Cable strand break warning method, device, equipment and storage medium

Abstract

The present invention relates to the technical field of cable strands, and discloses a cable strand break warning method, device, equipment and storage medium. The method comprises: performing multi-modal sensor data acquisition on a cable strand system to obtain vibration acceleration data and stress-strain data; performing multi-band distributed analysis to obtain a global vibration state diagram and performing time-frequency domain feature extraction to obtain a stress-strain feature diagram; performing data fusion and adaptive feature selection to obtain a target fusion feature set; constructing an adaptive Kalman filter combination warning algorithm and performing cable state estimation to obtain a cable state estimation result; performing multi-layer machine learning model analysis on the cable state estimation result to obtain a break risk prediction value and perform multi-level warning strategy decision-making to output intelligent break warning information. The present invention realizes intelligent break warning, can take corresponding preventive measures according to the risk level, and improves the pertinence and effectiveness of the warning.

Description

Technical Field

[0001] The present invention relates to the technical field of cable strands, and in particular to a cable strand break warning method, device, equipment and storage medium. Background Art

[0002] Cable stranding systems play a critical role in power transmission, telecommunications, and other fields. Their safe and reliable operation is directly related to socioeconomic development and people's quality of life. However, due to long-term exposure to mechanical stress, environmental corrosion, and other factors, cable strands are prone to fatigue damage and structural degradation. In severe cases, these problems can lead to cable breakage, resulting in significant economic losses and safety hazards. Traditional cable stranding inspection methods rely primarily on manual inspections and periodic testing, which are inefficient and lack real-time performance, making it difficult to detect potential cable breakage risks in a timely manner.

[0003] In recent years, with the rapid development of sensing technology, signal processing, and artificial intelligence, cable strand condition monitoring and early warning methods based on multimodal sensing and intelligent algorithms have gradually become a research hotspot. However, current research still faces several challenges: a single sensing method cannot fully reflect the complex working conditions of cable strands, and the fusion and feature extraction of multimodal sensing data still require further research. Secondly, the dynamic and nonlinear characteristics of cable strand systems pose challenges to state estimation, requiring the development of more robust and adaptive algorithms. How to effectively utilize historical data and expert knowledge to build an accurate and reliable disconnection risk prediction model remains a difficult problem that needs to be solved. Summary of the Invention

[0004] The present invention provides a cable wire break warning method, device, equipment and storage medium. The present invention realizes intelligent break warning, can take corresponding preventive measures according to the risk level, and improves the pertinence and effectiveness of the warning.

[0005] In a first aspect, the present invention provides a cable strand disconnection warning method, the cable strand disconnection warning method comprising:

[0006] Perform multi-modal sensor data acquisition on the cable stranding system to obtain vibration acceleration data and stress and strain data;

[0007] Performing multi-band distributed analysis on the vibration acceleration data to obtain a global vibration state diagram, and performing time-frequency domain feature extraction on the stress-strain data to obtain a stress-strain feature diagram;

[0008] Performing data fusion and adaptive feature selection on the global vibration state diagram and the stress-strain characteristic diagram to obtain a target fusion feature set;

[0009] Based on the adaptive factor update mechanism of covariance matching and combined with the dynamic window adjustment technology, an adaptive Kalman filter combined warning algorithm is constructed, and the cable state estimation is performed on the target fusion feature set to obtain the cable state estimation result;

[0010] A multi-layer machine learning model analysis is performed on the cable status estimation result to obtain a disconnection risk prediction value, and a multi-level warning strategy decision is made on the disconnection risk prediction value to output intelligent disconnection warning information.

[0011] In a second aspect, the present invention provides a cable strand break warning device, the cable strand break warning device comprising:

[0012] The acquisition module is used to collect multi-modal sensor data of the cable stranding system to obtain vibration acceleration data and stress and strain data;

[0013] an extraction module, configured to perform multi-band distributed analysis on the vibration acceleration data to obtain a global vibration state diagram, and perform time-frequency domain feature extraction on the stress-strain data to obtain a stress-strain feature diagram;

[0014] a fusion module, configured to perform data fusion and adaptive feature selection on the global vibration state diagram and the stress-strain characteristic diagram to obtain a target fusion feature set;

[0015] A state estimation module is used to construct an adaptive Kalman filter combined early warning algorithm based on an adaptive factor update mechanism based on covariance matching and a dynamic window adjustment technology, and to perform cable state estimation on the target fusion feature set to obtain a cable state estimation result;

[0016] The output module is used to perform a multi-layer machine learning model analysis on the cable status estimation result to obtain a disconnection risk prediction value, and to make a multi-level warning strategy decision on the disconnection risk prediction value to output intelligent disconnection warning information.

[0017] The third aspect of the present invention provides a computer device, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory to enable the computer device to execute the above-mentioned cable break warning method.

[0018] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned cable strand break warning method.

[0019] The technical solution provided by the present invention achieves comprehensive perception and precise description of the cable state by acquiring vibration acceleration and stress-strain data from the cable stranding system through multimodal sensor data acquisition, followed by data fusion and adaptive feature selection. This improves the reliability and accuracy of condition monitoring. Multi-band distributed analysis of the vibration acceleration data generates a global vibration state diagram, which effectively captures the vibration characteristics of the cable strands in different frequency bands and enhances the sensitivity and accuracy of anomaly detection. An adaptive Kalman filter combined early warning algorithm based on a covariance matching adaptive factor update mechanism and dynamic window adjustment technology is constructed, improving the robustness and adaptability of state estimation and adapting to the dynamic characteristics of the cable stranding system. A multi-layer machine learning model is used for disconnection risk prediction, including a multi-channel temporal convolutional network, an autoencoder, a hierarchical attention mechanism network, and a recursive neural network tree. This model fully exploits the temporal characteristics and semantic information of the cable state data, improving the accuracy of risk prediction. A multi-level early warning strategy is implemented based on the predicted disconnection risk value, achieving intelligent disconnection warning. Appropriate preventive measures can be taken based on the risk level, enhancing the pertinence and effectiveness of the warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 Schematic diagram of the steps of a cable strand break warning method according to an embodiment of the present invention;

[0022] Figure 2 Schematic diagram of the structure of the cable wire breakage warning device in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] Embodiments of the present invention provide a method, device, equipment and storage medium for early warning of cable breakage. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe the order or precedence of the targets. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or that are inherent to these processes, methods, products or devices.

[0024] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 An embodiment of a cable strand break warning method according to an embodiment of the present invention includes:

[0025] Step S1, performing multi-modal sensor data acquisition on the cable stranding system to obtain vibration acceleration data and stress and strain data;

[0026] It is understandable that the execution subject of the present invention may be a cable strand break warning device, or a terminal or a server, which is not limited here. The embodiment of the present invention is described by taking a server as the execution subject as an example.

[0027] Specifically, a multimodal sensor array is arranged in segments within the cable stranding system, establishing a sensor network topology and clarifying the relative positions of the individual sensors. Based on the sensor network topology, an adaptive algorithm dynamically adjusts the sensor sampling frequency to obtain the optimal sampling frequency parameters, ensuring data acquisition efficiency and accuracy. Using the optimal sampling frequency parameters, multi-channel synchronous data acquisition is performed to capture the system's raw sensor signals. Wavelet denoising techniques are used to denoise the signals, and a signal separation algorithm is applied to separate the different signal components, obtaining vibration acceleration signals and stress and strain signals. The instantaneous frequency spectrum of the vibration acceleration signal is extracted, and the frequency domain characteristics of the signal are analyzed to identify the valid frequency bands. These frequency bands are then filtered to obtain vibration acceleration data for analysis. Principal component analysis is also performed on the stress and strain signals to extract the primary stress and strain directions, reducing the data dimensionality while retaining the most important feature information. Tensor decomposition is performed on the stress and strain signals based on the principal stress and strain directions, breaking the complex signal into multiple manageable tensor components. The decomposed stress-strain tensor is processed to characterize the properties of the material or structure under stress by extracting the stress-strain eigenvalues. These stress-strain eigenvalues ​​are normalized to eliminate the effects of different dimensions and obtain stress-strain data.

[0028] Step S2: performing multi-band distributed analysis on the vibration acceleration data to obtain a global vibration state diagram, and performing time-frequency domain feature extraction on the stress-strain data to obtain a stress-strain feature diagram;

[0029] Specifically, wavelet packet decomposition is performed on the vibration acceleration data, decomposing the original vibration signal into multiple frequency band sub-signals, each representing the vibration characteristics within a different frequency range. Energy calculation is performed on the frequency band sub-signals to obtain the energy distribution of each frequency band and construct a frequency band energy spectrum. This frequency band energy spectrum displays the energy distribution of the vibration signal at different frequencies. Adaptive threshold segmentation is then used to process the frequency band energy spectrum, identifying frequency bands with abnormally concentrated energy. This identification of abnormal frequency bands indicates frequency ranges in the vibration signal that may harbor problems. Based on the identification of abnormal frequency bands, each monitored section of the cable strand is analyzed to pinpoint the specific location of the vibration anomaly and generate a localized abnormal region map. Spatial correlation analysis is performed on the localized abnormal region map to reveal the propagation path of the vibration anomaly, reflecting the manner and extent of the anomaly's spread from one region to other regions. Combining the localized abnormal region map and the abnormal propagation path, a global vibration state map is constructed, displaying the vibration state of the entire cable strand system. Simultaneously, a Hilbert-Huang transform is performed on the stress and strain data to decompose the time-frequency characteristics of the nonlinear and non-stationary signal, generating a time-frequency energy distribution map of the stress and strain data. The instantaneous frequency and amplitude are extracted from the time-frequency energy distribution diagram to form a time-frequency feature vector, which reflects the temporal and frequency variations of the stress-strain signal. Feature dimensionality reduction is performed on the time-frequency feature vector, retaining the most representative features to form a reduced feature set. Based on this reduced feature set, a stress-strain feature map is constructed to demonstrate the characteristic variations of stress and strain in different regions and over time.

[0030] Step S3, performing data fusion and adaptive feature selection on the global vibration state diagram and the stress-strain characteristic diagram to obtain a target fusion feature set;

[0031] Specifically, the global vibration state map is segmented into multiple local vibration regions, representing vibration characteristics at different locations or time periods. For each local vibration region, features such as vibration intensity, frequency, and duration are extracted to form a vibration feature vector. Simultaneously, the stress-strain feature map is decomposed into a trend term, a period term, and a residual term. The trend term reflects the long-term trend of the stress-strain signal, the period term reveals periodic fluctuations in the signal, and the residual term represents the portion of the signal that cannot be explained by the trend or period. By analyzing these components, the rate of change and cumulative amount of stress and strain are calculated to obtain the stress-strain feature vector. The vibration feature vector and the stress-strain feature vector are fused using Dempster-Shafer evidence theory. By combining evidence from different sources, this method effectively handles uncertainty and produces an initial fused feature set. Feature importance analysis is then performed on this initial fused feature set. By calculating the feature importance score for each feature, the contribution of each feature to the overall prediction is determined and the features are ranked based on this score. Based on the ranking of the importance scores, threshold screening is performed to select the most critical candidate feature subset. The feature contributions of the candidate feature subsets are calculated. The feature contribution measures the actual impact of each feature in disconnection warning. Based on the calculated results, each feature's contribution is dynamically weighted to produce an adaptive feature weight. This weighting is dynamically adjusted based on the feature's performance under different conditions, ensuring that the final feature combination is more adaptable to various situations. Based on the adaptive feature weights, the candidate feature subsets are weighted and combined to produce the target fused feature set.

[0032] Step S4, based on the adaptive factor update mechanism of covariance matching, an adaptive Kalman filter combined early warning algorithm is constructed in combination with the dynamic window adjustment technology, and the cable state estimation is performed on the target fusion feature set to obtain the cable state estimation result;

[0033] Specifically, a state-space model is constructed for the target fusion feature set, resulting in the system state equation and observation equation. These equations together describe the temporal evolution of the cable system state and the relationship between the observed data and the system state. These two equations are used to initialize the Kalman filter parameters, resulting in the initial state estimate and covariance matrix. The observation data sequence is partitioned into sliding windows to generate a dynamic observation window. This dynamic observation window is used to capture the temporal characteristics of the cable system state. By calculating the observation noise covariance within the dynamic observation window, an adaptive observation noise covariance matrix is ​​constructed. This matrix dynamically adjusts the noise level during the filtering process, thereby improving filtering accuracy and adaptability. Singular value decomposition is performed on the adaptive observation noise covariance matrix to obtain covariance eigenvectors, which reflect key information about the noise covariance matrix. This covariance is then used to calculate the adaptive factor. Calculating the adaptive factor is a crucial step in the filtering process, as it adjusts the state prediction covariance based on real-time data, enabling the filter to better adapt to changing system states. The updated state prediction covariance is decomposed to extract a lower triangular matrix. This lower triangular matrix is ​​used to generate an unscented transform sample set representing various possible system states. By performing state prediction and measurement prediction on the unscented transformation sample set, the mean and covariance of the predicted state are obtained, describing the state distribution of the system at the next moment. The Kalman gain is calculated based on the predicted state mean and covariance. The Kalman gain is a dynamically adjusted coefficient that combines the observed data and the state prediction results to update the system state estimate. The Kalman gain incorporates new information from the observed data into the state estimate, making the final state estimate more accurate and ultimately resulting in the cable state estimate.

[0034] Step S5: Perform a multi-layer machine learning model analysis on the cable status estimation result to obtain a disconnection risk prediction value, perform a multi-level warning strategy decision on the disconnection risk prediction value, and output intelligent disconnection warning information.

[0035] Specifically, empirical mode decomposition (EMD) is performed on the cable state estimation results. EMD is an analysis method suitable for nonlinear and non-stationary signals. It decomposes complex cable state estimation results into multiple intrinsic mode functions (IMFs), each representing the characteristic information of different frequency components. These IMFs are then fed into a multi-channel temporal convolutional network (TCN) within a multi-layer machine learning model for processing, extracting the data's temporal feature representation. TCNs have the ability to capture temporal patterns and analyze data at multiple time scales, acquiring rich temporal feature information. The temporal feature representation is then fed into an autoencoder within the multi-layer machine learning model for noise reduction. The autoencoder effectively filters noise by mapping the data into a low-dimensional space and then reconstructing the data from this low-dimensional space, resulting in a robust feature vector. This robust feature vector is then fed into a hierarchical attention network within the multi-layer machine learning model for contextual weighted analysis. The hierarchical attention network calculates the importance of different features in different contexts, weighting the features and generating weighted contextual information. This information undergoes dynamic time warping to align features across time periods, yielding an aligned temporal pattern. This processing effectively reduces errors caused by different time scales and ensures feature consistency across the temporal dimension. The aligned temporal patterns are then fed into a recursive neural network tree within a multi-layer machine learning model for processing. The recursive neural network tree extracts semantic information from the data at multiple levels, generating hierarchical semantic features. Multi-task learning is performed on these features to simultaneously obtain a shared representation and a task target representation. The shared representation contains feature information that is meaningful to all tasks, while the task target representation focuses on feature information specific to a particular task. The shared representation and task target representation are then fed into an ensemble gradient boosting tree within the multi-layer machine learning model for disconnection risk prediction. The gradient boosting tree constructs a strong classifier based on multiple weak classifiers, resulting in more accurate disconnection risk predictions. The disconnection risk predictions are then integrated and fused, using a weighted combination of the predictions from different models to produce a more robust comprehensive risk assessment. Based on this assessment, a multi-level warning strategy is implemented, ultimately outputting intelligent disconnection warning information.

[0036] A sliding window segmentation is performed on the aligned time series patterns, dividing the entire time series data into multiple continuous time segments and capturing feature information from different time intervals within the time series data. The time segments are sequentially fed into the leaf nodes of a recursive neural network tree for processing, resulting in an initial feature representation that captures the essential information within the time series segments. Local time series dependency analysis is performed on the initial feature representation to identify local dependencies between time segments and capture pattern features that change over short periods of time. Local time series dependency features reveal the dynamics of the data at the microscopic level. These features are then fed into the intermediate nodes of the recursive neural network tree for processing, forming a hierarchical feature combination. The hierarchical feature combination fuses and refines features at different levels, gradually constructing a more complex feature representation that reflects the multi-layered nature of the data. Long-term dependency analysis is performed on the hierarchical feature combination to capture data dependencies over longer time frames, generating long-term dependency features that reflect the state change trends of the cable stranding system over longer periods of time. The long-term dependency features are fed into the root node of the recursive neural network tree for processing, resulting in global semantic features. Global semantic features integrate all hierarchical information from leaf nodes to the root node, providing a holistic understanding of the time series data. An attention mechanism is applied to the global semantic features to identify the most important components of the global semantic features. These components are then weighted to generate weighted semantic features. The weighted semantic features are then fed into the multi-task learning network to construct a task-sharing layer. The task-sharing layer is a core component of multi-task learning, providing a shared feature foundation for different tasks and ensuring that each task can be learned and predicted within a unified feature space. A task-branch network analysis is performed on the task-sharing layer to process task-specific features. The information in the shared layer is then processed to generate a task target representation. The task target representation focuses on the prediction requirements of each specific task and can generate the most appropriate feature representation for that task. The task-sharing layer and the task target representation are then fused to obtain the final shared and task target representations. These two representations respectively contain the shared information in multi-task learning and task-specific information.

[0037] In this embodiment of the present invention, multimodal sensor data acquisition is performed on the cable stranding system to obtain vibration acceleration and stress-strain data. Data fusion and adaptive feature selection are then performed to achieve comprehensive perception and precise description of the cable state, improving the reliability and accuracy of condition monitoring. Multi-band distributed analysis of the vibration acceleration data is performed to generate a global vibration state diagram, which effectively captures the vibration characteristics of the cable strands in different frequency bands and enhances the sensitivity and accuracy of anomaly detection. An adaptive Kalman filter combined early warning algorithm, based on a covariance matching adaptive factor update mechanism and dynamic window adjustment technology, is constructed. This improves the robustness and adaptability of state estimation and adapts to the dynamic characteristics of the cable stranding system. A multi-layer machine learning model is used for disconnection risk prediction, including a multi-channel temporal convolutional network, an autoencoder, a hierarchical attention mechanism network, and a recursive neural network tree. This model fully exploits the temporal characteristics and semantic information of the cable state data, improving the accuracy of risk prediction. A multi-level early warning strategy is implemented based on the predicted disconnection risk value, achieving intelligent disconnection warning. Preventive measures can be taken according to the risk level, improving the relevance and effectiveness of the warning.

[0038] In a specific embodiment, the process of executing step S1 may specifically include the following steps:

[0039] The multimodal sensor array is arranged in segments on the cable strand system to obtain the sensor network topology. The sensor sampling frequency is adaptively adjusted according to the sensor network topology to obtain the optimal sampling frequency parameters.

[0040] Perform multi-channel synchronous data acquisition on the optimal sampling frequency parameters to obtain the original sensor signal, and perform wavelet denoising and signal separation on the original sensor signal to obtain vibration acceleration signal and stress strain signal;

[0041] Extracting the instantaneous frequency spectrum of the vibration acceleration signal, and filtering the vibration acceleration signal according to the instantaneous frequency spectrum to obtain vibration acceleration data;

[0042] Performing principal component analysis on the stress-strain signal to obtain the principal stress direction and principal strain direction, and performing tensor decomposition on the stress-strain signal according to the principal stress direction and principal strain direction to obtain the stress-strain tensor;

[0043] The stress-strain tensor is decomposed to obtain the stress-strain eigenvalues, and the stress-strain eigenvalues ​​are normalized to obtain the stress-strain data.

[0044] Specifically, a multimodal sensor array is arranged in sections of the cable strand system, and a sensor network topology is constructed through these sensor arrays. In order to fully cover all possible stress and vibration parts of the cable strand, the sensors are usually arranged in sections along the length of the cable. Multimodal sensors may include acceleration sensors and strain sensors, etc. These sensors can respectively collect vibration and stress and strain data of the cable. The sensor network topology refers to the relative layout of these sensors in space and their mutual connection relationship. This structure determines the path and method of data transmission. The sampling frequency of the sensor is adaptively adjusted according to the sensor network topology to obtain the optimal sampling frequency parameters. The sampling frequency is an important parameter in the signal acquisition process. Too high a sampling frequency will lead to data redundancy and increase the computational burden, while too low a sampling frequency may miss important signal features. The method of adaptively adjusting the sampling frequency can analyze the initial data collected by the sensor, use frequency domain analysis technology, such as Fourier transform, to determine the main frequency components of the signal, and then select an optimal sampling frequency that can cover these main frequencies. Assume is the sampling frequency, is the maximum frequency of the signal. According to the Nyquist sampling theorem, the sampling frequency needs to satisfy In practical applications, in order to ensure the integrity of the signal, the sampling frequency is usually set to Or higher. After determining the optimal sampling frequency parameters, perform multi-channel synchronous data acquisition on the cable stranding system. Process the original signal. Use wavelet denoising technology to denoise the signal. Wavelet denoising is a signal processing method with localization characteristics in both time domain and frequency domain. It can effectively remove noise from the signal without losing important signal components. Then perform signal separation on the denoised signal, and extract the vibration acceleration signal and stress strain signal respectively. Extract the instantaneous frequency spectrum of the vibration acceleration signal. The instantaneous frequency spectrum can describe the frequency changes of the signal at different times, reflecting the dynamic characteristics of the vibration signal. Assume that the vibration signal The instantaneous frequency is , then the instantaneous frequency can be obtained by Hilbert transform. Specifically, the signal The Hilbert transform is defined as

[0045] ;

[0046] in, yes The Hilbert transform of Indicates the principal value integral. Instantaneous frequency The envelope signal of the signal can be solved by After the instantaneous frequency spectrum is calculated, the vibration acceleration signal is filtered according to the results of the frequency spectrum to remove unnecessary frequency components and obtain the vibration acceleration data for analysis. The stress and strain signal is subjected to principal component analysis. Principal component analysis is a commonly used dimensionality reduction method that maps the data from the original high-dimensional space to the low-dimensional space by performing a linear transformation on the data, mainly retaining the direction with the largest variance in the data. Assume that the data matrix of the stress and strain signal is , where each row represents a sample and each column represents a variable. The core of principal component analysis is to solve the covariance matrix The eigenvalues ​​and eigenvectors of :

[0047] ;

[0048] in is the data matrix The transpose of is the number of samples. By performing eigenvalue decomposition on the covariance matrix, the principal stress direction and principal strain direction are found, representing the components with the largest changes in the stress-strain data. According to the principal component direction, the stress-strain signal is tensor decomposed to obtain the stress-strain tensor. Tensor decomposition is a high-order data analysis method that can decompose high-dimensional data into multiple low-dimensional tensor components, thereby simplifying the data structure and extracting the most important characteristic information. The obtained stress-strain tensor is decomposed to extract the stress-strain eigenvalues. The stress-strain eigenvalues ​​represent the stress-strain intensity in different directions and are important indicators for evaluating the state of the material. The stress-strain eigenvalues ​​are normalized and mapped to a unified scale. They are usually scaled to the range of [0, 1] to eliminate the influence between different dimensions and obtain stress-strain data.

[0049] In a specific embodiment, the process of executing step S2 may specifically include the following steps:

[0050] Performing wavelet packet decomposition on the vibration acceleration data to obtain multiple frequency band sub-signals, and calculating the energy distribution of each frequency band based on the multiple frequency band sub-signals to obtain the frequency band energy spectrum;

[0051] Adaptive threshold segmentation is performed on the frequency band energy spectrum to obtain abnormal frequency band identification, and abnormal location is performed on each monitoring section based on the abnormal frequency band identification to obtain a local abnormal area map;

[0052] Perform spatial correlation analysis on the local abnormal area map to obtain the abnormal propagation path, and construct a global vibration state map based on the abnormal propagation path and the local abnormal area map;

[0053] Perform Hilbert-Huang transform on stress-strain data to obtain time-frequency energy distribution diagram, and extract instantaneous frequency and instantaneous amplitude according to the time-frequency energy distribution diagram to obtain time-frequency feature vector;

[0054] The time-frequency feature vector is subjected to feature dimensionality reduction to obtain a feature set after dimensionality reduction, and a stress-strain feature map is constructed based on the feature set after dimensionality reduction.

[0055] Specifically, the vibration acceleration data is decomposed by wavelet packet. Wavelet packet decomposition is an effective signal processing method that can decompose the signal into sub-signals of different frequency bands, thereby analyzing the characteristics of the signal in each frequency band. For the vibration acceleration data, multiple frequency band sub-signals are obtained by wavelet packet decomposition. Assume that the original vibration signal is , the process of wavelet packet decomposition will be Decompose into sub-signals of different scales and frequencies ,in represents the number of decomposition levels, Indicates the number of the frequency band. The energy distribution of each frequency band is calculated based on multiple frequency band sub-signals to construct the frequency band energy spectrum. The frequency band energy spectrum is a graph that describes the distribution of signal energy in different frequency segments. For each frequency band sub-signal , its energy can be calculated by the following formula:

[0056] ;

[0057] in, Indicates the Tier The energy of the frequency band, is the signal strength in that frequency band. By calculating the energy distribution of all frequency bands, the frequency band energy spectrum of the entire signal is obtained, reflecting the energy distribution characteristics of the signal at different frequencies. Adaptive threshold segmentation is performed on the frequency band energy spectrum to identify frequency bands that may contain anomalies. The adaptive threshold segmentation method determines one or more thresholds based on the statistical characteristics of the frequency band energy spectrum to distinguish between normal and abnormal frequency bands. For example, a threshold based on the standard deviation is set. When the energy of a frequency band exceeds the threshold, it is identified as an abnormal frequency band. Based on the abnormal frequency band identification information, anomalies are located in each monitoring section. The identified abnormal frequency bands are matched with the actual monitoring locations, and a local abnormal area map is drawn to show areas of concentrated vibration in the cable stranding system. These areas may be structural weaknesses or locations exposed to external forces. Spatial correlation analysis is performed on the local abnormal area map to reveal the spatial propagation path of the vibration anomaly. Spatial correlation analysis determines how the abnormal vibration propagates between different areas by calculating the correlation between different areas. Based on the abnormal propagation path and the local abnormal area map, a global vibration state map is constructed to describe the vibration state of the cable stranding system over time and space. Perform Hilbert-Huang transform on stress and strain data. Hilbert-Huang transform is a time-frequency analysis method suitable for nonlinear and non-stationary signals. Through Hilbert-Huang transform, the stress and strain signal is decomposed into a series of intrinsic mode functions (IMFs), and the instantaneous frequency and instantaneous amplitude of the signal are extracted from them. Assume that the stress and strain signal is , the instantaneous frequency at each moment is obtained by Hilbert-Huang transform and instantaneous amplitude Time-frequency energy distribution diagram It can be expressed by the following formula:

[0058] ;

[0059] in, is the Dirac function, is the instantaneous frequency, is the instantaneous amplitude. The time-frequency energy distribution diagram shows the distribution of signal energy in time and frequency. According to the time-frequency energy distribution diagram, the instantaneous frequency and instantaneous amplitude are extracted to obtain the time-frequency feature vector. The time-frequency feature vector includes the frequency and amplitude information of the signal at different times, reflecting the dynamic change characteristics of the stress-strain signal. The time-frequency feature vector is subjected to feature dimensionality reduction processing. While retaining the most important information, the dimension of the feature vector is reduced to improve the computational efficiency. Based on the feature set after dimensionality reduction, a stress-strain feature diagram is constructed to show the characteristic distribution of stress-strain signals in different time and space, revealing the change law of materials under different stress states. For example, the signal collected by the distributed stress sensors of a cable stranding system shows that the instantaneous frequency of the signal changes significantly in certain time periods, indicating the possible existence of structural stress concentration. Through the Hilbert-Huang transform and feature dimensionality reduction processing, the constructed stress-strain feature diagram clearly shows the stress concentration area and time point, thereby indicating that there is a potential risk of disconnection in this area.

[0060] In a specific embodiment, the process of executing step S3 may specifically include the following steps:

[0061] Perform feature segmentation on the global vibration state diagram to obtain multiple local vibration regions, and extract vibration intensity, frequency and duration features based on the multiple local vibration regions to obtain vibration feature vectors;

[0062] The stress-strain characteristic diagram is decomposed into a time series to obtain trend terms, periodic terms and residual terms. The stress-strain change rate and cumulative amount are calculated based on the trend terms, periodic terms and residual terms to obtain the stress-strain characteristic vector.

[0063] The vibration eigenvector and stress-strain eigenvector are fused by Dempster-Shafer evidence theory to obtain the initial fusion feature set;

[0064] Perform feature importance analysis on the initial fusion feature set to obtain feature importance scores, and then sort and threshold the feature importance scores to obtain candidate feature subsets;

[0065] The feature contribution is calculated based on the candidate feature subsets, and the feature contribution is dynamically weighted to obtain the adaptive feature weights. The candidate feature subsets are weighted combined according to the adaptive feature weights to obtain the target fusion feature set.

[0066] Specifically, feature segmentation is performed on the global vibration state diagram, and the global vibration state diagram is divided into multiple local vibration regions. These regions may represent different vibration modes or abnormal regions in the system. Each local region after segmentation corresponds to a period of time and a specific spatial position. Vibration intensity, frequency and duration features are extracted based on multiple local vibration regions. Vibration intensity is usually measured by the amplitude or energy of the vibration signal, frequency represents the periodic change of the vibration signal, and duration reflects the time span of a specific vibration event. By extracting these features, a vibration feature vector is formed. Assume that the vibration signal of a local vibration region is , its vibration intensity It can be defined as the signal energy:

[0067] ;

[0068] in, and is the start and end time of the vibration event. Frequency The duration can be obtained by performing spectrum analysis on the signal. for . Vibration eigenvector The characteristics of the vibration event can be fully described. The stress-strain characteristic diagram is decomposed into time series to extract the trend term, period term and residual term. The stress-strain characteristic diagram shows the stress and strain changes of each part of the cable system at different times. The purpose of time series decomposition is to decompose the original signal into three parts: trend term , periodic items and the residual The trend term reflects the long-term trend of the signal, the periodic term reveals the periodic fluctuations in the signal, and the residual term represents the irregular fluctuations in the signal. The stress-strain change rate and cumulative amount are calculated based on the trend term, periodic term, and residual term. It can be expressed as:

[0069] ;

[0070] in, is the stress or strain signal. The cumulative amount is the cumulative effect of the signal over time, which can usually be calculated by integration. By calculation, the stress and strain characteristic vector is formed ,in is the cumulative stress and strain variable. The vibration eigenvector and the stress and strain eigenvector are fused by Dempster-Shafer evidence theory to obtain the initial fusion feature set. Dempster-Shafer theory is a method for dealing with uncertainty and multi-source information fusion. For each eigenvector, a trust function is defined , which represents the confidence that a feature belongs to a specific state. By applying the Dempster-Shafer rule to the vibration eigenvector and the stress-strain eigenvector, these confidences are combined to generate the initial fusion feature set. Assume that the two eigenvectors and The trust functions are and , then the fused trust function It can be expressed as:

[0071] ;

[0072] in, is a subset of the feature space, and is the support set of the feature vectors. Feature importance analysis is performed on the initial fused feature set. Each feature is assigned an importance score by calculating its contribution to the final prediction result. This score can be calculated using various methods, such as feature importance measurement based on gradient boosting decision trees. The resulting feature importance score reflects each feature's contribution to wire break warning. Based on the feature importance score, features are sorted and thresholds are set to select a subset of candidate features. Based on the candidate feature subset, the feature contribution of each feature is calculated. Feature contribution can be evaluated based on its performance under different conditions, taking into account its performance across various sample types. Based on the feature contribution, each feature is dynamically weighted to obtain an adaptive feature weight. Adaptive feature weights allow the influence of each feature to be dynamically adjusted based on actual needs at different times and under different circumstances. The candidate feature subsets are weighted and combined according to the adaptive feature weights to obtain the target fused feature set. The target fused feature set is the result of a weighted combination of multiple features. It represents the overall state of the cable strand system and integrates key information from vibration and stress-strain characteristics.

[0073] In a specific embodiment, the process of executing step S4 may specifically include the following steps:

[0074] Construct a state space model for the target fusion feature set to obtain the system state equation and observation equation, and initialize the Kalman filter parameters based on the system state equation and observation equation to obtain the initial state estimate and covariance matrix;

[0075] The observation data sequence is divided into sliding windows to obtain a dynamic observation window, and the observation noise covariance is calculated based on the dynamic observation window to obtain an adaptive observation noise covariance matrix;

[0076] Perform singular value decomposition on the adaptive observation noise covariance matrix to obtain the covariance eigenvector, and calculate the adaptive factor based on the covariance eigenvector to obtain the updated state prediction covariance;

[0077] Decompose the updated state prediction covariance to obtain a lower triangular matrix, and generate an unscented transformation sample set based on the lower triangular matrix;

[0078] The state prediction and measurement prediction are performed on the unscented transformation sample set to obtain the predicted state mean and covariance. The Kalman gain is calculated based on the predicted state mean and covariance, and the state estimation is updated in combination with the observed data to obtain the cable state estimation result.

[0079] Specifically, a state space model is constructed for the target fusion feature set to describe the dynamic behavior of the system. The state space model consists of the system state equation and the observation equation. The former is used to describe the evolution of the system state over time, and the latter is used to associate the system state with the observation data. Assume that the target fusion feature set is , the state variables of the system are , then the state equation can be expressed as:

[0080] ;

[0081] in, is the state transfer matrix, which describes the transfer relationship between states; is the control input matrix, is the control input vector; is the process noise, which is usually assumed to have a mean of zero and a covariance of Gaussian white noise. The observation equation can be expressed as:

[0082] ;

[0083] in, is the observation matrix, which maps the state variables to the observation space; is the observation noise, assuming it has zero mean and covariance Gaussian white noise. Initialize the Kalman filter parameters according to the system state equation and observation equation. Initial state estimation Usually obtained by averaging historical data or directly measuring, the initial covariance matrix It reflects the uncertainty of the initial state estimate and can usually be set to a small positive definite matrix. The observation data sequence is divided into sliding windows so that dynamic changes in time can be captured during data processing. The sliding window technique can analyze the local characteristics of the data by moving a fixed-size window on the time series. The data in each window is called a dynamic observation window. By processing these data, the observation noise covariance matrix is ​​calculated. , which reflects the uncertainty in the observation data. Its calculation method is usually to perform statistical analysis on the residuals of the observation data. Assuming that the residual is , then the covariance matrix can be expressed as:

[0084] ;

[0085] in, is the mean of the residuals, is the number of data points in the window. After calculating the adaptive observation noise covariance matrix, perform singular value decomposition on it to obtain the covariance eigenvector. Singular value decomposition can decompose the covariance matrix into eigenvectors and eigenvalues. These eigenvectors represent the main change direction in the observation data. Assume that the covariance matrix The singular value decomposition of is:

[0086] ;

[0087] in, is the eigenvector matrix, Is a diagonal matrix containing the singular values ​​of the covariance matrix. Based on these eigenvectors, the adaptive factor is calculated , this factor is used to update the covariance matrix of state prediction, the formula is:

[0088] ;

[0089] Updated state prediction covariance It is adjusted by multiplying the adaptive factor to better adapt to the characteristics of the current observation data. The updated state prediction covariance is decomposed to extract the lower triangular matrix , through Cholesky decomposition, the covariance matrix It can be expressed as:

[0090] ;

[0091] in, Is a lower triangular matrix. Using this matrix, an unscented transformation sample set is generated. These sample sets capture various possibilities of the system state by introducing nonlinear transformations. The generation of the sample set is usually based on the method of unscented Kalman filtering, which reflects the state distribution through the sampling point at the center of the distribution. State prediction and measurement prediction are performed on the unscented transformation sample set. State prediction is performed based on the state equation of the system, and measurement prediction is completed through the observation equation. These predictions will generate the predicted state mean respectively. and the predicted covariance . Use these predictions to calculate the Kalman gain , Kalman gain is a balancing coefficient used to combine observation data and prediction results to update state estimation. The calculation formula is:

[0092] ;

[0093] Using the Kalman gain, update the state estimate and the covariance matrix

[0094] ;

[0095] ;

[0096] in, is the identity matrix, The actual observation data is combined with the updated state estimation to obtain the estimated result of the cable state, which reflects the current operating state of the system. The accuracy of the state estimation is ensured through the above dynamic adjustment and prediction process.

[0097] In a specific embodiment, the process of executing step S5 may specifically include the following steps:

[0098] Perform empirical mode decomposition on the cable state estimation results to obtain multiple intrinsic mode functions, which are then input into a multi-channel time convolutional network in a multi-layer machine learning model to obtain a time series feature representation.

[0099] The time series feature representation is input into the autoencoder in the multi-layer machine learning model for noise reduction to obtain a robust feature vector;

[0100] The robust feature vector is input into the hierarchical attention mechanism network in the multi-layer machine learning model for context weighted analysis to obtain weighted context information, and the weighted context information is dynamically time-warped to obtain the aligned temporal pattern.

[0101] The aligned temporal patterns are input into a recursive neural network tree in a multi-layer machine learning model for processing to obtain hierarchical semantic features. The hierarchical semantic features are then processed through multi-task learning to obtain shared representations and task target representations.

[0102] The shared representation and the task target representation are input into the integrated gradient boosting tree in the multi-layer machine learning model to predict the disconnection risk and obtain the disconnection risk prediction value;

[0103] The disconnection risk prediction values ​​are integrated and integrated to obtain a comprehensive risk assessment result. Based on the comprehensive risk assessment result, a multi-level warning strategy is implemented to output intelligent disconnection warning information.

[0104] Specifically, empirical mode decomposition is performed on the cable state estimation result to extract different frequency components in the signal. Empirical mode decomposition is an adaptive signal processing method that decomposes complex nonlinear and non-stationary signals into several intrinsic mode functions (IMFs) by layer-by-layer decomposition. IMFs represent the fluctuation characteristics of the signal at different time scales, and each IMF captures the signal components within a specific frequency range. Assuming that the cable state estimation result is a signal , after empirical mode decomposition, can be expressed as:

[0105] ;

[0106] in, For the The intrinsic mode functions, is the modal number, The intrinsic mode function is fed into a multi-channel temporal convolutional network (TMN) in a multi-layer machine learning model for processing. The MCN is a deep learning model suitable for processing time series data, capable of extracting temporal features of signals at different time scales. By performing convolution operations on the IMF in parallel across multiple channels, the MCN captures the complex temporal dependencies of the signal, generating a temporal feature representation that reflects the signal's changing patterns at different moments. The temporal feature representation is fed into an autoencoder in the multi-layer machine learning model for noise reduction. An autoencoder is a neural network designed to learn a compact representation of data. It encodes the input data into a low-dimensional space and then decodes it back to the original data space, thereby learning the key features of the input data and removing noise. In this process, the temporal feature representation is compressed and reconstructed by the autoencoder, resulting in a robust feature vector that not only retains the key features of the signal but also reduces interference from noise and redundant information. The robust feature vector is fed into a hierarchical attention network in the multi-layer machine learning model for context-weighted analysis. The hierarchical attention network weights important features by calculating their importance in different contexts. Through the attention mechanism, the model automatically focuses on time segments or features that contribute more to the prediction, generating weighted contextual information. This weighted feature information is then fed into the dynamic time warping module for processing. Dynamic time warping is a method for aligning time series data. It adjusts for inconsistencies in feature vectors along the temporal dimension, ensuring that data from different time periods can be compared and analyzed on the same time scale, resulting in aligned time series patterns. This aligned time series pattern is then fed into a recursive neural network tree within a multi-layer machine learning model for processing. The recursive neural network tree, a model that combines the strengths of recursive neural networks and decision trees, can capture long-term signal dependencies and extract hierarchical semantic features from the data through a hierarchical tree structure. When processing time series data, recursive neural networks preserve information connections between previous and subsequent time points, while the tree structure facilitates the extraction of higher-level semantic features from the data. After processing the recursive neural network tree, the model generates hierarchical semantic features that represent the semantic information of the signal across different time and frequency domains. These hierarchical semantic features are then fed into a multi-task learning network, which simultaneously handles multiple related tasks through shared representations and task branching. In this network, hierarchical semantic features are first used to construct a task-sharing layer, which contains common features that are meaningful to all tasks. This shared representation is then assigned to a task-branch network to extract a task-specific target representation. The shared representation captures the general characteristics of cable status, while the task target representation is optimized for the specific task of cable breakage risk prediction. The shared and task target representations are then fed into an ensemble gradient boosting tree within a multi-layer machine learning model for cable breakage risk prediction.Gradient boosting tree ensemble learning is an ensemble learning method that combines multiple decision tree models to achieve more accurate predictions. In this model, each tree modifies the predictions of the previous tree. The resulting outage risk prediction combines the predictions of all models and accurately estimates the outage risk of the cable system. The outage risk predictions are integrated and fused, and multiple predictions are weighted averaged. Weights are adjusted to improve prediction stability and accuracy. By combining predictions from different time points and models, a comprehensive risk assessment is obtained.

[0107] In a specific embodiment, the step of inputting the aligned temporal patterns into a recursive neural network tree in a multi-layer machine learning model for processing to obtain hierarchical semantic features, and performing multi-task learning on the hierarchical semantic features to obtain a shared representation and a task target representation may specifically include the following steps:

[0108] Perform sliding window segmentation on the aligned time series pattern to obtain multiple time segments, and input the multiple time segments into the leaf nodes of the recursive neural network tree for processing to obtain the initial feature representation;

[0109] Perform local temporal dependency analysis on the initial feature representation to obtain local temporal dependency features, and input the local temporal dependency features into the intermediate nodes of the recursive neural network tree for processing to obtain a hierarchical feature combination;

[0110] Perform long-term dependency analysis on hierarchical feature combinations to obtain long-term dependency features, and construct the root nodes of a recursive neural network tree with the long-term dependency features for processing to obtain global semantic features.

[0111] Perform attention mechanism analysis on global semantic features to obtain weighted semantic features, and then construct a multi-task learning network with the weighted semantic features to obtain a task sharing layer;

[0112] The task branch network analysis is performed on the task sharing layer to obtain the task target representation, and feature fusion is performed based on the task sharing layer and the task target representation to obtain the shared representation and the task target representation.

[0113] Specifically, the aligned time series pattern is segmented by sliding windows to obtain multiple time segments. Sliding window segmentation technology is a time series data processing method that can capture the local characteristics of the signal in different time periods by moving a fixed-size window on the time axis. Assume that the aligned time series pattern is ,in Represents time, which is divided by sliding window to obtain a series of time segments ,in is the index of the window, is the time point within the window. Input the leaf nodes of the recursive neural network tree for processing to obtain the initial feature representation. The recursive neural network tree combines the advantages of recursive neural networks and decision trees. At the leaf nodes, the recursive neural network can capture the short-term dependencies within the time segment. Through the loop structure of the recursive neural network, the leaf nodes can learn the change pattern of the signal in a short period of time and obtain the initial feature representation of each time segment. , these initial feature representations reflect the basic temporal characteristics of the time segment. Perform local temporal dependency analysis to obtain more detailed feature information. Local temporal dependency analysis focuses on the relationship between features in a short period of time and can reveal the dynamic change pattern of the signal in a small time window. Through the intermediate nodes of the recursive neural network tree, the local temporal dependency features are further processed and combined to form a hierarchical feature combination. . For hierarchical feature combination The memory mechanism of the neural network for long-term dependency analysis can retain the dependency relationship of the signal over a longer time span and capture a wider range of time features. The long-term dependency features obtained by processing the root node of the recursive neural network tree are It is a summary of the entire time series pattern, reflecting the behavior and pattern of the signal on a large time scale. Input into the attention mechanism for analysis. The attention mechanism can highlight those features that are more critical to the overall prediction or classification task by assigning different weights to different time segments or features. corresponds to the feature The attention weights, the attention mechanism will calculate the weighted semantic features

[0114] ;

[0115] in, It is the weight value calculated by the attention mechanism, reflecting the importance of each long-term dependency feature in the final semantic representation. , the model can better focus on those key time series features and improve the accuracy and robustness of prediction. Input into the multi-task learning network for processing. The multi-task learning network can solve multiple related prediction tasks at the same time by combining shared features and task-specific features. In the multi-task learning network, by weighting semantic features Building a task sharing layer , the shared layer contains common feature representations that are meaningful to all tasks. The construction of the shared layer can be achieved through a set of shared neural network layers, which are responsible for extracting the most critical shared features from the weighted semantic features of the input. Perform task branch network analysis. Each task branch network is responsible for extracting features related to a specific task from the shared layer to form a task target representation. Assumptions It is with A task-related target representation can be obtained by extracting these features from the shared layer through a set of specific neural network layers:

[0116] ;

[0117] in, Yes and task Related feature extraction functions. In this way, different tasks can share some features while also retaining their own task-specific feature representations. and task objective representation Perform feature fusion to obtain the final shared representation and task objective representation Feature fusion can be achieved through simple weighting or splicing operations. Assume that the feature fusion operation is , then the shared representation and task target representation can be expressed as:

[0118] ;

[0119] Through the fusion operation, the final model can simultaneously consider shared global features and task-specific local features, providing more accurate prediction or classification results for each task.

[0120] The above describes the cable strand break warning method according to the embodiment of the present invention. The following describes the cable strand break warning device according to the embodiment of the present invention. Figure 2 In one embodiment of the present invention, a device for early warning of cable breakage includes:

[0121] The acquisition module is used to collect multi-modal sensor data of the cable stranding system to obtain vibration acceleration data and stress and strain data;

[0122] The extraction module is used to perform multi-band distributed analysis on the vibration acceleration data to obtain a global vibration state diagram, and to perform time-frequency domain feature extraction on the stress-strain data to obtain a stress-strain feature diagram;

[0123] The fusion module is used to perform data fusion and adaptive feature selection on the global vibration state diagram and stress-strain characteristic diagram to obtain the target fusion feature set;

[0124] The state estimation module is used to construct an adaptive Kalman filter combined warning algorithm based on the adaptive factor update mechanism of covariance matching and dynamic window adjustment technology, and to perform cable state estimation on the target fusion feature set to obtain the cable state estimation result;

[0125] The output module is used to perform multi-layer machine learning model analysis on the cable status estimation results to obtain the disconnection risk prediction value, make multi-level warning strategy decisions based on the disconnection risk prediction value, and output intelligent disconnection warning information.

[0126] Through the collaborative efforts of these components, the system acquires vibration acceleration and stress-strain data from the cable stranding system using multimodal sensor data. Data fusion and adaptive feature selection are then performed to achieve comprehensive perception and precise description of the cable state, improving the reliability and accuracy of condition monitoring. Multi-band distributed analysis of the vibration acceleration data generates a global vibration state diagram, effectively capturing the vibration characteristics of the cable strands at different frequency bands and enhancing the sensitivity and accuracy of anomaly detection. An adaptive Kalman filter combined early warning algorithm, based on a covariance matching adaptive factor update mechanism and dynamic window adjustment technology, is constructed. This improves the robustness and adaptability of state estimation and adapts to the dynamic characteristics of the cable stranding system. A multi-layered machine learning model is employed for breakage risk prediction, including a multi-channel temporal convolutional network, an autoencoder, a hierarchical attention mechanism network, and a recursive neural network tree. This model fully exploits the temporal characteristics and semantic information of the cable state data, improving the accuracy of risk prediction. A multi-level early warning strategy is implemented based on the predicted breakage risk value, enabling intelligent breakage warnings. Appropriate preventive measures are taken based on the risk level, enhancing the relevance and effectiveness of early warnings.

[0127] The present invention also provides a computer device, which includes a memory and a processor. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor executes the steps of the cable wire break warning method in the above-mentioned embodiments.

[0128] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions, and when the instructions are run on a computer, the computer executes the steps of the cable wire break warning method.

[0129] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0130] If the integrated unit is implemented as 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 technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0131] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features thereof can be replaced by equivalents. However, 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 embodiments of the present invention.

Claims

1. A cable wire break warning method, characterized in that: The cable strand breakage warning method comprises: Perform multi-modal sensor data acquisition on the cable stranding system to obtain vibration acceleration data and stress and strain data; Performing multi-band distributed analysis on the vibration acceleration data to obtain a global vibration state diagram, and performing time-frequency domain feature extraction on the stress-strain data to obtain a stress-strain feature diagram; Performing data fusion and adaptive feature selection on the global vibration state diagram and the stress-strain characteristic diagram to obtain a target fusion feature set; specifically comprising: performing feature segmentation on the global vibration state diagram to obtain multiple local vibration regions, and extracting vibration intensity, frequency and duration features based on the multiple local vibration regions to obtain a vibration feature vector; performing time series decomposition on the stress-strain characteristic diagram to obtain trend terms, periodic terms and residual terms, and calculating the stress-strain change rate and cumulative amount based on the trend terms, periodic terms and residual terms to obtain a stress-strain characteristic vector; performing Dempster-Shafer evidence theory fusion on the vibration feature vector and the stress-strain feature vector to obtain an initial fusion feature set; performing feature importance analysis on the initial fusion feature set to obtain a feature importance score, and performing sorting and threshold screening on the feature importance score to obtain a candidate feature subset; calculating feature contribution based on the candidate feature subset, dynamically assigning weights to the feature contribution to obtain an adaptive feature weight, and performing weighted combination on the candidate feature subset based on the adaptive feature weight to obtain a target fusion feature set; Based on the adaptive factor update mechanism of covariance matching and combined with the dynamic window adjustment technology, an adaptive Kalman filter combined warning algorithm is constructed, and the cable state estimation is performed on the target fusion feature set to obtain the cable state estimation result; A multi-layer machine learning model analysis is performed on the cable status estimation result to obtain a disconnection risk prediction value, and a multi-level warning strategy decision is made on the disconnection risk prediction value to output intelligent disconnection warning information.

2. The cable strand break warning method according to claim 1, characterized in that: The multi-modal sensor data acquisition of the cable strand system to obtain vibration acceleration data and stress and strain data includes: Arranging a multimodal sensor array in segments on the cable strand system to obtain a sensor network topology, and adaptively adjusting the sensor sampling frequency according to the sensor network topology to obtain an optimal sampling frequency parameter; Performing multi-channel synchronous data acquisition on the optimal sampling frequency parameters to obtain original sensor signals, and performing wavelet denoising and signal separation on the original sensor signals to obtain vibration acceleration signals and stress strain signals; Extracting an instantaneous frequency spectrum of the vibration acceleration signal, and filtering the vibration acceleration signal according to the instantaneous frequency spectrum to obtain vibration acceleration data; performing principal component analysis on the stress-strain signal to obtain principal stress directions and principal strain directions, and performing tensor decomposition on the stress-strain signal according to the principal stress directions and the principal strain directions to obtain a stress-strain tensor; The stress-strain tensor is decomposed to obtain stress-strain eigenvalues, and the stress-strain eigenvalues ​​are normalized to obtain stress-strain data.

3. The cable strand break warning method according to claim 1, characterized in that: The multi-band distributed analysis of the vibration acceleration data is performed to obtain a global vibration state diagram, and the time-frequency domain feature extraction of the stress-strain data is performed to obtain a stress-strain feature diagram, including: performing wavelet packet decomposition on the vibration acceleration data to obtain a plurality of frequency band sub-signals, and calculating the energy distribution of each frequency band based on the plurality of frequency band sub-signals to obtain a frequency band energy spectrum; Adaptively segmenting the frequency band energy spectrum using a threshold value to obtain abnormal frequency band identifiers, and locating abnormalities in each monitoring section based on the abnormal frequency band identifiers to obtain a local abnormal area map; Performing spatial correlation analysis on the local abnormal region map to obtain an abnormal propagation path, and constructing a global vibration state map based on the abnormal propagation path and the local abnormal region map; Performing a Hilbert-Huang transform on the stress-strain data to obtain a time-frequency energy distribution diagram, and extracting the instantaneous frequency and instantaneous amplitude according to the time-frequency energy distribution diagram to obtain a time-frequency feature vector; Performing feature dimensionality reduction on the time-frequency feature vector to obtain a feature set after dimensionality reduction, and constructing a stress-strain feature map based on the feature set after dimensionality reduction.

4. The cable strand break warning method according to claim 1, characterized in that: The adaptive factor update mechanism based on covariance matching is combined with the dynamic window adjustment technology to construct an adaptive Kalman filter combined warning algorithm, and the cable state estimation is performed on the target fusion feature set to obtain the cable state estimation result, including: Constructing a state space model for the target fusion feature set to obtain a system state equation and an observation equation, and initializing Kalman filter parameters according to the system state equation and the observation equation to obtain an initial state estimate and a covariance matrix; Performing sliding window division on the observation data sequence to obtain a dynamic observation window, and calculating the observation noise covariance based on the dynamic observation window to obtain an adaptive observation noise covariance matrix; Performing singular value decomposition on the adaptive observation noise covariance matrix to obtain a covariance eigenvector, and calculating an adaptive factor based on the covariance eigenvector to obtain an updated state prediction covariance; Decomposing the updated state prediction covariance to obtain a lower triangular matrix, and generating an unscented transformation sample set according to the lower triangular matrix; State prediction and measurement prediction are performed on the unscented transformation sample set to obtain a predicted state mean and covariance, and a Kalman gain is calculated based on the predicted state mean and covariance. The state estimation is updated in combination with the observed data to obtain a cable state estimation result.

5. The cable strand break warning method according to claim 1, characterized in that: The cable status estimation result is subjected to a multi-layer machine learning model analysis to obtain a disconnection risk prediction value, and a multi-level warning strategy decision is made on the disconnection risk prediction value to output intelligent disconnection warning information, including: Performing empirical mode decomposition on the cable state estimation result to obtain a plurality of intrinsic mode functions, and inputting the plurality of intrinsic mode functions into a multi-channel time convolutional network in a multi-layer machine learning model to obtain a time series feature representation; Inputting the time series feature representation into an autoencoder in a multi-layer machine learning model for noise reduction to obtain a robust feature vector; Inputting the robust feature vector into a hierarchical attention mechanism network in a multi-layer machine learning model to perform context weighted analysis to obtain weighted context information, and performing dynamic time warping on the weighted context information to obtain an aligned temporal pattern; Inputting the aligned temporal patterns into a recursive neural network tree in a multi-layer machine learning model for processing to obtain hierarchical semantic features, and performing multi-task learning processing on the hierarchical semantic features to obtain a shared representation and a task target representation; Inputting the shared representation and the task target representation into an integrated gradient boosting tree in a multi-layer machine learning model to perform disconnection risk prediction, thereby obtaining a disconnection risk prediction value; The disconnection risk prediction values ​​are integrated and fused to obtain a comprehensive risk assessment result, and a multi-level warning strategy is executed according to the comprehensive risk assessment result to output intelligent disconnection warning information.

6. The cable strand break warning method according to claim 5, characterized in that: The aligned temporal patterns are input into a recursive neural network tree in a multi-layer machine learning model for processing to obtain hierarchical semantic features, and the hierarchical semantic features are subjected to multi-task learning processing to obtain a shared representation and a task target representation, including: Performing sliding window segmentation on the aligned time series pattern to obtain multiple time segments, and inputting the multiple time segments into leaf nodes of a recursive neural network tree for processing to obtain initial feature representations; Performing local temporal dependency analysis on the initial feature representation to obtain local temporal dependency features, and inputting the local temporal dependency features into an intermediate node of a recursive neural network tree for processing to obtain a hierarchical feature combination; Performing a long-term dependency analysis on the hierarchical feature combination to obtain a long-term dependency feature, and constructing a root node of a recursive neural network tree with the long-term dependency feature for processing to obtain a global semantic feature; Performing an attention mechanism analysis on the global semantic features to obtain weighted semantic features, and constructing a multi-task learning network with the weighted semantic features to obtain a task sharing layer; Performing task branch network analysis on the task sharing layer to obtain a task target representation, and performing feature fusion on the task sharing layer and the task target representation to obtain a shared representation and a task target representation.

7. A cable strand break warning device, characterized in that: Used to execute the cable wire breakage warning method according to any one of claims 1 to 6, the cable wire breakage warning device comprises: The acquisition module is used to collect multi-modal sensor data of the cable stranding system to obtain vibration acceleration data and stress and strain data; an extraction module, configured to perform multi-band distributed analysis on the vibration acceleration data to obtain a global vibration state diagram, and perform time-frequency domain feature extraction on the stress-strain data to obtain a stress-strain feature diagram; a fusion module, configured to perform data fusion and adaptive feature selection on the global vibration state diagram and the stress-strain characteristic diagram to obtain a target fusion feature set; A state estimation module is used to construct an adaptive Kalman filter combined early warning algorithm based on an adaptive factor update mechanism based on covariance matching and a dynamic window adjustment technology, and to perform cable state estimation on the target fusion feature set to obtain a cable state estimation result; The output module is used to perform a multi-layer machine learning model analysis on the cable status estimation result to obtain a disconnection risk prediction value, and to make a multi-level warning strategy decision on the disconnection risk prediction value to output intelligent disconnection warning information.

8. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and is characterized in that when the processor executes the computer program, the cable wire breakage warning method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the processor is enabled to execute the cable wire breakage warning method according to any one of claims 1 to 6.

Images