Cable suspension fluctuation detection method and system

Abstract

The invention provides a cable suspension fluctuation detection method and system, and is suitable for the technical field of cable detection, and the method comprises the steps: according to current cable detection information, historical cable detection information, cable detection environment information, a cable detection time sequence segmentation window and a plurality of cable detection information feature extraction matrixes, obtaining a plurality of cable detection information feature extraction matrixes; multiple pieces of cable detection feature information are obtained; according to the multiple pieces of cable detection feature information and the multiple pieces of initial cable detection feature analysis parameter information, multiple pieces of target cable detection feature analysis parameter information are obtained through calculation; and according to the multiple pieces of target cable detection feature analysis parameter information, carrying out analysis processing on the multiple pieces of cable detection feature information to obtain cable suspension fluctuation detection information. The data features of cable detection information can be deeply excavated, the dynamic change condition of the cable is accurately captured, the timeliness and accuracy of cable suspension fluctuation detection are effectively improved, and a reliable basis is provided for cable operation and maintenance decisions.

Description

Technical Field

[0001] The present application belongs to the field of cable detection technology, and in particular to a cable sag fluctuation detection method and system. Background Art

[0002] With the rapid development of science and technology, cables, as the key carrier of power transmission and communication signal transmission, are increasingly used in a wide range of scenarios. From high-voltage transmission networks to complex communication base stations, from industrial automation production lines to daily smart home systems, they all rely on the support of cables.

[0003] Among existing cable detection technologies, the most commonly used are those based on power line carrier technology, fully isolated high-voltage live-state detection, and infrared beamforming. Power line carrier technology uses the cable itself as a signal transmission medium, analyzing the characteristics of the transmitted signal to determine the cable's condition. Fully isolated high-voltage live-state detection focuses on detecting whether the cable is energized. Infrared beamforming uses changes in infrared light obstruction to detect abnormalities in the cable's surrounding environment.

[0004] However, these current detection technologies have significant shortcomings. For one thing, existing detection methods struggle to accurately identify whether a cable's copper shield has been stolen, leading to the risk of signal interference or short circuits during power transmission due to missing shielding. Furthermore, in complex and changing application environments, such as areas of strong electromagnetic interference and extreme temperatures and humidity, the accuracy and stability of existing detection technologies are significantly compromised, making it impossible to promptly and reliably detect potential cable faults, which in serious cases could impact the normal operation of the entire power or communication system. Summary of the Invention

[0005] In view of this, an embodiment of the present application provides a cable sag fluctuation detection method and system, aiming to solve the problem of insufficient accuracy and stability in detecting cable sag fluctuation conditions in complex environments in the prior art.

[0006] A first aspect of an embodiment of the present application provides a cable sag fluctuation detection method, comprising: Get current cable detection information, historical cable detection information, and cable detection environment information; Obtaining a plurality of cable detection feature information according to the current cable detection information, the historical cable detection information, the cable detection environment information, the preset cable detection time sequence segmentation window, and a plurality of preset cable detection information feature extraction matrices; Calculating a plurality of target cable detection feature parsing parameter information based on the plurality of cable detection feature information and a plurality of randomly generated initial cable detection feature parsing parameter information; According to the plurality of target cable detection feature parsing parameter information, the plurality of cable detection feature information is parsed and processed to obtain cable sag fluctuation detection information.

[0007] A second aspect of an embodiment of the present application provides a cable sag fluctuation detection system, comprising: The cable detection information acquisition module is used to obtain current cable detection information, historical cable detection information, and cable detection environment information; a cable detection feature information generation module, configured to obtain a plurality of cable detection feature information based on the current cable detection information, historical cable detection information, cable detection environment information, a preset cable detection time sequence segmentation window, and a plurality of preset cable detection information feature extraction matrices; a target cable detection feature parsing parameter information calculation module, configured to calculate a plurality of target cable detection feature parsing parameter information based on the plurality of cable detection feature information and a plurality of randomly generated initial cable detection feature parsing parameter information; The cable sag fluctuation detection information determination module is used to parse and process the plurality of cable detection feature information according to the plurality of target cable detection feature parsing parameter information to obtain the cable sag fluctuation detection information.

[0008] A third aspect of an embodiment of the present application provides a terminal device, which includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, it implements the steps of the cable sag fluctuation detection method described in the first aspect above.

[0009] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, comprising: storing a computer program, which, when executed by a processor, implements the steps of the cable sag fluctuation detection method as described in the first aspect above.

[0010] Compared with the prior art, the beneficial effects of the embodiments of the present application are as follows: the present application ensures the integrity and diversity of cable detection information by comprehensively acquiring current cable detection information, historical cable detection information and cable detection environment information, and then deeply mines the data characteristics of cable detection information, accurately captures the dynamic changes of cables, effectively improves the timeliness and accuracy of cable suspension fluctuation detection, and provides a reliable basis for cable operation and maintenance decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0012] Figure 1 This is a schematic diagram of the implementation flow of the cable sag fluctuation detection method provided in Example 1 of the present application; Figure 2 This is a schematic diagram of the implementation flow of the cable sag fluctuation detection method provided in Example 2 of the present application; Figure 3 This is a schematic diagram of the implementation flow of the cable sag fluctuation detection method provided in Example 3 of the present application; Figure 4 1 is a schematic diagram of the implementation flow of the cable sag fluctuation detection method provided in the fourth embodiment of the present application; Figure 5 This is a schematic diagram of the implementation flow of the cable sag fluctuation detection method provided in Example 5 of the present application; Figure 6 1 is a schematic diagram of the implementation flow of the cable sag fluctuation detection method provided in Example 6 of the present application; Figure 7 1 is a schematic diagram of the implementation flow of the cable sag fluctuation detection method provided in Example 7 of the present application; Figure 8 Schematic diagram of the structure of the cable sag fluctuation detection system provided in an embodiment of the present application; Figure 9 It is a schematic diagram of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0013] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0014] In order to illustrate the technical solution described in this application, specific embodiments are provided below.

[0015] Figure 1 The following is a flowchart of the cable sag fluctuation detection method according to the first embodiment of the present application, which is described in detail as follows: Step S101: Acquire current cable detection information, historical cable detection information, and cable detection environment information.

[0016] In this embodiment, current cable detection information refers to various types of detection data collected during real-time cable operation, typically reflecting the cable's current physical characteristics, electrical parameters, and operating status. Vibration sensors, tension sensors, temperature sensors, inclination sensors, and the like can be deployed on the cable to monitor physical parameters such as vibration frequency, tension changes, temperature, and inclination angle in real time. Current sensors and voltage sensors can be used to obtain electrical parameters such as current, voltage, and power. Professional equipment such as optical cable monitors and cable condition monitoring devices can be used to perform real-time detection of cable insulation performance, partial discharge, and mechanical damage. Historical cable detection information refers to cable detection data records over a period of time, including historical operating parameters, fault records, and maintenance data. This information is used to analyze the long-term operating patterns and trends of the cable. This information can be extracted from the cable operation and maintenance management system's historical database, such as past detection reports, periodic inspection data, and fault handling records. This information includes historical vibration data, tension change curves, temperature history, and electrical parameter fluctuation records. Historical detection data collected and stored by sensors and online monitoring equipment can also be retrieved from local storage devices (such as hard drives or servers) or cloud platforms. Cable detection environment information can refer to data on external environmental factors that affect the operating status of the cable, including relevant information such as the natural environment, surrounding facilities and human activities. It can be obtained by using equipment such as meteorological stations and environmental monitoring terminals to obtain natural environmental data such as temperature and humidity, wind speed and direction, rainfall, and light intensity; it can also collect environmental interference information such as surrounding electromagnetic interference and mechanical vibration interference through noise sensors, electromagnetic interference monitors, etc.

[0017] Step S102 : obtaining a plurality of cable detection feature information according to the current cable detection information, historical cable detection information, cable detection environment information, a preset cable detection time sequence segmentation window, and a plurality of preset cable detection information feature extraction matrices.

[0018] In this embodiment, the preset cable detection time series segmentation window and the multiple preset cable detection information feature extraction matrices can be manually set. The current cable detection information, historical cable detection information, and cable detection environment information can be aggregated and fused. The fused time series data is then segmented based on the preset cable detection time series segmentation window at fixed time intervals and window lengths to form multiple independent data segments. Each data segment is then calculated using the multiple preset cable detection information feature extraction matrices. Key features reflecting the cable operating status, environmental factors, and historical change trends can be extracted from the data segments through operations such as matrix multiplication and convolution, thereby obtaining multiple cable detection feature information.

[0019] Step S103: Calculate and obtain multiple target cable detection feature parsing parameter information based on the multiple cable detection feature information and multiple randomly generated initial cable detection feature parsing parameter information.

[0020] In this embodiment, multiple cable detection feature information can be used as input data, combined with multiple randomly generated initial cable detection feature analysis parameter information to construct an initial parameter optimization space, and then iterative exploration of the parameter space can be performed: on the one hand, a local search is performed near the current optimal parameter, and the cable detection feature information is analyzed by adjusting the parameter value to adapt to the data characteristics and improve the analysis effect; on the other hand, a global search is triggered with a certain probability, and by introducing random perturbations or individual difference combinations, a potential better solution is found in a wider parameter space. In each iteration, the results of the analysis are evaluated according to the preset fitness evaluation criteria, and the parameter combination that makes the analysis effect better is retained. The parameters are continuously updated. After multiple rounds of iteration, multiple target cable detection feature analysis parameter information is calculated, and efficient analysis and optimization of the cable detection feature information is achieved.

[0021] Step S104: parse and process the plurality of cable detection feature information according to the plurality of target cable detection feature parsing parameter information to obtain cable sag fluctuation detection information.

[0022] In this embodiment, multiple target cable detection feature analysis parameter information can be matched with corresponding multiple cable detection feature information respectively, and the cable detection feature information can be deeply mined and analyzed through mathematical operations such as matrix operations, weighted summation, and nonlinear transformation; the features can be weighted using the weight coefficients in the target cable detection feature analysis parameter information to highlight the role of key features, and effective information in the features can be further extracted through transformations such as activation functions, thereby integrating the processing results to form cable sag fluctuation detection information that reflects the cable sag fluctuation status, trends, and abnormal conditions, providing accurate decision-making basis for cable operation and maintenance.

[0023] The cable sag fluctuation detection method provided in the embodiment of the present application ensures the integrity and diversity of cable detection information by comprehensively acquiring current cable detection information, historical cable detection information and cable detection environment information, and then deeply mines the data characteristics of cable detection information, accurately captures the dynamic changes of cables, effectively improves the timeliness and accuracy of cable sag fluctuation detection, and provides a reliable basis for cable operation and maintenance decisions.

[0024] Figure 2 The flowchart of the cable sag fluctuation detection method provided in the second embodiment of the present application is shown. The difference between the second embodiment and the first embodiment is that the step S102 specifically includes: Step S201, according to the preset cable detection time sequence segmentation window, the current cable detection information, the historical cable detection information and the cable detection environment information are time sequence segmentation processing, and the current cable detection time sequence information, the historical cable detection time sequence information and the cable detection environment time sequence information are obtained.

[0025] In the embodiment, the preset cable detection time sequence segmentation window can be a fixed time interval set according to the cable operation characteristics and detection requirements. The current cable detection information, the historical cable detection information and the cable detection environment information can be time sequence segmented by the sliding window technology, to ensure that each segmented time sequence information segment contains a complete fluctuation characteristic period; the historical cable detection time sequence information can be matched with the historical data by time stamp, and the cable detection environment time sequence information is synchronously associated with the environmental parameters of the corresponding time period, to form three types of time sequence information with time alignment.

[0026] Step S202, according to a plurality of preset cable detection information feature extraction matrices, the current cable detection time sequence information, the historical cable detection time sequence information and the cable detection environment time sequence information are feature extraction processing, and the current cable detection time sequence feature information, the historical cable detection time sequence feature information and the cable detection environment time sequence feature information are obtained.

[0027] In the embodiment, the plurality of preset cable detection information feature extraction matrices can include a frequency domain feature extraction matrix based on Fourier transform, a time-frequency feature extraction matrix based on wavelet transform and a feature extraction matrix based on deep learning, etc.; by performing convolution operation, matrix multiplication and other operations on the current cable detection time sequence information, the historical cable detection time sequence information and the cable detection environment time sequence information with each feature extraction matrix, multi-dimensional feature information reflecting the cable vibration frequency distribution, energy change trend and environmental factor influence law is extracted, and three types of time sequence feature information are formed.

[0028] Step S203, the current cable detection time sequence feature information, the historical cable detection time sequence feature information and the cable detection environment time sequence feature information are odd-even time sequence separation processing, and the current cable detection odd time sequence feature information, the historical cable detection odd time sequence feature information, the cable detection environment odd time sequence feature information, the current cable detection even time sequence feature information, the historical cable detection even time sequence feature information and the cable detection environment even time sequence feature information are obtained.

[0029] In this embodiment, the odd-even timing separation processing refers to dividing the timing feature information according to the parity of the time index, for example, the feature information of odd time points is classified as odd timing feature information, and the feature information of even time points is classified as even timing feature information; through this separation, the high-frequency changes of cable fluctuations (usually concentrated in even timing) and the low-frequency trends (usually concentrated in odd timing) can be decoupled, which facilitates subsequent targeted processing and improves the ability to capture fluctuation patterns of different frequencies.

[0030] Step S204, based on a preset cable detection odd timing feature transformation function, the current cable detection odd timing feature information, the historical cable detection odd timing feature information, and the cable detection environment odd timing feature information are subjected to timing feature transformation processing to obtain a current cable detection odd timing feature vector, a historical cable detection odd timing feature vector, and a cable detection environment odd timing feature vector.

[0031] In this embodiment, the preset cable detection odd-numbered time series feature transformation function can be a time series feature mapping function based on the LSTM network or a feature enhancement function based on the self-attention mechanism. By performing nonlinear transformation on the current cable detection odd-numbered time series feature information, the historical cable detection odd-numbered time series feature information, and the cable detection environment odd-numbered time series feature information, the time series features are mapped to a high-dimensional feature space, and feature vectors that can reflect the long-term fluctuation trend of the cable, the historical state dependency, and the influence of slow-changing environmental factors are extracted to form three types of odd-numbered time series feature vectors.

[0032] Step S205, based on the preset cable detection even timing feature transformation function, the current cable detection even timing feature information, the historical cable detection even timing feature information and the cable detection environment even timing feature information are subjected to timing feature transformation processing to obtain the current cable detection even timing feature vector, the historical cable detection even timing feature vector and the cable detection environment even timing feature vector.

[0033] In this embodiment, the preset cable detection even-numbered timing feature transformation function can be a fast response function based on a gated recurrent unit (GRU) or a time-frequency analysis function based on a short-time Fourier transform. By performing timing feature transformation on the current cable detection even-numbered timing feature information, the historical cable detection even-numbered timing feature information, and the cable detection environment even-numbered timing feature information, the ability to capture high-frequency dynamic features such as sudden cable vibration and environmental mutation is enhanced, and they are mapped into feature vectors that can reflect the real-time fluctuation state changes of the cable, forming three types of even-numbered timing feature vectors.

[0034] Step S206 , performing feature vector fusion processing on the current cable detection odd-numbered timing feature vector, the historical cable detection odd-numbered timing feature vector, the cable detection environment odd-numbered timing feature vector, the current cable detection even-numbered timing feature vector, the historical cable detection even-numbered timing feature vector, and the cable detection environment even-numbered timing feature vector to obtain multiple cable detection feature information.

[0035] In this embodiment, the feature vector fusion processing can be to automatically assign weights according to the contribution of each type of feature vector to the cable suspension fluctuation detection, for example, assigning higher weights to the odd-numbered time-series feature vectors of the current cable detection to highlight the real-time trend, and assigning lower weights to the even-numbered time-series feature vectors of the cable detection environment to weaken environmental interference; through weighted summation, tensor splicing and other operations, the six types of feature vectors are fused into a unified feature representation to form multiple cable detection feature information that can comprehensively reflect the cable operation status.

[0036] The cable sag fluctuation detection method provided in the embodiment of the present application deeply integrates and enhances the features of cable detection information of different time granularities and different frequency characteristics through multi-stage processing such as time series segmentation, feature extraction, odd-even separation, feature transformation and fusion. It not only retains the time series dependency of the original data, but also separates high-frequency dynamic features and low-frequency trend features, effectively improving the multi-scale analysis capability of cable sag fluctuations, improving the accuracy and timeliness of cable sag fluctuation detection, and providing more reliable technical support for cable operation and maintenance in complex environments.

[0037] Figure 3 The following is a flowchart of a cable sag fluctuation detection method according to the third embodiment of the present application, which differs from the second embodiment in that: The plurality of preset cable detection information feature extraction matrices include a preset cable detection information association feature extraction matrix, a preset cable detection information feature identifier extraction matrix, and a preset cable detection information feature load extraction matrix; The step S202 specifically includes: Step S301 , obtaining current cable detection associated feature information, historical cable detection associated feature information and cable detection environment associated feature information according to the current cable detection timing information, historical cable detection timing information, cable detection environment timing information and a preset cable detection information associated feature extraction matrix.

[0038] In this embodiment, the preset cable detection information correlation feature extraction matrix, the preset cable detection information feature identifier extraction matrix, and the preset cable detection information feature load extraction matrix can all be manually set. The preset cable detection information correlation feature extraction matrix can be used to explore the potential connections between different types of detection information. By performing tensor operations on the current cable detection timing information, historical cable detection timing information, and cable detection environment timing information with the matrix, it is possible to extract correlation features such as the cable vibration frequency and the ambient wind speed, and the correlation features between historical temperature changes and current tension fluctuations, thereby obtaining the current cable detection correlation feature information, historical cable detection correlation feature information, and cable detection environment correlation feature information that reflect the coupling relationship of multiple sources of information, providing a basis for analyzing the comprehensive influencing factors of cable fluctuations.

[0039] Step S302: obtaining current cable detection feature identification information, historical cable detection feature identification information, and cable detection environment feature identification information according to the current cable detection timing information, historical cable detection timing information, cable detection environment timing information, and a preset cable detection information feature identification extraction matrix.

[0040] In this embodiment, a pre-set cable detection information feature extraction matrix, based on pattern recognition principles, features current cable detection timing information, historical cable detection timing information, and cable detection environment timing information. This matrix can identify specific waveform signatures of abnormal cable vibration, parameter anomalies during historical faults, and signatures from harsh environmental conditions. It then derives current cable detection feature signature information, historical cable detection feature signature information, and cable detection environment feature signature information, enabling precise location and labeling of key features.

[0041] Step S303, according to the current cable detection associated feature information, historical cable detection associated feature information, cable detection environment associated feature information, current cable detection feature identification information, historical cable detection feature identification information and cable detection environment feature identification information, obtain current cable detection feature coding information, historical cable detection feature coding information and cable detection environment feature coding information.

[0042] In this embodiment, the current cable detection associated feature information, historical cable detection associated feature information, and cable detection environment associated feature information are fused and encoded with the corresponding current cable detection feature identification information, historical cable detection feature identification information, and cable detection environment feature identification information. The associated features and identification information can be mapped into a unique feature code using hash coding, binary coding, or other methods to generate the current cable detection feature coding information, historical cable detection feature coding information, and cable detection environment feature coding information, facilitating the efficient storage and retrieval of cable features.

[0043] Step S304 , obtaining current cable detection characteristic load information, historical cable detection characteristic load information and cable detection environment characteristic load information according to the current cable detection timing information, historical cable detection timing information, cable detection environment timing information and a preset cable detection information characteristic load extraction matrix.

[0044] In this embodiment, a preset cable detection information feature load extraction matrix is ​​used to quantify the importance of feature information. Through matrix operations, current cable detection timing information, historical cable detection timing information, and cable detection environment timing information are weighted to calculate the contribution of each feature in reflecting the cable's fluctuation state. The resulting current cable detection feature load information, historical cable detection feature load information, and cable detection environment feature load information highlight the impact of key features on the detection results.

[0045] Step S305, according to the current cable detection feature coding information, historical cable detection feature coding information, cable detection environment feature coding information, current cable detection feature load information, historical cable detection feature load information and cable detection environment feature load information, obtain the current cable detection timing feature information, historical cable detection timing feature information and cable detection environment timing feature information.

[0046] In this embodiment, the current cable detection feature coding information, historical cable detection feature coding information, and cable detection environment feature coding information are combined with the corresponding current cable detection feature load information, historical cable detection feature load information, and cable detection environment feature load information. Through operations such as feature weighted fusion and code parsing, the feature coding and load information are restored to time-series feature information, resulting in the current cable detection time-series feature information, historical cable detection time-series feature information, and cable detection environment time-series feature information. The resulting feature information contains both the correlation relationship and key identifiers of the multi-source information.

[0047] The cable suspension fluctuation detection method provided in the embodiment of the present application deeply explores the intrinsic connection between cable detection information, accurately marks key features, quantifies the importance of features, and realizes the refined extraction and expression of cable operation status features, thereby more comprehensively and accurately capturing the complex characteristics of cable fluctuations, effectively improving the detection capability of subtle fluctuations and abnormal conditions, and providing more in-depth and reliable technical support for cable operation and maintenance decisions.

[0048] Figure 4 The following is a flowchart of a cable sag fluctuation detection method according to the fourth embodiment of the present application, which differs from the first embodiment in that: The plurality of randomly generated initial cable detection feature parsing parameter information includes randomly generated initial cable detection feature parsing weight information, randomly generated initial cable detection feature parsing bias information, randomly generated initial cable detection feature parsing dimension information, and randomly generated initial cable detection feature parsing iteration count; The step S103 specifically includes: In step S401, a plurality of preset cable detection information feature extraction matrices, randomly generated initial cable detection feature parsing weight information, randomly generated initial cable detection feature parsing bias information, randomly generated initial cable detection feature parsing dimension information, and randomly generated initial cable detection feature parsing iteration times are concatenated to generate a plurality of initial cable detection feature parsing parameter variable array information.

[0049] In this embodiment, the initial cable detection feature parsing weight information refers to a set of weight parameter matrices randomly initialized when constructing the cable detection feature parsing model. This can be used to establish a mapping relationship between the cable detection feature information and the target parsing results. The purpose is to provide a variety of initial solutions for the subsequent optimization algorithm and avoid falling into local optimality. The initial cable detection feature parsing bias information can refer to a set of bias vectors randomly initialized in the cable detection feature parsing model. The initial cable detection feature parsing dimension information can refer to randomly set dimensional parameters in the cable detection feature parsing process. This can be used to determine the dimensionality change of feature information during the conversion process, such as controlling the number of dimensions of the output features in dimensionality reduction or dimensionality increase operations. The initial cable detection feature parsing iteration count can refer to the maximum number of iterations randomly set for the cable detection feature parsing process. This is used to determine the termination condition during the cable detection feature parsing parameter optimization process. Randomly setting the number of iterations can prevent the calculation process from falling into invalid long iterations and at the same time find the optimal range of iterations through multiple experiments. The splicing process can be to perform tensor splicing according to the preset arrangement rules on the dimensional parameters of the preset cable detection information feature extraction matrix, the randomly generated numerical matrix of the initial cable detection feature analysis weight information, the vector value of the initial cable detection feature analysis bias information, the dimensional configuration parameters of the initial cable detection feature analysis dimension information, and the scalar value of the initial cable detection feature iterative analysis times, to generate multiple initial cable detection feature analysis parameter variable array information with a unified data structure, so as to ensure the coordination and consistency of each parameter in subsequent calculations.

[0050] Step S402 , calculating and obtaining a plurality of initial cable detection feature analysis parameter variable array quality index information based on the plurality of initial cable detection feature analysis parameter variable array information, cable detection feature information, a preset cable detection feature classification function, and a preset cable detection feature prediction model.

[0051] In the embodiment, the initial cable detection feature analysis parameter variable array information can be input into a preset cable detection feature classification function, combined with cable detection feature information for classification prediction, and a preset cable detection feature prediction model can be used for fluctuation trend prediction. According to evaluation indexes such as classification accuracy and prediction mean square error, a plurality of initial cable detection feature analysis parameter variable array quality index information reflecting the effectiveness of the parameter variable array information in feature analysis can be calculated, thereby providing a quantitative basis for parameter optimization.

[0052] In step S403, the initial cable detection feature analysis parameter variable array information corresponding to the maximum value of the plurality of initial cable detection feature analysis parameter variable array quality index information is taken as cable detection feature analysis parameter variable reference array information.

[0053] In the embodiment, the initial cable detection feature analysis parameter variable array information corresponding to the maximum value can be selected as a reference standard by comparing the numerical values of the plurality of initial cable detection feature analysis parameter variable array quality index information. The reference array information represents the optimal solution in the current parameter combination, thereby providing a reference for subsequent parameter optimization and ensuring that the iteration process converges to a better direction.

[0054] In step S404, a plurality of target cable detection feature analysis parameter information can be calculated according to the plurality of initial cable detection feature analysis parameter variable array information and the cable detection feature analysis parameter variable reference array information.

[0055] In the embodiment, the plurality of initial cable detection feature analysis parameter variable array information can be subjected to differential evolution operation based on the cable detection feature analysis parameter variable reference array information. New parameter combinations can be generated in the neighborhood of the reference array by introducing parameters such as mutation coefficient and crossover probability. After multiple rounds of iteration optimization, a plurality of target cable detection feature analysis parameter information capable of more accurately analyzing cable detection feature information can be calculated, thereby achieving efficient extraction and analysis of cable fluctuation characteristics.

[0056] The cable suspension fluctuation detection method provided by the embodiment of the application can significantly improve the analysis accuracy of cable fluctuation characteristic information by structuring and splicing initial cable detection feature analysis parameters and quality evaluation, and using quality index screening evolution optimization, thereby achieving accurate identification of fluctuation patterns in complex environments and providing more reliable decision basis for cable state evaluation.

[0057] Figure 5 An implementation flowchart of the cable suspension fluctuation detection method provided by the fifth embodiment of the application is shown. The difference between the fifth embodiment and the fourth embodiment described above is that step S402 specifically includes: Step S501 : Calculating and obtaining a plurality of cable sag fluctuation detection feature classification information based on the plurality of cable detection feature information and a preset cable detection feature classification function.

[0058] In this embodiment, the pre-set cable detection feature classification function is built based on the support vector machine (SVM) algorithm. This function achieves multi-classification recognition of cable conditions by calculating the kernel function similarity between cable detection feature information and a predefined fluctuation pattern library. For example, feature vectors such as vibration frequency and temperature change rate are mapped to a high-dimensional space. Hyperplane partitioning is used to classify different fluctuation types, such as "normal fluctuation," "breeze vibration," and "dancing," generating classification information that includes the fluctuation type label and confidence level.

[0059] Step S502 : Calculate and obtain a plurality of initial cable detection feature classification information and a plurality of initial cable detection feature prediction information based on the plurality of cable detection feature information and the initial cable detection feature parsing parameter variable array information.

[0060] In this embodiment, the calculation process can be divided into two parallel branches: on the one hand, the cable detection feature information is multiplied by the weight matrix in the parameter variable array, and then translated by the bias vector, and the initial classification information is output after activation by the Softmax function; on the other hand, the dimensionality information in the parameter array is used to reduce the dimension of the features, and the number of iterations parameter is combined to control the number of time series expansion steps of the LSTM network to generate initial prediction information including fluctuation trend prediction.

[0061] Step S503: Calculate and obtain multiple cable detection feature classification accuracy information based on the multiple initial cable detection feature classification information and the cable sag fluctuation detection feature classification information.

[0062] In this embodiment, the classification accuracy can be calculated using a confusion matrix evaluation method. By comparing the predicted labels in the initial classification information with the actual labels in the cable sag fluctuation detection feature classification information, the precision, recall, and F1 value for each category are calculated. For example, for the "breeze vibration" category, the precision reflects the proportion of samples predicted to belong to that category that actually belong to that category, while the recall reflects the proportion of samples that actually belong to that category that were correctly predicted. The overall classification accuracy is then calculated through weighted averaging.

[0063] Step S504: Calculate and obtain a plurality of cable detection feature prediction reference information based on the plurality of cable detection feature information and a preset cable detection feature prediction model.

[0064] In this embodiment, the preset cable detection feature prediction model can be constructed based on a gated recurrent unit (GRU) network. It inputs time series data from historical cable detection feature information and predicts future trends by learning the temporal dependencies of fluctuation patterns. The model considers the influence of environmental factors, such as wind speed, temperature, and humidity, as external input variables. It outputs predictions of vibration amplitude and frequency variation over a future time period, providing a benchmark for subsequent evaluation.

[0065] Step S505 : Calculate and obtain multiple cable detection feature prediction accuracy information based on the multiple initial cable detection feature prediction information and the cable detection feature prediction reference information.

[0066] In this embodiment, forecast accuracy is evaluated using a combination of the root mean square error (RMSE) and the mean absolute percentage error (MAPE). For each time step, the predicted value and the true value in the reference data are averaged and squared to obtain the RMSE, reflecting the absolute error of the prediction. Simultaneously, the average absolute percentage error is calculated to obtain the MAPE, reflecting the relative error. This combination of these two metrics comprehensively evaluates the accuracy of the forecast model under varying fluctuations.

[0067] Step S506 , calculating and obtaining a plurality of initial cable detection feature analysis parameter variable array quality indicator information based on the plurality of cable detection feature classification accuracy information, the cable detection feature prediction accuracy information, and the preset cable feature analysis weight information.

[0068] In this embodiment, the preset cable feature analysis weights include classification accuracy weights and prediction accuracy weights, corresponding to the classification and regression capabilities of the feature analysis, respectively. After normalizing the classification accuracy and prediction accuracy information, a weighted sum is taken based on the classification accuracy weights and prediction accuracy weights to produce a comprehensive quality index.

[0069] The cable sag fluctuation detection method provided in the embodiment of the present application decouples feature classification from prediction tasks, performs targeted optimization of analytical parameters, and realizes multi-dimensional evaluation of cable sag fluctuation characteristics, significantly improving the early warning capability of abnormal cable fluctuations in complex environments, and providing more reliable technical support for intelligent inspection and preventive maintenance of abnormal cable fluctuations.

[0070] Figure 6 The flowchart of the cable sag fluctuation detection method provided in the sixth embodiment of the present application is shown. The difference between the sixth embodiment and the fourth embodiment is that the step S404 specifically includes: Step S601: obtaining a plurality of cable detection feature parsing parameter variable array adjustment distance information according to a plurality of initial cable detection feature parsing parameter variable array information and a cable detection feature parsing parameter variable reference array information.

[0071] In this embodiment, the cable detection feature parsing parameter variable array adjustment distance information is used to measure the degree of difference between each initial parameter variable array and the reference array. Metrics such as Euclidean distance and Manhattan distance are calculated to quantify the numerical differences between elements such as the weight matrix, bias vector, and dimensional parameters. For example, the weight matrix in the initial parameter array is subtracted from the corresponding matrix in the reference array element by element, and the overall distance is calculated using the norm. This distance value reflects the degree of deviation of the parameter combination from the current optimal solution, providing guidance for subsequent optimization.

[0072] Step S602: Optimize the plurality of initial cable detection feature parsing parameter variable array information based on the plurality of cable detection feature parsing parameter variable array adjustment distance information and the preset cable detection feature parsing parameter variable array adjustment times information to generate a plurality of intermediate cable detection feature parsing parameter variable array information.

[0073] In this embodiment, the preset number of cable detection feature analysis parameter variable array adjustments can be manually set. Optimization processing, based on this preset number of cable detection feature analysis parameter variable array adjustments, employs a simulated annealing or particle swarm optimization algorithm. Guided by the adjustment distance information, each initial parameter variable array is iteratively adjusted. If the distance is large, a global search is performed using random perturbations (e.g., increasing the random offset of the weight matrix elements); if the distance is small, local fine-tuning is performed within the neighborhood of the reference array (e.g., scaling the bias vector). After each adjustment, an intermediate parameter variable array is generated, ensuring that the optimization process covers the entire parameter space while focusing on potential optimal regions.

[0074] Step S603: Count the number of times the plurality of intermediate cable detection feature parsing parameter variable array information is generated to obtain information on the number of times the intermediate cable detection feature parsing parameter variable array is generated.

[0075] In this embodiment, the generation count of the intermediate cable detection feature parsing parameter variable arrays is counted to record the update frequency of each parameter combination during the iterative optimization process. By establishing a mapping table between parameter arrays and generation counts, the depth of exploration of different parameter combinations can be tracked. For example, if a parameter array is continuously optimized and adjusted over multiple iterations, its generation count is high, reflecting the potential of this combination in the optimization direction. Conversely, an array with a low generation count may be stuck in a local optimum or deviate from the global optimal solution.

[0076] Step S604, judging whether the intermediate cable detection feature analysis parameter variable array generation frequency information is equal to the preset intermediate cable detection feature analysis parameter variable array generation frequency threshold value; if yes, entering step S605; if no, entering step S607.

[0077] In the embodiment, the matching of the generation frequency information and the preset threshold value is to balance the optimization efficiency and the result accuracy. If the generation frequency reaches the threshold value, it indicates that the algorithm has fully explored the parameter space, and the iteration can be terminated to avoid overfitting; if the threshold value is not reached, it indicates that there is still optimization space for the current parameter combination, and the quality index needs to be recalculated in step S402 to continue adjusting the parameters through multiple iterations until the termination condition is met.

[0078] Step S605, performing average value calculation on the plurality of intermediate cable detection feature analysis parameter variable array information to generate target cable detection feature analysis parameter variable array information.

[0079] In the embodiment, the average value calculation is performed on the intermediate parameter variable array, and the multiple optimization results are fused through weighted average or arithmetic average. In the weighted average, weights are assigned according to the generation frequency (the higher the generation frequency, the greater the weight), so that the final parameter array is more inclined to high-quality solutions that appear frequently; in the arithmetic average, the average value of all intermediate array elements is directly summarized to smooth the parameter fluctuation, thereby effectively suppressing random noise in the optimization process and outputting a stable and representative target parameter variable array.

[0080] Step S606, performing element extraction processing on the target cable detection feature analysis parameter variable array information to obtain a plurality of target cable detection feature analysis parameter information.

[0081] In the embodiment, the element extraction processing is performed on the target cable detection feature analysis parameter variable array information according to the preset parameter structure for splitting. For example, the first N elements in the array are extracted as a weight matrix, and the subsequent elements correspond to a bias vector, a dimension parameter and an iteration number, respectively, thereby forming a plurality of independent target cable detection feature analysis parameter information. The split parameter information can be directly applied to the cable detection feature analysis model to realize accurate analysis of the cable fluctuation state.

[0082] Step S607, taking the plurality of intermediate cable detection feature analysis parameter variable array information as a plurality of initial cable detection feature analysis parameter variable array information, and returning to step S402.

[0083] In the embodiment, the intermediate parameter variable array is returned as initial values in step S402, forming a closed-loop iterative optimization mechanism, so as to allow the algorithm to continue to adjust the parameters based on the current optimization result when the generation number threshold is not reached, gradually approaching the global optimal solution through multiple rounds of quality evaluation and parameter updating, thereby ensuring the continuity and adaptive ability of the parameter optimization process through the dynamic feedback mechanism, and avoiding the problem of suboptimal solution caused by premature termination.

[0084] The cable suspension fluctuation detection method provided by the embodiment of the application introduces parameter adjustment distance measurement, multi-round iterative optimization and dynamic termination strategy, significantly improves the stability and convergence speed of parameter optimization by quantifying differences, controlling the number of iterations and fusing the results of multiple rounds, and realizes high-precision analysis of cable fluctuation characteristics in complex environments, thereby providing more time-effective and reliable technical support for cable operation and maintenance decision-making.

[0085] Figure 7 An implementation flowchart of the cable suspension fluctuation detection method provided by the seventh embodiment of the application is shown, which is different from the fourth embodiment described above in that: The target cable detection feature analysis parameter information includes target cable detection feature analysis weight information, target cable detection feature analysis bias information, target cable detection feature analysis dimension information and target cable detection feature iterative analysis number; The step S104 specifically includes: Step S701, according to the target cable detection feature analysis weight information, weighted sum of a plurality of cable detection feature information is obtained, and cable detection feature aggregation information is obtained.

[0086] In the embodiment, the target cable detection feature analysis weight information is a set of optimized weight matrices, which is used to quantify the importance of different cable detection feature information. By performing dot product operation on each cable detection feature information and the corresponding weight matrix, and then summing by row or column, weighted aggregation of the features is realized. For example, a higher weight is assigned to the vibration frequency feature to highlight its influence on fluctuation detection, and a lower weight is assigned to the environmental temperature and humidity feature to weaken the secondary factors, thereby generating cable detection feature aggregation information containing feature importance differences.

[0087] Step S702, according to the cable detection feature aggregation information and the target cable detection feature analysis bias information, cable detection feature bias information is obtained.

[0088] In this embodiment, cable detection feature bias information is generated by performing a matrix addition operation on the aggregated cable detection feature information and the target cable detection feature parsing bias information. The introduction of the bias vector adjusts the numerical distribution of the aggregated features, making them more consistent with the input requirements of the subsequent dimensional decomposition. For example, if the aggregated feature values ​​are generally small, adding a bias vector can shift them to the sensitive range of the activation function, improving the effectiveness of feature parsing.

[0089] Step S703 : performing dimension decomposition processing on the cable detection feature offset information according to the target cable detection feature parsing dimension information to generate a plurality of cable detection feature dimension conversion information.

[0090] In this embodiment, the target cable detection feature parsing dimension information defines the dimensional parameters for feature conversion (e.g., feature dimensions after dimensionality reduction, mapping space after dimensionality increase, etc.). Dimensional decomposition processing transforms the cable detection feature bias information based on these parameters. For dimensionality reduction, principal component analysis (PCA) or linear discriminant analysis (LDA) is used to compress feature dimensions and remove redundant information. For dimensionality increase, kernel function mapping is used to map features to a higher-dimensional space, enhancing the expressiveness of nonlinear features. The resulting cable detection feature dimensionality conversion information reflects the characteristic distribution of cable fluctuations in different dimensional spaces.

[0091] Step S704, determining whether the number of times the cable detection feature dimension conversion information is generated is equal to the number of iterative analyses of the target cable detection feature; if so, proceeding to step S705; if not, proceeding to step S706.

[0092] In this embodiment, determining whether the number of times cable detection feature dimensionality conversion information is generated reaches the target number of cable detection feature iterations is used to control the iteration depth of feature analysis. If the number of times generated does not reach the target number of iterations, it indicates that the current feature transformation has not fully captured the dynamic patterns of cable fluctuations and further iterations are required. If the target number of times is reached, the feature analysis is considered to have converged and the iterations can be terminated to avoid redundant computations.

[0093] Step S705: obtaining cable sag fluctuation detection information based on the plurality of cable detection feature dimension conversion information.

[0094] In this embodiment, the generation of cable sag fluctuation detection information requires integrating the results of multiple rounds of iterative dimensionality conversion. By performing temporal correlation analysis (such as time series-based trend fitting and outlier detection) on multiple cable detection feature dimensionality conversion information and combining it with a library of historical fluctuation patterns, the current cable fluctuation type (such as normal vibration, breeze vibration, and dancing), fluctuation amplitude, and potential abnormal trends are identified. This generates comprehensive detection information including fluctuation status, risk level, and maintenance recommendations.

[0095] Step S706: Dimensionally convert the plurality of cable detection feature information as cable detection feature information, and return to step S701.

[0096] In this embodiment, when the target number of iterations is not reached, weighted aggregation and dimensional decomposition are continued based on the currently converted features, and the feature representation is gradually optimized through multiple rounds of iterations until the complex characteristics of the cable fluctuations are fully captured.

[0097] The cable sag fluctuation detection method provided in the embodiment of the present application realizes multi-level analysis of cable detection features by introducing an iterative mechanism of weight aggregation, bias adjustment and dimensional decomposition. It not only uses the optimized parameters to improve the quantitative accuracy of feature importance, but also enhances the expression ability of complex fluctuation patterns through iterative dimensional conversion, significantly improving the accuracy and robustness of cable sag fluctuation detection, and providing a more refined and dynamic decision-making basis for cable operation and maintenance.

[0098] Corresponding to the method of the above embodiment, Figure 8 A structural block diagram of a cable sag fluctuation detection system provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown. Figure 8 The exemplary cable sag fluctuation detection system may be an execution subject of the cable sag fluctuation detection method provided in the aforementioned embodiment 1.

[0099] Reference Figure 8 , the cable sag fluctuation detection system includes: The cable detection information acquisition module 810 is used to obtain current cable detection information, historical cable detection information, and cable detection environment information; a cable detection feature information generation module 820 configured to obtain a plurality of cable detection feature information based on the current cable detection information, historical cable detection information, cable detection environment information, a preset cable detection time segmentation window, and a plurality of preset cable detection information feature extraction matrices; a target cable detection feature parsing parameter information calculation module 830, configured to calculate a plurality of target cable detection feature parsing parameter information based on the plurality of cable detection feature information and a plurality of randomly generated initial cable detection feature parsing parameter information; The cable sag fluctuation detection information determination module 840 is configured to parse the plurality of cable detection feature information based on the plurality of target cable detection feature parsing parameter information to obtain the cable sag fluctuation detection information.

[0100] The process of each module realizing its own function in the cable sag fluctuation detection system provided in the embodiment of the present application can be specifically referred to the aforementioned Figure 1 The description of the first embodiment is omitted here.

[0101] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0102] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0103] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0104] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0105] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish descriptions and should not be understood as indicating or implying relative importance. It should also be understood that although the terms "first", "second", etc. are used in the text to describe various elements in some embodiments of the present application, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first table can be named a second table, and similarly, a second table can be named a first table without departing from the scope of the various described embodiments. Both the first table and the second table are tables, but they are not the same table.

[0106] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0107] The cable sag fluctuation detection method provided in the embodiments of the present application can be applied to terminal devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptop computers, ultra-mobile personal computers (UMPCs), netbooks, and personal digital assistants (PDAs). The embodiments of the present application do not impose any restrictions on the specific type of terminal device.

[0108] For example, the terminal device can be a station (STAION, ST) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a vehicle networking terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, a wireless modem card, a TV set-top box (STB), customer premise equipment (CPE) and / or other devices for communicating on a wireless system and a next-generation communication system, such as a mobile terminal in a 5G network or a mobile terminal in a future evolved Public Land Mobile Network (PLMN) network.

[0109] As an example and not a limitation, when the terminal device is a wearable device, the wearable device can also be a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are full-featured, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0110] Figure 9 This is a schematic diagram of the structure of a terminal device provided by an embodiment of the present application. Figure 9 As shown, the terminal device 9 of this embodiment includes: at least one processor 90 ( Figure 9 Only one is shown), a memory 91, wherein the memory 91 stores a computer program 92 that can be run on the processor 90. When the processor 90 executes the computer program 92, the steps in the above-mentioned embodiments of the cable sag fluctuation detection method are implemented, such as Figure 1 Alternatively, when the processor 90 executes the computer program 92, the functions of the modules / units in the above-mentioned system embodiments are realized, for example, Figure 8 Functions of modules 810 to 840 are shown.

[0111] The terminal device 9 can be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device can include, but is not limited to, a processor 90 and a memory 91. It can be understood by those skilled in the art that Figure 9 It is only an example of the terminal device 9 and does not constitute a limitation on the terminal device 9. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include an input and sending device, a network access device, a bus, etc.

[0112] The processor 90 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0113] The memory 91 can be an internal storage unit of the terminal device 9 in some embodiments, for example, a hard disk or a memory of the terminal device 9. The memory 91 can also be an external storage device of the terminal device 9, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 91 can also include both the internal storage unit and the external storage device of the terminal device 9. The memory 91 is used to store an operating system, application programs, a boot loader, data and other programs, for example, program codes of the computer program, etc. The memory 91 can also be used to temporarily store data that has been or will be transmitted.

[0114] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0115] The embodiments of the present application also provide a terminal device, which comprises at least one memory, at least one processor and a computer program stored in the at least one memory and executable on the at least one processor, and the processor executes the computer program to enable the terminal device to implement the steps in any of the above method embodiments.

[0116] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps in any of the above method embodiments.

[0117] An embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0118] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application can implement all or part of the processes in the above-mentioned embodiment method by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium.

[0119] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0120] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0121] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0122] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A cable sag fluctuation detection method, characterized in that: include: Get current cable detection information, historical cable detection information, and cable detection environment information; Obtaining a plurality of cable detection feature information according to the current cable detection information, the historical cable detection information, the cable detection environment information, the preset cable detection time sequence segmentation window, and a plurality of preset cable detection information feature extraction matrices; Calculating a plurality of target cable detection feature parsing parameter information based on the plurality of cable detection feature information and a plurality of randomly generated initial cable detection feature parsing parameter information; According to the plurality of target cable detection feature parsing parameter information, the plurality of cable detection feature information is parsed and processed to obtain cable sag fluctuation detection information.

2. The cable sag fluctuation detection method according to claim 1, wherein: The step of obtaining a plurality of cable detection feature information based on the current cable detection information, the historical cable detection information, the cable detection environment information, the preset cable detection time sequence segmentation window, and the plurality of preset cable detection information feature extraction matrices specifically includes: According to a preset cable detection timing segmentation window, the current cable detection information, the historical cable detection information, and the cable detection environment information are subjected to timing segmentation processing to obtain the current cable detection timing information, the historical cable detection timing information, and the cable detection environment timing information; According to a plurality of preset cable detection information feature extraction matrices, feature extraction processing is performed on the current cable detection timing information, the historical cable detection timing information, and the cable detection environment timing information to obtain the current cable detection timing feature information, the historical cable detection timing feature information, and the cable detection environment timing feature information; Performing odd-even timing separation processing on the current cable detection timing feature information, the historical cable detection timing feature information, and the cable detection environment timing feature information to obtain current cable detection odd timing feature information, historical cable detection odd timing feature information, cable detection environment odd timing feature information, current cable detection even timing feature information, historical cable detection even timing feature information, and cable detection environment even timing feature information; Based on a preset cable detection odd-numbered time series feature transformation function, a time series feature transformation process is performed on the current cable detection odd-numbered time series feature information, the historical cable detection odd-numbered time series feature information, and the cable detection environment odd-numbered time series feature information to obtain a current cable detection odd-numbered time series feature vector, a historical cable detection odd-numbered time series feature vector, and a cable detection environment odd-numbered time series feature vector; Based on a preset cable detection even-numbered timing feature transformation function, a timing feature transformation process is performed on the current cable detection even-numbered timing feature information, the historical cable detection even-numbered timing feature information, and the cable detection environment even-numbered timing feature information to obtain a current cable detection even-numbered timing feature vector, a historical cable detection even-numbered timing feature vector, and a cable detection environment even-numbered timing feature vector; Feature vector fusion processing is performed on the current cable detection odd-numbered timing feature vector, the historical cable detection odd-numbered timing feature vector, the cable detection environment odd-numbered timing feature vector, the current cable detection even-numbered timing feature vector, the historical cable detection even-numbered timing feature vector, and the cable detection environment even-numbered timing feature vector to obtain multiple cable detection feature information.

3. The cable sag fluctuation detection method according to claim 2, wherein: The plurality of preset cable detection information feature extraction matrices include a preset cable detection information association feature extraction matrix, a preset cable detection information feature identifier extraction matrix, and a preset cable detection information feature load extraction matrix; The step of performing feature extraction processing on the current cable detection timing information, the historical cable detection timing information, and the cable detection environment timing information according to a plurality of preset cable detection information feature extraction matrices to obtain the current cable detection timing feature information, the historical cable detection timing feature information, and the cable detection environment timing feature information specifically includes: Obtaining current cable detection associated feature information, historical cable detection associated feature information, and cable detection environment associated feature information based on the current cable detection timing information, historical cable detection timing information, cable detection environment timing information, and a preset cable detection information associated feature extraction matrix; Obtaining current cable detection feature identification information, historical cable detection feature identification information, and cable detection environment feature identification information based on the current cable detection timing information, historical cable detection timing information, cable detection environment timing information, and a preset cable detection information feature identification extraction matrix; Obtaining current cable detection feature coding information, historical cable detection feature coding information, and cable detection environment feature coding information based on the current cable detection associated feature information, historical cable detection associated feature information, cable detection environment associated feature information, current cable detection feature identification information, historical cable detection feature identification information, and cable detection environment feature identification information; Obtaining current cable detection characteristic load information, historical cable detection characteristic load information, and cable detection environment characteristic load information based on the current cable detection timing information, historical cable detection timing information, cable detection environment timing information, and a preset cable detection information characteristic load extraction matrix; According to the current cable detection feature coding information, historical cable detection feature coding information, cable detection environment feature coding information, current cable detection feature load information, historical cable detection feature load information and cable detection environment feature load information, the current cable detection timing feature information, historical cable detection timing feature information and cable detection environment timing feature information are obtained.

4. The cable sag fluctuation detection method according to claim 1, wherein: The plurality of randomly generated initial cable detection feature parsing parameter information includes randomly generated initial cable detection feature parsing weight information, randomly generated initial cable detection feature parsing bias information, randomly generated initial cable detection feature parsing dimension information, and randomly generated initial cable detection feature parsing iteration count; The step of calculating a plurality of target cable detection feature parsing parameter information based on the plurality of cable detection feature information and a plurality of randomly generated initial cable detection feature parsing parameter information specifically includes: Splicing multiple preset cable detection information feature extraction matrices, randomly generated initial cable detection feature parsing weight information, randomly generated initial cable detection feature parsing bias information, randomly generated initial cable detection feature parsing dimension information, and randomly generated initial cable detection feature parsing iteration times to generate multiple initial cable detection feature parsing parameter variable array information; Calculating a plurality of initial cable detection feature parsing parameter variable array information, cable detection feature information, a preset cable detection feature classification function, and a preset cable detection feature prediction model to obtain a plurality of initial cable detection feature parsing parameter variable array quality indicator information; using the initial cable detection feature parsing parameter variable array information corresponding to the maximum value of the plurality of initial cable detection feature parsing parameter variable array quality indicator information as the cable detection feature parsing parameter variable reference array information; A plurality of target cable detection feature parsing parameter information is calculated based on the plurality of initial cable detection feature parsing parameter variable array information and the cable detection feature parsing parameter variable reference array information.

5. The cable sag fluctuation detection method according to claim 4, wherein: The step of calculating and obtaining a plurality of initial cable detection feature parsing parameter variable array quality indicator information based on the plurality of initial cable detection feature parsing parameter variable array information, the cable detection feature information, a preset cable detection feature classification function, and a preset cable detection feature prediction model specifically includes: Calculating and obtaining a plurality of cable sag fluctuation detection feature classification information based on the plurality of cable detection feature information and a preset cable detection feature classification function; Calculating a plurality of initial cable detection feature classification information and a plurality of initial cable detection feature prediction information based on the plurality of cable detection feature information and the initial cable detection feature parsing parameter variable array information; Calculating a plurality of cable detection feature classification accuracy information based on the plurality of initial cable detection feature classification information and the cable suspension fluctuation detection feature classification information; Calculating a plurality of cable detection feature prediction reference information based on the plurality of cable detection feature information and a preset cable detection feature prediction model; Calculating a plurality of cable detection feature prediction accuracy information based on the plurality of initial cable detection feature prediction information and the cable detection feature prediction reference information; Based on the plurality of cable detection feature classification accuracy information, the cable detection feature prediction accuracy information and the preset cable feature analysis weight information, a plurality of initial cable detection feature analysis parameter variable array quality indicator information is calculated.

6. The cable sag fluctuation detection method according to claim 4, wherein: The step of calculating a plurality of target cable detection feature parsing parameter information based on the plurality of initial cable detection feature parsing parameter variable array information and the cable detection feature parsing parameter variable reference array information specifically includes: Obtaining a plurality of cable detection feature parsing parameter variable array adjustment distance information according to the plurality of initial cable detection feature parsing parameter variable array information and the cable detection feature parsing parameter variable reference array information; Optimizing the plurality of initial cable detection feature parsing parameter variable array information based on the plurality of cable detection feature parsing parameter variable array adjustment distance information and the preset cable detection feature parsing parameter variable array adjustment number information to generate a plurality of intermediate cable detection feature parsing parameter variable array information; Counting the number of times the plurality of intermediate cable detection feature parsing parameter variable array information is generated to obtain information on the number of times the intermediate cable detection feature parsing parameter variable array is generated; Determining whether the intermediate cable detection feature parsing parameter variable array generation count information is equal to a preset intermediate cable detection feature parsing parameter variable array generation count threshold; If yes, then average the plurality of intermediate cable detection feature analysis parameter variable array information to generate target cable detection feature analysis parameter variable array information; Performing element extraction processing on the target cable detection feature analysis parameter variable array information to obtain a plurality of target cable detection feature analysis parameter information; If not, the multiple intermediate cable detection feature parsing parameter variable array information is used as multiple initial cable detection feature parsing parameter variable array information, and the process returns to the step of calculating multiple initial cable detection feature parsing parameter variable array quality index information based on the multiple initial cable detection feature parsing parameter variable array information, cable detection feature information, preset cable detection feature classification function and preset cable detection feature prediction model.

7. The cable sag fluctuation detection method according to claim 4, wherein: The target cable detection feature parsing parameter information includes target cable detection feature parsing weight information, target cable detection feature parsing bias information, target cable detection feature parsing dimension information, and target cable detection feature parsing iteration times; The step of parsing the plurality of cable detection feature information based on the plurality of target cable detection feature parsing parameter information to obtain the cable sag fluctuation detection information specifically includes: performing weighted summation on a plurality of the cable detection feature information according to the target cable detection feature parsing weight information to obtain cable detection feature aggregation information; Obtaining cable detection feature bias information according to the cable detection feature aggregation information and the target cable detection feature parsing bias information; Performing dimension decomposition processing on the cable detection feature bias information according to the target cable detection feature parsing dimension information to generate a plurality of cable detection feature dimension conversion information; Determining whether the number of times the cable detection feature dimension conversion information is generated is equal to the number of iterative analyses of the target cable detection feature; If so, converting the information according to the plurality of cable detection feature dimensions to obtain cable sag fluctuation detection information; If not, the plurality of cable detection feature dimension conversion information is used as cable detection feature information, and the process returns to the step of parsing the weight information according to the target cable detection feature, performing weighted summation on the plurality of cable detection feature information, and obtaining cable detection feature aggregation information.

8. A cable sag fluctuation detection system, characterized in that: include: The cable detection information acquisition module is used to obtain current cable detection information, historical cable detection information, and cable detection environment information; a cable detection feature information generation module, configured to obtain a plurality of cable detection feature information based on the current cable detection information, historical cable detection information, cable detection environment information, a preset cable detection time sequence segmentation window, and a plurality of preset cable detection information feature extraction matrices; a target cable detection feature parsing parameter information calculation module, configured to calculate a plurality of target cable detection feature parsing parameter information based on the plurality of cable detection feature information and a plurality of randomly generated initial cable detection feature parsing parameter information; The cable sag fluctuation detection information determination module is used to parse and process the plurality of cable detection feature information according to the plurality of target cable detection feature parsing parameter information to obtain the cable sag fluctuation detection information.

9. A terminal device, characterized in that: The terminal device includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images