Power distribution network cable joint aging prediction method and system

Abstract

The invention relates to the technical field of cable joint aging prediction, and particularly provides a power distribution network cable joint aging prediction method and system, and the method comprises the steps: obtaining the multi-mode operation data, joint type information and operation condition information of a to-be-predicted cable joint; performing aging feature extraction on operation data of different modes in the multi-mode operation data based on a preset aging feature extraction rule to obtain joint aging features corresponding to the different modes, and then performing feature fusion on all the joint aging features to obtain fused aging features; determining target parameters of an aging degree prediction algorithm according to the joint type information and the operation condition information; performing aging degree prediction according to the fused aging features by using an aging degree prediction algorithm to obtain an aging prediction result; according to the method, the aging degree prediction algorithm can have dynamic adaptability to real-time operation conditions and joint types.

Description

Technical Field

[0001] The present application relates to the technical field of cable joint aging prediction, and in particular to a method and system for predicting aging of cable joints in a distribution network. Background Art

[0002] Cable connectors are critical components of power networks, and their reliability directly impacts grid security and power supply stability. Over long-term operation, the internal insulation material of cable connectors gradually degrades, resulting in reduced partial discharge inception voltage, increased dielectric loss, and increased contact resistance due to oxidation of the metal contact surface. These performance degradations can cause partial discharge or overheating, ultimately leading to insulation breakdown or connection failure, potentially causing line failures and widespread power outages.

[0003] In order to effectively manage cable joints and avoid failure losses, existing technologies need to accurately predict the aging of cable joints. Existing cable joint aging prediction methods use a parameter threshold-based judgment method to predict the aging of cable joints. That is, the existing cable joint aging prediction method first collects the operating data of the cable joint, and then predicts the aging of the cable joint by analyzing whether the operating data exceeds a preset threshold or analyzing which preset range the operating data is in.

[0004] However, in actual applications, there are differences in the materials and manufacturing processes of different types of cable connectors, that is, the aging mechanisms of different types of cable plugs and their sensitivity to operating conditions and environmental stresses are different, and the operating conditions of cable connectors are also constantly changing (for example, seasonal temperature and humidity changes, load growth or grid topology adjustments). These dynamic changes affect the real-time aging process of cable connectors, that is, the aging of cable connectors is a nonlinear process affected by multiple factors. Since the existing cable connector aging prediction method uses a parameter threshold judgment-based method to predict the aging of cable connectors, that is, the existing cable connector aging prediction method lacks dynamic adaptability to real-time operating conditions and connector types, the existing technology has the problem that the predicted aging condition cannot accurately reflect the actual aging condition of the cable connector due to the lack of dynamic adaptability of the cable connector aging prediction method to real-time operating conditions and connector types, thereby resulting in low accuracy and reliability of cable connector aging prediction.

[0005] There is no effective technical solution to the above problems. It should be noted that the above information disclosed in this section is only used to understand the background of the present invention, and therefore may contain information that does not constitute prior art. Summary of the Invention

[0006] The purpose of this application is to provide a distribution network cable joint aging prediction method and system, which can effectively solve the problem that the predicted aging conditions cannot accurately reflect the actual aging conditions of the cable joints due to the lack of dynamic adaptability of the cable joint aging prediction method to real-time operating conditions and joint types.

[0007] In a first aspect, the present application provides a method for predicting aging of cable joints in a distribution network, which comprises the following steps: S1. Obtain multimodal operation data, joint type information, and operation condition information of the cable joint to be predicted; S2. Extracting aging features from the operating data of different modes in the multimodal operating data based on preset aging feature extraction rules to obtain joint aging features corresponding to different modes, and then fusing all joint aging features to obtain fused aging features; S3, determining the target parameters of the aging degree prediction algorithm based on the joint type information and the operating condition information; S4. Utilize an aging degree prediction algorithm to predict the aging degree according to the fused aging features to obtain an aging prediction result.

[0008] The present application provides a method for predicting the aging of distribution network cable joints, which can enable the aging degree prediction algorithm to adapt to different types of cable joints and dynamically changing operating conditions by dynamically determining the parameters of the aging degree prediction algorithm based on the joint type information and operating condition information. That is, the present application can enable the aging degree prediction algorithm to have dynamic adaptability to real-time operating conditions and joint types. Therefore, the present application can effectively solve the problem that the predicted aging condition cannot accurately reflect the actual aging condition of the cable joint due to the lack of dynamic adaptability of the cable joint aging prediction method to real-time operating conditions and joint types, thereby effectively improving the accuracy and reliability of the cable joint aging prediction.

[0009] In a second aspect, the present application also provides a distribution network cable joint aging prediction system, which includes: A data acquisition module is used to obtain multimodal operating data, joint type information and operating condition information of the cable joint to be predicted; The data fusion module is used to extract aging features from the operating data of different modes in the multimodal operating data based on preset aging feature extraction rules to obtain joint aging features corresponding to different modes, and then perform feature fusion on all joint aging features to obtain fused aging features; A prediction algorithm parameter determination module is used to determine the target parameters of the aging degree prediction algorithm based on the joint type information and the operating condition information; The aging degree prediction module is used to use the aging degree prediction algorithm to predict the aging degree according to the fusion aging characteristics to obtain an aging prediction result.

[0010] The present application provides a distribution network cable joint aging prediction system, which can enable the aging degree prediction algorithm to adapt to different types of cable joints and dynamically changing operating conditions by dynamically determining the parameters of the aging degree prediction algorithm based on the joint type information and operating condition information. That is, the present application can enable the aging degree prediction algorithm to have dynamic adaptability to real-time operating conditions and joint types. Therefore, the present application can effectively solve the problem that the predicted aging condition cannot accurately reflect the actual aging condition of the cable joint due to the lack of dynamic adaptability of the cable joint aging prediction method to real-time operating conditions and joint types, thereby effectively improving the accuracy and reliability of the cable joint aging prediction.

[0011] From the above, it can be seen that the aging prediction method and system for distribution network cable joints provided by the present application can enable the aging degree prediction algorithm to adapt to different types of cable joints and dynamically changing operating conditions by dynamically determining the parameters of the aging degree prediction algorithm based on the joint type information and operating condition information. That is, the present application can enable the aging degree prediction algorithm to have dynamic adaptability to real-time operating conditions and joint types. Therefore, the present application can effectively solve the problem that the predicted aging condition cannot accurately reflect the actual aging condition of the cable joint due to the lack of dynamic adaptability of the cable joint aging prediction method to real-time operating conditions and joint types, thereby effectively improving the accuracy and reliability of the cable joint aging prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flowchart of a method for predicting aging of cable joints in a distribution network provided in an embodiment of the present application.

[0013] Figure 2 A schematic diagram of the structure of a distribution network cable joint aging prediction system provided in an embodiment of the present application.

[0014] Reference numerals: 1. Data acquisition module; 2. Data fusion module; 3. Prediction algorithm parameter determination module; 4. Aging degree prediction module. DETAILED DESCRIPTION

[0015] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work fall within the scope of protection of the present application.

[0016] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0017] First, as Figure 1 As shown, the present application provides a method for predicting aging of cable joints in a distribution network, which includes the following steps: S1. Obtain multimodal operation data, joint type information, and operation condition information of the cable joint to be predicted; S2. Extracting aging features from the operating data of different modes in the multimodal operating data based on preset aging feature extraction rules to obtain joint aging features corresponding to different modes, and then fusing all joint aging features to obtain fused aging features; S3, determining the target parameters of the aging degree prediction algorithm based on the joint type information and the operating condition information; S4. Utilize an aging degree prediction algorithm to predict the aging degree according to the fused aging features to obtain an aging prediction result.

[0018] The cable joint to be predicted refers to the cable joint whose aging degree needs to be predicted. Multimodal operating data refers to the operating indicators of the cable joint from different sensors. The multimodal operating data of this embodiment preferably includes temperature data collected by the temperature sensor, current data collected by the current monitor, voltage data collected by the voltage recorder and vibration data collected by the accelerometer. The multimodal operating data can comprehensively reflect the operating status and potential signs of aging of the cable joint from multiple dimensions. The connector type information refers to the type of the cable joint. This embodiment can obtain the connector type information by querying the equipment archive, querying the database, reading the nameplate or identifying the label on the cable joint that records its type. Since different types of cable joints have different materials and manufacturing processes, and different types of cable plugs have different aging mechanisms and sensitivities to operating conditions and environmental stresses, this embodiment can understand the inherent characteristics, aging mechanisms and sensitivity of the cable joint to be predicted to the cable joint to be predicted by obtaining the connector type information. Operating condition information refers to the external conditions in which the cable joint is located during operation. This embodiment can obtain operating condition information by using sensors to collect data on the external conditions in which the cable joint is located, or by using a power grid monitoring system to monitor the external conditions in which the cable joint is located. The operating condition information includes at least operating load and environmental parameters. The operating condition information can also include the pollution level of the environment in which the cable joint is located. The operating condition information can reflect the dynamic external factors that affect the aging process of the cable joint. The preset aging feature extraction rules refer to a predefined set of rules for identifying and quantifying specific patterns or indicators related to cable joint aging from original multimodal operating data. The preset aging feature extraction rules can be based on signal processing methods, statistical analysis methods, or machine learning models. For example, the preset aging feature extraction rules can be based on the current data collected by the current monitor and the voltage data collected by the voltage recorder to extract the discharge amount, number of discharges, and phase distribution of partial discharge, and based on the temperature data collected by the temperature sensor to extract the rate of change, maximum value, and volatility of the temperature curve. This embodiment can use the preset aging feature extraction rules to convert original and heterogeneous multimodal data into structured features that can characterize the aging state. Feature fusion refers to the process of integrating aging features extracted from different modal data to form a unified feature representation. This embodiment can achieve feature fusion by feature splicing, weighted averaging based on weights, or fusion using a deep learning network. For example, the temperature feature vector and the partial discharge feature vector are directly spliced, or different weights are assigned according to the importance of the features for linear combination. This embodiment can achieve comprehensive utilization of aging information from different data sources to form a more comprehensive and robust fused feature vector by fusing all joint aging features.The target parameters of the aging degree prediction algorithm refer to the parameters used to configure or adjust the aging prediction model to adapt to a specific prediction task. The aging degree prediction algorithm can be an existing aging degree prediction algorithm (such as a finite element analysis algorithm and an Arrhenius equation) or an aging prediction model (such as a support vector machine, a neural network or a decision tree). It should be understood that this embodiment can first train a pre-built deep learning model based on a gradient descent algorithm using a pre-calibrated training data set (including multiple sets of training aging features and their corresponding training aging degree scores), then use a validation set (including validation aging features and their corresponding validation aging degree scores) to optimize the hyperparameters of the deep learning model, and finally use the test set to optimize the hyperparameters of the deep learning model. An aging prediction model is obtained by performing a performance test on a deep learning model using a test set (including test aging features and their corresponding test aging degree scores). The target parameter can be any one or more of the parameters that affect the output results of the aging prediction model, such as the weight, hyperparameter, and rule threshold of the aging prediction model. Since this embodiment determines the target parameters of the aging degree prediction algorithm based on the joint type information and the operating condition information, that is, this embodiment is equivalent to personalizing the aging degree prediction algorithm according to the joint type and the operating condition, this embodiment can enable the aging degree prediction algorithm to have dynamic adaptability to real-time operating conditions and joint types, thereby effectively improving the adaptability and pertinence of the aging degree prediction algorithm.

[0019] The core innovation of this application is that by dynamically determining the parameters of the aging degree prediction algorithm based on the connector type information and operating condition information, the aging degree prediction algorithm can adapt to different types of cable connectors and dynamically changing operating conditions. That is, this application can enable the aging degree prediction algorithm to have dynamic adaptability to real-time operating conditions and connector types. Therefore, this application can effectively solve the problem that the predicted aging condition cannot accurately reflect the actual aging condition of the cable connector due to the lack of dynamic adaptability of the cable connector aging prediction method to real-time operating conditions and connector types, thereby effectively improving the accuracy and reliability of the cable connector aging prediction.

[0020] Specifically, this method first acquires multimodal operating data, joint type information, and operating condition information for the cable joint to be predicted. This information is the basis for accurate prediction. Then, based on pre-defined aging feature extraction rules, feature extraction is performed on the data from different modes within the acquired multimodal operating data to obtain joint aging features corresponding to each mode. Because these joint aging features are abstracted and refined from the original multimodal operating data, they better reflect the aging state than the original multimodal operating data. Next, all extracted joint aging features are fused to form a comprehensive fused aging feature that incorporates aging information from multiple data sources. Subsequently, the key parameters (target parameters) of the aging degree prediction algorithm used for subsequent predictions are dynamically determined based on the acquired joint type information and operating condition information. This allows the aging degree prediction algorithm to dynamically adjust according to the specific joint characteristics and operating conditions. Finally, the fused aging features are used as input to an aging assessment algorithm that determines the target parameters. This allows the aging degree prediction algorithm to predict the aging degree based on the fused aging features and output the final aging prediction result. The entire process forms a closed loop, from multi-source data input to the adjustment of the dynamic aging degree prediction algorithm to the final prediction output, ensuring that the prediction results can more accurately reflect the actual aging status of the cable connector.

[0021] As a preferred embodiment, the solution of this application is implemented as follows: First, sensors installed near the cable joint, a remote monitoring system, and equipment records are used to obtain multimodal operating data (cable joint temperature, partial discharge signals, and dielectric loss data), operating condition information (operating load and environmental parameters (such as ambient temperature and humidity)), and joint type information. Next, signal processing techniques (preset aging feature extraction rules) are used to extract temperature change rate and maximum temperature features from the temperature data, discharge amount and number of discharges features from the partial discharge signal, and dielectric loss tangent value features from the dielectric loss data. These extracted temperature, partial discharge, and dielectric loss features are then concatenated to form a fused feature vector. Subsequently, based on the acquired joint model information, current load, ambient temperature and humidity, a pre-established mapping table is queried or a rule engine is used to determine parameters such as the learning rate and regularization coefficient of the neural network model used for prediction (equivalent to determining the target parameters of the aging degree prediction algorithm). Finally, the fused feature vector is input into the neural network model with the determined parameters, so that the model outputs a numerical value or grade representing the aging degree of the cable joint (aging prediction result).

[0022] The present application provides a method for predicting the aging of distribution network cable joints, which can enable the aging degree prediction algorithm to adapt to different types of cable joints and dynamically changing operating conditions by dynamically determining the parameters of the aging degree prediction algorithm based on the joint type information and operating condition information. That is, the present application can enable the aging degree prediction algorithm to have dynamic adaptability to real-time operating conditions and joint types. Therefore, the present application can effectively solve the problem that the predicted aging condition cannot accurately reflect the actual aging condition of the cable joint due to the lack of dynamic adaptability of the cable joint aging prediction method to real-time operating conditions and joint types, thereby effectively improving the accuracy and reliability of the cable joint aging prediction.

[0023] In some preferred embodiments, step S3 includes: S31. Querying a pre-built mapping relationship table of joint type, operating condition, and aging degree prediction algorithm parameters based on the joint type information and operating condition information to obtain preliminary parameters of the aging degree prediction algorithm; S32. Obtain the cumulative maintenance times and historical maintenance content set of the cable joint to be predicted; S33. Obtain a first prediction algorithm parameter adjustment strategy based on the cumulative maintenance times and the historical maintenance content set; S34. Adjust the preliminary parameters according to the first prediction algorithm parameter adjustment strategy to determine the target parameters of the aging degree prediction algorithm.

[0024] The mapping table for connector types, operating conditions, and aging prediction algorithm parameters refers to a data structure that stores the correspondence between different connector types, different operating conditions, and the preliminary parameters of the aging prediction algorithm. The preliminary parameters of the aging prediction algorithm refer to the initial values ​​of the aging prediction algorithm parameters obtained by querying the mapping table based on the connector type and operating condition. The cumulative maintenance count records the total number of maintenance operations performed on the cable connector to be predicted since it was put into operation. The historical maintenance content set records the details of each maintenance operation (e.g., maintenance date, maintenance type, problems discovered, measures taken, etc.) performed on the cable connector to be predicted since it was put into operation. The first prediction algorithm parameter adjustment strategy refers to a rule or method determined based on the cumulative maintenance count and historical maintenance content set of the cable connector to guide how to modify the preliminary parameters to make them more consistent with the actual situation of the connector. For example, if the historical maintenance content set indicates that the connector has been maintained multiple times due to overheating, the first prediction algorithm parameter adjustment strategy indicates increasing the weight or acceleration factor of temperature-related aging parameters. This embodiment can obtain a first prediction algorithm parameter adjustment strategy by querying a pre-constructed mapping relationship table of maintenance times, maintenance content combinations, and prediction algorithm parameter adjustment strategies based on the cumulative maintenance times and historical maintenance content sets. This embodiment can also obtain a first prediction algorithm parameter adjustment strategy by inputting the cumulative maintenance times and historical maintenance content sets into a pre-trained algorithm parameter adjustment strategy formulation model based on maintenance records. Because differences in maintenance conditions can affect the actual aging state and future aging trends of cable joints under the same other conditions, this embodiment can integrate maintenance history information into the parameter determination process to prevent the parameters of the aging prediction algorithm from being inaccurate and unreliable due to the lack of sufficient consideration of the impact of historical maintenance conditions on the aging process and the selection of prediction algorithm parameters. Therefore, this embodiment can effectively improve the accuracy and reliability of the parameter determination of the aging prediction algorithm, so that the parameters of the aging prediction algorithm can more finely reflect the individual characteristics and actual aging process of the joint to be predicted, thereby further improving the accuracy and reliability of the cable joint aging prediction.

[0025] In some preferred embodiments, step S34 includes: S341. Acquire quality inspection data and installation process information of the cable joint to be predicted; S342. Obtain a second prediction algorithm parameter adjustment strategy based on quality inspection data and installation process information; S343 : Adjust the preliminary parameters according to the first prediction algorithm parameter adjustment strategy and the second prediction algorithm parameter adjustment strategy to determine the target parameters of the aging degree prediction algorithm.

[0026] Quality inspection data refers to data reflecting the inherent performance and quality of the cable joint to be predicted during manufacture or factory delivery. This embodiment can obtain the quality inspection data for the cable joint to be predicted based on factory test reports, material composition analysis reports, insulation withstand voltage test results, and partial discharge test results. Installation process information refers to data recording relevant details and specifications of the cable joint during on-site installation. This embodiment can obtain the installation process information for the cable joint to be predicted by integrating installation records, on-site photos, installer qualifications, environmental condition records, and inspection results of key operations (such as stripping dimensions, crimping force, and sealing treatment). The second prediction algorithm parameter adjustment strategy refers to a rule or method determined based on the quality inspection data and installation process information to guide how to modify the preliminary parameters of the aging degree prediction algorithm. For example, if the quality inspection data indicates that the insulation resistance is below a certain threshold or the partial discharge inception voltage is low, the second prediction algorithm parameter adjustment strategy is to increase the parameters related to the insulation resistance or discharge voltage in the aging rate by a specific ratio. For another example, if the installation process information indicates that the installer qualifications are unqualified or the sealing inspection results are unsatisfactory, the second prediction algorithm parameter adjustment strategy is to increase the parameters related to moisture or partial discharge by a specific ratio. This embodiment can obtain the second prediction algorithm parameter adjustment strategy by querying a pre-built mapping relationship table of quality inspection data, installation process and prediction algorithm parameter adjustment strategy based on quality inspection data and installation process information. This embodiment can also obtain the second prediction algorithm parameter adjustment strategy by inputting quality inspection data and installation process information into a pre-trained algorithm parameter adjustment strategy formulation model based on quality inspection data and installation process. Since the initial quality and installation process of the cable joint are also key factors affecting its long-term performance and aging rate, this embodiment can adjust the parameters of the aging degree prediction algorithm based on the initial quality and installation process of the cable joint by first obtaining the second prediction algorithm parameter adjustment strategy based on the quality inspection data and installation process information, and then adjusting the preliminary parameters based on the second prediction algorithm parameter adjustment strategy. Therefore, this embodiment can make the aging degree prediction algorithm better adapt to cable joints with different initial qualities and installation conditions, thereby further improving the accuracy and reliability of cable joint aging prediction.

[0027] In some preferred embodiments, step S343 includes: A1. Obtain the historical operating conditions of the cable joint to be predicted; A2. Obtain the third prediction algorithm adjustment strategy based on historical operating conditions; A3. Adjust the preliminary parameters according to the first prediction algorithm parameter adjustment strategy, the second prediction algorithm parameter adjustment strategy, and the third prediction algorithm parameter adjustment strategy to determine the target parameters of the aging degree prediction algorithm.

[0028] Historical operating conditions refer to the records of operating conditions that the cable joint has experienced in the past. This embodiment can obtain the historical operating conditions of the cable joint to be predicted by obtaining data sets such as historical load curves, ambient temperature records, humidity records or voltage fluctuation records. The historical operating conditions can reflect the actual stress accumulation that the cable joint to be predicted has endured in different historical operating stages. The third prediction algorithm adjustment strategy refers to the rules or functions derived from the analysis of historical operating conditions for guiding how to adjust the preliminary parameters of the aging degree prediction algorithm. For example, when the accumulated stress is high, the third prediction algorithm adjustment strategy is to indicate an increase in the weight of parameters related to thermal aging. This embodiment can obtain the third prediction algorithm parameter adjustment strategy by querying a pre-constructed mapping relationship table of historical operating conditions and prediction algorithm parameter adjustment strategies based on historical operating conditions. This embodiment can also obtain the third prediction algorithm parameter adjustment strategy by inputting historical operating conditions into a pre-trained algorithm parameter adjustment strategy formulation model based on historical operating conditions. Since this embodiment first obtains the third prediction algorithm adjustment strategy based on the historical operating conditions, and then adjusts the preliminary parameters based on the third prediction algorithm parameter adjustment strategy, this embodiment can effectively avoid the situation where the aging degree prediction algorithm cannot adapt to the dynamically changing cable joint stress accumulation due to the failure to consider the actual stress accumulation of the cable joint to be predicted in different historical operating stages when determining the target parameters of the aging degree prediction algorithm, thereby further improving the accuracy and reliability of the aging degree prediction algorithm parameter determination, and further improving the accuracy and reliability of the cable joint aging prediction.

[0029] In some preferred embodiments, step S2 includes: S21. Obtaining the cumulative operating time and historical operating data of the cable joint to be predicted; S22. Obtaining aging stage information of the cable joint to be predicted based on the accumulated operating time and historical operating data analysis; S23. Querying a pre-built mapping relationship table between aging stages and aging feature extraction rules according to the aging stage information to obtain preset aging feature extraction rules; S24, extracting aging features from the operation data of different modes in the multimodal operation data based on a preset aging feature extraction rule to obtain joint aging features corresponding to the different modes; S25. Perform feature fusion on all joint aging features to obtain a fused aging feature.

[0030] Cumulative operating time refers to the total operating time of the cable joint to be predicted from its commissioning to the current moment. This cumulative operating time can reflect the total accumulated operating time experienced by the cable joint to be predicted. Historical operating data refers to a collection of various operating status parameters (such as temperature data, current data, and voltage data) collected over time for the cable joint to be predicted. This historical operating data contains operating status information of the cable joint to be predicted during different time periods. The cable joint to be predicted can be stored in the form of time series data, statistical summary data, etc. Aging stage information refers to the aging stage of the cable joint to be predicted, determined based on the cumulative operating time and historical operating data. This aging stage information can be represented by a discrete stage identifier (e.g., early, mid-stage, late-stage) or a continuous aging degree indicator. In this embodiment, aging stage information can be obtained by querying a pre-built mapping table of operating time, historical operating data, and aging stage based on the cumulative operating time and historical operating data. In this embodiment, aging stage information can also be obtained by inputting the cumulative operating time and historical operating data into a pre-trained aging stage assessment model. The mapping relationship table between aging stages and aging feature extraction rules refers to a pre-established data structure used to associate different aging stages with the feature extraction rules applicable to those stages. The preset aging feature extraction rules refer to a specific set of rules obtained from the mapping relationship table based on the current aging stage information of the cable connector to guide the feature extraction process. The preset aging feature extraction rules may include specific algorithms, parameter settings, or feature selection criteria for different modal data. For example, for the early aging stage, the preset aging feature extraction rules focus on extracting features such as partial discharge inception voltage and dielectric loss; for the late aging stage, the preset aging feature extraction rules focus on extracting features such as temperature change rate and contact resistance. The aging mechanism and key characteristics of cable joints at different aging stages may be different. The use of fixed aging feature extraction rules may not accurately capture the characteristics of the current joint that best reflect its aging degree at the current aging stage. Since this embodiment can first obtain the aging stage information of the cable joint to be predicted based on the cumulative operating time and historical operating data analysis, and then determine the preset aging feature extraction rules based on the aging stage information to achieve dynamic adjustment of the feature extraction rules according to the aging stage, this embodiment can accurately capture the characteristics of the current joint that best reflect its aging degree at the current aging stage based on the aging feature extraction rules, thereby effectively improving the accuracy and reliability of aging feature extraction, and further improving the accuracy and reliability of cable joint aging prediction.

[0031] In some preferred embodiments, step S22 includes: S221, querying a pre-built mapping relationship table between aging stages and aging feature extraction rules according to the aging stage information to obtain preliminary aging feature extraction rules; S222: querying a pre-built mapping relationship table between the joint type and the feature extraction rule adjustment strategy according to the joint type information to obtain the aging feature extraction rule adjustment strategy; S223 : Adjust the preliminary aging feature extraction rule according to the aging feature extraction rule adjustment strategy to obtain a preset aging feature extraction rule.

[0032] The mapping relationship table of connector types and feature extraction rule adjustment strategies refers to a data structure that stores feature extraction rule adjustment strategies corresponding to different connector types. The aging feature extraction rule adjustment strategy refers to instructions or parameters obtained from the mapping relationship table based on connector type information for modifying or improving preliminary aging feature extraction rules. The aging feature extraction rule adjustment strategy may include adding features of a specific type, adjusting the weights of certain features, or modifying feature calculation methods. For example, when the connector type information is heat shrinkable (the cable connector to be predicted is more sensitive to temperature changes), the aging feature extraction rule adjustment strategy is to increase the weights of temperature-related features and increase the extraction of temperature gradient features. This embodiment can adjust the aging feature extraction rules based on the connector type of the cable connector to be predicted so that the extracted structural aging features more accurately reflect the actual aging conditions of a specific type of cable connector at a specific aging stage, thereby further improving the accuracy and reliability of aging feature extraction, and further improving the accuracy and reliability of cable connector aging prediction.

[0033] In some preferred embodiments, step S25 includes: S251. Performing feature quality assessment on each joint aging feature to obtain a feature quality score corresponding to each joint aging feature; S252. Determine the fusion weight corresponding to each joint aging feature according to all feature quality scores; S253. Perform feature fusion according to all joint aging features and their corresponding fusion weights to obtain a fused aging feature.

[0034] Feature quality assessment refers to the process of measuring the reliability, information content, or correlation with the degree of aging of extracted joint aging features. This embodiment can implement feature quality assessment for each joint aging feature using statistical methods (e.g., calculating feature variance or signal-to-noise ratio), expert knowledge-based rules, or feature quality assessment learning models (e.g., assessing the correlation between features and known aging indicators). A feature quality score is a quantified numerical representation of the quality assessment results for each joint aging feature, which can reflect the reliability of the corresponding joint aging feature. A fusion weight is a coefficient assigned to each joint aging feature during the feature fusion process. This fusion weight determines the contribution of the corresponding joint aging feature to the final fusion result. Specifically, joint aging features with higher quality scores have corresponding fusion weights. This embodiment can determine the fusion weights for each joint aging feature by querying a pre-established combination of feature quality scores and fusion weights based on all feature quality scores. This embodiment can also determine the fusion weights for each joint aging feature by normalizing all feature quality scores. Since this embodiment can distinguish the quality and importance of different joint aging features, and this embodiment can highlight the role of high-quality features and suppress the negative impact of low-quality features by weighted fusion of all joint aging features based on all fusion weights, this embodiment can obtain more effective and reliable fused aging features, thereby effectively improving the accuracy and reliability of the fused aging features, and further improving the accuracy and reliability of cable joint aging prediction.

[0035] In some preferred embodiments, step S1 includes: S11, obtaining multimodal operation data, joint type information, and operation condition information of the cable joint to be predicted; S12. Preprocess the multimodal operation data, including data cleaning, data synchronization and format conversion.

[0036] Preprocessing refers to the preparation process of the original multimodal operation data before data analysis, which includes data cleaning, data synchronization and format conversion. Data cleaning refers to the identification and processing of errors, noise, outliers or missing values ​​in the data, which can be achieved by deletion, correction, filling and other methods. Data synchronization refers to the alignment of data from different sources or different acquisition frequencies in the time dimension, which can be achieved by timestamp alignment, resampling, interpolation and other methods. Format conversion refers to the uniform conversion of data in different formats into one or several standard formats, which can be achieved by data format parsing, data structure conversion and other methods. This embodiment can improve the data quality and availability of multimodal operation data by preprocessing the multimodal operation data, laying the foundation for subsequent feature extraction and aging prediction based on multimodal data, thereby improving the accuracy and reliability of the entire aging prediction method.

[0037] In some preferred embodiments, the operating condition information includes operating load and environmental parameters. Operating load refers to electrical parameters such as active power and voltage, which reflect the current electrical stress level and operating intensity of the cable joint to be predicted. Environmental parameters refer to the external environmental conditions of the cable joint, such as ambient temperature and humidity, which can reflect the current environmental stress level of the cable joint to be predicted. In this embodiment, devices such as temperature sensors and humidity sensors can be used to measure environmental parameters.

[0038] From the above, it can be seen that the aging prediction method for distribution network cable joints provided by the present application can enable the aging degree prediction algorithm to adapt to different types of cable joints and dynamically changing operating conditions by dynamically determining the parameters of the aging degree prediction algorithm based on the joint type information and operating condition information. That is, the present application can enable the aging degree prediction algorithm to have dynamic adaptability to real-time operating conditions and joint types. Therefore, the present application can effectively solve the problem that the predicted aging condition cannot accurately reflect the actual aging condition of the cable joint due to the lack of dynamic adaptability of the cable joint aging prediction method to real-time operating conditions and joint types, thereby effectively improving the accuracy and reliability of the cable joint aging prediction.

[0039] Second, as Figure 2 As shown, the present application also provides a distribution network cable joint aging prediction system, which includes: Data acquisition module 1, for obtaining the multi-modal operation data, joint type information and operating condition information of the cable joint to be predicted; Data fusion module 2 is used to extract aging features from the operating data of different modes in the multimodal operating data based on preset aging feature extraction rules to obtain joint aging features corresponding to different modes, and then perform feature fusion on all joint aging features to obtain fused aging features; Prediction algorithm parameter determination module 3, for determining the target parameters of the aging degree prediction algorithm based on the joint type information and operating condition information; The aging degree prediction module 4 is used to use the aging degree prediction algorithm to predict the aging degree according to the fused aging features to obtain an aging prediction result.

[0040] A distribution network cable joint aging prediction system provided in the present application includes a data acquisition module 1, a data fusion module 2, a prediction algorithm parameter determination module 3 and an aging degree prediction module 4. The distribution network cable joint aging prediction system provided in this embodiment is used to execute the steps in the distribution network cable joint aging prediction method provided in the first aspect above. The principle of the distribution network cable joint aging prediction system provided in this embodiment is the same as the principle of the distribution network cable joint aging prediction method provided in the first aspect above, and will not be discussed in detail here.

[0041] From the above, it can be seen that the aging prediction method and system for distribution network cable joints provided by the present application can enable the aging degree prediction algorithm to adapt to different types of cable joints and dynamically changing operating conditions by dynamically determining the parameters of the aging degree prediction algorithm based on the joint type information and operating condition information. That is, the present application can enable the aging degree prediction algorithm to have dynamic adaptability to real-time operating conditions and joint types. Therefore, the present application can effectively solve the problem that the predicted aging condition cannot accurately reflect the actual aging condition of the cable joint due to the lack of dynamic adaptability of the cable joint aging prediction method to real-time operating conditions and joint types, thereby effectively improving the accuracy and reliability of the cable joint aging prediction.

[0042] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the above-mentioned units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another robot, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0043] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0044] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any actual relationship or order between these entities or operations.

[0045] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for predicting aging of cable joints in a distribution network, characterized in that: The distribution network cable joint aging prediction method comprises the following steps: S1. Obtain multimodal operation data, joint type information, and operation condition information of the cable joint to be predicted; S2. Extracting aging features from the operation data of different modes in the multimodal operation data based on a preset aging feature extraction rule to obtain joint aging features corresponding to the different modes, and then fusing all the joint aging features to obtain a fused aging feature. S3, according to the joint type information and the operating condition information to determine the target parameters of the aging degree prediction algorithm; S4. Utilizing the aging degree prediction algorithm to perform aging degree prediction according to the fused aging features to obtain an aging prediction result.

2. The method for predicting aging of cable joints in a distribution network according to claim 1, characterized in that: Step S3 includes: S31, querying a pre-built mapping relationship table of joint type, operating condition, and aging degree prediction algorithm parameters according to the joint type information and the operating condition information to obtain preliminary parameters of the aging degree prediction algorithm; S32. Obtaining the cumulative maintenance times and historical maintenance content set of the cable joint to be predicted; S33, obtaining a first prediction algorithm parameter adjustment strategy according to the accumulated maintenance times and the historical maintenance content set; S34. Adjust the preliminary parameters according to the first prediction algorithm parameter adjustment strategy to determine target parameters of the aging degree prediction algorithm.

3. The method for predicting aging of cable joints in distribution network according to claim 2, characterized in that: Step S34 includes: S341, obtaining quality inspection data and installation process information of the cable joint to be predicted; S342. Obtain a second prediction algorithm parameter adjustment strategy based on the quality inspection data and the installation process information; S343: Adjust the preliminary parameters according to the first prediction algorithm parameter adjustment strategy and the second prediction algorithm parameter adjustment strategy to determine target parameters of the aging degree prediction algorithm.

4. The method for predicting aging of cable joints in a distribution network according to claim 3, characterized in that: Step S343 includes: A1. Obtaining the historical operating conditions of the cable joint to be predicted; A2. Obtaining a third prediction algorithm adjustment strategy based on the historical operating conditions; A3. Adjust the preliminary parameters according to the first prediction algorithm parameter adjustment strategy, the second prediction algorithm parameter adjustment strategy, and the third prediction algorithm parameter adjustment strategy to determine the target parameters of the aging degree prediction algorithm.

5. The method for predicting aging of cable joints in a distribution network according to claim 1, characterized in that: Step S2 includes: S21, obtaining the cumulative operating time and historical operating data of the cable joint to be predicted; S22. Analyzing and obtaining aging stage information of the cable joint to be predicted based on the accumulated operating time and historical operating data; S23. Querying a pre-built mapping relationship table between aging stages and aging feature extraction rules according to the aging stage information to obtain preset aging feature extraction rules; S24, performing aging feature extraction on the operation data of different modes in the multimodal operation data based on the preset aging feature extraction rule to obtain joint aging features corresponding to different modes; S25. Perform feature fusion on all the joint aging features to obtain a fused aging feature.

6. The method for predicting aging of cable joints in a distribution network according to claim 5, characterized in that: Step S22 includes: S221, querying a pre-built mapping relationship table between aging stages and aging feature extraction rules according to the aging stage information to obtain preliminary aging feature extraction rules; S222: querying a pre-built mapping relationship table between connector types and feature extraction rule adjustment strategies based on the connector type information to obtain an aging feature extraction rule adjustment strategy; S223 : Adjust the preliminary aging feature extraction rule according to the aging feature extraction rule adjustment strategy to obtain a preset aging feature extraction rule.

7. The method for predicting aging of cable joints in a distribution network according to claim 5, characterized in that: Step S25 includes: S251, performing feature quality assessment on each of the joint aging features to obtain a feature quality score corresponding to each of the joint aging features; S252, determining a fusion weight corresponding to each of the joint aging features according to all the feature quality scores; S253: Perform feature fusion according to all the joint aging features and their corresponding fusion weights to obtain a fused aging feature.

8. The method for predicting aging of cable joints in a distribution network according to claim 1, characterized in that: Step S1 includes: S11, obtaining multimodal operation data, joint type information, and operation condition information of the cable joint to be predicted; S12. Preprocess the multimodal operation data, where the preprocessing includes data cleaning, data synchronization, and format conversion.

9. The method for predicting aging of cable joints in a distribution network according to claim 1, characterized in that: The operating condition information includes operating load and environmental parameters.

10. A distribution network cable joint aging prediction system, characterized in that: The distribution network cable joint aging prediction system includes: A data acquisition module is used to obtain multimodal operating data, joint type information and operating condition information of the cable joint to be predicted; a data fusion module, configured to extract aging features from the operation data of different modes in the multimodal operation data based on preset aging feature extraction rules to obtain joint aging features corresponding to different modes, and then perform feature fusion on all the joint aging features to obtain a fused aging feature; A prediction algorithm parameter determination module for determining target parameters of an aging degree prediction algorithm based on the joint type information and the operating condition information; The aging degree prediction module is used to use the aging degree prediction algorithm to perform aging degree prediction according to the fused aging features to obtain an aging prediction result.

Images