Composite transmission line sensing and monitoring device

Abstract

The present invention provides a composite transmission line sensing monitoring device, which relates to the field of transmission line monitoring technology, including: a topological network layout module; a probability analysis module, which is used to monitor the electrical parameters and environmental parameters of multiple line locations, respectively perform line damage probability analysis and corrosion probability classification, obtain a line damage probability set and a corrosion probability set, and calculate and obtain a physical damage probability set; a monitoring accuracy configuration module, which is used to configure multiple analysis quantities for integrated abnormality analysis, and multiple monitoring accuracies for external image monitoring and recognition; a sensing monitoring result acquisition module, which is used to obtain multiple corrosion damage levels and multiple physical damage levels as transmission line sensing monitoring results. The present invention solves the technical problem that the prior art usually adopts a unified monitoring intensity for all line locations, and cannot dynamically adjust the monitoring resources according to the actual damage risk of the line, resulting in insufficient monitoring accuracy or waste of resources.

Description

Technical Field

[0001] The present invention relates to the technical field of power transmission line monitoring, and in particular to a composite power transmission line sensing and monitoring device. Background Art

[0002] In the power transmission system, transmission lines are the key part that supports the stable operation of the entire power grid. Monitoring and ensuring the safety and reliability of lines is the primary task of power companies. However, traditional transmission line monitoring is mostly concentrated in local areas or individual lines, which has the problem of limited monitoring areas. Due to the wide distribution range and large number of transmission lines, traditional monitoring methods cannot cover all line locations, which easily leads to the lack of monitoring of certain high-risk areas, resulting in potential problems that cannot be discovered in time. In addition, existing power line monitoring has great limitations in terms of accuracy and flexibility. For complex environmental conditions, it is impossible to flexibly adjust the monitoring accuracy according to different line locations and risk levels, resulting in inaccurate monitoring in high-risk areas and waste of resources in low-risk areas. It lacks the ability to dynamically optimize and intelligently configure monitoring resources. Summary of the invention

[0003] The present application provides a composite transmission line sensing and monitoring device, aiming to solve the technical problem that the prior art usually adopts a unified monitoring intensity for all line locations, and is unable to dynamically adjust the monitoring resources according to the actual damage risk of the line, resulting in insufficient monitoring accuracy at some key line locations, or waste of resources at non-key locations.

[0004] The present application discloses a composite transmission line perception monitoring device, the device comprising: a topology network layout module, used to obtain the laying route information of the composite transmission line, and perform monitoring topology network layout, wherein the monitoring topology network includes multiple distributed monitoring points, each distributed monitoring point; a probability analysis module, used to monitor and obtain the electrical parameters and environmental parameters of multiple line positions of the composite transmission line based on the multiple distributed monitoring points, obtain an electrical parameter set and an environmental parameter set, respectively perform line damage probability analysis and corrosion probability classification of the multiple line positions, obtain a line damage probability set and a corrosion probability set, and calculate to obtain a physical damage probability set; a monitoring accuracy configuration module, used to configure multiple analysis quantities for integrated abnormal analysis of the environmental parameters of the multiple line positions according to the corrosion probability set, and configure multiple monitoring accuracies for external image monitoring and identification of the multiple line positions according to the physical damage probability set; a perception monitoring result acquisition module, used to identify the environmental parameter set according to the multiple analysis quantities, obtain multiple corrosion damage levels, perform image monitoring and identification on the multiple line positions according to the multiple monitoring accuracies, and obtain multiple physical damage levels as the transmission line perception monitoring result.

[0005] One or more technical solutions provided in this application have at least the following beneficial effects:

[0006] Through the topological network layout module, a monitoring topological network covering composite transmission lines is established to achieve full coverage of the laying routes, and multiple distributed monitoring points are used to improve the comprehensiveness and accuracy of monitoring; through the probability analysis module, multiple distributed monitoring points are used to collect electrical parameters and environmental parameters of multiple line locations of the transmission line, and line damage probability analysis and corrosion probability classification are performed for multiple line locations respectively, and line damage probability sets and corrosion probability sets are obtained, thereby quantifying and classifying damage risks, and further calculating physical damage probability sets, which can distinguish different damage types, provide data support for subsequent monitoring configuration, and significantly improve the scientificity and efficiency of analysis; through monitoring The measurement accuracy configuration module dynamically adjusts the number of analyses and image monitoring accuracy according to the corrosion probability and physical damage probability. For example, more analysis resources are allocated to line locations with high corrosion probability, and higher monitoring accuracy is allocated to locations with high physical damage probability. Through this dynamic adjustment mechanism, optimal resource utilization is achieved to avoid excessive monitoring or waste of resources, while ensuring higher monitoring accuracy at key locations. Through the perception monitoring result acquisition module, the corrosion damage level based on environmental parameters and the physical damage level based on image monitoring are integrated to form a comprehensive perception monitoring result of the transmission line. This module uniformly expresses multi-dimensional damage data as an intuitive damage level, providing a comprehensive and reliable reference for line maintenance. In general, the composite transmission line perception monitoring device improves the reliability of transmission line monitoring, adaptability to complex environments, and accuracy of line damage identification through modular design and intelligent data processing. Especially in the context of large-scale distribution of transmission lines, the device can efficiently respond to the diversified monitoring needs of different locations and different damage types, and improve the operational safety of transmission lines.

[0007] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic diagram of the structure of a composite power transmission line sensing and monitoring device provided in an embodiment of the present application.

[0009] Figure 2 A schematic diagram of the implementation process of the topology network layout module in the composite power transmission line sensing and monitoring device provided in an embodiment of the present application.

[0010] Explanation of the reference numerals: topology network layout module 10, probability analysis module 20, monitoring accuracy configuration module 30, perception monitoring result acquisition module 40. DETAILED DESCRIPTION

[0011] The embodiments of the present application provide a composite transmission line sensing and monitoring device, which solves the technical problems that the prior art usually adopts a uniform monitoring intensity for all line locations and cannot dynamically adjust monitoring resources according to the actual damage risk of the line, resulting in insufficient monitoring accuracy at some key line locations or waste of resources at non-key locations.

[0012] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0013] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a composite transmission line sensing and monitoring device, the device comprising:

[0014] The topology network layout module 10 is used to obtain the laying route information of the composite transmission line and to perform monitoring topology network layout, wherein the monitoring topology network includes a plurality of distributed monitoring points, each distributed monitoring point.

[0015] The laying route information is obtained from the design planning drawings of the composite transmission line, GIS data or related transmission line management database, including the geometric distribution, geographical location, direction, terrain, landform and surrounding environment information of the transmission line.

[0016] According to the laying route information, the laying route is divided into multiple location points, such as the bending points of the transmission line, the points crossing rivers or valleys, and the key monitoring areas susceptible to environmental influences. Distributed monitoring points are arranged at the multiple divided line location points. The layout of the monitoring points should cover the operating status of the entire line. Each monitoring point includes an electrical parameter sensor, an environmental parameter sensor, a data acquisition module and a communication module. These distributed monitoring points are connected through the network to form a monitoring topology network. By constructing the monitoring topology network, efficient monitoring of composite transmission lines can be achieved, providing basic data support for subsequent line damage and corrosion probability analysis.

[0017] The probability analysis module 20 is used to monitor and obtain the electrical parameters and environmental parameters of multiple line locations of the composite transmission line based on the multiple distributed monitoring points, obtain an electrical parameter set and an environmental parameter set, perform line damage probability analysis and corrosion probability classification for the multiple line locations respectively, obtain a line damage probability set and a corrosion probability set, and calculate to obtain a physical damage probability set.

[0018] Each distributed monitoring point collects the electrical parameters and environmental parameters of the corresponding line location in real time. The electrical parameters include voltage, current, surface resistance, power factor, etc., which constitute an electrical parameter set; the environmental parameters include ambient temperature and humidity, pH value, chemical concentration, wind speed and wind direction, etc., which constitute an environmental parameter set.

[0019] Line damage mainly comes from corrosion and physical stress. Changes in electrical parameters (such as voltage and surface resistance) can reflect line damage. The probability of corrosion is closely related to environmental conditions, especially pH value and chemical concentration. A line abnormality probability classification channel is constructed through historical data, wherein the line abnormality probability classification channel includes a line damage probability classification path and a corrosion probability classification branch. The line damage probability analysis is performed on the electrical parameter set through the line damage probability classification path, and the line damage probability set is output; the corrosion probability classification branch is used to classify the environmental parameter set for corrosion probability, and the corrosion probability set is output.

[0020] The physical damage probability can be obtained by subtracting the corrosion probability from the line damage probability. For each line position, the corresponding line damage probability is subtracted from the corrosion probability. The calculated result is the physical damage probability of the position. All line positions are traversed to obtain the physical damage probability set.

[0021] The monitoring accuracy configuration module 30 is used to configure multiple analysis quantities for integrated abnormal analysis of environmental parameters of the multiple line locations according to the corrosion probability set, and to configure multiple monitoring accuracies for external image monitoring and identification of the multiple line locations according to the physical damage probability set.

[0022] Integrated anomaly analysis mainly targets the environmental parameters of the line location where the line is located, and is used to identify potential abnormal environmental changes that may accelerate corrosion or affect the long-term stability of the line. Specifically, based on the environmental parameters, the analysis target of each line location is set, mainly to monitor the changing trend of environmental parameters to identify anomalies. The maximum number of analyses is set according to the analysis target to cope with different environmental change monitoring needs. The more analyses, the higher the accuracy, but more computing resources are required. According to the corrosion probability set, the maximum number of analyses for the corresponding line location is dynamically adjusted to obtain multiple numbers of analyses. For example, areas with severe corrosion can be configured with more analyses to ensure that abnormal environmental changes are discovered in a timely manner.

[0023] External image monitoring identifies physical damage at the location of the line, such as breaks, cracks, signs of corrosion, etc. The monitoring accuracy is related to the resolution of the image. The higher the resolution, the higher the accuracy, but it also requires higher computing power and storage space. The maximum monitoring accuracy for external image monitoring is obtained. According to the physical damage probability set, the maximum monitoring accuracy of the corresponding line location is dynamically adjusted to obtain multiple monitoring accuracies. For example, in high-risk areas or corrosion-prone areas, higher image resolution is configured to ensure accurate identification.

[0024] The perception monitoring result acquisition module 40 is used to identify the environmental parameter set according to the multiple analysis quantities to obtain multiple corrosion damage levels, and to perform image monitoring and identification on the multiple line locations according to the multiple monitoring accuracies to obtain multiple physical damage levels as the transmission line perception monitoring results.

[0025] The environmental parameters of each line location are input into the pre-built corrosion damage analysis channel. The channel has pre-trained corrosion damage analysis branches with multiple analysis numbers. The higher the number of analyses, the higher the recognition accuracy, which is suitable for line locations with higher corrosion risks. Each branch corresponds to a different analysis path and parameter model. Each analysis branch evaluates the degree of corrosion damage based on the environmental parameters and outputs the corrosion damage grade. The average value is calculated through the output results of multiple branches, and finally the corrosion damage grade of each line location is obtained, and multiple corrosion damage grades are obtained.

[0026] Use drones, high-definition cameras, etc. to collect surface images of transmission line locations. The image acquisition process must meet the monitoring accuracy requirements. Line locations with high damage probability are assigned high monitoring accuracy, and those with low damage probability are assigned low monitoring accuracy. Based on the collected images, the pre-trained convolutional neural network model is used to identify the physical damage characteristics of the line surface, such as crack length, size and shape of material peeling areas, etc., and the identification results are quantified into physical damage levels and multiple physical damage levels.

[0027] By integrating multiple corrosion damage levels and multiple physical damage levels, we can obtain the perception monitoring results of the transmission lines. The perception monitoring results of each line location are composed of the corrosion damage level and the physical damage level, which can intuitively show the health status of the transmission lines and provide data support for operation and maintenance decisions.

[0028] Furthermore, if Figure 2 As shown, the topology network layout module includes the following operation steps:

[0029] Acquire the laying route information of the composite transmission line; divide the laying route information to obtain multiple line locations; arrange distributed monitoring points at the multiple line locations to obtain multiple distributed monitoring points to form the monitoring topology network.

[0030] Obtain the laying route information of the composite transmission line. Specifically, collect the geographical information of the transmission line through GIS (Geographic Information System) or other related technical tools to obtain the geographical location, topography and geological information of the line; obtain the laying information of the route according to the design blueprint or engineering drawing of the line, including the line direction, supporting structure, access point, etc.; collect information such as materials used in the laying process of the line, construction technology, and environmental characteristics of the region through the transmission line management database. Integrate the collected information into laying route information to provide reference for subsequent monitoring and analysis.

[0031] The laying route information is divided. Specifically, according to terrain changes, environmental factors or line length, the transmission line is divided at a certain interval to form several line locations; according to the potential risks of different locations, such as corrosion, wind force, temperature changes, etc., the lines are divided and high-risk areas are monitored first; for areas with important facilities or high damage risks, such as substations and support towers, they are specially divided into independent monitoring locations. The above division results are integrated to form multiple line locations, which will serve as key areas for subsequent monitoring and management.

[0032] Distributed monitoring points are deployed at multiple line locations. First, ensure that each designated line location can be covered by distributed monitoring points, especially high-risk areas. According to the characteristics of each monitoring point, the corresponding monitoring technology is selected for deployment, including environmental parameter monitoring and electrical parameter monitoring. High-density monitoring points are deployed in important areas such as substations and intersections, while low-density monitoring points are used in some ordinary line sections. These distributed monitoring points are connected through the network to form a complete monitoring topology. Each monitoring point is connected to the central control system through a wireless or wired network to ensure real-time data upload and processing.

[0033] Furthermore, the probability analysis module includes the following steps:

[0034] A line abnormality probability classification channel is constructed, wherein the line abnormality probability classification channel includes a line damage probability classification path and a corrosion probability classification branch; a plurality of electrical parameters and environmental parameters in the electrical parameter set and the environmental parameter set are respectively input into the line damage probability classification path and the corrosion probability classification branch, and a line damage probability set and a corrosion probability set are obtained as classification outputs; and a physical damage probability set is obtained by subtracting the corrosion probability from the line damage probability of each line position in the line damage probability set and the corrosion probability set.

[0035] Collect the electrical parameters of the line, such as voltage, current, surface resistance, etc. These parameters can reflect whether the line is damaged. Use classification algorithms such as decision trees to build a line damage probability classification path based on electrical parameters. This path inputs different electrical parameters into the decision tree to generate the line damage probability. Collect environmental parameters around the line through environmental sensors, such as temperature, humidity, pH value, etc. These environmental factors directly affect the corrosion rate and probability of the line. Based on the environmental parameters, use the decision tree model to build a corrosion probability classification branch. This branch evaluates the probability of corrosion of the line according to environmental conditions. Combine the damage probability classification path and the corrosion probability classification branch to build a comprehensive line abnormality probability classification channel, which can handle line damage and corrosion problems at the same time and provide a more accurate assessment of the line health status.

[0036] Multiple electrical parameters in the electrical parameter set are input into the constructed line damage probability classification path, and the electrical parameters are classified through the decision tree model to output the damage probability value of each line position, which form the line damage probability set. Multiple environmental parameters in the environmental parameter set are input into the constructed corrosion probability classification branch, and the environmental parameters are classified through the decision tree model to output the corrosion probability value of each line position, which form the corrosion probability set.

[0037] For each line position, first obtain the line damage probability of the position from the line damage probability set, then obtain the corrosion probability of the position from the corrosion probability set, and obtain the physical damage probability of the line position by calculating the difference between the line damage probability and the corrosion probability. Through the above calculation, traverse all line positions to form a physical damage probability set. This set can reflect the damage probability of each line position due to physical damage, such as pressure, bending, stretching and other mechanical factors.

[0038] Furthermore, the probability analysis module further includes a line abnormality probability classification channel construction unit, and the line abnormality probability classification channel construction unit includes the following operation steps:

[0039] According to the monitoring data of the composite transmission line in the historical time, a set of sample electrical parameters is collected, and the proportion of line damage under different sample electrical parameters is collected to obtain a set of sample line damage probability; the sample electrical parameter set and the sample line damage probability set are used to construct a line damage probability classification path based on a decision tree; a set of sample environmental parameters is collected, and the proportion of line corrosion under different environmental parameters is collected to obtain a set of sample corrosion probability; the sample environmental parameter set and the sample corrosion probability set are used to construct a corrosion probability classification branch based on a decision tree; the line damage probability classification path and the corrosion probability classification branch are combined to obtain a line abnormality probability classification channel.

[0040] Electrical parameter data within a historical period is obtained from distributed monitoring points or central control systems to form a sample electrical parameter set, including voltage, current, power, surface resistance, etc. Usually, these electrical parameters will change with aging, corrosion or external physical damage of the line.

[0041] Through on-site inspections, test reports or fault records of electrical systems, the actual situation of line damage under different electrical parameter conditions is collected, including physical damage, corrosion, and fracture of the line. Based on different electrical parameters, the proportion of line damage under corresponding conditions is calculated. This can be done by statistically analyzing the line damage events that appear in historical data, and the probability of line damage under each set of electrical parameters is obtained to form a sample line damage probability set.

[0042] The sample electrical parameter set and line damage probability set are divided into a training set and a test set. For example, 70% to 80% of the data is used as the training set and the rest of the data is used as the test set to ensure the generalization ability of the model. The model is trained using the decision tree algorithm using the training set data. At each node, the algorithm partitions the data set based on the conditions of the input features until the leaf node of the tree. The leaf node represents the final line damage probability classification. According to the damage probability set, the decision tree selects the best features for each partition by maximizing the information gain to minimize the error and improve the prediction accuracy. The decision tree model is evaluated using the test set, and performance indicators such as accuracy are calculated to ensure that the model can effectively predict the line damage probability. Finally, a line damage probability classification path is generated through the decision tree. At each decision node, the path guides the classification based on the electrical parameters, and finally the probability category of the line damage is obtained. Each path corresponds to a different combination of electrical parameters to help predict the probability of the corresponding line damage.

[0043] Collect environmental data of the area where the line is located and establish a set of sample environmental parameters. These environmental parameters directly affect the corrosion rate of the line, such as humidity, temperature, pH value, etc. According to the corrosion situation of the line and environmental conditions, calculate the proportion of line corrosion under different environmental parameters. For example, in areas with high humidity and high salt concentration, the probability of line corrosion is higher. The frequency of corrosion under different environmental conditions is counted and converted into corrosion probability to form a set of sample corrosion probability.

[0044] Using the sample environmental parameter set and the sample corrosion probability set, a corrosion probability classification branch is constructed based on the decision tree. Each node of the branch represents a condition of an environmental parameter. Finally, the corrosion probability of the line is judged according to these conditions. Each path corresponds to a specific combination of environmental parameters, and finally the probability of corrosion is given. The construction process of the corrosion probability classification branch is exactly the same as the line damage probability classification path. For the sake of brevity of the specification, it will not be repeated here.

[0045] The line damage probability classification path and the corrosion probability classification branch are combined to obtain the line abnormality probability classification channel. These two classification paths evaluate the damage probability and corrosion probability of the line respectively, providing a decision-making basis for fault diagnosis, preventive maintenance and optimization management of transmission lines.

[0046] Furthermore, the monitoring accuracy configuration module includes the following operation steps:

[0047] The maximum number of analyses for integrated abnormal analysis of environmental parameters is obtained; a plurality of corrosion probabilities in the corrosion probability set are respectively adopted, multiplied by the maximum number of analyses and rounded to obtain a plurality of analysis numbers.

[0048] Environmental parameters, such as temperature, humidity, pH value, chemical concentration, etc., may vary between different line locations, causing changes in the corrosion of the line. In order to accurately analyze the impact of the environment on line corrosion, an integrated anomaly analysis is required. The maximum number of analyses for integrated anomaly analysis usually depends on multiple factors, including the type of environmental parameters, the frequency of data collection, and the complexity of the analysis. Specifically, this number can be determined by historical data analysis or based on the required analysis accuracy. For example, if historical data shows that certain environmental parameters change more frequently, a higher number of analyses is required to capture these changes. If there are multiple variables in the environmental parameters, a separate anomaly analysis is required for each variable, so the maximum number of analyses is the total analysis of these parameters combined. The maximum number of analyses can be obtained by calculating the number of calculation steps or the number of sensor data points required in the integrated analysis, for example, by calculating the product of the number of environmental variables to be analyzed and the maximum acquisition frequency of each environmental variable.

[0049] Each value in the corrosion probability set represents the corrosion probability of a specific line location. For example, the corrosion probability of a line location is 0.6, which means that the probability of corrosion at this location within a certain period of time is 60%. The number of analyses for each line location can be obtained by multiplying the corrosion probability of the location by the maximum number of analyses. For example, if the corrosion probability of a line location is 0.6 and the maximum number of analyses is 10, the number of analyses for this location is 0.6 multiplied by 10, which is 6. In order to avoid obtaining a non-integer number of analyses, it is usually rounded down or rounded to ensure that the number of analyses for each location is an integer. For each corrosion probability value in the corrosion probability set, the above calculation process is repeated, and multiple numbers of analyses are finally obtained, each value representing the amount of analysis required for the line location in the integrated anomaly analysis.

[0050] Furthermore, the monitoring accuracy configuration module also includes the following operation steps:

[0051] The maximum monitoring accuracy of external image monitoring of the composite transmission line is obtained, wherein the external image monitoring includes multiple monitoring accuracy levels; multiple physical damage probabilities in the physical damage probability set are respectively used, multiplied by the maximum monitoring accuracy, and the closest monitoring accuracy level is matched according to the calculation results to obtain multiple monitoring accuracies.

[0052] Monitoring accuracy is expressed by image resolution or recognition capability, such as the minimum detection value of crack width or rust area. The higher the monitoring accuracy, the more details the image can capture, but it requires higher computing power and storage capacity. The maximum monitoring accuracy is determined by the highest resolution of the monitoring equipment, such as drone cameras or fixed monitoring equipment. For example, if the equipment supports the highest 4K resolution, the maximum monitoring accuracy can be set to 3840×2160 pixels. Among them, external image monitoring includes multiple monitoring accuracy levels, for example, low, medium, and high accuracy correspond to 720p, 1080p, and 4K, respectively.

[0053] The higher the probability of physical damage at each line location, the greater the risk of damage at that location, and higher monitoring accuracy is required to capture potential problems. The physical damage probability is a value between 0 and 1, which is directly used as a weight to multiply the maximum monitoring accuracy for dynamic adjustment of the monitoring accuracy. The closest monitoring accuracy level is selected based on the calculation results. For each value in the physical damage probability set, the above calculation and matching process is repeated, and finally multiple monitoring accuracies are formed to ensure that the monitoring accuracy of each line location meets actual needs.

[0054] Furthermore, the perception monitoring result acquisition module includes the following operation steps:

[0055] Pre-training includes a corrosion damage analysis channel of the corrosion damage analysis branch with the maximum number of analysis; inputting multiple environmental parameters in the environmental parameter set into the corrosion damage analysis branches of the multiple analysis numbers selected randomly, analyzing to obtain multiple output corrosion damage level sets, and calculating the mean to obtain multiple corrosion damage levels; performing image monitoring and acquisition on the multiple line locations according to the multiple monitoring accuracies to obtain multiple line images; performing physical damage identification on the multiple line images to obtain multiple physical damage levels; and combining the multiple corrosion damage levels and the multiple physical damage levels to obtain a transmission line perception monitoring result.

[0056] Based on historical data, a corrosion damage analysis channel with the maximum number of corrosion damage analysis branches is constructed to accurately evaluate the corrosion damage of the environmental parameter set. Each branch focuses on a part of the environmental parameter data and outputs the corresponding corrosion damage level.

[0057] From the pre-trained corrosion damage analysis channel, a specified number of corrosion damage analysis branches are randomly selected, such as 5 branches are selected from the maximum number of analysis branches. The diversity of the analysis is increased by random selection to avoid deviation. Each environmental parameter in the environmental parameter set is input into the randomly selected multiple analysis branches for analysis. Each branch processes the input environmental parameter independently and outputs the output corrosion damage level set corresponding to the environmental parameter. Multiple environmental parameters are analyzed to form multiple output corrosion damage level sets.

[0058] For each set of output corrosion damage levels of environmental parameters, the mean is calculated to obtain the final corrosion damage level of the environmental parameter. The mean results of all environmental parameters are integrated to form multiple corrosion damage levels as the final output of the corrosion damage assessment.

[0059] According to the multiple monitoring accuracies obtained, corresponding image acquisition requirements are set for different line positions, and image acquisition equipment, such as cameras, drone-mounted equipment, etc., are installed at multiple line positions. The image acquisition equipment should support adjustment of resolution and viewing angle to match the preset monitoring accuracy, trigger image acquisition, and obtain image data of the line surface. The acquisition content includes outer surface cracks of the line, surface coating status, integrity of insulating materials, etc., to form multiple line images at multiple line positions.

[0060] Use the pre-trained convolutional neural network model to identify physical damage in line images, automatically detect physical damage features in the image, such as cracks, peeling, and notches, extract features from each line image, generate a set of physical damage features, and match the physical damage level according to the identified damage features based on preset rules. For example, the preset rules set a crack length of <1cm as slight damage, a crack length of 1-5cm as moderate damage, and a crack length of >5cm as severe damage. Summarize the recognition results of all line images to obtain multiple physical damage levels at multiple line locations.

[0061] Integrate multiple corrosion damage levels and multiple physical damage levels to form complete transmission line perception monitoring results for repair and maintenance decisions.

[0062] Furthermore, the sensing monitoring result acquisition module further includes a corrosion damage analysis channel construction unit, and the corrosion damage analysis channel construction unit includes the following operation steps:

[0063] According to the composite transmission line corrosion detection data in historical time, a set of sample environmental parameters is collected, and the average corrosion damage level of the transmission line under different sample environmental parameters is obtained to obtain a set of sample corrosion damage levels; according to the maximum analysis quantity, the sample environmental parameter set and the sample corrosion damage level set are evenly divided to obtain multiple supervised training data of the maximum analysis quantity; the multiple supervised training data are respectively used to train the corrosion damage analysis branches of the maximum analysis quantity, and the corrosion damage analysis channels are obtained by combination.

[0064] From the composite transmission line corrosion detection data in historical time, environmental parameters related to line corrosion, such as temperature and humidity, concentration of chemical substances in the air, pH value, etc., are extracted, and these historical monitoring data are converted into a structured parameter set to form a sample environmental parameter set.

[0065] The corrosion damage level is defined according to the actual corrosion degree of the transmission line. For example, 0 represents no corrosion, 1 represents slight corrosion, 2 represents moderate corrosion, and 3 represents severe corrosion. The corrosion damage data under different sample environmental parameters are counted, and the average corrosion damage level is calculated to generate a sample corrosion damage level set.

[0066] The sample environmental parameter set and the sample corrosion damage level set are evenly divided according to the maximum number of analyses. For example, the maximum number of analyses is 10, and the sample environmental parameter set ranges from pH=1 to 7. They are evenly divided into 10 parts according to the range, and each part corresponds to an interval. The corresponding corrosion damage level set is divided according to the same logic, so that the samples are evenly divided into several subsets according to the parameter range or level range. The data of each subset includes the environmental parameters and the corresponding corrosion damage level, which are used as a set of supervised training data to obtain multiple supervised training data.

[0067] For each supervised training data, a machine learning method, such as decision tree, random forest or neural network, is used to train a corrosion damage analysis branch separately. The input is the environmental parameters and the output is the predicted corrosion damage level. Each analysis branch focuses on a part of the data to ensure more refined classification results. All analysis branches are combined to form a complete corrosion damage analysis channel. This corrosion damage analysis channel can automatically assign the input data to the corresponding branch for prediction based on the range of the input parameters, and output the corrosion damage level of each line location to support further decision-making.

[0068] In summary, the composite transmission line sensing and monitoring device provided in the embodiment of the present application has the following technical effects:

[0069] 1. Through the topological network deployment module, a monitoring topological network covering the composite transmission lines is established to achieve full coverage of the laying routes, and multiple distributed monitoring points are used to improve the comprehensiveness and accuracy of monitoring.

[0070] 2. Through the probability analysis module, multiple distributed monitoring points are used to collect electrical parameters and environmental parameters at multiple line locations of the transmission line, and line damage probability analysis and corrosion probability classification are performed at multiple line locations respectively to obtain line damage probability sets and corrosion probability sets, thereby quantifying and classifying damage risks, and further calculating physical damage probability sets, which can distinguish different damage types, provide data support for subsequent monitoring configuration, and significantly improve the scientificity and efficiency of the analysis.

[0071] 3. Through the monitoring accuracy configuration module, the analysis quantity and image monitoring accuracy are dynamically adjusted according to the corrosion probability and physical damage probability. For example, more analysis resources are allocated to line locations with high corrosion probability, and higher monitoring accuracy is allocated to locations with high physical damage probability. Through this dynamic adjustment mechanism, optimal utilization of resources is achieved, excessive monitoring or waste of resources is avoided, and higher monitoring accuracy is ensured at key locations.

[0072] 4. Through the perception monitoring result acquisition module, the corrosion damage level based on environmental parameters and the physical damage level based on image monitoring are integrated to form a comprehensive perception monitoring result of the transmission line. This module uniformly expresses multi-dimensional damage data into an intuitive damage level, providing a comprehensive and reliable reference basis for line maintenance.

[0073] In general, this composite transmission line sensing and monitoring device improves the reliability of transmission line monitoring, adaptability to complex environments, and accuracy of line damage identification through modular design and intelligent data processing. Especially in the context of large-scale distribution of transmission lines, the device can efficiently respond to diversified monitoring needs at different locations and with different damage types, thereby improving the operational safety of transmission lines.

[0074] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A composite transmission line sensing and monitoring device, characterized in that: The device comprises: A topological network layout module is used to obtain the laying route information of the composite transmission line and to perform monitoring topological network layout, wherein the monitoring topological network includes a plurality of distributed monitoring points, each of which is a distributed monitoring point; A probability analysis module, configured to monitor and obtain electrical parameters and environmental parameters of multiple line locations of the composite transmission line based on the multiple distributed monitoring points, obtain an electrical parameter set and an environmental parameter set, respectively perform line damage probability analysis and corrosion probability classification of the multiple line locations, obtain a line damage probability set and a corrosion probability set, and calculate and obtain a physical damage probability set; A monitoring accuracy configuration module, configured to configure multiple analysis quantities for integrated abnormal analysis of environmental parameters of the multiple line locations according to the corrosion probability set, and to configure multiple monitoring accuracies for external image monitoring and identification of the multiple line locations according to the physical damage probability set; A sensing monitoring result acquisition module is used to identify the environmental parameter set according to the multiple analysis quantities to obtain multiple corrosion damage levels, and to perform image monitoring and identification on the multiple line locations according to the multiple monitoring accuracies to obtain multiple physical damage levels as the transmission line sensing monitoring results; The monitoring accuracy configuration module includes the following steps: Get the maximum number of analyses for integrated anomaly analysis of environmental parameters; Respectively use multiple corrosion probabilities in the corrosion probability set, multiply by the maximum analysis quantity and round up to obtain multiple analysis quantities; The monitoring accuracy configuration module further includes the following steps: Obtaining a maximum monitoring accuracy of external image monitoring of a composite transmission line, wherein the external image monitoring includes multiple monitoring accuracy levels; A plurality of physical damage probabilities in the physical damage probability set are respectively used, multiplied by the maximum monitoring accuracy, and the closest monitoring accuracy level is matched according to the calculation results to obtain a plurality of monitoring accuracies.

2. The composite transmission line sensing and monitoring device according to claim 1, characterized in that: The topology network layout module includes the following steps: Obtaining laying route information of composite transmission lines; Dividing the laying route information to obtain multiple route locations; Distributed monitoring points are arranged at the multiple line locations to obtain multiple distributed monitoring points to form the monitoring topology network.

3. The composite power transmission line sensing and monitoring device according to claim 1, characterized in that: The probability analysis module includes the following steps: Constructing a line abnormality probability classification channel, wherein the line abnormality probability classification channel includes a line damage probability classification path and a corrosion probability classification branch; Inputting multiple electrical parameters and environmental parameters in the electrical parameter set and the environmental parameter set into the line damage probability classification path and the corrosion probability classification branch respectively, and classifying and outputting a line damage probability set and a corrosion probability set; The line damage probability set and the corrosion probability set are used to obtain the line damage probability set and the corrosion probability set for each line position, minus the corrosion probability.

4. The composite transmission line sensing and monitoring device according to claim 3, characterized in that: The probability analysis module further includes a line abnormality probability classification channel construction unit, and the line abnormality probability classification channel construction unit includes the following operation steps: Based on the monitoring data of the composite transmission line in the historical period, a set of sample electrical parameters is collected, and the proportion of line damage under different sample electrical parameters is collected to obtain a set of sample line damage probabilities; Using the sample electrical parameter set and the sample line damage probability set, based on a decision tree, construct a line damage probability classification path; Collect a set of sample environmental parameters, and collect the proportion of line corrosion under different environmental parameters to obtain a set of sample corrosion probabilities; Using the sample environmental parameter set and the sample corrosion probability set, based on a decision tree, a corrosion probability classification branch is constructed; The line damage probability classification path and the corrosion probability classification branch are combined to obtain a line abnormality probability classification channel.

5. The composite transmission line sensing and monitoring device according to claim 1, characterized in that: The perception monitoring result acquisition module includes the following operation steps: Pre-training the corrosion damage analysis channel including the maximum number of corrosion damage analysis branches; Inputting the multiple environmental parameters in the environmental parameter set into the randomly selected corrosion damage analysis branches of the multiple analysis quantities, respectively, analyzing to obtain multiple output corrosion damage level sets, and calculating the mean to obtain multiple corrosion damage levels; According to the multiple monitoring accuracies, image monitoring and acquisition are performed on the multiple line positions to obtain multiple line images; Performing physical damage identification on the multiple line images to obtain multiple physical damage levels; The multiple corrosion damage levels and the multiple physical damage levels are combined to obtain a transmission line perception monitoring result.

6. The composite transmission line sensing and monitoring device according to claim 5, characterized in that: The sensing monitoring result acquisition module further includes a corrosion damage analysis channel construction unit, and the corrosion damage analysis channel construction unit includes the following operation steps: According to the composite transmission line corrosion detection data in the historical time, a sample environmental parameter set is collected, and the average corrosion damage level of the transmission line under different sample environmental parameters is obtained to obtain a sample corrosion damage level set; According to the maximum number of analyses, the sample environmental parameter set and the sample corrosion damage level set are evenly divided to obtain a plurality of supervised training data of the maximum number of analyses; The plurality of supervised training data are respectively used to train and obtain the corrosion damage analysis branches with the maximum number of analyses, and the corrosion damage analysis channels are obtained by combining them.

Images