Power transmission and transformation line health state assessment atlas display method and system and medium

Abstract

The embodiment of the invention discloses a power transmission and transformation line health state assessment mapping display method and system and a medium, and the method comprises the steps: collecting multi-dimensional data of a power transmission and transformation line, integrating the multi-dimensional data, and obtaining final fusion data; determining a life prediction value and a fault prediction probability according to historical fault data, historical operation data and environmental data in the final fusion data; determining a comprehensive health index according to the final fusion data and the life prediction value; determining a comprehensive risk level according to the comprehensive health index and the fault prediction probability; determining a residual life prediction value according to the historical operation data, the comprehensive health index and the environment data; the comprehensive health index, the comprehensive risk level and the residual life prediction value are displayed in a map form, user interaction operation is supported, and the user's ability to understand and analyze complex data is enhanced through interactive visualization, so that the user can quickly position problems and make decisions.

Description

Technical Field

[0001] The present invention relates to the technical field of power system monitoring and management, and in particular to a method, system and medium for graphically displaying health status assessment of power transmission and transformation lines. Background Art

[0002] In modern power systems, power transmission and transformation lines are the key link in power transmission, and their health status is directly related to the safety and reliability of power supply. With the continuous growth of power demand and the increasing complexity of the power grid structure, power transmission and transformation lines are facing more and more challenges, such as equipment aging, environmental changes, load fluctuations, etc. These factors may lead to line failures, thus causing power outages and causing significant losses to the society and economy.

[0003] Traditional methods for assessing the health status of power transmission and transformation lines mainly rely on manual inspections and regular testing, which often result in delayed information acquisition, subjective judgment, and inaccurate assessments. In addition, existing monitoring technologies also have limitations in data collection and processing, and cannot reflect the health status of the lines in real time. With the development of smart grid and Internet of Things technologies, how to efficiently and accurately assess the health status of power transmission and transformation lines has become an important issue that needs to be urgently addressed in the power industry. Summary of the invention

[0004] Based on this, it is necessary to propose a graphical display method, system and medium for health status assessment of power transmission and transformation lines to address the above problems.

[0005] A method for graphically displaying health status assessment of a power transmission and transformation line, the method comprising:

[0006] Collect multi-dimensional data of the power transmission and transformation lines, integrate the multi-dimensional data, and obtain final fused data.

[0007] The life prediction value and the failure prediction probability are determined according to the historical failure data, the historical operation data and the environmental data in the final fused data.

[0008] A comprehensive health index is determined based on the final fused data and the life expectancy prediction value.

[0009] A comprehensive risk level is determined based on the comprehensive health index and the failure prediction probability.

[0010] The remaining life prediction value is determined based on the historical operating data, the comprehensive health index and the environmental data.

[0011] The comprehensive health index, comprehensive risk level and remaining life expectancy prediction value are displayed in a graphical form.

[0012] The collecting of multi-dimensional data of the power transmission and transformation lines, integrating the multi-dimensional data, and obtaining final fused data specifically include:

[0013] Collect multi-dimensional data of power transmission and transformation lines.

[0014] The multi-dimensional data is weightedly fused to obtain fused data.

[0015] The line topology features of the power transmission and transformation lines are extracted through graph convolutional networks.

[0016] The multidimensional data features of the multidimensional data are extracted by generating an adversarial network.

[0017] The fused data, the line topology characteristics of the power transmission and transformation lines and the multi-dimensional data characteristics are fused to generate final fused data.

[0018] The step of performing weighted fusion on the multi-dimensional data to obtain fused data specifically includes:

[0019] A multimodal data fusion model is determined according to the weight of the sensor data in the multidimensional data, and the multimodal data fusion model is:

[0020]

[0021] Among them, X is the fusion data, α i is the weight of the i-th sensor data, f(X i ) is the characteristic function of sensor data, W i is the weight matrix, Wj is the reliability weight of the jth sensor data, X i is multidimensional data, and T is the transposed amount.

[0022] The multi-dimensional data is weightedly fused according to the multimodal data fusion model to obtain fused data.

[0023] The extracting of line topology features of the power transmission and transformation line through the graph convolutional network specifically includes:

[0024] The node and edge information of the power transmission and transformation line is collected, a topological structure diagram of the power transmission and transformation line is constructed, and the topological structure data of the power transmission and transformation line is extracted from the topological structure diagram.

[0025] An adjacency matrix and a characteristic matrix are determined according to the topological structure data and the multidimensional data of each node in the graph.

[0026] Based on the graph convolutional network, the line topology characteristics of the power transmission and transformation line are obtained through the adjacency matrix and the feature matrix.

[0027] Wherein, the line topology characteristics of the power transmission and transformation line are obtained through the adjacency matrix and the feature matrix based on the graph convolution network, specifically including:

[0028] Based on the graph convolutional network, a graph convolutional network model is constructed through the adjacency matrix and the feature matrix.

[0029]

[0030] Among them, H (l+1) is the line topology feature of the power transmission and transformation line, A is the adjacency matrix, H (l) is the feature matrix of each node, σ is the activation function, D is the degree matrix, W (l) is the learnable weight matrix of the lth layer.

[0031] The line topology characteristics of the current power transmission and transformation lines are obtained based on the graph convolutional network model.

[0032] The step of extracting multidimensional data features of multidimensional data by generating an adversarial network specifically includes:

[0033] Based on the generative adversarial network, a generative adversarial network model is constructed according to the multidimensional data, and the generative adversarial network model is:

[0034]

[0035] in, is the multidimensional data feature of multidimensional data, x t is the input data at time t, y t is the self-supervised generated label, Generate adversarial networks.

[0036] The line topology features of the transmission and transformation lines are extracted based on the graph convolutional network model.

[0037] The step of fusing the fused data, the line topology features of the power transmission and transformation lines and the multi-dimensional data features to generate the final fused data specifically includes:

[0038] A data processing model for a power transmission and transformation line is constructed based on the fused data, the line topology characteristics of the power transmission and transformation line, and the multi-dimensional data characteristics. The data processing model for a power transmission and transformation line is:

[0039]

[0040] Among them, X final is the final fused data, X is the fused data, H (l+l) is the line topology characteristic of the transmission and transformation line, is the multidimensional data feature of multidimensional data, θ * Model parameters optimized for meta-learning, Wt is the temporal convolution kernel, W s is the spatial convolution kernel, j is the jth power transmission and transformation line, and k is the kth multidimensional data.

[0041] The final fusion data of the current power transmission and transformation line is determined according to the power transmission and transformation line data processing model.

[0042] The step of determining the comprehensive health index according to the final fusion data and the life expectancy prediction value specifically includes:

[0043] The health index model is determined according to the weight of the final fusion data, and the health index model is:

[0044]

[0045] Among them, H weight is the health index of the transmission and transformation line; w i is the weight of the i-th final fusion data, x i is the value of the i-th final fused data, and n is the number of final fused data.

[0046] A fuzzy comprehensive evaluation model is determined according to the weight vector and fuzzy membership matrix of the final fusion data.

[0047] The health index of the current power transmission and transformation line is determined according to the health index model.

[0048] The health level vector of the current power transmission and transformation line is determined according to the fuzzy comprehensive evaluation model.

[0049] A comprehensive health index fusion model is determined according to the health index, health level vector and life prediction value, and the comprehensive health index fusion model is:

[0050] H final =α1·H weight +α2·S+α3·L dnn ;

[0051] Among them, H final is the comprehensive health index, H weight is the health index of the transmission and transformation line, S is the health level vector, L dnn is the life prediction value output by the deep learning model, α1 is the weight coefficient of the health index model, α2 is the weight coefficient of the fuzzy comprehensive evaluation model, and α3 is the weight coefficient of the deep learning model.

[0052] The comprehensive health index of the current power transmission and transformation line is determined according to the comprehensive health index fusion model.

[0053] The step of determining the comprehensive risk level according to the comprehensive health index and the failure prediction probability specifically includes:

[0054] A risk assessment model is determined based on the comprehensive health index and the failure prediction probability, and the risk assessment model is:

[0055] R final =β1·H final +β2·P failure ;

[0056] Among them, R final is the comprehensive risk level, H final is the comprehensive health index, P failure is the failure prediction probability, β1 and β2 are the weight coefficients in risk assessment.

[0057] The comprehensive risk level of the current power transmission and transformation line is determined according to the risk assessment model.

[0058] The method of determining the remaining life prediction value according to the historical operation data, the comprehensive health index and the environmental data specifically includes:

[0059] The remaining life prediction model is determined based on the historical operation data, the comprehensive health index and the environmental data. The remaining life prediction model is:

[0060] L pred =γ1·L historical +γ2·H final +γ3·E;

[0061] Among them, L pred is the predicted remaining life, L historical is the historical life expectancy forecast value, H final is the current comprehensive health index, and E is the environmental data.

[0062] The remaining life prediction value of the current transmission and transformation line is determined based on the remaining life prediction model.

[0063] Among them, after displaying the comprehensive health index, comprehensive risk level and remaining life prediction value in a graphical form, it also specifically includes:

[0064] The comprehensive health index, comprehensive risk level and remaining life prediction value are used as health assessment data to determine whether the health status assessment data is greater than or equal to a preset risk threshold.

[0065] If it is determined that the health status assessment data is greater than or equal to the preset risk threshold, the transmission and transformation line is marked as a high-risk line.

[0066] If it is determined that the health status assessment data is less than the preset risk threshold, the transmission and transformation line is marked as a non-high-risk line.

[0067] A graphical display system for evaluating the health status of a power transmission and transformation line, the system comprising:

[0068] The final fused data acquisition module is used to collect multi-dimensional data of the power transmission and transformation lines, integrate the multi-dimensional data, and obtain the final fused data.

[0069] The life prediction value and fault prediction probability determination module is used to determine the life prediction value and fault prediction probability based on the historical fault data, historical operation data and environmental data in the final fusion data.

[0070] The comprehensive health index determination module is used to determine the comprehensive health index according to the final fusion data and the life expectancy prediction value.

[0071] The comprehensive risk level determination module is used to determine the comprehensive risk level according to the comprehensive health index and the failure prediction probability.

[0072] The remaining life prediction value determination module is used to determine the remaining life prediction value based on the historical operation data, the comprehensive health index and the environmental data.

[0073] The graphical display module is used to display the comprehensive health index, comprehensive risk level and remaining life prediction value in a graphical form.

[0074] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor is caused to execute the steps of the method described above.

[0075] The embodiments of the present invention have the following beneficial effects:

[0076] The present invention first integrates the multi-dimensional data of the power transmission and transformation lines collected by various sensors to ensure the accuracy and consistency of the data, thereby improving the comprehensiveness of the health status assessment and reducing the misjudgment caused by a single data source. Secondly, the life prediction value and the failure prediction probability are determined based on the historical fault data, historical operation data and environmental data in the final fusion data; the comprehensive health index is determined based on the final fusion data and the life prediction value; the comprehensive risk level is determined based on the comprehensive health index and the failure prediction probability; the remaining life prediction value is determined based on the historical operation data, the comprehensive health index and the environmental data; the comprehensive health index, the comprehensive risk level and the remaining life prediction value are displayed in a graphical form to support user interactive operations. This interactive visualization enhances the user's understanding and analysis capabilities of complex data, enabling them to quickly locate problems and make decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0078] in:

[0079] Figure 1 A schematic diagram of a flow chart of an embodiment of a method for graphically displaying health status assessment of a power transmission and transformation line provided by the present invention;

[0080] Figure 2 A schematic diagram of a flow chart of another embodiment of a method for graphically displaying health status assessment of a power transmission and transformation line provided by the present invention;

[0081] Figure 3 A schematic diagram of the structure of an embodiment of a graphical display system for evaluating the health status of a power transmission and transformation line provided by the present invention;

[0082] Figure 4 A schematic structural diagram of an embodiment of the medium provided by the present invention. DETAILED DESCRIPTION

[0083] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0084] like Figure 1 As shown, Figure 1 A schematic diagram of a flow chart of an embodiment of a method for graphically displaying the health status evaluation of a power transmission and transformation line provided by the present invention. A method for graphically displaying the health status evaluation of a power transmission and transformation line, the method comprising:

[0085] S101: Collect multi-dimensional data of the power transmission and transformation lines, integrate the multi-dimensional data, and obtain final fused data.

[0086] Exemplarily, multi-dimensional data of power transmission and transformation lines are collected; weighted fusion is performed on the multi-dimensional data to obtain fused data; line topology features of the power transmission and transformation lines are extracted through a graph convolutional network; multi-dimensional data features of the multi-dimensional data are extracted through a generative adversarial network; the fused data, line topology features of the power transmission and transformation lines and multi-dimensional data features are fused to generate final fused data.

[0087] S102: Determine a life prediction value and a failure prediction probability according to the historical failure data, historical operation data and environmental data in the final fused data.

[0088] For example, the deep learning model is responsible for predicting the future fault status and life of the power transmission and transformation line. By learning the historical fault data, historical operation data and environmental data in the final fusion data, the model outputs the life prediction value and fault prediction probability.

[0089] S103: Determine a comprehensive health index based on the final fusion data and the life expectancy prediction value.

[0090] Exemplarily, the health index model is determined according to the weight of the final fusion data, and the health index model is shown in the following formula:

[0091]

[0092] Among them, H weight is the health index of the transmission and transformation line; w i is the weight of the i-th final fusion data, x i is the value of the i-th final fused data, and n is the number of final fused data.

[0093] The current final fusion data is input into the health index model to determine the health index of the current transmission and transformation line.

[0094] At the same time, the fuzzy comprehensive evaluation model is determined according to the weight vector and fuzzy membership matrix of the final fusion data, and the current final fusion data is input into the fuzzy comprehensive evaluation model to determine the health level vector of the current transmission and transformation line.

[0095] In the fuzzy comprehensive evaluation model, first, based on the final fusion data input, the membership function is used to convert each evaluation indicator (such as temperature, vibration, pressure, etc.) into a membership value, and fuzzy classification is performed according to the preset evaluation set. Each evaluation indicator will be assigned a corresponding weight to reflect its importance in the evaluation process. Then, combined with the membership matrix and the weight vector, the comprehensive evaluation result is calculated through the fuzzy comprehensive evaluation matrix to represent the health status or risk level of the equipment. Finally, the fuzzy evaluation result is converted into a health level vector through a defuzzification method (such as the weighted average method), providing a clear health status index or risk level to provide decision support for operation and maintenance personnel.

[0096] Furthermore, a comprehensive health index fusion model is determined according to the health index, health level vector and life expectancy prediction value. The comprehensive health index fusion model is shown in the following formula:

[0097] H final =α1·H weight +α2·S+α3·Ldnn ;

[0098] Among them, H final is the comprehensive health index, H weight is the health index of the transmission and transformation line, S is the health level vector, L dnn is the life prediction value output by the deep learning model, α1 is the weight coefficient of the health index model, α2 is the weight coefficient of the fuzzy comprehensive evaluation model, and α3 is the weight coefficient of the deep learning model.

[0099] The health index, health grade vector and life prediction value of the current power transmission and transformation line are input into the comprehensive health index fusion model to determine the comprehensive health index of the current power transmission and transformation line.

[0100] S104: Determine the comprehensive risk level based on the comprehensive health index and the failure prediction probability.

[0101] Exemplarily, a risk assessment model is determined based on the comprehensive health index and the failure prediction probability, and the risk assessment model is shown in the following formula:

[0102] R final =β1·H final +β2·P failure ;

[0103] Among them, R final is the comprehensive risk level, H final is the comprehensive health index, P failure is the failure prediction probability, β1 and β2 are the weight coefficients in risk assessment.

[0104] The comprehensive health index and fault prediction probability of the current power transmission and transformation line are input into the risk assessment model to determine the comprehensive risk level of the current power transmission and transformation line.

[0105] S105: Determine the remaining life prediction value based on historical operation data, comprehensive health index and environmental data.

[0106] Exemplarily, the remaining life prediction model is determined based on historical operation data, comprehensive health index and environmental data. The remaining life prediction model is shown in the following formula:

[0107] L pred =γ1·L historical +γ2·H final +γ3·E;

[0108] Among them, L pred is the predicted remaining life, L historical is the historical life expectancy forecast value, H final is the current comprehensive health index, and E is the environmental data.

[0109] The current comprehensive health index is input into the remaining life prediction model to determine the remaining life prediction value of the current transmission and transformation line.

[0110] S106: The comprehensive health index, comprehensive risk level and remaining life expectancy prediction value are displayed in a graphical form.

[0111] Exemplarily, the comprehensive health index, comprehensive risk level and remaining life prediction value are displayed in a graphical form. Specifically, the comprehensive health index, comprehensive risk level and remaining life prediction value of the transmission and transformation lines are dynamically presented in the form of charts, graphs, three-dimensional maps, etc. through visualization technology to build an interactive graph platform. The platform supports users to view health status, historical trends and risk predictions in real time in a multi-dimensional space, provides dynamic update functions, and upgrades static data display to interactive multi-dimensional graphs. This solution greatly improves users' ability to analyze and understand data, helps to identify potential problems more efficiently, and assists in quick decision-making. The interactive graph platform includes:

[0112] (1) Chart generation module:

[0113] Various two-dimensional and three-dimensional charts are generated based on the processed data, including line charts, pie charts, bar charts and network topology diagrams, which are used to dynamically present information such as the comprehensive health index, comprehensive risk level and remaining life prediction value of the transmission and transformation lines.

[0114] (2) 3D map display module:

[0115] This module builds a three-dimensional spatial map based on the geographical location information of the power transmission and transformation lines. The health status of each node and related equipment of the line is presented on the map through color identification and dynamic change effects. Users can freely rotate and zoom the three-dimensional map to view the line status at different locations.

[0116] (3) Risk prediction and early warning module:

[0117] The comprehensive health index, comprehensive risk level and remaining life prediction value of the transmission and transformation lines are compared with historical data, and the future fault risk level is generated through the prediction algorithm, and dynamically marked in a graphical manner on the atlas platform. The fault risk is dynamically displayed using different color gradients, and the equipment with higher risk will flash as a prompt.

[0118] (4) Multidimensional data interaction module:

[0119] The platform supports users to view data in real time in multiple dimensions, including time dimension, device dimension, geographic dimension, etc. Users can filter data by selecting different dimensions to view the historical change curve of health status and its distribution in different spatial locations.

[0120] (5) Dynamic update module:

[0121] The system has the ability to dynamically update data, and receives new health assessment results from the data processing module in real time, including the comprehensive health index, comprehensive risk level and remaining life prediction value of the transmission and transformation lines, and updates and displays them on the graph platform in real time. This function ensures that users can make accurate judgments based on the latest data and improves the real-time performance of the system.

[0122] It should be noted that on the interactive map display platform, users can also view the health status assessment data of specific lines in real time by hovering the mouse, clicking, etc., including the comprehensive health index, comprehensive risk level and remaining life prediction value, to help users identify and locate potential risk areas. Through the interactive function, users can clearly understand the status of each device and line, providing basic data for subsequent operation and maintenance decisions.

[0123] From the above description, it can be seen that the present invention first integrates the multi-dimensional data of the power transmission and transformation lines collected by various sensors to ensure the accuracy and consistency of the data, thereby improving the comprehensiveness of the health status assessment and reducing the misjudgment caused by a single data source. Secondly, the life prediction value and the failure prediction probability are determined based on the historical fault data, historical operation data and environmental data in the final fusion data; the comprehensive health index is determined based on the final fusion data and the life prediction value; the comprehensive risk level is determined based on the comprehensive health index and the failure prediction probability; the remaining life prediction value is determined based on the historical operation data, the comprehensive health index and the environmental data; the comprehensive health index, the comprehensive risk level and the remaining life prediction value are displayed in a graphical form to support user interactive operations. This interactive visualization enhances the user's understanding and analysis capabilities of complex data, enabling them to quickly locate problems and make decisions. It also combines time, space and environmental factors to provide comprehensive historical trend analysis and future risk prediction.

[0124] like Figure 2 As shown, Figure 2 A schematic diagram of another embodiment of a method for graphically displaying the health status of a power transmission and transformation line provided by the present invention. A method for graphically displaying the health status of a power transmission and transformation line, the method comprising:

[0125] S201: Collect multi-dimensional data of power transmission and transformation lines.

[0126] S202: Perform weighted fusion on the multi-dimensional data to obtain fused data.

[0127] Exemplarily, a multimodal data fusion model is determined according to the weight of sensor data in the multidimensional data, and the multimodal data fusion model is:

[0128]

[0129] Among them, X is the fusion data, αi is the weight of the i-th sensor data, f(X i ) is the characteristic function of sensor data, W i is the weight matrix, Wj is the reliability weight of the jth sensor data, X i is multidimensional data, T is the transposed amount;

[0130] The multi-dimensional data is weightedly fused according to the multimodal data fusion model to obtain fused data.

[0131] S203: Extracting line topology features of the power transmission and transformation lines through a graph convolutional network.

[0132] Exemplarily, node and edge information of the power transmission and transformation line is collected, a topological structure diagram of the power transmission and transformation line is constructed, and topological structure data of the power transmission and transformation line is extracted from the topological structure diagram; an adjacency matrix and a characteristic matrix are determined according to the topological structure data and multidimensional data of each node in the diagram;

[0133] Based on the graph convolutional network, the graph convolutional network model is constructed through the adjacency matrix and feature matrix.

[0134]

[0135] Among them, H (l+1) is the line topology feature of the power transmission and transformation line, A is the adjacency matrix, H (l) is the feature matrix of each node, σ is, D is the degree matrix, W (l) is the learnable weight matrix of the lth layer.

[0136] The line topology characteristics of the current power transmission and transformation lines are obtained based on the graph convolutional network model.

[0137] S204: Extracting multidimensional data features of the multidimensional data by generating an adversarial network.

[0138] Exemplarily, based on a generative adversarial network, a generative adversarial network model is constructed according to multidimensional data, and the generative adversarial network model is:

[0139]

[0140] in, is the multidimensional data feature of multidimensional data, x t is the input data at time t, y t is the self-supervised generated label, Generate adversarial networks.

[0141] The line topology features of the transmission and transformation lines are extracted based on the graph convolutional network model.

[0142] S205: Fusing the fused data, the line topology features of the power transmission and transformation lines, and the multi-dimensional data features to generate final fused data.

[0143] Exemplarily, a data processing model for a power transmission and transformation line is constructed based on the fusion data, the line topology characteristics of the power transmission and transformation line, and the multi-dimensional data characteristics. The data processing model for the power transmission and transformation line is:

[0144]

[0145] Among them, X final is the final fused data, X is the fused data, H (l+1) is the line topology characteristic of the transmission and transformation line, is the multidimensional data feature of multidimensional data, θ * Model parameters optimized for meta-learning, W t is the temporal convolution kernel, W s is the spatial convolution kernel, j is the jth power transmission and transformation line, and k is the kth multidimensional data.

[0146] The final fusion data of the current power transmission and transformation line is determined according to the power transmission and transformation line data processing model.

[0147] S206: Determine the life prediction value and the failure prediction probability according to the historical failure data, historical operation data and environmental data in the final fused data.

[0148] S207: Determine a comprehensive health index based on the final fusion data and the life expectancy prediction value.

[0149] Exemplarily, the health index model is determined according to the weight of the final fusion data, and the health index model is:

[0150]

[0151] Among them, H weight is the health index of the transmission and transformation line; w i is the weight of the i-th final fusion data, x i is the value of the i-th final fused data, and n is the number of final fused data;

[0152] Determine the fuzzy comprehensive evaluation model based on the weight vector and fuzzy membership matrix of the final fusion data. Determine the health index of the current transmission and transformation line based on the health index model; determine the health level vector of the current transmission and transformation line based on the fuzzy comprehensive evaluation model; determine the comprehensive health index fusion model based on the health index, health level vector and life prediction value. The comprehensive health index fusion model is:

[0153] H final =α1·H weight +α2·S+α3·Ldnn ;

[0154] Among them, H final is the comprehensive health index, H weight is the health index of the transmission and transformation line, S is the health level vector, L dnn is the life prediction value output by the deep learning model, α1 is the weight coefficient of the health index model, α2 is the weight coefficient of the fuzzy comprehensive evaluation model, and α3 is the weight coefficient of the deep learning model.

[0155] The comprehensive health index of the current transmission and transformation line is determined based on the comprehensive health index fusion model.

[0156] S208: Determine the comprehensive risk level based on the comprehensive health index and the failure prediction probability.

[0157] Exemplarily, a risk assessment model is determined according to the comprehensive health index and the failure prediction probability, and the risk assessment model is:

[0158] R final =β1·H final +β2·P failure ;

[0159] Among them, R final is the comprehensive risk level, H final is the comprehensive health index, P failure is the failure prediction probability, β1 and β2 are the weight coefficients in risk assessment.

[0160] Determine the comprehensive risk level of the current transmission and transformation lines based on the risk assessment model.

[0161] S209: Determine the remaining life prediction value based on historical operating data, comprehensive health index and environmental data.

[0162] Exemplarily, a remaining life prediction model is determined based on historical operation data, comprehensive health index and environmental data, and the remaining life prediction model is:

[0163] L pred =γ1·L historical +γ2·H final +γ3·E;

[0164] Among them, L pred is the predicted remaining life, L historical is the historical life expectancy forecast, H final is the current comprehensive health index, and E is the environmental data.

[0165] The remaining life prediction value of the current transmission and transformation line is determined based on the remaining life prediction model.

[0166] S210: The comprehensive health index, comprehensive risk level and remaining life expectancy prediction value are displayed in a graphical form.

[0167] It should be noted that step S210 Figure 1 This has been discussed in detail in the implementation scenario shown and will not be repeated here.

[0168] S211: Use the comprehensive health index, comprehensive risk level and remaining life prediction value as health assessment data to determine whether the health status assessment data is greater than or equal to a preset risk threshold.

[0169] S2111: If it is determined that the health status assessment data is greater than or equal to a preset risk threshold, the transmission and transformation line is marked as a high-risk line.

[0170] S2112: If it is determined that the health status assessment data is less than a preset risk threshold, the transmission and transformation line is marked as a non-high-risk line.

[0171] Exemplarily, whether to generate a risk warning is determined by comparing the comprehensive health index, comprehensive risk level and remaining life prediction value with the preset risk threshold set by the system. When the health status of the equipment reaches the predetermined risk level threshold, the high-risk equipment is dynamically identified on the platform through color changes (such as red highlight or flashing prompts) to remind users to pay attention to potential risks and perform preventive maintenance. Specifically, if it is determined that the health status assessment data is greater than or equal to the preset risk threshold, the transmission and transformation line is marked as a high-risk line, and a risk warning is issued for the high-risk line. If it is determined that the health status assessment data is less than the preset risk threshold, the transmission and transformation line is marked as a non-high-risk line.

[0172] It should be noted that the interactive graph display platform can also automatically generate personalized operation and maintenance recommendations by analyzing health status assessment data and user operation and maintenance needs. The platform can provide specific maintenance time, priority sorting and recommended maintenance operations to assist users in making reasonable maintenance plans. The operation and maintenance plan supports visual display to help users intuitively understand and adjust the plan, making the health management of the transmission and transformation lines more scientific and systematic.

[0173] From the above description, it can be seen that the present invention can effectively reduce power outages and related losses caused by faults through risk warning, thereby reducing operation and maintenance costs and improving overall operating efficiency. The adaptability and scalability of its design also enable the system to be adjusted according to different power transmission and transformation lines and specific needs, continuously adapting to the needs of technological development, and providing a more efficient and scientific solution.

[0174] like Figure 3 As shown, Figure 3A schematic diagram of a system for displaying the health status of a power transmission and transformation line provided by the present invention. A system for displaying the health status of a power transmission and transformation line 10, the system comprising:

[0175] The final fused data acquisition module 11 is used to collect multi-dimensional data of the power transmission and transformation lines, integrate the multi-dimensional data, and obtain the final fused data.

[0176] The life prediction value and fault prediction probability determination module 12 is used to determine the life prediction value and fault prediction probability according to the historical fault data, historical operation data and environmental data in the final fusion data.

[0177] The comprehensive health index determination module 13 is used to determine the comprehensive health index according to the final fusion data and the life expectancy prediction value.

[0178] The comprehensive risk level determination module 14 is used to determine the comprehensive risk level according to the comprehensive health index and the failure prediction probability.

[0179] The remaining life prediction value determination module 15 is used to determine the remaining life prediction value based on historical operation data, comprehensive health index and environmental data.

[0180] The graphical display module 16 is used to display the comprehensive health index, the comprehensive risk level and the remaining life prediction value in a graphical form.

[0181] Exemplarily, in the final fusion data module 11, multi-dimensional data of the power transmission and transformation lines are collected; the multi-dimensional data are weightedly fused to obtain fused data; the line topology features of the power transmission and transformation lines are extracted through a graph convolutional network; the multi-dimensional data features of the multi-dimensional data are extracted through a generative adversarial network; the fused data, the line topology features of the power transmission and transformation lines and the multi-dimensional data features are fused to generate the final fused data. In the life prediction value and fault prediction probability determination module 12, the life prediction value and the fault prediction probability are determined based on the historical fault data, historical operation data and environmental data in the final fused data. In the comprehensive health index determination module 13, the health index model is determined based on the weight of the final fused data, and the health index model is:

[0182]

[0183] Among them, H weight is the health index of the transmission and transformation line; w i is the weight of the i-th final fusion data, x i is the value of the i-th final fused data, and n is the number of final fused data;

[0184] The fuzzy comprehensive evaluation model is determined according to the weight vector and fuzzy membership matrix of the final fusion data.

[0185] Determine the health index of the current transmission and transformation line based on the health index model.

[0186] The health level vector of the current transmission and transformation line is determined based on the fuzzy comprehensive evaluation model.

[0187] The comprehensive health index fusion model is determined based on the health index, health level vector and life expectancy prediction value. The comprehensive health index fusion model is:

[0188] H final =α1·H weight +α2·S+α3·L dnn ;

[0189] Among them, H final is the comprehensive health index, H weight is the health index of the transmission and transformation line, S is the health level vector, L dnn is the life prediction value output by the deep learning model, α1 is the weight coefficient of the health index model, α2 is the weight coefficient of the fuzzy comprehensive evaluation model, and α3 is the weight coefficient of the deep learning model.

[0190] The comprehensive health index of the current transmission and transformation line is determined based on the comprehensive health index fusion model.

[0191] Furthermore, in the comprehensive risk level determination module 14, the comprehensive risk level is determined according to the comprehensive health index and the failure prediction probability. In the remaining life prediction value determination module 15, the remaining life prediction value is determined according to the historical operation data, the comprehensive health index and the environmental data.

[0192] Finally, in the graphical display module 16, the comprehensive health index, the comprehensive risk level and the remaining life prediction value are displayed in a graphical form.

[0193] like Figure 4 As shown, Figure 4 The structure diagram of an embodiment of the medium provided by the present invention is shown in FIG. The medium 20 stores at least one computer program 21, which is executed by a processor to implement the following Figure 1 and Figure 2 In one embodiment, the medium 20 may be a storage chip, a hard disk, a mobile hard disk, a USB flash drive, an optical disk, or other readable and writable storage tools, or a server, etc.

[0194] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0195] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer-readable storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0196] The apparatus, device, non-volatile computer-readable storage medium and method provided in the embodiments of this specification correspond to each other, and therefore, the apparatus, device, and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the corresponding apparatus, device, and non-volatile computer storage medium will not be repeated here.

[0197] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0198] For the convenience of description, the above device is described by being divided into various units according to their functions and described separately. Of course, when implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware. It should be understood by those skilled in the art that this specification embodiment can be provided as a method, system, or computer program product. Therefore, this specification embodiment can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification embodiment can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0199] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0200] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0201] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A graphical display method for evaluating the health status of a power transmission and transformation line, characterized in that: The method comprises: Collecting multi-dimensional data of power transmission and transformation lines, integrating the multi-dimensional data, and obtaining final fused data; Determine a life prediction value and a failure prediction probability according to the historical failure data, the historical operation data and the environmental data in the final fused data; Determine a comprehensive health index based on the final fused data and the life expectancy prediction value; Determining a comprehensive risk level based on the comprehensive health index and the predicted probability of failure; Determining a remaining life prediction value based on the historical operating data, the comprehensive health index and the environmental data; The comprehensive health index, comprehensive risk level and remaining life expectancy prediction value are displayed in a graphical form.

2. A method for displaying the health status of a power transmission and transformation line according to claim 1, characterized in that: The collecting of multi-dimensional data of the power transmission and transformation lines and integrating the multi-dimensional data to obtain final fused data specifically includes: Collect multi-dimensional data of power transmission and transformation lines; Performing weighted fusion on the multidimensional data to obtain fused data; Extract the line topology features of the power transmission and transformation lines through graph convolutional networks; Extracting multidimensional data features of the multidimensional data by generating an adversarial network; The fused data, the line topology characteristics of the power transmission and transformation lines and the multi-dimensional data characteristics are fused to generate final fused data.

3. A method for displaying the health status of a power transmission and transformation line according to claim 2, characterized in that: The weighted fusion of the multi-dimensional data to obtain fused data specifically includes: A multimodal data fusion model is determined according to the weight of the sensor data in the multidimensional data, and the multimodal data fusion model is: Among them, X is the fusion data, α i is the weight of the i-th sensor data, f(X i ) is the characteristic function of sensor data, W i is the weight matrix, Wj is the reliability weight of the jth sensor data, X i is multidimensional data, T is the transposed amount; The multi-dimensional data is weightedly fused according to the multimodal data fusion model to obtain fused data.

4. A method for displaying the health status of a power transmission and transformation line according to claim 2, characterized in that: The extracting of the line topology features of the power transmission and transformation line by using the graph convolutional network specifically includes: Collecting node and edge information of the power transmission and transformation line, constructing a topological structure diagram of the power transmission and transformation line, and extracting topological structure data of the power transmission and transformation line from the topological structure diagram; Determine an adjacency matrix and a characteristic matrix according to the topological structure data and the multidimensional data of each node in the graph; Based on the graph convolutional network, the line topology characteristics of the power transmission and transformation line are obtained through the adjacency matrix and the feature matrix.

5. A graphical display method for evaluating the health status of a power transmission and transformation line according to claim 4, characterized in that: The method of obtaining the line topology characteristics of the power transmission and transformation line through the adjacency matrix and the feature matrix based on the graph convolution network specifically includes: Based on the graph convolutional network, a graph convolutional network model is constructed through the adjacency matrix and the feature matrix. Among them, H (l+1) is the line topology feature of the power transmission and transformation line, A is the adjacency matrix, H (l) is the feature matrix of each node, σ is the activation function, D is the degree matrix, W (l) is the learnable weight matrix of the lth layer; The line topology characteristics of the current power transmission and transformation lines are obtained based on the graph convolutional network model.

6. A method for displaying the health status of a power transmission and transformation line according to claim 2, characterized in that: The method of extracting multidimensional data features of multidimensional data by generating an adversarial network specifically includes: Based on the generative adversarial network, a generative adversarial network model is constructed according to the multidimensional data, and the generative adversarial network model is: in, is the multidimensional data feature of multidimensional data, x t is the input data at time t, y t is the self-supervised generated label, To generate adversarial networks; The line topology features of the transmission and transformation lines are extracted based on the graph convolutional network model.

7. A method for displaying the health status of a power transmission and transformation line according to claim 2, characterized in that: The step of fusing the fused data, the line topology characteristics of the power transmission and transformation line, and the multi-dimensional data characteristics to generate final fused data specifically includes: A data processing model for a power transmission and transformation line is constructed based on the fused data, the line topology characteristics of the power transmission and transformation line, and the multi-dimensional data characteristics. The data processing model for a power transmission and transformation line is: Among them, X final is the final fused data, X is the fused data, H (l+1) is the line topology characteristic of the transmission and transformation line, is the multidimensional data feature of multidimensional data, θ * Model parameters optimized for meta-learning, W t is the temporal convolution kernel, W s is the spatial convolution kernel, j is the jth power transmission and transformation line, and k is the kth multidimensional data. The final fusion data of the current power transmission and transformation line is determined according to the power transmission and transformation line data processing model.

8. A method for displaying the health status of a power transmission and transformation line according to claim 2, characterized in that: Determining the comprehensive health index according to the final fusion data and the life expectancy prediction value specifically includes: The health index model is determined according to the weight of the final fusion data, and the health index model is: Among them, H weight is the health index of the transmission and transformation line; w i is the weight of the i-th final fusion data, x i is the value of the i-th final fused data, and n is the number of final fused data; Determine a fuzzy comprehensive evaluation model according to the weight vector and fuzzy membership matrix of the final fusion data; Determine the health index of the current power transmission and transformation line according to the health index model; Determine the health level vector of the current power transmission and transformation line according to the fuzzy comprehensive evaluation model; A comprehensive health index fusion model is determined according to the health index, health level vector and life prediction value, and the comprehensive health index fusion model is: H final =α1·H weight +α2·S+α3·L dnn ; Among them, H final is the comprehensive health index, H weight is the health index of the transmission and transformation line, S is the health level vector, L dnn is the life prediction value output by the deep learning model, α1 is the weight coefficient of the health index model, α2 is the weight coefficient of the fuzzy comprehensive evaluation model, and α3 is the weight coefficient of the deep learning model; The comprehensive health index of the current power transmission and transformation line is determined according to the comprehensive health index fusion model.

9. A method for displaying the health status of a power transmission and transformation line according to claim 1, characterized in that: Determining the comprehensive risk level according to the comprehensive health index and the failure prediction probability specifically includes: A risk assessment model is determined based on the comprehensive health index and the failure prediction probability, and the risk assessment model is: R final =β1·H final +β2·P failure ; Among them, R final is the comprehensive risk level, H final is the comprehensive health index, P failure is the failure prediction probability, β1 and β2 are the weight coefficients in risk assessment; The comprehensive risk level of the current power transmission and transformation line is determined according to the risk assessment model.

10. A method for displaying the health status of a power transmission and transformation line according to claim 1, characterized in that: The determining of the remaining life prediction value according to the historical operation data, the comprehensive health index and the environmental data specifically includes: The remaining life prediction model is determined based on the historical operation data, the comprehensive health index and the environmental data. The remaining life prediction model is: L pred =γ1·L historical +γ2·H final +γ3·E; Among them, L pred is the predicted remaining life, L historical is the historical life expectancy forecast, H final is the current comprehensive health index, and E is the environmental data; The remaining life prediction value of the current transmission and transformation line is determined based on the remaining life prediction model.

11. A method for displaying the health status of a power transmission and transformation line in a graphical manner according to claim 1, characterized in that: After displaying the comprehensive health index, comprehensive risk level and remaining life expectancy in a graphical form, it also specifically includes: Using the comprehensive health index, comprehensive risk level and remaining life expectancy prediction value as health assessment data, determining whether the health status assessment data is greater than or equal to a preset risk threshold; If it is determined that the health status assessment data is greater than or equal to the preset risk threshold, the transmission and transformation line is marked as a high-risk line; If it is determined that the health status assessment data is less than the preset risk threshold, the transmission and transformation line is marked as a non-high-risk line.

12. A graphical display system for evaluating the health status of power transmission and transformation lines, characterized in that: The system comprises: The final fusion data acquisition module is used to collect multi-dimensional data of the power transmission and transformation lines, integrate the multi-dimensional data, and obtain the final fusion data; A life prediction value and failure prediction probability determination module, used to determine the life prediction value and failure prediction probability according to the historical failure data, historical operation data and environmental data in the final fusion data; A comprehensive health index determination module, used to determine the comprehensive health index according to the final fusion data and the life expectancy prediction value; A comprehensive risk level determination module, used to determine the comprehensive risk level according to the comprehensive health index and the failure prediction probability; A remaining life prediction value determination module, used to determine the remaining life prediction value based on the historical operation data, the comprehensive health index and the environmental data; The graphical display module is used to display the comprehensive health index, comprehensive risk level and remaining life prediction value in a graphical form.

13. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 11.

Images