Method, device and equipment for predicting insulation state of OPGW (Optical Fiber Composite Overhead Ground Wire) section insulation line
By acquiring temperature and strain distribution data of OPGW segmented insulated lines through distributed fiber optic sensors, and combining this data with environmental data, the insulation status is predicted and corrected using a pre-set model. This solves the problem of the lack of preventive monitoring for OPGW segmented insulated lines, improves monitoring accuracy, and ensures the stability of transmission lines.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-04
- Publication Date
- 2026-03-31
AI Technical Summary
Existing technologies lack preventative insulation condition monitoring solutions for OPGW segmented insulated lines across the entire line and throughout their entire lifecycle, and the accuracy of such monitoring needs to be improved.
Accumulated temperature and strain distribution data of OPGW segmented insulated lines are acquired by distributed optical fiber sensors, along with environmental data of the target area. Using a preset insulation state prediction model and insulation failure scenario detection model, the insulation state is predicted and corrected to obtain a more accurate probability of insulation failure.
It enables comprehensive prediction of the insulation status of OPGW segmented insulated lines, improves monitoring accuracy, reduces the occurrence of insulation failure, and ensures the normal operation of transmission lines.
Smart Images
Figure CN121763006A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power grid monitoring technology, and in particular to a method, apparatus and equipment for predicting the insulation status of OPGW segmented insulated lines. Background Technology
[0002] Optical Fiber Composite Overhead Ground Wire (OPGW) is an overhead ground wire composite optical cable that combines communication and overhead ground wire functions. It is crucial for building communication networks, realizing dispatch automation, and relay protection and safe and stable control in power systems.
[0003] Traditional OPGW (Operating Power Wire Grounding) typically uses a tower-by-tower grounding method, leading to: ① High energy loss: Electromagnetic induction between the conductor and the ground wire creates a continuous induced current in the OPGW (e.g., up to 70A in a 500kV line), resulting in annual losses of tens of thousands of kWh / km. ② Limited de-icing: When the ground wire is grounded tower-by-tower, DC voltage cannot be applied for de-icing, and severe icing can lead to line breakage or tower collapse. To address these issues, segmented insulation technology has been proposed. In OPGW segmented insulation, to reduce energy loss, the OPGW is grounded only on one tower within an insulation section, while other towers are insulated from the ground. Therefore, the insulation condition of the OPGW segmented insulation line is crucial for the normal operation of the transmission line.
[0004] However, the inventors discovered that current insulation condition monitoring generally involves monitoring insulator contamination, lacking a comprehensive, full-lifecycle monitoring solution for OPGW segmented insulated lines. Furthermore, current methods typically analyze the cause of failure only after an insulation failure occurs in an OPGW segmented insulated line, lacking preventative measures. Summary of the Invention
[0005] This invention provides a method, apparatus, and equipment for predicting the insulation status of OPGW segmented insulated lines, in order to address the current lack of preventative insulation status monitoring schemes for OPGW segmented insulated lines and the need to improve monitoring accuracy.
[0006] In a first aspect, embodiments of the present invention provide a method for predicting the insulation state of OPGW segmented insulated lines, comprising: Accumulated temperature distribution data and accumulated strain distribution data of the target insulation section in the OPGW segmented insulation line are obtained based on distributed optical fiber sensors, and the accumulated environmental data of the area where the target insulation section is located are also obtained. Input the cumulative temperature distribution data and cumulative strain distribution data into the preset insulation state prediction model to obtain the initial insulation state failure probability of the target insulation section. Input the cumulative temperature distribution data, cumulative strain distribution data and cumulative environmental data into the preset insulation failure scenario detection model to determine the target insulation failure scenario corresponding to the target insulation section. The initial insulation failure probability is corrected based on the target insulation failure scenario to obtain the target insulation failure probability of the target insulation section.
[0007] Secondly, embodiments of the present invention provide an insulation condition prediction device for OPGW segmented insulated lines, comprising: The acquisition module is used to acquire the cumulative temperature distribution data and cumulative strain distribution data of the target insulation section in the OPGW segmented insulation line based on distributed optical fiber sensors, and to acquire the cumulative environmental data of the area where the target insulation section is located. The initial prediction module is used to input the cumulative temperature distribution data and cumulative strain distribution data into the preset insulation state prediction model to obtain the initial insulation state failure probability of the target insulation section. The scenario detection module is used to input the cumulative temperature distribution data, cumulative strain distribution data and cumulative environmental data into the preset insulation failure scenario detection model to determine the target insulation failure scenario corresponding to the target insulation section. The prediction and correction module is used to correct the initial insulation failure probability based on the target insulation failure scenario, thereby obtaining the target insulation failure probability of the target insulation section.
[0008] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect or any possible implementation thereof.
[0009] In this embodiment of the invention, cumulative temperature distribution data and cumulative strain distribution data of the target insulation section in an OPGW segmented insulated line are acquired using distributed optical fiber sensors, along with cumulative environmental data of the area where the target insulation section is located. The cumulative temperature distribution data and cumulative strain distribution data are then input into a preset insulation state prediction model to obtain the initial insulation state failure probability of the target insulation section. The cumulative temperature distribution data, cumulative strain distribution data, and cumulative environmental data are then input into a preset insulation failure scenario detection model to determine the target insulation failure scenario corresponding to the target insulation section. Furthermore, the initial insulation state failure probability is corrected based on the target insulation failure scenario to obtain the target insulation state failure probability of the target insulation section. On the one hand, the insulation state of the target insulation section is comprehensively predicted using the cumulative temperature distribution data, cumulative strain distribution data, and cumulative environmental data of the area where the target insulation section is located throughout the entire lifecycle of the target insulation section in the OPGW segmented insulated line. On the other hand, the predicted initial insulation state failure probability is corrected based on different insulation failure scenarios, thereby obtaining a more accurate target insulation state failure probability for the target insulation section. This helps reduce the occurrence of insulation state failures in OPGW segmented insulated lines and ensures the normal operation of transmission lines. Attached Figure Description
[0010] Figure 1 This is a flowchart illustrating the implementation of the insulation state prediction method for OPGW segmented insulated lines provided in this embodiment of the invention. Figure 2 This is a schematic diagram of the insulation state prediction device for OPGW segmented insulated lines provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation
[0011] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
[0012] See Figure 1 The document illustrates a flowchart of the insulation state prediction method for OPGW segmented insulated lines provided in this embodiment of the invention, which is described in detail below: Step 101: Based on distributed optical fiber sensors, acquire the cumulative temperature distribution data and cumulative strain distribution data of the target insulation section in the OPGW segmented insulation line, and acquire the cumulative environmental data of the area where the target insulation section is located.
[0013] Distributed fiber optic sensors utilize optical fibers themselves as the sensing medium. They acquire spatial distribution information of physical quantities such as temperature and strain along the fiber path by analyzing the scattered signals (e.g., Rayleigh scattering, Raman scattering, Brillouin scattering) generated when light propagates through the fiber. By measuring changes in the characteristics of the scattered signals (e.g., intensity, frequency shift, time delay) and combining this with the speed of light propagation in the fiber, the specific location of temperature or strain changes along the fiber's length can be precisely located, and the temperature or strain value at that point can be quantitatively measured. This provides continuous, spatially resolved measurement data.
[0014] The cumulative temperature distribution data is obtained by distributed optical fiber sensors continuously and point-by-point measuring and recording the temperature values along the entire length of the OPGW (Optical Fiber-Coated Wire) section of the target insulation segment. Over time, it not only provides a "snapshot" of the temperature distribution at a specific moment, but more importantly, it provides long-term temperature data, thus reflecting the historical temperature changes and spatial distribution characteristics of the segment during operation.
[0015] Similarly, cumulative strain distribution data is obtained by continuously and point-by-point measuring and recording the tensile or compressive deformation (strain) of the optical fiber along the target insulation section using distributed optical fiber sensors. The spatiotemporal evolution of strain in this section can be recorded through cumulative strain distribution data throughout the monitoring period.
[0016] The area where the target insulation section is located refers to the geographical location and surrounding environment of the target insulation section.
[0017] Cumulative environmental data refers to the external environmental parameters collected in the area during the same period as the monitoring of the target insulated section. These data may come from weather stations, environmental monitoring stations, or other sensor networks, and typically include, but are not limited to: ambient temperature (air temperature), wind speed and direction, precipitation (rain, snow), humidity, icing / snow thickness, etc.
[0018] Accumulated environmental data helps to understand, analyze, and interpret the temperature and strain data measured by fiber optic sensors in the target insulation section. This allows for differentiation between increased OPGW temperature due to increased line current (increased load) and enhanced solar radiation (increased ambient temperature). It also helps to determine whether strain changes are caused by thermal expansion and contraction or mechanical loads such as strong winds and icing. This establishes a correlation between line condition and environmental factors, enabling better identification of insulation failure scenarios.
[0019] Step 102: Input the cumulative temperature distribution data and cumulative strain distribution data into the preset insulation state prediction model to obtain the initial insulation state failure probability of the target insulation section.
[0020] Among them, the preset insulation condition prediction model is a pre-trained data-driven model (such as a machine learning model, physical degradation model, or probabilistic statistical model). It learns or establishes a mapping relationship between temperature, strain, and insulation performance degradation through historical data, so as to achieve early warning of insulation condition.
[0021] Step 103: Input the cumulative temperature distribution data, cumulative strain distribution data, and cumulative environmental data into the preset insulation failure scenario detection model to determine the target insulation failure scenario corresponding to the target insulation section.
[0022] In one embodiment, the training process of the preset insulation failure scenario detection model may include: The training set is constructed by acquiring cumulative temperature distribution data, cumulative strain distribution data, and cumulative environmental data corresponding to insulator surface discharge, lightning strike or short circuit fault, junction box seal failure, insulator mechanical damage, icing overload, discharge gap offset, and down conductor wear.
[0023] The initial clustering network is trained based on the training set to obtain a preset insulation failure scenario detection model.
[0024] In this embodiment, surface discharge on the insulator, such as insulator contamination, can lead to increased local resistance, heat generation when current flows (Joule effect), and abnormal temperature rise (e.g., temperature rise at the junction box > 5°C). During lightning strikes or short-circuit faults, the strong current can instantly cause a rapid temperature rise in the OPGW metal layer (>100°C), triggering a fuse warning. When the junction box seal fails, moisture intrusion can cause the insulation material to become damp, leading to a decrease in local resistance and continuous heating. Mechanical damage to the insulator, such as insulator breakage or loose fittings, can cause OPGW tension imbalance and a sudden increase in local strain (e.g., >1000με). Under icing overload conditions, the weight of ice can increase the OPGW sag, and tensile strain can occur after the fiber optic excess length is exhausted (typical threshold: 60% of rated breaking force). Discharge gap offset, i.e., mechanical deformation, changes the discharge gap distance, thus affecting insulation performance. Wear on the downlead leads can cause the downlead clamp to loosen or deform; long-term wear may cause the downlead clamp to break, resulting in the OPGW drooping and insufficient safe distance from the conductor, leading to a short circuit.
[0025] Therefore, a training set is constructed by acquiring cumulative temperature distribution data, cumulative strain distribution data, and cumulative environmental data corresponding to insulator surface discharge, lightning strike or short circuit fault, junction box sealing failure, insulator mechanical damage, icing overload, discharge gap offset, and down conductor wear. The initial clustering network is trained based on the training set to obtain a preset insulation failure scenario detection model. This model can then more accurately assess the insulation failure probability of the target insulation section based on the target insulation failure scenarios corresponding to the cumulative temperature distribution data, cumulative strain distribution data, and cumulative environmental data.
[0026] Step 104: Correct the initial insulation state failure probability according to the target insulation failure scenario to obtain the target insulation state failure probability of the target insulation section.
[0027] In this embodiment, based on the obtained initial insulation failure probability, the initial insulation failure probability is further corrected according to the target insulation failure scenario, thereby obtaining a more accurate target insulation failure probability for the target insulation section.
[0028] In one embodiment, step 104 may include: Obtain standard cumulative temperature distribution data, standard cumulative strain distribution data, and standard cumulative environmental data corresponding to the target insulation failure scenario.
[0029] Data with the same cumulative duration as the cumulative temperature distribution data are extracted from the standard cumulative temperature distribution data and recorded as the first standard cumulative data; data with the same cumulative duration as the cumulative strain distribution data are extracted from the standard cumulative strain distribution data and recorded as the second standard cumulative data; data with the same cumulative duration as the cumulative environmental data are extracted from the standard cumulative environmental data and recorded as the third standard cumulative data.
[0030] Calculate the first similarity between the cumulative temperature distribution data and the first standard cumulative data, the second similarity between the cumulative strain distribution data and the second standard cumulative data, and the third similarity between the cumulative environmental data and the third standard cumulative data.
[0031] The failure probability of the initial insulation state is corrected based on the first similarity, the second similarity, and the third similarity to obtain the failure probability of the target insulation state of the target insulation section.
[0032] In this embodiment, data with the same cumulative duration as the cumulative temperature distribution data, cumulative strain distribution data, and cumulative environmental data are extracted, and then the similarity is calculated. This makes the standard cumulative temperature distribution data, standard cumulative strain distribution data, and standard cumulative environmental data more comparable to the cumulative temperature distribution data, cumulative strain distribution data, and cumulative environmental data. As a result, the initial insulation failure probability can be better corrected based on the standard cumulative temperature distribution data, standard cumulative strain distribution data, and standard cumulative environmental data corresponding to the target insulation failure scenario, and a more accurate target insulation failure probability can be obtained.
[0033] For example, the first similarity between the cumulative temperature distribution data and the first standard cumulative data, the second similarity between the cumulative strain distribution data and the second standard cumulative data, and the third similarity between the cumulative environmental data and the third standard cumulative data can be calculated using methods such as the Pearson correlation coefficient.
[0034] In one embodiment, correcting the initial insulation state failure probability based on a first similarity, a second similarity, and a third similarity to obtain the target insulation state failure probability of the target insulation section may include: The confidence level of the initial insulation state failure probability is determined based on the first similarity, second similarity, and third similarity.
[0035] Determine whether the confidence level of the probability of initial insulation failure is less than the confidence threshold.
[0036] If the confidence level of the initial insulation failure probability is less than the confidence level threshold, the initial insulation failure probability is corrected according to the target control coefficients corresponding to the first similarity, the second similarity and the third similarity, to obtain the target insulation failure probability of the target insulation section.
[0037] In one embodiment, after determining whether the confidence level of the initial insulation state failure probability is less than a confidence threshold, the method may further include: If the confidence level of the initial insulation failure probability is greater than or equal to the confidence threshold, then the initial insulation failure probability is determined as the target insulation failure probability of the target insulation section.
[0038] In this embodiment, the confidence level of the initial insulation state failure probability is determined based on the first similarity, the second similarity, and the third similarity. The closer the first similarity, the second similarity, and the third similarity are to 1, the closer the cumulative temperature distribution data, the cumulative strain distribution data, and the cumulative environmental data are to the standard data (i.e., the standard cumulative temperature distribution data, the standard cumulative strain distribution data, and the standard cumulative environmental data). Therefore, the confidence level of the initial insulation state failure probability obtained based on the cumulative temperature distribution data and the cumulative strain distribution data is higher.
[0039] For example, a basic confidence level of the initial insulation state failure probability can be determined based on the first similarity and the second similarity. Then, the third similarity is used to characterize the degree of deviation of the accumulated environmental data relative to the standard accumulated environmental data. The correction coefficient of the basic confidence level corresponding to this degree of deviation is then measured by the third similarity. The basic confidence level is then corrected using the correction coefficient to obtain the confidence level of the initial insulation state failure probability.
[0040] Based on this, if the confidence level of the initial insulation failure probability is less than the confidence threshold, the initial insulation failure probability needs to be further corrected. If the confidence level of the initial insulation failure probability is greater than or equal to the confidence threshold, the initial insulation failure probability can be directly determined as the target insulation failure probability of the target insulation section.
[0041] For example, the initial insulation failure probability can be corrected based on the target control coefficients corresponding to the first similarity, second similarity, and third similarity to obtain the target insulation failure probability of the target insulation section.
[0042] For example, the target control coefficient can be determined by looking up a table showing the correspondence between the first similarity, the second similarity, the third similarity, and the control coefficient.
[0043] In another embodiment, correcting the initial insulation failure probability based on the target insulation failure scenario to obtain the target insulation failure probability of the target insulation section may include: The cumulative temperature distribution data and cumulative strain distribution data are corrected according to the target insulation failure scenario to obtain corrected cumulative temperature distribution data and corrected cumulative strain distribution data.
[0044] Input the corrected cumulative temperature distribution data and the corrected cumulative strain distribution data into the preset insulation state prediction model to obtain the corrected insulation state failure probability of the target insulation section.
[0045] The initial insulation failure probability is corrected based on the corrected insulation failure probability to obtain the target insulation failure probability of the target insulation section.
[0046] This embodiment provides another method for correcting the initial insulation failure probability based on the target insulation failure scenario. In this embodiment, the cumulative temperature distribution data and cumulative strain distribution data are corrected using the target insulation failure scenario. In different insulation failure scenarios, different data may contribute differently to the determination of the insulation state. Therefore, the weights or proportions of the cumulative temperature distribution data and cumulative strain distribution data used can be updated using the target insulation failure scenario as corrected cumulative temperature distribution data and corrected cumulative strain distribution data. Then, the corrected cumulative temperature distribution data and corrected cumulative strain distribution data are input into the preset insulation state prediction model to predict the insulation state again and obtain the corrected insulation failure probability. Thus, the target insulation failure probability of the target insulation section is determined by combining the corrected insulation failure probability and the initial insulation failure probability.
[0047] For example, the target insulation failure probability of the target insulation section can be obtained by weighted summation of the corrected insulation failure probability and the initial insulation failure probability.
[0048] In one embodiment, after correcting the initial insulation state failure probability according to the target insulation failure scenario to obtain the target insulation state failure probability of the target insulation section, the method may further include: If the probability of failure of the target insulation condition is greater than the preset threshold, an insulation condition warning message for the target insulation section will be generated.
[0049] In this embodiment, when the probability of failure of the target insulation condition is greater than a preset threshold, an insulation condition warning message for the target insulation section is generated. The insulation condition warning message can then be sent to relevant personnel via SMS, email, or other means, enabling them to promptly inspect and maintain the OPGW segmented insulation line, thereby ensuring the normal operation of the transmission line using OPGW segmented insulation.
[0050] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0051] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.
[0052] Figure 2 A schematic diagram of the insulation state prediction device for OPGW segmented insulated lines provided in an embodiment of the present invention is shown. For ease of explanation, only the parts relevant to the embodiment of the present invention are shown, and are described in detail below: like Figure 2 As shown, the insulation state prediction device for OPGW segmented insulated lines includes: an acquisition module 21, an initial prediction module 22, a scene detection module 23, and a prediction correction module 24.
[0053] The acquisition module 21 is used to acquire the cumulative temperature distribution data and cumulative strain distribution data of the target insulation section in the OPGW segmented insulation line based on the distributed optical fiber sensor, and to acquire the cumulative environmental data of the area where the target insulation section is located. The initial prediction module 22 is used to input the cumulative temperature distribution data and the cumulative strain distribution data into the preset insulation state prediction model to obtain the initial insulation state failure probability of the target insulation section. Scene detection module 23 is used to input cumulative temperature distribution data, cumulative strain distribution data and cumulative environmental data into a preset insulation failure scene detection model to determine the target insulation failure scene corresponding to the target insulation section; The prediction correction module 24 is used to correct the initial insulation state failure probability according to the target insulation failure scenario, so as to obtain the target insulation state failure probability of the target insulation section.
[0054] This embodiment acquires cumulative temperature and strain distribution data of the target insulation section in an OPGW segmented insulated line using distributed fiber optic sensors, and also obtains cumulative environmental data of the area where the target insulation section is located. The cumulative temperature and strain distribution data are then input into a preset insulation state prediction model to obtain the initial insulation failure probability of the target insulation section. The cumulative temperature, strain, and environmental data are then input into a preset insulation failure scenario detection model to determine the target insulation failure scenario corresponding to the target insulation section. Finally, the initial insulation failure probability is corrected based on the target insulation failure scenario to obtain the target insulation failure probability of the target insulation section. On the one hand, it comprehensively predicts the insulation state of the target insulation section using the cumulative temperature and strain distribution data throughout the entire lifecycle of the target insulation section in the OPGW segmented insulated line, as well as the cumulative environmental data of the area where the target insulation section is located. On the other hand, it corrects the predicted initial insulation failure probability based on different insulation failure scenarios, thereby obtaining a more accurate target insulation failure probability for the target insulation section. This helps reduce the occurrence of insulation failures in OPGW segmented insulated lines and ensures the normal operation of transmission lines.
[0055] In one possible implementation, the prediction correction module 24 can be used to obtain standard cumulative temperature distribution data, standard cumulative strain distribution data, and standard cumulative environmental data corresponding to the target insulation failure scenario; extract data from the standard cumulative temperature distribution data that has the same cumulative duration as the cumulative temperature distribution data, and record it as the first standard cumulative data; extract data from the standard cumulative strain distribution data that has the same cumulative duration as the cumulative strain distribution data, and record it as the second standard cumulative data; extract data from the standard cumulative environmental data that has the same cumulative duration as the cumulative environmental data, and record it as the third standard cumulative data; calculate the first similarity between the cumulative temperature distribution data and the first standard cumulative data, the second similarity between the cumulative strain distribution data and the second standard cumulative data, and the third similarity between the cumulative environmental data and the third standard cumulative data; and correct the initial insulation state failure probability based on the first similarity, the second similarity, and the third similarity to obtain the target insulation state failure probability of the target insulation section.
[0056] In one possible implementation, the prediction correction module 24 can be used to determine the confidence level of the initial insulation state failure probability based on the first similarity, the second similarity, and the third similarity; determine whether the confidence level of the initial insulation state failure probability is less than a confidence threshold; if the confidence level of the initial insulation state failure probability is less than the confidence threshold, then the initial insulation state failure probability is corrected according to the target control coefficients corresponding to the first similarity, the second similarity, and the third similarity to obtain the target insulation state failure probability of the target insulation section.
[0057] In one possible implementation, the prediction correction module 24 can also be used to determine the initial insulation state failure probability as the target insulation state failure probability of the target insulation section if the confidence level of the initial insulation state failure probability is greater than or equal to the confidence level threshold.
[0058] In one possible implementation, the target control coefficient is determined by looking up a table showing the correspondence between the first similarity, second similarity, third similarity, and control coefficient.
[0059] In one possible implementation, the training process of the pre-defined insulation failure scenario detection model includes: The training set is constructed by acquiring cumulative temperature distribution data, cumulative strain distribution data, and cumulative environmental data corresponding to insulator surface discharge, lightning strike or short circuit fault, junction box sealing failure, insulator mechanical damage, icing overload, discharge gap offset, and down conductor wear. The initial clustering network is trained based on the training set to obtain the preset insulation failure scenario detection model.
[0060] In one possible implementation, the prediction correction module 24 can be used to correct the cumulative temperature distribution data and cumulative strain distribution data according to the target insulation failure scenario to obtain corrected cumulative temperature distribution data and corrected cumulative strain distribution data; input the corrected cumulative temperature distribution data and corrected cumulative strain distribution data into a preset insulation state prediction model to obtain the corrected insulation state failure probability of the target insulation section; and correct the initial insulation state failure probability according to the corrected insulation state failure probability to obtain the target insulation state failure probability of the target insulation section.
[0061] In one possible implementation, the prediction correction module 24 can also be used to generate insulation status warning information for the target insulation section if the failure probability of the target insulation state is greater than a preset threshold.
[0062] Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Figure 3 As shown, the electronic device 3 of this embodiment includes a processor 30 and a memory 31. The memory 31 stores a computer program 32. When the processor 30 executes the computer program 32, it implements the steps in the various method embodiments described above. Alternatively, when the processor 30 executes the computer program 32, it implements the functions of each module / unit in the various device embodiments described above.
[0063] For example, computer program 32 may be divided into one or more modules / units, which are stored in memory 31 and executed by processor 30 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 32 in electronic device 3.
[0064] Electronic device 3 may include, but is not limited to, processor 30 and memory 31. Those skilled in the art will understand that... Figure 3 This is merely an example of electronic device 3 and does not constitute a limitation on electronic device 3. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 3 may also include input / output devices, network access devices, buses, etc.
[0065] For the sake of simplicity and clarity, only the above-described functional modules / units are used as examples. In practical applications, the functions described above can be assigned to different functional modules / units as needed. These modules / units can be implemented in hardware, software, or a combination of both.
[0066] In the above embodiments, the descriptions of each embodiment have their own emphasis. Parts not detailed or described in a particular embodiment can be referred to in the relevant descriptions of other embodiments. Unless otherwise specified or in conflict with logic, the terminology and / or descriptions between different embodiments are consistent and can be referenced interchangeably. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.
[0067] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.
Claims
1. A method of predicting an insulation condition of an OPGW sectionalized insulated line, characterized by, The method comprises the following steps: obtaining cumulative temperature distribution data and cumulative strain distribution data of a target insulation section in an OPGW segmented insulated line based on a distributed optical fiber sensor, and obtaining cumulative environmental data of a region where the target insulation section is located; inputting the cumulative temperature distribution data and the cumulative strain distribution data into a preset insulation state prediction model to obtain an initial insulation state failure probability of the target insulation section; inputting the cumulative temperature distribution data, the cumulative strain distribution data and the cumulative environmental data into a preset insulation failure scene detection model to determine a target insulation failure scene corresponding to the target insulation section; correcting the initial insulation state failure probability according to the target insulation failure scene to obtain a target insulation state failure probability of the target insulation section.
2. The method of claim 1, wherein The method for correcting the initial insulation state failure probability according to the target insulation failure scene to obtain the target insulation state failure probability of the target insulation section comprises the following steps: obtaining standard cumulative temperature distribution data, standard cumulative strain distribution data and standard cumulative environmental data corresponding to the target insulation failure scene; cutting data in the standard cumulative temperature distribution data with the same cumulative time length as the cumulative temperature distribution data, and recording the data as first standard cumulative data; cutting data in the standard cumulative strain distribution data with the same cumulative time length as the cumulative strain distribution data, and recording the data as second standard cumulative data; cutting data in the standard cumulative environmental data with the same cumulative time length as the cumulative environmental data, and recording the data as third standard cumulative data; calculating a first similarity between the cumulative temperature distribution data and the first standard cumulative data, a second similarity between the cumulative strain distribution data and the second standard cumulative data, and a third similarity between the cumulative environmental data and the third standard cumulative data; correcting the initial insulation state failure probability according to the first similarity, the second similarity and the third similarity to obtain the target insulation state failure probability of the target insulation section.
3. The method of claim 2, wherein The method for correcting the initial insulation state failure probability according to the first similarity, the second similarity and the third similarity to obtain the target insulation state failure probability of the target insulation section comprises the following steps: determining a confidence degree of the initial insulation state failure probability according to the first similarity, the second similarity and the third similarity; judging whether the confidence degree of the initial insulation state failure probability is less than a confidence degree threshold value; if the confidence degree of the initial insulation state failure probability is less than the confidence degree threshold value, correcting the initial insulation state failure probability according to target regulation coefficients corresponding to the first similarity, the second similarity and the third similarity to obtain the target insulation state failure probability of the target insulation section.
4. The method of claim 3, wherein After judging whether the confidence degree of the initial insulation state failure probability is less than the confidence degree threshold value, the method further comprises the following step: if the confidence degree of the initial insulation state failure probability is greater than or equal to the confidence degree threshold value, determining the initial insulation state failure probability as the target insulation state failure probability of the target insulation section.
5. The method of claim 3, wherein the method further comprises: The target regulation coefficients are determined by looking up a corresponding relationship table of the first similarity, the second similarity, the third similarity and the regulation coefficients.
6. The method of claim 1, wherein The training process of the preset insulation failure scene detection model comprises the following steps: The cumulative temperature distribution data, the cumulative strain distribution data and the cumulative environmental data corresponding to the surface discharge of the insulator, lightning or short circuit failure, sealing failure of the joint box, mechanical damage of the insulator, icing overload, discharge gap offset, and downlead wear are acquired to form a training set; The initial clustering network is trained according to the training set to obtain a preset insulator failure scene detection model.
7. The method of claim 1, wherein The initial insulator state failure probability is corrected according to the target insulator failure scene to obtain a target insulator state failure probability of the target insulator section, including: The cumulative temperature distribution data and the cumulative strain distribution data are corrected according to the target insulator failure scene to obtain corrected cumulative temperature distribution data and corrected cumulative strain distribution data; The corrected cumulative temperature distribution data and the corrected cumulative strain distribution data are input into the preset insulator state prediction model to obtain a corrected insulator state failure probability of the target insulator section; The initial insulator state failure probability is corrected according to the corrected insulator state failure probability to obtain the target insulator state failure probability of the target insulator section.
8. The method of claim 1, wherein, After the initial insulator state failure probability is corrected according to the target insulator failure scene to obtain the target insulator state failure probability of the target insulator section, the method further includes: If the target insulator state failure probability is greater than a preset threshold, insulator state warning information of the target insulator section is generated.
9. An insulation condition prediction device for an OPGW sectionalized line, characterized by, The method includes: An acquisition module is configured to acquire cumulative temperature distribution data and cumulative strain distribution data of a target insulator section in an OPGW segmented insulator line based on a distributed optical fiber sensor, and acquire cumulative environmental data of a region where the target insulator section is located; An initial prediction module is configured to input the cumulative temperature distribution data and the cumulative strain distribution data into a preset insulator state prediction model to obtain an initial insulator state failure probability of the target insulator section; A scene detection module is configured to input the cumulative temperature distribution data, the cumulative strain distribution data and the cumulative environmental data into a preset insulator failure scene detection model to determine a target insulator failure scene corresponding to the target insulator section; A prediction correction module is configured to correct the initial insulator state failure probability according to the target insulator failure scene to obtain a target insulator state failure probability of the target insulator section.
10. An electronic device, comprising: The method includes a memory and a processor, the memory stores a computer program, and the processor implements the method of any one of claims 1 to 8 when executing the computer program.