: The underground cable pipeline time series data collected by each sensor in the same cluster is divided into several subsequences containing continuous observation values ​​according to the preset parameter content; Perform cluster analysis on each subsequence to obtain the clustering results of each subsequence; Abnormal data points are obtained based on the distance algorithm and clustering results.

[0071] In this way, potential anomalies in time series data can be mined. Secondary clustering is based on the similarity of time series data, such as the shape and change trend of the time series. After the secondary clustering is completed, abnormal data points that are significantly different from most data points are identified. Through two clusterings, the spatial distribution of sensors and time series data characteristics can be integrated to more accurately identify abnormal data points and avoid the influence of the same type of sensors with different spatial locations on abnormal data analysis.

[0072] In this embodiment, the first clustering can use clustering algorithms such as K-means, hierarchical clustering, DBSCAN, etc., and the second clustering can use clustering algorithms suitable for time series data such as dynamic time warping, hidden Markov model, autoregressive model, etc.

[0073] In other cases, there may be sensors that deviate from all cluster centers in one clustering. In this case, step S32 further includes: The sensor to be checked is obtained according to a preset threshold of clustering; Based on the historical underground cable pipeline monitoring data of the sensor to be checked and the current underground cable pipeline time series data, it is determined whether the sensor to be checked is abnormal. If so, the sensor abnormality information is output.

[0074] In this case, if the current underground cable pipeline time series data conforms to the fluctuation curve of the historical underground cable pipeline monitoring data, the sensor to be checked is considered normal. If the current underground cable pipeline time series data does not conform to the fluctuation curve of the historical underground cable pipeline monitoring data, the sensor to be checked is considered abnormal, and the sensor abnormality information is output, which is convenient for the staff to check whether the sensor has its own offset or failure.

[0075] In this embodiment, a method for monitoring abnormalities in underground cable pipelines further includes: S5: Obtain the offset grid data within a preset time segment, obtain the offset fluctuation trend of each grid based on the offset grid data, and determine whether the underground cable pipeline has an offset anomaly based on the offset fluctuation trend of each grid and the grid offset threshold. If so, output the underground cable pipeline offset anomaly information.

[0076] By judging whether the offset fluctuation trend of each grid within a preset time segment exceeds the grid offset threshold, it is determined whether the offset of the underground cable pipeline needs to be processed, thereby improving the efficiency and accuracy of the abnormal investigation of underground cable pipelines. In some cases, the grid offset threshold is the offset difference threshold of the opposite grid lines, that is, if the offset difference of the opposite grid lines gradually increases, the corresponding grid will appear larger or smaller, which indicates that the soil environment of the underground cable pipeline has undergone a major migration change or the underground cable pipeline has deformed. At this time, it is necessary to prompt the staff to investigate the actual environment of the underground cable pipeline, and locate the offset anomaly by outputting the corresponding grid coordinates to facilitate the staff to investigate.

[0077] As a third embodiment of the present application, a system for monitoring abnormalities of underground cable pipelines includes: The sensor deployment module builds a three-dimensional grid based on the regional soil distribution and obtains the collection distribution corresponding to each sensor type to be deployed; A data acquisition module is used to obtain the underground cable pipeline time series data collected by each sensor; The data analysis module performs cluster analysis based on the underground cable pipeline time series data to obtain abnormal data points, and analyzes and outputs the abnormal information of the underground cable pipeline.

[0078] In this embodiment, a three-dimensional grid is constructed through the sensor deployment module to obtain the collection distribution corresponding to each type of sensor to be deployed, thereby facilitating the early deployment of sensors. After obtaining the underground cable pipeline time series data collected by each sensor, the data analysis module performs cluster analysis on the underground cable pipeline time series data collected by each sensor and obtains the three-dimensional coordinates of the abnormal data points based on the three-dimensional grid, which improves the accuracy of the underground cable pipeline abnormal analysis and can directly obtain the abnormal coordinates based on the three-dimensional grid, thereby improving the efficiency of the abnormal analysis.

[0079] The data acquisition module at least includes: a strain gauge, a vibration sensor, a temperature sensor for monitoring the state of the pipeline itself, and a humidity sensor and a gas sensor for monitoring the pipeline environment.

[0080] The data analysis module at least includes: an abnormal data judgment unit, an abnormal position determination unit and an abnormal state judgment unit. The abnormal data judgment unit is used to perform cluster analysis on the pre-processed underground cable pipeline time series data to identify abnormal data points in the underground cable pipeline time series data; the abnormal position determination unit is used to combine the monitoring data of multiple sensors, use multi-source data fusion and three-dimensional positioning algorithm to locate the abnormal data points and obtain the abnormal position; the abnormal state judgment unit is used to combine the abnormal position and the changes in the sensor monitoring data at the abnormal data point to determine the abnormal state of the abnormal data point.

[0081] In some other embodiments, a system for monitoring abnormalities of underground cable pipelines further includes: The display module interacts with the user to display the abnormal position and abnormal state of the underground cable pipeline.

[0082] As a fourth embodiment of the present application, a computer-readable storage medium is used to store a computer program or instruction. When the computer program or instruction is executed by a processing device, the above-mentioned underground cable pipeline abnormality monitoring method is implemented. The computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state hard disk), etc.

[0083] The specific implementation described above is a preferred implementation of an underground cable pipeline abnormality monitoring method and system of the present application, and is not intended to limit the specific implementation scope of the present application. The scope of the present application includes but is not limited to the specific implementation embodiment. All equivalent changes made in accordance with the shape and structure of the present application are within the protection scope of the present application.

Claims

1. A method for monitoring abnormalities of underground cable pipelines, characterized in that: The steps include: S1: Construct a three-dimensional grid based on the regional soil distribution, and obtain a collection point data set based on the three-dimensional grid and underground cable pipeline data; S2: based on the type of sensor to be deployed and the data set of the collection points, obtaining the collection distribution corresponding to each type of sensor to be deployed; S3: acquiring the underground cable pipeline time series data collected by each sensor based on the collection distribution, performing cluster analysis on the underground cable pipeline time series data, and obtaining abnormal data points; S4: Obtain the abnormal position according to the abnormal data points and the collection distribution, and output the abnormal information of the underground cable pipeline according to the abnormal position.

2. The method for monitoring abnormalities of underground cable pipelines according to claim 1, characterized in that: The constructing of a three-dimensional grid based on regional soil distribution includes: Construct a horizontal grid at preset intervals along the horizontal direction; Construct vertical grids based on soil structure information; Construct a three-dimensional grid with horizontal and vertical grids.

3. The method for monitoring abnormalities of underground cable pipelines according to claim 2, characterized in that: The step of constructing a horizontal grid at preset intervals along the horizontal direction comprises: The interval is obtained based on expert experience, the average interval is obtained based on the horizontal underground cable pipeline layout, minimum cost and interval, and the horizontal grid is constructed using the average interval as the preset interval.

4. The method for monitoring abnormalities of underground cable pipelines according to claim 1, characterized in that: The acquisition of the collection point data set based on the three-dimensional grid and the underground cable pipeline data includes: A grid intersection set is obtained based on the three-dimensional grid, the layout point angle is obtained based on the pipeline shape, and the collection point data set is obtained based on the grid intersection set and the layout point angle.

5. The method for monitoring abnormalities of underground cable pipelines according to claim 1, characterized in that: The acquiring of the collection distribution corresponding to each type of sensor to be deployed based on the type of sensor to be deployed and the collection point data set comprises: Based on the demand for data to be collected, the type of sensor to be deployed is obtained, the collection parameter characteristics corresponding to the sensor type to be deployed are obtained, and the collection distribution that meets the collection parameter characteristic requirements is obtained in the collection point data set corresponding to each sensor type to be deployed.

6. The method for monitoring abnormalities of underground cable pipelines according to claim 1, characterized in that: The performing cluster analysis on the underground cable pipeline time series data to obtain abnormal data points includes: Divide the underground cable pipeline time series data into several subsequences containing continuous observation values ​​according to the preset parameter content; Perform cluster analysis on each subsequence to obtain the clustering results of each subsequence; Abnormal data points are obtained based on the distance algorithm and clustering results.

7. The method for monitoring abnormalities of underground cable pipelines according to claim 1, characterized in that: The obtaining of the abnormal position according to the abnormal data point and the collection distribution includes: Obtain the corresponding sensor set according to each abnormal data point; Using the sensor set to obtain a sensor position point set; The abnormal area is obtained by using the sensor location point set and collection distribution, and the sensor monitoring data corresponding to the abnormal area is obtained; Based on the relative position relationship of the sensors, the sensor monitoring data is weighted averaged to obtain the abnormal position.

8. The method for monitoring abnormalities of underground cable pipelines according to claim 1, characterized in that: The outputting of underground cable pipeline abnormal information according to the abnormal position also includes: Obtain historical underground cable pipeline data, and build an anomaly recognition model based on the historical underground cable pipeline data; Key feature recognition is performed according to the sensors corresponding to the abnormal positions and the underground cable pipeline time series data corresponding to the sensors, and the abnormal information of the underground cable pipeline is obtained based on the key features and the abnormal recognition model.

9. The method for monitoring abnormalities of underground cable pipelines according to claim 1, characterized in that: The S3 further includes: S31: obtaining a current offset physical quantity based on historical underground cable pipeline offset data and soil distribution in the current area, and constructing an offset grid using the current offset physical quantity and a three-dimensional grid; S32: acquiring underground cable pipeline time series data collected by each sensor based on the collection distribution, performing cluster analysis on the underground cable pipeline time series data based on the offset grid, and acquiring abnormal data points.

10. The method for monitoring abnormalities of underground cable pipelines according to claim 9, characterized in that: The S31 further includes: Obtain the correlation between soil distribution and displacement physical quantity based on historical underground cable pipeline displacement data; Obtain the current offset physical quantity according to the regional soil distribution and the correlation between the soil distribution and the offset physical quantity; Constructs an offset mesh using the current offset physics and the 3D mesh.

11. The method for monitoring abnormalities of underground cable pipelines according to claim 9, characterized in that: The S32 further includes: Acquire underground cable pipeline time series data collected by each sensor based on the collection distribution; Perform a clustering of each sensor based on the offset grid and the acquisition distribution; Perform secondary clustering based on the underground cable pipeline time series data collected by each sensor in the same cluster in the primary clustering; Abnormal data points are obtained based on secondary clustering.

12. The method for monitoring abnormalities of underground cable pipelines according to claim 11, characterized in that: The S32 further includes: The sensor to be checked is obtained according to a preset threshold of clustering; Based on the historical underground cable pipeline monitoring data of the sensor to be checked and the current underground cable pipeline time series data, it is determined whether the sensor to be checked is abnormal. If so, the sensor abnormality information is output.

13. The method for monitoring abnormalities of underground cable pipelines according to claim 9, characterized in that: Also includes: S5: Obtain the offset grid data within a preset time segment, obtain the offset fluctuation trend of each grid based on the offset grid data, and determine whether the underground cable pipeline has an offset anomaly based on the offset fluctuation trend of each grid and the grid offset threshold. If so, output the underground cable pipeline offset anomaly information.

14. An underground cable pipeline abnormality monitoring system, used to implement the method according to any one of claims 1 to 13, characterized in that: include: The sensor deployment module builds a three-dimensional grid based on the regional soil distribution and obtains the collection distribution corresponding to each sensor type to be deployed; A data acquisition module is used to obtain the underground cable pipeline time series data collected by each sensor; The data analysis module performs cluster analysis based on the underground cable pipeline time series data to obtain abnormal data points, and analyzes and outputs the abnormal information of the underground cable pipeline.

Images