A big data-based cable system fault analysis method

Abstract

The present invention discloses a method for analyzing cable system faults based on big data, belonging to the technical field of cable fault analysis. Specifically, it includes: implanting flexible deformation sensing units at several preset position points of the cable, and each sensing unit synchronously collects multi-dimensional deformation data at the position point where it is located; mapping the real-time deformation data collected by each sensing unit to a virtual cable three-dimensional model to generate sensing nodes; performing spatio-temporal clustering analysis on the deformation data of all sensing nodes, calculating the similarity metric values of the deformation characteristics of the data of different sensing nodes, and marking the sensing nodes with abnormal data patterns as an abnormal node set; according to the spatial distribution characteristics of the abnormal node set, by analyzing the diffusion direction of the abnormal data cluster and the correlation of the deformation data of adjacent nodes, locating the cable fault probability interval segment; and marking a visual warning sign; realizing the detection of defects in early faults of non-electrical factors.

Description

Technical Field

[0001] The present invention relates to the technical field of cable fault analysis, and specifically relates to a method for analyzing cable system faults based on big data. Background Art

[0002] With the increasing dependence of modern society on electricity, as a key carrier for power transmission, the stability and reliability of cable operation are crucial. In the construction of large-scale power infrastructure such as smart grids and urban utility tunnels, long-distance and high-capacity cable systems have been widely used. However, the cable laying environment is complex, affected by various factors such as geological changes, external force damage, temperature changes, and material aging, and is prone to failures, which may further lead to large-scale power outages, seriously affecting social economy and people's lives.

[0003] For a long time, cable fault detection and analysis methods have mainly focused on electrical parameters, and the monitoring of parameters such as current, voltage, and resistance has become the core of traditional methods. Although this monitoring mode can detect obvious electrical faults to a certain extent, it is ineffective in the face of early faults caused by non-electrical factors such as mechanical stress causing local structural deformation of the cable or cable stretching and extrusion caused by geological settlement. For example, when the cable is subjected to mechanical stress generated by surrounding construction excavation and begins to show slight structural deformation, its electrical parameters may remain within the normal fluctuation range for a long time, making it difficult to timely and accurately reflect this potential fault hidden danger. By the time the electrical parameters change significantly, the cable fault has often developed to a more serious stage.

[0004] Therefore, the existing method of relying solely on electrical parameter monitoring for cable faults has serious monitoring blind spots when dealing with early faults caused by non-electrical factors in a complex operating environment, and it is difficult to achieve early accurate warning and effective diagnosis of cable faults. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for analyzing cable system faults based on big data, and solve the following technical problems:

[0006] Collecting only parameters in the electrical dimension cannot analyze early faults caused by non-electrical factors such as mechanical stress and structural deformation.

[0007] The purpose of the present invention can be achieved by the following technical solutions:

[0008] A method for analyzing cable system faults based on big data includes the following steps:

[0009] Flexible deformation sensing units are implanted at several preset position points of the cable, and each sensing unit synchronously collects multi-dimensional deformation data at the corresponding position point, including the surface curvature change amount, the axial tensile strain rate, and the radial compression fluctuation frequency;

[0010] Map the real-time deformation data collected by each sensing unit to a virtual three-dimensional cable model to generate sensing nodes, and dynamically adjust the model weights based on the deformation coupling relationship between adjacent sensing nodes;

[0011] Perform spatio-temporal clustering analysis on the deformation data of all sensing nodes, calculate the similarity metric values of the deformation characteristics of the data of different sensing nodes, and mark the sensing nodes with abnormal data patterns as an abnormal node set;

[0012] According to the spatial distribution characteristics of the abnormal node set, locate the cable fault probability interval segment by analyzing the diffusion direction of the abnormal data cluster and the correlation of the deformation data of adjacent nodes;

[0013] Mark a visual warning sign on the corresponding physical actual interval segment of the cable in the cable fault probability interval segment.

[0014] As a further solution of the present invention: the flexible deformation sensing unit is composed of a high-elasticity base material and a distributed optical fiber sensing array. The surface of the high-elasticity base material is provided with a wavy microstructure, and a flexible circuit wound in a spiral is embedded inside. The optical fiber sensing array covers the circumferential surface of the cable in a staggered arrangement manner, and the communication link between the sensing units adopts an adaptive frequency hopping mechanism.

[0015] As a further solution of the present invention: the construction process of the virtual three-dimensional cable model is as follows:

[0016] Discretize the physical structure of the cable into a node network with weights. The node weights reflect the historical fault probability of the corresponding position point. Input the real-time deformation data into the node network, dynamically update the connection edge weights according to the deformation data difference degree of adjacent nodes, introduce a time decay factor to adjust the data weights of the deformation data in different time sequences, and automatically trigger the topology reconstruction mechanism when it is detected that the weights of three consecutive nodes increase abnormally synchronously.

[0017] As a further solution of the present invention: the specific process of the spatio-temporal clustering analysis is as follows:

[0018] Convert the deformation data collected by each sensing node into data units containing spatial position encoding, time series identification, and multi-dimensional feature vectors, and identify abnormal data patterns through a preset spatio-temporal density clustering algorithm. In the spatio-temporal density clustering algorithm, cable physical structure constraint conditions are introduced, and nodes in the same material property section are assigned set spatial correlation weights. During the clustering process, the conduction attenuation characteristics of the deformation features along the cable axis are synchronously excluded. When abnormal data of an isolated node is detected, by comparing the deformation fluctuation correlation of the upstream and downstream nodes of the isolated node within a preset time window, the true fault signal is distinguished from local interference noise. Finally, a set of abnormal data clusters with spatio-temporal continuity is generated, and the spatial distribution of the data cluster set represents the interval range of potential cable faults.

[0019] As a further solution of the present invention: The process of spatio-temporal clustering analysis further includes:

[0020] Perform physical rationality verification on the generated set of abnormal data clusters, screen out data clusters that conform to the material damage evolution law by calling the cable material fatigue characteristic database; establish a dynamic weight adjustment mechanism to automatically adjust the clustering density threshold according to the time persistence and spatial extensibility of the data clusters; introduce an expert experience rule base to perform confidence weighting on data clusters located at cable branch nodes or high-incidence areas of historical faults; finally output the verified optimized clustering results, and generate fault type labels by comparing the clustering feature vectors with the feature templates in the typical fault mode database.

[0021] As a further solution of the present invention: The process of locating the cable fault probability interval section includes:

[0022] Taking the core node of the abnormal data cluster as the base point, extend to both sides to establish a dynamic detection interval, and determine the interval boundary by analyzing the gradient change rate and statistical distribution consistency of the deformation data in the extension direction. For the interval section that crosses the cable branch node, automatically call the branch line historical fault database to adjust the boundary threshold, generate a preliminary fault probability interval section and attach a confidence rating.

[0023] As a further solution of the present invention: The calculation process of the confidence rating is:

[0024] Extract the deformation feature vectors within the preliminary fault probability interval section, perform similarity matching with the feature templates in the typical fault mode database, and calculate the probability value of the fault occurrence within the interval section according to the matching result; at the same time, introduce time dimension analysis to assign a higher confidence weight to the interval section with continuous abnormal data; finally output an optimized fault probability interval section with a confidence rating, and the confidence rating is used to mark the priority order of operation and maintenance.

[0025] As a further solution of the present invention: The visual warning sign marks the fault probability interval in the form of a gradient color band, and the color depth of the color band is in direct proportion to the aggregation density of abnormal data within the interval.

[0026] Advantages of the present invention:

[0027] By implanting a flexible deformation sensing unit capable of collecting multi-dimensional deformation data such as surface curvature change amount, axial tensile strain rate, and radial compression fluctuation frequency at a preset position of the cable, it makes up for the defect that only relying on electrical parameter monitoring cannot reflect the physical deformation state of the cable and it is difficult to detect early faults caused by non-electrical factors. Mapping the real-time deformation data to the virtual 3D cable model and dynamically adjusting the model weights, combined with spatio-temporal clustering analysis, can accurately locate abnormal nodes and fault probability intervals, overcoming the problems of incomplete monitoring and inaccurate fault diagnosis in traditional methods. The visual warning sign intuitively presents the fault probability interval, and the color depth of the color band is proportional to the aggregation density of abnormal data, realizing timely warning and ensuring the safe and stable operation of the cable system. Description of the Drawings

[0028] The present invention will be further described below with reference to the drawings.

[0029] Figure 1 It is a flow schematic diagram of the present invention. Detailed Embodiments

[0030] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts shall fall within the protection scope of the present invention.

[0031] Please refer to Figure 1 As shown, the present invention is a method for analyzing cable system faults based on big data, including the following steps:

[0032] First, at several precisely preset position points of the cable, flexible deformation sensing units are ingeniously implanted. These sensing units are the so-called "intelligent sensing pioneers". They are composed of a composite of a highly elastic substrate material and a distributed fiber optic sensing array. The surface of the highly elastic substrate material is provided with a unique wavy microstructure, and a helically wound flexible circuit is embedded inside. The fiber optic sensing array closely covers the circumferential surface of the cable in a staggered arrangement. The communication link between the sensing units adopts an adaptive frequency hopping mechanism to ensure stable data transmission. Each sensing unit can synchronously collect rich multi-dimensional deformation data at the position point where it is located, including the surface curvature change amount that accurately reflects the change in the bending degree of the cable surface, the axial tensile strain rate that clearly reflects the degree of stretching of the cable in the axial direction, and the radial compression fluctuation frequency that accurately represents the change in the compression frequency of the cable in the radial direction.

[0033] Subsequently, the real-time deformation data collected by each sensing unit is mapped into a carefully constructed virtual three-dimensional cable model by a sophisticated algorithm, and then sensing nodes are generated. In this virtual model, based on the deformation coupling relationship existing between adjacent sensing nodes, that is, when a certain node deforms, it will affect adjacent nodes, the weights of the model are dynamically adjusted. For example, when a node undergoes axial tensile strain due to external factors, the strain conditions of adjacent nodes will be fed back into the model, and by continuously adjusting the weights, the model can better fit the real operating state of the cable.

[0034] Next, in-depth spatio-temporal clustering analysis is carried out on the deformation data of all sensing nodes. First, the deformation data collected by each sensing node is converted into data units containing spatial position coding, time series identification, and multi-dimensional feature vectors, and then the preset spatio-temporal density clustering algorithm is used to identify abnormal data patterns. In this process, the physical structure constraints of the cable are introduced, and set spatial correlation weights are assigned to the nodes in the same material property section, and at the same time, the conduction attenuation characteristics of the deformation characteristics along the axial direction of the cable are cleverly excluded. When abnormal data of an isolated node is detected, by comparing the deformation fluctuation correlation of the upstream and downstream nodes of the isolated node within a preset time window, the real fault signal and local interference noise are accurately distinguished, and finally a set of abnormal data clusters with spatio-temporal continuity is generated. The spatial distribution of these data cluster sets intuitively represents the interval range of potential cable faults.

[0035] Then, according to the spatial distribution characteristics of the abnormal node set, a dynamic detection interval is established by extending from the core node of the abnormal data cluster to both sides. By carefully analyzing the gradient change rate and statistical distribution consistency of the deformation data in the extension direction, the interval boundary is determined. For the interval section spanning the cable branch node, the branch line historical fault database is automatically called to adjust the boundary threshold, so as to accurately locate the cable fault probability interval section and attach a confidence rating.

[0036] Finally, in the physical actual interval section of the cable corresponding to the cable fault probability interval section, visual warning signs are marked in an intuitive and eye-catching manner. The signs are presented in the form of a gradient color band, and the depth of the color of the color band is proportional to the density of abnormal data aggregation within the interval. Staff can quickly judge the high and low fault probability through the depth of the color, so as to take corresponding measures in a timely manner, greatly ensuring the safe and stable operation of the cable system.

[0037] In a preferred embodiment of the present invention, the flexible deformation sensing unit adopted has a unique and delicate structure. It is composed of a highly elastic base material and a distributed optical fiber sensing array, and this combination is a perfect match. The highly elastic base material is like a solid and tough "protective armor", providing basic support for the entire sensing unit. The wavy microstructures carefully set on its surface greatly increase the contact friction with the cable surface, ensuring that the sensing unit is firmly attached to the cable surface and is not easily displaced due to external impact or the daily vibration of the cable. For example, in some urban underground pipe galleries, the cable will have a small displacement due to the vibration of passing vehicles, and the wavy microstructures can effectively handle such situations. A flexible circuit wound in a spiral is embedded inside, just like the neural network of the human body, responsible for transmitting various electrical signals and ensuring the stability of data collection and transmission. The optical fiber sensing array tightly covers the circumferential surface of the cable in a staggered arrangement, and can comprehensively and without dead angles sense the subtle deformations of the cable in all directions. The optical fiber sensing units at different positions can simultaneously monitor the deformations of different parts of the cable, just like multiple "scouts" working together to ensure comprehensive information acquisition. The communication link between the sensing units adopts an adaptive frequency hopping mechanism, which can automatically adjust the communication frequency according to the changes in the surrounding electromagnetic environment, effectively avoiding signal interference. For example, near a substation with a complex electromagnetic environment, the adaptive frequency hopping mechanism can enable the sensing unit to stably transmit data and ensure the accuracy of monitoring.

[0038] In another preferred embodiment of the present invention, the construction process of the virtual cable three-dimensional model involves advanced technical logic. First, the physical structure of the cable is discretized into a weighted node network, which is like dividing a continuous cable into multiple key "monitoring points". The weight of each node reflects the historical failure probability of the corresponding position point. For example, during past operation, a certain section of the cable was frequently affected by the vibration of construction machinery due to its proximity to a construction site, resulting in frequent failures. Then the weight of the node corresponding to this position will be relatively high. Next, the real-time deformation data is input into this node network, and the connection edge weights are dynamically updated according to the difference degree of the deformation data of adjacent nodes. Suppose there are adjacent nodes A and B. If the axial tensile strain rate detected at node A suddenly increases, while the strain rate change at node B is relatively small, then the edge weight connecting nodes A and B will be adjusted according to this difference degree to more accurately reflect the actual mechanical conduction relationship of the cable. At the same time, a time decay factor is introduced to adjust the data weights of deformation data in different time sequences, and higher weights are assigned to the deformation data that occurred recently because it can better reflect the current operating state of the cable. For example, the weight of the deformation data from a week ago will be lower than the data newly collected yesterday. When it is detected that the weights of three consecutive nodes increase synchronously and abnormally, the topology reconstruction mechanism is automatically triggered. For example, due to geological settlement in a certain area of the cable, the weights of three adjacent nodes increase significantly within a short period of time. At this time, the system will immediately start topology reconstruction and optimize the node network again to more accurately monitor the potential cable faults in this area and provide a more reliable model basis for subsequent fault analysis.

[0039] In another preferred embodiment of the present invention, the specific process of spatio-temporal clustering analysis is as follows:

[0040] First, the deformation data collected by each sensing node is processed and converted into data units containing spatial position encoding, time series identification, and multi-dimensional feature vectors. The spatial position encoding is like assigning a unique "geographical coordinate" to each sensing node, which can clearly identify its specific position on the cable. For example, if the cable is divided into multiple sections, and each section has multiple monitoring points, the spatial position encoding can be accurate to the specific section and monitoring point number. The time series identification records the time information of data collection, which can reflect the change of deformation data over time. For example, it can mark the deformation data of a certain monitoring point at different times within a day. The multi-dimensional feature vector contains multi-dimensional information such as surface curvature change amount, axial tensile strain rate, and radial compression fluctuation frequency, comprehensively describing the deformation state of the cable at this position.

[0041] Next, the preset spatio-temporal density clustering algorithm is used to identify abnormal data patterns. This algorithm introduces the physical structure constraints of the cable because the physical structure and material properties of different parts of the cable are different, which will affect the propagation and manifestation of deformation. For example, when the cable passes through different geological regions, due to the different hardness and stability of the soil, the stress on the cable will also be different. Therefore, a set spatial correlation weight is assigned to the nodes in the same material property section. Suppose a section of cable is laid in a uniform rock layer, and the spatial correlation weight between the nodes in this section is relatively high because their deformations may affect each other. At the same time, during the clustering process, the conduction attenuation characteristics of the deformation characteristics along the axial direction of the cable are excluded synchronously. When the cable transmits deformation axially, it will attenuate with the increase of distance, just like the sound weakens gradually during propagation. Excluding this characteristic can avoid misjudgment caused by attenuation and make the clustering result more accurate.

[0042] When abnormal data of an isolated node is detected, it is necessary to carefully distinguish whether it is a real fault signal or local interference noise. It is judged by comparing the deformation fluctuation correlation of the upstream and downstream nodes of the isolated node within a preset time window. For example, within a one-hour time window, if an isolated node shows an abnormal axial tensile strain rate, but the deformation fluctuations of its upstream and downstream nodes are normal during the same time and there is no obvious correlation, then this abnormal data is very likely to be local interference noise; on the contrary, if the upstream and downstream nodes also show similar deformation fluctuation trends, it is more likely to be a real fault signal. After such a series of processes, a set of abnormal data clusters with spatio-temporal continuity is finally generated, and the spatial distribution of these data clusters clearly characterizes the range of potential cable faults.

[0043] In a preferred case of this embodiment, in order to further improve the accuracy and reliability of spatio-temporal clustering analysis, multi-faceted optimization processing is also performed on the generated set of abnormal data clusters.

[0044] The first step is to perform physical rationality verification. By calling the cable material fatigue characteristic database, the data clusters that conform to the material damage evolution law are screened out. Different cable materials will have specific damage evolution laws during long-term use. For example, after a certain number of tensile and compressive cycles, a certain cable material will show a specific deformation pattern. If an abnormal data cluster conforms to the damage evolution law of this material, then it is more likely to represent a real fault.

[0045] The second step is to establish a dynamic weight adjustment mechanism. Automatically adjust the clustering density threshold according to the time persistence and spatial extensibility of the data clusters. If an abnormal data cluster continuously appears, it indicates that the fault may be developing continuously; if it has a large extension range in space, it also means that the fault may be relatively serious. In this case, appropriately reducing the clustering density threshold can capture fault information more sensitively. For example, when an abnormal data cluster appears continuously for three days and covers a long section of the cable, the clustering density threshold can be reduced to include more relevant abnormal data in this data cluster.

[0046] The third step is to introduce an expert experience rule base. Perform confidence weighting on the data clusters located at cable branch nodes or high-incidence areas of historical faults. The stress distribution at cable branch nodes is relatively complex and prone to faults; in high-incidence areas of historical faults, there is a higher probability of reoccurrence of faults. Experts have summarized some rules based on past experience. For example, at a specific branch node, if a specific type of deformation anomaly appears, the probability of a fault is higher. By introducing the expert experience rule base and assigning higher confidence weights to the data clusters in these areas, the fault risk can be evaluated more accurately.

[0047] Finally, output the verified optimized clustering results, and generate fault type labels by comparing the clustering feature vectors with the feature templates in the typical fault mode database. The typical fault mode database stores the feature templates of various common faults. For example, faults such as local damage and overstretching of the cable have their unique features. By comparing the clustering feature vectors with these templates, the type of fault can be quickly and accurately determined, providing a strong basis for subsequent repair and treatment.

[0048] In another preferred embodiment of the present invention, the process of locating the cable fault probability interval section includes:

[0049] First, take the core node of the abnormal data cluster as the base point. The core node of the abnormal data cluster is determined in the previous spatio-temporal clustering analysis. It represents the position where the abnormal data is most concentrated and the features are most obvious, just like the center of a storm. Starting from this core node, extend to both sides to establish a dynamic detection interval. This dynamic detection interval is not fixed and will be adjusted according to the actual situation of the cable and the changes in the data.

[0050] When determining the interval boundaries, it is necessary to analyze the gradient change rate and statistical distribution consistency of the deformation data in the extension direction. The gradient change rate of the deformation data reflects how fast the deformation changes in space. For example, if the gradient change rate of the deformation data suddenly increases in a certain direction, it indicates that the deformation of the cable in this direction has changed relatively violently, and it is very likely the boundary affected by the fault. The statistical distribution consistency refers to analyzing whether the data in the extension direction conforms to a certain specific statistical law. If there are obvious differences in the statistical distribution of the data at a certain position, it can also be used as a basis for determining the interval boundaries.

[0051] When encountering an interval segment that spans a cable branch node, the situation becomes more complex. The cable branch node is a key position in the cable line. Its structure and stress conditions are different from those of ordinary lines, and it is also more prone to faults historically. At this time, the system will automatically call the historical fault database of the branch line. This database records various information about past faults on this branch line, including the location, type, frequency, etc. of the faults. By analyzing these historical data, the boundary threshold can be adjusted. For example, if a certain branch node has often experienced faults caused by external force extrusion in the past, then when determining the boundaries of the interval segment that spans this node, the boundary range will be appropriately expanded to more comprehensively cover the areas where faults may occur. After such processing, a preliminary fault probability interval segment is generated, and a confidence rating will be attached to it.

[0052] The calculation process of the confidence rating is a further evaluation of the preliminary fault probability interval segment. It can help the operation and maintenance personnel more accurately judge the possibility and severity of the fault. The process is as follows:

[0053] The first step is to extract the deformation feature vectors within the preliminary fault probability interval segment. The deformation feature vectors contain various deformation information of the cable within this interval segment, such as the surface curvature change amount, axial tensile strain rate, and radial compression fluctuation frequency, etc. These feature vectors are matched with the feature templates in the typical fault mode database. The typical fault mode database stores the feature templates of various known faults, just like a "dictionary" of faults. For example, if the deformation feature vectors within a certain interval segment have a high similarity with the feature template of "local cable damage" in the database, it indicates that the possibility of local cable damage fault occurring in this interval segment is relatively high. According to the matching results, the probability value of the fault occurring within the interval segment is calculated.

[0054] Meanwhile, time - dimension analysis is introduced. If abnormal data continuously appears in an interval segment, it indicates that the fault may be continuously developing or has existed for some time, and its severity may be higher. Therefore, a higher confidence - weight will be assigned to the interval segment where abnormal data continuously appears. For example, if abnormal axial tensile strain rates are detected in an interval segment for three consecutive days, its confidence - weight will be higher than that of an interval segment where abnormal data appears only for one day.

[0055] Finally, an optimized fault - probability interval segment with a confidence rating is output. This confidence rating is like a "priority label", based on which operation and maintenance personnel can determine the order of operation and maintenance. An interval segment with a high confidence rating means a greater likelihood of a fault occurring and a more serious impact, and thus requires priority inspection and maintenance; while an interval segment with a low confidence rating can be processed later. This can improve the efficiency of operation and maintenance work and ensure the rational utilization of limited resources.

[0056] In another preferred embodiment of the present invention, the visual warning sign uses a gradient - color band form to visually mark the fault - probability interval segment of the cable. The higher the density of abnormal data aggregation within the interval, the deeper the color of the color band. For example, in a certain section of the cable, if due to long - term external force extrusion, abnormal data is densely distributed, the color of the color band corresponding to this interval will be dark and rich; while in the area where abnormal data is relatively sparse, the color of the color band is light. Operation and maintenance personnel can quickly lock in high - risk fault areas just by visual observation, greatly improving the efficiency of fault troubleshooting and ensuring the stable operation of the cable system.

[0057] The above has described a detailed description of an embodiment of the present invention, but the content described is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A method for analyzing cable system faults based on big data, characterized in that, Including the following steps: Flexible deformation sensing units are implanted at several preset position points of the cable. Each sensing unit synchronously collects multi-dimensional deformation data at the corresponding position point, including surface curvature change amount, axial tensile strain rate, and radial compression fluctuation frequency; The real-time deformation data collected by each sensing unit is mapped to a virtual 3D cable model to generate sensing nodes, and the model weights are dynamically adjusted based on the deformation coupling relationship between adjacent sensing nodes; Spatio-temporal clustering analysis is performed on the deformation data of all sensing nodes to calculate the similarity metric values of the deformation characteristics of the data of different sensing nodes, and the sensing nodes with abnormal data patterns are marked as an abnormal node set; According to the spatial distribution characteristics of the abnormal node set, by analyzing the diffusion direction of the abnormal data cluster and the correlation of the deformation data of adjacent nodes, the cable fault probability interval segment is located; Visual warning signs are marked on the corresponding physical actual interval segment of the cable in the cable fault probability interval segment; The construction process of the virtual 3D cable model is as follows: The physical structure of the cable is discretized into a weighted node network. The node weight reflects the historical fault probability of the corresponding position point. The real-time deformation data is input into the node network, and the connection edge weights are dynamically updated according to the deformation data difference degree of adjacent nodes. A time decay factor is introduced to adjust the data weights of the deformation data in different time sequences. When it is detected that the weights of three consecutive nodes increase abnormally synchronously, the topology reconstruction mechanism is automatically triggered; The process of locating the cable fault probability interval segment includes: Taking the core node of the abnormal data cluster as the base point, a dynamic detection interval is established by extending to both sides. The interval boundary is determined by analyzing the gradient change rate and statistical distribution consistency of the deformation data in the extension direction. For the interval segment crossing the cable branch node, the historical fault database of the branch line is automatically called to adjust the boundary threshold, and a preliminary fault probability interval segment is generated and attached with a confidence rating.

2. The method for analyzing cable system faults based on big data according to claim 1, wherein, The flexible deformation sensing unit is composed of a high-elastic base material and a distributed optical fiber sensing array. The surface of the high-elastic base material is provided with a wavy microstructure, and a flexible circuit wound in a spiral is embedded inside. The optical fiber sensing array covers the circumferential surface of the cable in a staggered arrangement manner, and the communication link between the sensing units adopts an adaptive frequency hopping mechanism.

3. The method for analyzing faults of a big data cable system according to claim 1, wherein, The specific process of the spatio-temporal clustering analysis is as follows: The deformation data collected by each sensing node is converted into a data unit including spatial position coding, time series identification, and multi-dimensional feature vectors. Abnormal data patterns are identified through a preset spatio-temporal density clustering algorithm. In the spatio-temporal density clustering algorithm, cable physical structure constraint conditions are introduced, and set spatial correlation weights are assigned to the nodes in the same material property section. During the clustering process, the conduction attenuation characteristics of the deformation characteristics along the axial direction of the cable are synchronously excluded. When abnormal data of an isolated node is detected, by comparing the deformation fluctuation correlation of the upstream and downstream nodes of the isolated node within a preset time window, the real fault signal is distinguished from local interference noise, and finally an abnormal data cluster set with spatio-temporal continuity is generated. The spatial distribution of the data cluster set represents the interval range of potential cable faults.

4. A method for analyzing faults in a big data cable system according to claim 3, characterized in that, The process of the spatio-temporal clustering analysis also includes: Perform physical rationality verification on the generated abnormal data cluster set, and screen out the data clusters that conform to the material damage evolution law by calling the cable material fatigue characteristic database; establish a dynamic weight adjustment mechanism to automatically adjust the clustering density threshold according to the time persistence and spatial extensibility of the data clusters; introduce an expert experience rule base to perform confidence weighting on the data clusters located at cable branch nodes or high-incidence areas of historical faults; finally, output the verified optimized clustering results, and generate fault type labels by comparing the clustering feature vectors with the feature templates in the typical fault mode database.

5. A method for analyzing faults in a big data cable system according to claim 1, characterized in that, The calculation process of the confidence rating is as follows: Extract the deformation feature vectors within the preliminary fault probability interval segment, perform similarity matching with the feature templates in the typical fault mode database, and calculate the probability value of fault occurrence within the interval segment according to the matching results; at the same time, introduce time dimension analysis and assign a higher confidence weight to the interval segment with continuously abnormal data; finally, output the optimized fault probability interval segment with a confidence rating, and the confidence rating is used to mark the priority ranking of operation and maintenance.

6. A method for analyzing faults in a big data cable system according to claim 1, characterized in that, The visual warning sign marks the fault probability interval segment in the form of a gradient color band, and the depth of the color of the color band is directly proportional to the aggregation density of abnormal data within the interval.

Images