Intelligent early warning and monitoring system for power line faults in tunnel environment

Abstract

The application discloses a tunnel environment power line fault intelligent early warning and monitoring system and relates to the field of power fault identification.The system comprises an instruction control module, a line planning module and the like.The instruction control module is used for accessing the power line general network of a target tunnel, acquiring operation data access and control instruction issuing authority, and the like.The line planning module is based on the topological structure and historical fault point position distribution of the power line of the target tunnel, takes the same point data historical fault distribution as the target, divides the overall line into different scales, and outputs a plurality of different scale lines with physical coordinates and electrical parameters.Through dynamic adjustable multi-scale line division, the traditional global fixed monitoring mode is broken through, the line is divided into different scale independent monitoring units, dynamic merging or cutting according to data trends is supported, the division scale of the line is dynamically adjusted according to the trend deterioration degree and historical data analysis, the optimal segmentation point is flexibly selected under different conditions by using an optimization algorithm, and local fine monitoring is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power failure identification, in particular to an intelligent early warning and monitoring system for power line failure in a tunnel environment. BACKGROUND

[0002] Power lines are a key part of power supply inside and outside the tunnel, and any failure can cause power interruption, seriously affecting the safe operation of the tunnel. The tunnel generally has a narrow space, limited traffic capacity and complex geographical conditions, and the laying of power lines often faces many technical challenges. With the development of Internet of Things and big data technology, intelligent monitoring and early warning systems have gradually emerged, which can monitor various environmental parameters in real time and perform data analysis. The tunnel environment is affected by geological activities, traffic load and construction vibration, and other factors, which can cause vibration and settlement of power lines.

[0003] In a tunnel environment, one of the factors that has a significant interference effect is vibration. In most cases, ordinary vibration does not have much impact due to the seismic design of the tunnel, but if the frequency or intensity exceeds the safety standard, it may cause sudden line failure in certain circumstances, thereby affecting power transmission.

[0004] Traditional identification, early warning and monitoring methods often focus on global general screening. For abnormal data acquisition, data can be collected through sensors, etc. However, if global prediction is still used for future abnormal data warning, it not only lacks accuracy, but also is time-consuming, resulting in waste of computing power and storage resources. It is difficult to accurately identify specified areas with analysis value and conduct targeted prediction analysis, resulting in insufficient sensitivity of fault monitoring and missing potential local hazards. In the case of long tunnels and large data collection, resource consumption is significant, and many important abnormal trend information cannot be effectively utilized, and it is difficult to adaptively adjust the size of several identifiable areas according to the prediction trend. SUMMARY

[0005] (I) Technical problems solved

[0006] In view of the above-mentioned shortcomings of the prior art, the present application provides an intelligent early warning and monitoring system for power line failure in a tunnel environment, which can effectively solve the problems of the prior art.

[0007] (II) Technical solutions

[0008] To achieve the above object, the present application is realized by the following technical solutions,

[0009] The present application discloses an intelligent early warning and monitoring system for power line failure in a tunnel environment, comprising:

[0010] The instruction control module is configured to access a power line total network of the target tunnel, and obtain a running data access and control instruction issuing authority.

[0011] The line planning module is configured to divide the overall line into different scales based on a topology structure and a historical fault point position distribution of the power line of the target tunnel, and take the historical fault distribution of the same point data as a target, and output a plurality of different scale lines with physical coordinates and electrical parameters.

[0012] The data acquisition module is configured to deploy distributed Internet of Things sensors, and collect power fluctuation data, humidity, temperature and vibration data at a specified period.

[0013] The abnormal association module is configured to analyze the collected data, identify abnormal power fluctuation, humidity and temperature data exceeding a threshold, and synchronously acquire vibration data of a planning scale line based on the abnormal fluctuation, humidity and temperature parameters, and acquire power fluctuation data, humidity, temperature data and line setting attribute data of all associated lines based on a type amplitude of the vibration data, and the vibration data of the type amplitude.

[0014] The model establishment module is configured to construct an identification model, input the associated line data extracted by the model, and output a data change trend in a future preset period.

[0015] The trend prediction module is configured to determine a positive or negative state of the data trend.

[0016] The alarm prompt module is configured to be triggered when the data trend is negatively changed, and to perform alarm prompting.

[0017] The line definition unit is configured to calculate a plurality of cutting points based on the data of the negatively changed data trend, cut the identified line according to the cutting points, acquire a plurality of scale lines, provide collected data feedback as an independent segment in a current period, and if the data trend is positively changed, merge adjacent scale lines in the current period.

[0018] Further, the abnormal association module is deployed with a sub-module, and the sub-module includes an abnormal detection module, a vibration analysis module and an association extraction module.

[0019] The abnormal detection module is configured to compare all data participating in detection according to a preset standard, detect abnormal values by a statistical method, record time, position and specific values of the abnormal data, and mark the identified abnormal data as traceable items.

[0020] a vibration analysis module for collecting vibration data when abnormal data occurs, classifying the vibration data, identifying its type and amplitude characteristics, classifying the vibration data according to characteristics, and matching a plurality of planning scale line routes with related vibration characteristics;

[0021] an association extraction module for associating the abnormal data identified by the abnormality detection module with the vibration data provided by the vibration analysis module, and obtaining power fluctuation, humidity, temperature and line setting attribute data belonging to the same planning scale line route.

[0022] Further, the process of the association extraction module is:

[0023] S1: Based on the vibration data type and amplitude threshold, the same vibration characteristic data of the line section to which the current abnormal power fluctuation, humidity or temperature data belongs is filtered out, and a vibration and abnormal parameter mapping relationship is established;

[0024] S2: According to the collection time stamp and line section identifier of the data collection module, the abnormal power fluctuation, humidity, temperature data and vibration data are bound according to time synchronization and space scale line section;

[0025] S3: Extract the line setting attribute data corresponding to the bound data, including line material, installation age and seismic grade, and form a multi-dimensional association data set;

[0026] S4: According to the association results of steps S1-S3, only the historical and real-time data of the line section with excessive vibration amplitude and its adjacent preset range line section are extracted as input feature parameters of the trend prediction module, and the dynamic division identifier of the line section is labeled.

[0027] Further, the trend prediction module uses time series prediction algorithm and multivariate coupling analysis based on associated line data, inputs the power fluctuation, humidity, temperature and vibration characteristic parameters of the associated line section in the current period, and outputs the abnormal fluctuation amplitude prediction value, temperature and humidity change gradient and trend score of the line section in the future preset period.

[0028] Further, the sensors deployed by the data collection module include three-axis vibration sensors, temperature and humidity sensors, and electric field distortion composite sensors. The data collection module reduces the sampling storage of normal data, records all frequency bands of abnormal data, supports phase synchronous collection of vibration and electric parameters, and performs preliminary filtering on collected data to remove noise.

[0029] Further, the line definition unit is deployed with a sub-module, which includes a cutting calculation module and a line integration module. The cutting calculation module and the line integration module are connected through a wireless network, wherein:

[0030] The cutting calculation module is configured to calculate an optimal cutting point according to a trend change degree, identify a cutting point of the scale line if the trend is negative, split the line according to the cutting point to form independent scale lines, and record characteristic data of each line segment;

[0031] The line integration module is configured to merge adjacent scale lines when the trend is positive, integrate power fluctuation, humidity and temperature data corresponding to the independent lines, and generate a new scale line.

[0032] Further, the working logic of the cutting calculation module is as follows:

[0033] Quantize negative trend data of each line segment output by the trend prediction module to obtain quantization parameters of voltage fluctuation variance, temperature rise gradient and vibration energy spectrum density change rate;

[0034] An optimal segmentation objective function is established for the line segment to be cut, and the formula is as follows:

[0035]

[0036] In the formula, J(k) represents a line cutting quality evaluation function, a smaller value indicates a higher comprehensive optimization degree of the segmentation scheme, k represents the number of candidate segments, w i represents a trend deterioration weight coefficient of the i-th segment, represents a comprehensive variance of the predicted data in the segment, Y represents a model complexity penalty factor, L avg represents the average segment length of the current line, and a represents a nonlinear adjustment index.

[0037] The dynamic programming algorithm is used to solve the optimal segmentation number k and the cutting point set under the constraint condition {k min ≤ k ≤ k max | k max = f loor (1.5L / L b )}, wherein L is the total length of the line, and L b is a basic segment length threshold.

[0038] The segmentation density constraint is applied to the dangerous area with a radius less than R, and an overlapping monitoring buffer zone is forced to be generated on both sides of the area, and the buffer zone length L b = β·v·Δt, wherein v is the average vibration speed of the last three periods, Δt is the data acquisition period, and β is the buffer coefficient.

[0039] When the difference between the deterioration trends of adjacent segments exceeds the threshold Y, the asymmetric segmentation strategy is activated, and the encryption cutting point layout is adopted on the side with a larger deterioration gradient.

[0040] Further, the cutting calculation module and the line integration module are connected with a configuration module through an electrical medium, and the configuration module is configured to configure the division parameters to the line planning module according to the division performance of the cutting calculation module and the line integration module in the current period, and support manual adjustment of the division standard of the line.

[0041] Further, the instruction control module is connected with a cloud storage module through a wireless network, and the cloud storage module is configured to store all collected data and analyzed data, perform cloud distributed storage, store the space-time evolution mode and treatment scheme of the fault case, automatically generate a fault treatment decision tree through a cognitive map technology, and automatically eliminate out-of-date fault mode data.

[0042] Further, the instruction control module and the line planning module are connected through a wireless network, the data collection module is connected with the instruction control module and the abnormal association module through an electrical medium, the abnormal association module is connected with the model establishment module through a wireless network, the model establishment module is connected with the trend prediction module through a wireless network, and the trend prediction module is connected with the alarm prompt module and the line definition unit through a wireless network.

[0043] (III) Beneficial effects

[0044] Compared with the known prior art, the technical scheme provided by the present application has the following beneficial effects,

[0045] 1. By dynamically adjusting the multi-scale line division, the traditional global fixed monitoring mode is broken through, the line is divided into independent monitoring units of different scales based on historical fault distribution and topological structure, and dynamic merging or cutting is supported according to data trends, the division scale of the line is dynamically adjusted according to the trend deterioration degree and historical data analysis, the optimal segmentation point is flexibly selected under different conditions by using an optimization algorithm, the precision of data processing can be updated in real time according to the state change, local fine monitoring is realized, and waste of computing power is avoided.

[0046] 2. By introducing vibration data classification and space-time binding of multi-dimensional parameters, a mapping relationship between vibration types and abnormal parameters is established, the composite influence of the vibration exceeding area on the power line is accurately located through a multi-dimensional associated data set, the false alarm rate is reduced, a prediction model is used, a dynamic strategy of triggering cutting combined with negative trend and triggering merging combined with positive trend is realized, the monitoring granularity is adaptively optimized, and the monitoring range is dynamically adjusted to reduce redundant calculation while ensuring sensitivity.

[0047] 3. For high-risk areas such as curves, a segmented density constraint and an overlapping monitoring buffer zone are forcibly applied, the buffer zone length is dynamically adjusted combined with vibration speed, space-adaptive encryption monitoring is performed, and line fatigue hidden dangers caused by vibration accumulation in curves are captured in advance. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0049] Figure 1 The framework diagram of the present application is shown in the figure.

[0050] Figure 2 The framework diagram of the abnormal association module in the present application is shown in the figure.

[0051] Figure 3 The framework diagram of the line definition unit in the present application is shown in the figure.

[0052] The numbers in the figure respectively represent 1, instruction control module; 2, line planning module; 3, data acquisition module; 4, abnormal association module; 41, abnormal detection module; 42, vibration analysis module; 43, association extraction module; 5, model establishment module; 6, trend prediction module; 7, alarm prompt module; 8, line definition unit; 81, slitting calculation module; 82, line integration module; 83, configuration module; 9, cloud storage module. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0054] The present application will be further described below in combination with the embodiments.

[0055] ①Embodiment 1

[0056] The tunnel environment power line fault intelligent early warning and monitoring system of the present embodiment, as shown in the figure, includes: Figure 1

[0057] ​The instruction control module 1 is used for accessing the power line total network of the target tunnel, acquiring operation data access and control instruction issuing authority; the instruction control module 1 is connected with the cloud storage module 9 through wireless network interaction, the cloud storage module 9 is used for storing all collected data and analyzed data, performing cloud distributed storage, storing the spatiotemporal evolution mode and disposal scheme of the fault case, and automatically generating a fault disposal decision tree through a cognitive graph technology, and automatically eliminating out-of-date fault mode data;

[0058] The line planning module 2 is based on the topological structure and historical fault point distribution of the target tunnel power line, and divides the overall line into different scales based on the same point data historical fault distribution as the target, and outputs a plurality of different scale lines with physical coordinates and electrical parameters;

[0059] The data collection module 3 is used for deploying distributed Internet of Things sensors, collecting power fluctuation data, humidity, temperature and vibration data at a specified period; the sensors deployed by the data collection module 3 include a three-axis vibration sensor, a temperature and humidity sensor and an electric field distortion composite sensor, the data collection module 3 performs downsampling storage on normal data and full-band recording on abnormal data, supports phase synchronous collection of vibration and electrical parameters, performs preliminary filtering on collected data, and removes noise processing;

[0060] The abnormal association module 4 is used for analyzing collected data, identifying abnormal power fluctuation, humidity and temperature data exceeding a threshold, and synchronously acquiring vibration data of a planning scale line based on abnormal fluctuation, humidity and temperature parameters, and acquiring power fluctuation data, humidity, temperature data and line setting attribute data of all associated lines based on the type and amplitude of the vibration data;

[0061] As shown in Figure 2 The abnormal association module 4 is deployed with a sub-module, the sub-module includes an abnormal detection module 41, a vibration analysis module 42 and an association extraction module 43, the abnormal detection module 41 and the vibration analysis module 42 are connected through an electrical medium, and the vibration analysis module 42 and the association extraction module 43 are connected through an electrical medium, wherein:

[0062] The abnormal detection module 41 is used for comparing all data participating in detection according to a preset standard, detecting abnormal values through a statistical method, recording the time, position and specific value of abnormal data, and marking the identified abnormal data as a traceable item;

[0063] The vibration analysis module 42 is used for collecting vibration data when abnormal data occurs, classifying vibration data, identifying type and amplitude characteristics of the vibration data, classifying the vibration data according to characteristics, and corresponding to match a plurality of planning scale lines with related vibration characteristics;

[0064] The association extraction module 43 is configured to associate the abnormal data identified by the abnormality detection module 41 with the vibration data provided by the vibration analysis module 42, and obtain power fluctuation, humidity, temperature and line setting attribute data belonging to the same planning scale line;

[0065] The model establishment module 5 is configured to construct an identification model, input the associated line data, and output the data variation trend in a future preset period;

[0066] The trend prediction module 6 is configured to judge the positive and negative states of the data trend, calculate a trend deterioration index according to the deviation degree of the predicted value from the safety threshold, and determine that the trend is “towards negative” if the index exceeds a dynamic adjustment threshold, and otherwise determine that the trend is “towards positive”. The trend prediction module 6 inputs the power fluctuation, humidity, temperature and vibration characteristic parameters of the associated line section in the current period based on the associated line data, and outputs the abnormal fluctuation amplitude prediction value, temperature and humidity change gradient and trend score of the line section in a future preset period by using a time series prediction algorithm and multivariate coupling analysis.

[0067] The alarm prompting module 7 is configured to be triggered when the data trend is negative, and perform alarm prompting.

[0068] The line definition unit 8 is configured to calculate a plurality of segmentation points according to the data of the negative data trend, segment the identified line according to the segmentation points, obtain a plurality of scale lines, provide the collected data feedback as an independent section in the current period, and merge adjacent scale lines in the current period if the data trend is positive.

[0069] As a preferred embodiment in the embodiment, as shown in Figure 3 The line definition unit 8 is deployed with a sub-module, and the sub-module includes a segmentation calculation module 81 and a line integration module 82. The segmentation calculation module 81 and the line integration module 82 are connected through a wireless network, and the segmentation calculation module 81 and the line integration module 82 are connected through a wireless network.

[0070] The segmentation calculation module 81 is configured to calculate an optimal segmentation point according to the trend variation degree. If the trend is negative, the segmentation point of the scale line is identified, the line is segmented according to the segmentation point, the independent scale line is formed, and the characteristic data of each line is recorded.

[0071] The line integration module 82 is configured to merge adjacent scale lines when the trend is positive, integrate the power fluctuation, humidity and temperature data corresponding to the independent line, and generate a new scale line.

[0072] The slitting calculation module 81 and the line integration module 82 are connected with the configuration module 83 through an electrical medium, and the configuration module 83 is used for configuring the division parameters to the line planning module 2 application according to the division performance of the slitting calculation module 81 and the line integration module 82 in the current period, and supporting manual active adjustment of the division standard of the line;

[0073] The instruction control module 1 and the line planning module 2 are connected through a wireless network, the data acquisition module 3 and the instruction control module 1 and the abnormal association module 4 are connected through an electrical medium, the abnormal association module 4 and the model establishment module 5 are connected through a wireless network, the model establishment module 5 and the trend prediction module 6 are connected through a wireless network, and the trend prediction module 6 and the alarm prompt module 7 and the line definition unit 8 are connected through a wireless network.

[0074] Compared with the prior art, the embodiment can more timely discover potential faults by collecting power fluctuation, humidity, temperature and vibration data in real time through distributed Internet of Things sensors, improve the monitoring ability of the line state, analyze future data trends and dynamically adjust thresholds by using a model, and realize early warning of faults, thereby effectively avoiding fault expansion and greater losses caused by the faults;

[0075] Through effective association of abnormal data and vibration data, various parameters related to faults can be accurately identified, thereby further improving the accuracy of fault identification, having the ability to split and merge lines, dynamically adjusting according to changes in data trends, improving the flexibility and adaptability of the line, and better adapting to line operation conditions in different environments;

[0076] By monitoring power fluctuations and taking into account humidity, temperature and vibration and other factors, potential risks are more comprehensively evaluated through multi-dimensional analysis. Through the alarm prompt and data trend analysis provided by the system, managers can quickly respond and optimize management decisions, thereby improving overall operational efficiency. Combined with time series prediction algorithms and multivariate coupling analysis, the embodiment has higher technical advancement and can handle complex line data and trend changes, thereby improving the scientificity and accuracy of fault prediction.

[0077] ②Embodiment 2

[0078] In other aspects, the embodiment also provides another optimization mechanism based on embodiment 1, which is a working logic of a slitting calculation module 81, and specifically comprises:

[0079] Quantitative processing of negative trend data of each line segment output by the trend prediction module 6 to obtain quantitative parameters of voltage fluctuation variance, temperature rise gradient and vibration energy spectrum density change rate;

[0080] A segmented optimization objective function is established for the to-be-slitted line segment, and the formula is:

[0081]

[0082] In the formula, J(k) represents a line segmenting quality evaluation function, the smaller the value, the higher the comprehensive optimization degree of the segmenting scheme, k represents the number of candidate segments, w i represents the trend deterioration weight coefficient of the i-th segment, represents the comprehensive variance of the predicted data in the segment, Y represents a model complexity penalty factor, which is dynamically adjusted according to the tunnel type: 0.18 for a rock tunnel, 0.25 for a soft soil tunnel, and 0.22 for a composite stratum, L avg represents the current average segment length of the line, which is calculated according to the ratio of the total length of the effective line in the current monitoring period to the historical average number of segments, and a represents a nonlinear adjustment index, which takes the value according to the following rules: when the main frequency of vibration is greater than 100 Hz, a = 1.2; when the main frequency of vibration is between 50 Hz and 100 Hz, a = 1.0; and when the main frequency of vibration is less than 50 Hz, a = 0.8;

[0083] The dynamic programming algorithm is used to solve the optimal number of segments k and the segmenting point set under the constraint condition {k min ≤k≤k max ∣k max =f loor (1.5L / L b )} where L is the total length of the line, and L b is the basic segment length threshold;

[0084] The segment density constraint is applied to the dangerous area with a radius less than R, and the overlapping monitoring buffer zone is generated on both sides of the area, and the buffer zone length L b = β·v·Δt, where v is the average vibration speed of the last three periods, Δt is the data acquisition period, and β is the buffer coefficient;

[0085] When the difference in deterioration trend of adjacent segments exceeds the threshold Y, the asymmetric segmentation strategy is activated, and the encryption segmenting point layout is used on the side with a larger deterioration gradient;

[0086] The nonlinear combination of multi-dimensional deterioration indicators is introduced, and the coupling weighting of electrical parameters, mechanical vibration and environmental changes is realized through w i The variable upper limit dynamic constraint mechanism is used to ensure that the segmenting granularity is adaptively scaled with the length of the line, to avoid the waste of computing power caused by over-segmentation of short lines, the overlapping buffer zone technology can effectively capture the edge effect in the vibration wave propagation process, and the false negative rate can be reduced, the asymmetric segmentation strategy is used to optimize the anisotropic characteristics of vibration transmission in the tunnel, to improve the monitoring resolution of the key area, the spatial attenuation effect is introduced, to make the segmenting penalty of long lines show super-linear growth, and to effectively suppress the false segmentation caused by the superposition of mechanical vibration waves.

[0087] ③Example 3

[0088] The embodiment provides a process for correlation processing, in particular:

[0089] S1: Based on the vibration data type and the amplitude threshold, vibration feature data of the same line section as the current abnormal power fluctuation, humidity or temperature data is screened out, and a vibration and abnormal parameter mapping relationship is established;

[0090] S2: According to the acquisition time stamp of the data acquisition module 3 and the line section identifier, the abnormal power fluctuation, humidity, temperature data and vibration data are bound according to time synchronization and space scale line section; in the time-space synchronization correlation process, the vibration data triggering time is taken as the reference, the preset time window is traced back, the fluctuation peak and the change rate of the abnormal power fluctuation, humidity and temperature data in the same line section are obtained, and the vibration data exceeding the safety threshold is matched with the physically adjacent scale line section according to the line topology structure; the sensor data and attribute parameters of the adjacent line section are extracted;

[0091] S3: Extracting the line setting attribute data corresponding to the bound data, including line material, installation age and seismic grade, forming a multi-dimensional correlation data set;

[0092] S4: According to the correlation results of steps S1-S3, only the historical and real-time data of the line section with excessive vibration amplitude and its adjacent preset range line section are extracted as the input feature parameters of the trend prediction module 6, and the dynamic division identifier of the line section is labeled, which is used for adaptive cutting or merging operation of the cloud storage module 9, in particular: when the correlation strength of the vibration data and the abnormal data exceeds the preset risk threshold, the independent monitoring mode of the line section is started, and the cutting point coordinate parameter is generated; different from the traditional global scanning, the vibration data exceeding the standard is used as the trigger condition, only the abnormal line section and the adjacent area data are associated, the redundant calculation is reduced, the time stamp, the line section identifier and the physical topology relationship are combined to ensure the accuracy of data correlation, and the correlation result is directly mapped to the line division operation to form a closed loop of data correlation and dynamic adjustment, and the adaptability of the system is embodied.

[0093] Working principle: when the present application is loaded, the instruction control module 1 is connected to the tunnel power grid through the Internet of Things and connected to the cloud storage module 9 in the cloud, the line planning module 2 divides the line into multi-scale physical coordinate segments based on the topological structure, the data acquisition module 3 deploys a composite sensor network to collect environmental data and preprocesses, the abnormal association module 4 identifies abnormal values through the sub-module abnormal detection module 41, analyzes vibration characteristics through the vibration analysis module 42, and associates multi-dimensional data through the association extraction module 43, the model establishment module 5 constructs a prediction model to input associated data and output trends, the trend prediction module 6 judges the positive and negative trends based on the deterioration index, if negative, the alarm prompt module 7 alarms, and triggers the line definition unit 8 to split the fault segment through the sub-module split cutting calculation module 81, the line integration module 82 merges the stable segment, and the configuration module 83 dynamically optimizes the division parameters and feeds back to the line planning module 2, forming a closed loop iteration.

[0094] By deploying a composite sensor, the phase synchronization collection and noise filtering of power, temperature and humidity, and vibration parameters are realized, the fault decision tree generated by the cloud cognitive graph and the historical spatiotemporal pattern analysis are combined, the data correlation is effectively improved, the dynamic line splitting technology is adopted, the monitoring scale is adjusted in real time according to the trend deterioration index, and the transition from fixed threshold judgment to multivariate prediction of fault early warning is realized.

[0095] At the same time, the distributed storage down-sampling and full-band abnormal record strategy optimize the resource utilization rate, through the fine diagnosis ability and the agile response characteristics of topological self-adaptation, the accuracy and early warning timeliness of power line fault identification in complex tunnel environment are significantly improved.

[0096] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications or replacements will not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent early warning and monitoring system for power line faults in a tunnel environment, characterized in that, include: The command control module is used to access the power line network of the target tunnel and obtain the permission to access operation data and issue control commands. The line planning module, based on the topology and historical fault location distribution of the target tunnel power line, uses the historical fault distribution of the same location data as the target, divides the overall line into different scales, and outputs several segments of the line with physical coordinates and electrical parameters. The data acquisition module is used to deploy distributed IoT sensors to collect power fluctuation data, humidity, temperature and vibration data at specified intervals; The anomaly correlation module is used to analyze the collected data, identify abnormal power fluctuations, humidity and temperature data that exceed the threshold, and simultaneously acquire vibration data of the planned scale lines based on the abnormal fluctuation, humidity and temperature parameters. Based on the type and amplitude of the vibration data, it acquires the power fluctuation data, humidity and temperature data and line setting attribute data of all associated lines that have vibration data of that type and amplitude. The model building module is used to build a recognition model. The model takes the extracted associated route data as input and outputs the data change trend for a future preset period. The trend prediction module is used to determine the positive or negative state of data trends; The alarm notification module is used to trigger an alarm notification when the data trend changes negatively. The line definition unit is used to calculate several cutting points based on the negative trend of the data. The identified line is then cut according to the cutting points to obtain several scale lines. In the current period, these segments are treated as independent segments and provide data feedback separately. If the data trend is positive, adjacent scale lines are merged in the current period.

2. The intelligent early warning and monitoring system for power line faults in a tunnel environment according to claim 1, characterized in that, The anomaly correlation module has sub-modules deployed below it, including: an anomaly detection module, a vibration analysis module, and a correlation extraction module. The anomaly detection module and the vibration analysis module are interconnected via an electrical medium, and the vibration analysis module and the correlation extraction module are interconnected via an electrical medium. The anomaly detection module is used to compare all data participating in the detection according to preset standards, detect outliers through statistical methods, record the time, location and specific value of the outlier data, and mark the identified outlier data as traceable items. The vibration analysis module is used to collect vibration data when abnormal data occurs, classify the vibration data, identify its type and amplitude characteristics, classify the vibration data according to characteristics, and match it with several planned scale lines with relevant vibration characteristics. The correlation extraction module is used to correlate the abnormal data identified by the anomaly detection module with the vibration data provided by the vibration analysis module to obtain power fluctuation, humidity, temperature and line setting attribute data of lines belonging to the same planning scale.

3. The intelligent early warning and monitoring system for power line faults in a tunnel environment according to claim 2, characterized in that, The association processing in the association extraction module is as follows: S1: Based on the vibration data type and amplitude threshold, filter out the vibration characteristic data that are the same as the line segment to which the current abnormal power fluctuation, humidity or temperature data belong, and establish the mapping relationship between vibration and abnormal parameters; S2: Based on the data acquisition timestamp and line segment identifier of the data acquisition module, abnormal power fluctuation, humidity, temperature data and vibration data are bound to line segments of the same time synchronization and spatial scale. S3: Extract the line setting attribute data corresponding to the bound data, including line material, installation years and seismic resistance level, to form a multidimensional associated dataset; S4: Based on the correlation results of steps S1-S3, extract historical and real-time data only for line segments with excessive vibration amplitude and their adjacent preset range line segments, use them as input feature parameters for the trend prediction module, and mark the dynamic division identifier of the line segments.

4. The intelligent early warning and monitoring system for power line faults in a tunnel environment according to claim 1, characterized in that, The trend prediction module is based on the associated line data. It uses time series prediction algorithm and multivariate coupling analysis to input the power fluctuation, humidity, temperature and vibration characteristic parameters of the associated line segment in the current period, and outputs the predicted value of the abnormal fluctuation amplitude, temperature and humidity change gradient and trend score of the line segment in the future preset period.

5. The intelligent early warning and monitoring system for power line faults in a tunnel environment according to claim 1, characterized in that, The data acquisition module is equipped with sensors including a triaxial vibration sensor, a temperature and humidity sensor, and an electric field distortion composite sensor. The data acquisition module downsamples and stores normal data, records abnormal data across the entire frequency band, supports phase synchronization acquisition of vibration and electrical parameters, and performs preliminary filtering and noise removal on the acquired data.

6. The intelligent early warning and monitoring system for power line faults in a tunnel environment according to claim 1, characterized in that, The line definition unit has sub-modules deployed at its lower level, including a segmentation calculation module and a line integration module. The segmentation calculation module and the line integration module are interconnected via a wireless network. The segmentation calculation module is used to calculate the optimal segmentation point based on the degree of trend change. If the trend is negative, the segmentation point of the scale line is identified, the line is segmented according to the segmentation point to form independent scale lines, and the feature data of each line segment is recorded. The line integration module is used to merge adjacent scale lines when the trend is positive, and to integrate the power fluctuation, humidity and temperature data of the corresponding independent lines to generate new scale lines.

7. The intelligent early warning and monitoring system for power line faults in a tunnel environment according to claim 6, characterized in that, The working logic of the segmentation calculation module is as follows: The negative trend data of each line segment output by the trend prediction module are quantified to obtain the quantification parameters of voltage fluctuation variance, temperature rise gradient and vibration energy spectral density change rate. For the line segment to be segmented, a segmentation optimization objective function is established, and the formula is: In the formula, J(k) represents the line segmentation quality evaluation function; the smaller the value, the higher the overall optimization degree of the segmentation scheme. k represents the number of candidate segments, and w i The weight coefficient representing the deterioration of the trend in the i-th segment. L represents the overall variance of the predicted data within this segment, Y represents the model complexity penalty factor, and L represents the variance of the predicted data within this segment. avg represents the current average segment length of the line, and 'a' represents the nonlinear adjustment index. Using dynamic programming algorithm under constraints {k min ≤k≤k max |k max =f loor (1.5L / L b The solution is to find the optimal number of segments k and the set of cutting points, where L is the total length of the line. b The basic segment length threshold; For dangerous areas with a curve radius less than R, segmented density constraints are applied, forcing the generation of overlapping monitoring buffer zones on both sides of the area, with a buffer length L. b =β·v·Δt, where v is the average vibration velocity of the most recent three cycles, Δt is the data acquisition cycle, and β is the buffer coefficient; When the difference in the deterioration trend between adjacent segments exceeds the threshold Y, the asymmetric segmentation strategy is activated, and a denser slicing point layout is adopted on the side with a larger deterioration gradient.

8. The intelligent early warning and monitoring system for power line faults in a tunnel environment according to claim 6, characterized in that, The slicing calculation module and the line integration module are interconnected by a configuration module via an electrical medium. The configuration module is used to configure the partitioning parameters to the line planning module application based on the partitioning performance of the slicing calculation module and the line integration module in the current cycle, and supports manual adjustment of the line partitioning criteria.

9. The intelligent early warning and monitoring system for power line faults in a tunnel environment according to claim 1, characterized in that, The command control module is connected to a cloud storage module via a wireless network. The cloud storage module is used to store all collected and analyzed data, perform distributed cloud storage, store the spatiotemporal evolution patterns and handling plans of fault cases, automatically generate fault handling decision trees through cognitive graph technology, and automatically eliminate outdated fault mode data.

10. The intelligent early warning and monitoring system for power line faults in a tunnel environment according to claim 1, characterized in that, The command control module and the route planning module are interconnected via a wireless network. The data acquisition module, command control module, and anomaly association module are connected via an electrical medium. The anomaly association module and the model building module are interconnected via a wireless network. The model building module and the trend prediction module are interconnected via a wireless network. The trend prediction module, alarm prompt module, and route definition unit are interconnected via a wireless network.

Images