Cable bridge fault diagnosis method based on sensor network and related equipment

Abstract

The invention relates to a cable bridge fault diagnosis method and related equipment based on a sensor network, and the method comprises the following steps: carrying out the vibration monitoring of a cable bridge, and obtaining dynamic response data; obtaining an abnormal vibration time period sequence through time window segmentation and abnormal identification; tracking a vibration propagation path, and positioning a fault source area; a bridge weak link distribution map is generated by combining structural stress concentration degree analysis; and performing fault grade judgment according to the map, and outputting a maintenance decision suggestion, thereby solving the technical problems that most schemes still stay in a static parameter acquisition stage, an effective analysis mechanism for dynamic vibration response is lacked, and the occurrence position and evolution trend of the abnormal behavior of the bridge are difficult to accurately recognize.

Description

Technical Field

[0001] The present invention relates to the technical field of cable bridges, and in particular to a cable bridge fault diagnosis method based on a sensor network and related equipment. Background Art

[0002] Cable trays, as crucial support and protection structures in power systems, are widely used in industry, buildings, and public facilities. With the acceleration of urbanization and the continued growth of electricity demand, the scale and complexity of cable trays are increasing. Their structural safety and stability are crucial to the normal operation of power systems. However, due to long-term mechanical loads, environmental corrosion, and external vibration, cable trays are prone to potential failures such as fatigue damage, loose connections, and localized deformation. Failure to detect and address these risks can lead to serious safety incidents.

[0003] Traditional cable tray inspection methods rely primarily on manual inspections and regular maintenance, which suffer from low efficiency, high costs, and delayed response times, making it difficult to accurately assess and assess the cable tray's structural status in real time. Although some recent studies have attempted to introduce sensing technology for structural health monitoring, most solutions remain at the static parameter acquisition stage and lack effective analysis mechanisms for dynamic vibration responses, making it difficult to accurately identify the location and evolution of abnormal cable tray behavior. Furthermore, existing technologies still have significant limitations in locating fault sources and identifying structural weaknesses, resulting in a lack of scientific basis for maintenance decisions and impacting the ability to ensure the safe operation of power facilities.

[0004] Therefore, there is an urgent need to develop a cable tray fault diagnosis method that can integrate dynamic sensor data and achieve high temporal and spatial resolution to overcome the shortcomings of traditional methods in terms of real-time performance, accuracy, and intelligence. By building an automated diagnostic system based on a sensor network, not only can the efficiency of fault identification be improved, but it can also provide strong support for condition assessment and maintenance decision-making for the cable tray structure, thereby promoting the development of intelligent operation and maintenance of power infrastructure. Summary of the Invention

[0005] The main purpose of the present invention is to provide a cable tray fault diagnosis method based on a sensor network, which solves the technical problem that most solutions are still at the static parameter acquisition stage, lack an effective analysis mechanism for dynamic vibration response, and find it difficult to accurately identify the occurrence location and evolution trend of abnormal behavior of the cable tray.

[0006] To achieve the above object, the present invention provides a cable tray fault diagnosis method based on a sensor network, comprising the following steps: Vibration monitoring of the cable bridge is performed by using a piezoelectric sensor array arranged at key nodes of the cable bridge to obtain dynamic response data of the bridge structure; The bridge structure dynamic response data is segmented into time windows and anomalies are marked to obtain a bridge abnormal vibration period identification sequence, wherein the bridge abnormal vibration period identification sequence includes a moment of amplitude mutation, a continuous vibration duration, and a vibration attenuation period; Tracing the vibration propagation path of the cable tray based on the abnormal vibration period identification sequence of the cable tray to obtain the fault source area; Calculating the structural stress concentration of the cable tray based on the fault source area to obtain a distribution map of weak links of the cable tray; The cable tray is subjected to fault level determination based on the weak link distribution map of the cable tray to obtain a fault level, and a cable tray maintenance decision suggestion is obtained based on the fault level, including an emergency repair location, preventive replacement components, and a reinforcement plan.

[0007] Furthermore, the time window segmentation processing and abnormality identification of the bridge structure dynamic response data to obtain the bridge abnormal vibration period identification sequence includes the following steps: Performing time domain segmentation on the dynamic response data of the bridge structure by using an adaptive sliding window technology to obtain multiple time window sequences, and performing frequency domain decomposition on the dynamic response data of the bridge structure based on the time window sequences to obtain a time-frequency feature matrix; Performing singular spectrum analysis on the dynamic response data of the bridge structure based on the time-frequency characteristic matrix to obtain a bridge vibration modal sequence, and extracting nonlinear features in the bridge vibration modal sequence through Hilbert-Huang transform to obtain bridge vibration nonlinear features; Based on a preset bridge frame abnormal vibration discrimination threshold, detecting whether there is an abnormality in the nonlinear characteristics of the bridge frame vibration, and if so, obtaining a preliminary abnormal vibration period candidate set; Based on the preliminary abnormal vibration period candidate set, wavelet packet entropy analysis is performed on the dynamic response data of the bridge structure to obtain a multi-scale entropy value sequence, and the abnormality degree of the multi-scale entropy value sequence is identified by fuzzy c-means clustering to obtain a bridge abnormal vibration period identification sequence, wherein the bridge abnormal vibration period identification sequence includes the amplitude mutation time point, continuous vibration duration, and vibration attenuation period.

[0008] Furthermore, the vibration propagation path of the cable tray is tracked based on the abnormal vibration period identification sequence of the cable tray to obtain the fault source area, including: Based on the abnormal vibration period identification sequence of the bridge frame, time difference estimation is performed on the dynamic response data of the bridge frame structure to obtain a vibration wave arrival time difference matrix, and cross-correlation function peak detection is performed on the vibration wave arrival time difference matrix to obtain a vibration propagation delay sequence; Based on the vibration propagation delay sequence, the cable tray is subjected to wave velocity field modeling to obtain a wave velocity distribution diagram of the cable tray structure; and based on the wave velocity distribution diagram of the cable tray structure, the vibration propagation delay sequence is subjected to wave front trajectory reconstruction to obtain a vibration wave front propagation trajectory; Based on the vibration wavefront propagation trajectory, analyzing the vibration energy attenuation degree in the dynamic response data of the bridge structure, generating a vibration energy gradient field, and calculating the vibration energy convergence point in the vibration energy gradient field; The fault area of ​​the cable tray is mapped based on the vibration energy convergence point to obtain the fault source area.

[0009] Furthermore, the structural stress concentration of the cable tray is calculated based on the fault source area to obtain a distribution map of weak links of the cable tray, including: Performing stress field calculation on the cable tray based on the fault source area to obtain a stress distribution matrix of the cable tray nodes, and performing stress gradient analysis on the stress distribution matrix of the cable tray nodes to obtain a stress concentration area diagram of the cable tray; Performing local structural analysis on the bridge stress concentration area map by finite element meshing to obtain the bridge local stress field distribution, and extracting singular feature points in the bridge local stress field distribution to obtain a bridge structure dangerous point sequence; Based on the bridge structure danger point sequence, a stiffness degradation analysis is performed on the bridge support structure in the cable bridge to obtain degradation assessment data of the bridge support structure, and fatigue life estimation is performed on the degradation assessment data of the bridge support structure using a stress intensity factor to obtain a fatigue damage map of the bridge structure, wherein the fatigue damage map of the bridge structure includes crack growth rate, number of stress cycles, and material strength degradation rate; Based on the fatigue damage map of the bridge structure, the load-bearing capacity of the bridge support structure is evaluated to obtain the load-bearing capacity result of the bridge structure, and based on the load-bearing capacity result of the bridge structure, the failure mode of the bridge support structure is identified to obtain the distribution map of the weak links of the bridge.

[0010] Furthermore, the stiffness degradation analysis of the bridge support structure in the cable tray is performed based on the bridge structure dangerous point sequence to obtain degradation assessment data of the bridge support structure, including: By means of nonlinear dynamics, the stiffness of the bridge support structure in the cable bridge is calculated based on the dangerous point sequence of the bridge structure, and a bridge support point elastic coefficient matrix is ​​obtained. A dynamic response analysis of the bridge support point elastic coefficient matrix is ​​performed to obtain a bridge support stiffness attenuation curve; Based on the bridge support stiffness attenuation curve, a buckling stability analysis is performed on the bridge support structure to obtain a critical load value of the bridge support structure, and based on the critical load value of the bridge support structure, a bearing capacity calculation is performed through elastic-plastic mechanics to obtain a bridge support strength margin diagram; Performing cumulative damage calculation on the bridge support strength margin diagram through finite element fatigue analysis to obtain a bridge support structure damage state quantity, and performing structural reliability assessment based on the bridge support structure damage state quantity to obtain a bridge support failure probability distribution; A life cycle analysis is performed on the bridge support structure based on the bridge support failure probability distribution to obtain a remaining life estimate of the bridge support structure, and degradation assessment data of the bridge support structure is evaluated based on the remaining life estimate.

[0011] Furthermore, the performing of a life cycle analysis on the bridge support structure based on the bridge support failure probability distribution to obtain an estimated remaining life of the bridge support structure includes: The failure criterion analysis of the bridge support failure probability distribution is performed using damage accumulation theory to obtain a support component damage evolution curve, and critical failure points in the support component damage evolution curve are identified to obtain a critical failure state set of the bridge support structure, wherein the critical failure state set includes a crack growth critical value, a material strength attenuation rate, and a structural deformation limit; Performing a stress history analysis on the bridge support structure based on the failure critical state set to obtain a stress spectrum function of the bridge support structure, and performing cyclic load statistics on the stress spectrum function of the bridge support structure using a rain flow counting technique to obtain a fatigue damage spectrum of the bridge support structure; Analyzing crack propagation of the bridge support structure based on a fatigue damage spectrum of the bridge support structure to obtain a crack propagation rate curve, and performing fracture mechanics calculation based on the crack propagation rate curve to obtain a life prediction diagram of the bridge support structure; A reliability analysis is performed on the life prediction diagram to obtain a reliability curve, and the estimated remaining life of the bridge support structure is evaluated based on the reliability curve using a preset probabilistic statistical technique, wherein the estimated remaining life of the bridge support structure includes the structural failure time, the maintenance and replacement cycle, and the safe operation range.

[0012] Furthermore, the crack growth of the bridge support structure is analyzed based on the fatigue damage spectrum of the bridge support structure to obtain a crack growth rate curve, including: Calculating the crack tip stress field distribution of the bridge support structure based on the fatigue damage spectrum of the bridge support structure, and performing plastic zone correction based on the crack tip stress field distribution to obtain a crack propagation driving force sequence; Calibrate fatigue crack growth parameters of the bridge support structure based on the crack growth driving force sequence to obtain a material fatigue constant matrix, and perform stress ratio effect analysis on the material fatigue constant matrix to obtain a crack growth threshold curve; Predicting a crack propagation path based on the crack propagation threshold curve using fracture mechanics criteria, and performing crack tip strain field analysis based on the crack propagation path to obtain a crack propagation velocity field, wherein the crack propagation velocity field includes a crack propagation direction angle, a propagation rate gradient, and a critical propagation length; Based on the crack propagation velocity field, the crack propagation integration of the bridge support structure is performed to obtain the crack length increment distribution, and based on the crack length increment distribution, a periodic accumulation calculation is performed to obtain a crack propagation rate curve; wherein, the crack propagation rate curve includes a crack propagation acceleration period, a stable propagation interval and a rapid propagation critical point.

[0013] The present invention also provides a cable tray fault diagnosis device based on a sensor network, comprising: A monitoring module is used to monitor the vibration of the cable bridge through a piezoelectric sensor array arranged at key nodes of the cable bridge to obtain dynamic response data of the bridge structure; A segmentation module is used to segment the dynamic response data of the bridge structure into time windows and identify abnormalities to obtain a bridge abnormal vibration period identification sequence, wherein the bridge abnormal vibration period identification sequence includes the moment of amplitude mutation, continuous vibration duration, and vibration attenuation period; A tracking module, configured to track the vibration propagation path of the cable tray based on the abnormal vibration period identification sequence of the cable tray to obtain a fault source area; A calculation module, configured to calculate the structural stress concentration of the cable tray based on the fault source area to obtain a distribution map of weak links of the cable tray; A determination module is used to determine the fault level of the cable tray based on the distribution map of weak links in the tray, obtain the fault level, and obtain a maintenance decision suggestion for the tray based on the fault level, including an emergency repair location, preventive replacement parts, and reinforcement plan.

[0014] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0015] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0016] The present invention provides a cable tray fault diagnosis method based on a sensor network, comprising the following steps: performing vibration monitoring on the cable tray to obtain dynamic response data of the tray structure; performing time window segmentation and abnormality identification on the dynamic response data of the tray structure to obtain a tray abnormal vibration period identification sequence; tracing the vibration propagation path of the cable tray based on the tray abnormal vibration period identification sequence to obtain a fault source area; calculating the structural stress concentration of the cable tray based on the fault source area to obtain a tray weak link distribution map; determining the fault level of the cable tray based on the tray weak link distribution map to obtain a fault level, and obtaining tray maintenance decision recommendations based on the fault level. The method solves the technical problem that most solutions still remain at the static parameter acquisition stage, lack an effective analysis mechanism for dynamic vibration response, and are difficult to accurately identify the occurrence location and evolution trend of abnormal tray behavior. The method realizes the generation of a tray weak link distribution map by calculating the stress concentration of the fault source mapping area, achieving a transition from qualitative judgment to quantitative analysis, and providing a scientific basis for subsequent maintenance decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 1 is a schematic diagram of the steps of a cable tray fault diagnosis method based on a sensor network in one embodiment of the present invention; Figure 2 This is a structural block diagram of a cable tray fault diagnosis device based on a sensor network in one embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0018] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] like Figure 1 As shown, Figure 1 A cable tray fault diagnosis method based on a sensor network in one embodiment of the present invention includes the following steps: Step S1: Vibration monitoring of the cable bridge is performed by using a piezoelectric sensor array arranged at key nodes of the cable bridge to obtain dynamic response data of the bridge structure.

[0021] Specifically, the vibration of the cable bridge is monitored by placing a piezoelectric sensor array at the key nodes of the cable bridge to obtain the dynamic response data of the bridge structure. This step aims to use the piezoelectric sensor array to collect and record the structural vibration caused by external excitations (such as wind load, mechanical vibration, electromagnetic force, etc.) to the cable bridge during operation in real time, so as to obtain its dynamic response characteristics. Piezoelectric sensors are widely deployed at key stress nodes, connection points and areas with large suspended spans of cable bridges due to their high sensitivity, wide frequency response range and good environmental adaptability. These locations are often potential weak points of the structure that are easily damaged or stress concentrated. By distributing multiple piezoelectric sensors in the form of an array at the above-mentioned key nodes, multi-channel synchronous collection of vibration signals of the bridge at different spatial positions can be achieved, thereby constructing a structural dynamic response data set with spatiotemporal characteristics. For example, in industrial plants, cable trays usually carry a large number of cables and span a large space. When the local structural stiffness of the cable tray changes due to long-term uneven load or loose connections, the piezoelectric sensor array can capture the tiny vibration differences caused by structural abnormalities and convert them into electrical signal outputs for subsequent analysis modules to perform time window segmentation processing, thereby identifying key parameters such as the moment of amplitude mutation, continuous vibration duration, and vibration attenuation period, providing a data basis for subsequent fault source location and weak link identification.

[0022] Step S2, performing time window segmentation and abnormality identification on the dynamic response data of the bridge structure to obtain a bridge abnormal vibration period identification sequence, wherein the bridge abnormal vibration period identification sequence includes the amplitude mutation time point, continuous vibration duration, and vibration attenuation period.

[0023] Specifically, the time-window segmentation and anomaly identification of the cable tray structure's dynamic response data aims to identify time periods with structural anomalies from the continuous vibration signals collected by the piezoelectric sensor array. A systematic analysis process then extracts a sequence of engineering-significant abnormal vibration periods. This sequence not only includes time-domain characteristic parameters such as the moment of amplitude mutation, duration of vibration, and vibration decay period, but also classifies and labels these characteristics as changes in structural health through the anomaly identification process, thereby achieving refined perception of the cable tray's operating status. In its implementation, the system first uses adaptive sliding window technology to perform time-domain segmentation on the cable tray structure's dynamic response data, dividing the raw signal into multiple time window sequences. Each window is typically set to 5-10 seconds in length, with a certain overlap (e.g., 50%) to ensure that short-duration, high-frequency vibration events are not missed. The system then performs spectral analysis and time-domain statistics on the vibration signal within each time window, extracting characteristic parameters such as root mean square value (RMS), crest factor, and kurtosis. A dynamic threshold model is then established based on historical data from normal operating conditions. Based on this, the system performs an anomaly identification operation, comparing the characteristic parameters of the current window with a preset anomaly threshold. If the amplitude change in a window exceeds the threshold (for example, exceeding 2.5 standard deviations of the historical average), it is marked as a potential anomaly window and further analyzed for subsequent signal trends. By continuously monitoring the signal recovery, the system determines whether the abnormal vibration has a certain persistence (for example, the duration of the vibration reaches 4.3 seconds) and calculates its energy decay period (for example, the time required for the peak value to drop to 90% of the initial value is 2.8 seconds). Ultimately, the system integrates this information into a sequence of abnormal bridge vibration period identifiers. Each entry contains the time of the amplitude change (for example, 10:23:17 on June 1, 2025), the duration of the vibration (for example, 4.3 seconds), and the vibration decay period (for example, 2.8 seconds). The anomaly identifier also indicates which abnormal mode the event belongs to (for example, loose connection anomaly or local resonance anomaly). For example, in an industrial plant, when a section of bridge bridge suffers a localized loss of stiffness due to loose bolts, it can produce significant nonlinear vibration responses when subjected to external excitations (such as equipment startup and shutdown). The system then processes the structural dynamic response data through time window segmentation. Combined with an anomaly identification mechanism, it accurately identifies the specific occurrence time, duration, and attenuation characteristics of the abnormal event, recording it as a typical entry in the bridge bridge abnormal vibration period identification sequence, providing precise data support for subsequent fault source location and vulnerability assessment.

[0024] Step S3: tracing the vibration propagation path of the cable tray based on the abnormal vibration period identification sequence of the cable tray to obtain the fault source area.

[0025] Specifically, the vibration propagation path of the cable tray is tracked based on the abnormal vibration time period sequence. This is done to identify the initial excitation source causing the abnormal vibration by analyzing the time difference and propagation characteristics of vibration events between different key nodes, thereby obtaining a fault source mapping area. This step fully utilizes information such as the amplitude mutation moment, duration of sustained vibration, and vibration decay period extracted from the abnormal vibration time period sequence of the cable tray in the previous step. Combined with the spatial topological relationship of the piezoelectric sensor array on the cable tray, this step constructs a time series model of the structural vibration propagation between different nodes. By comparing the response time sequence of each sensor node and the vibration intensity change trend during the same abnormal event, the system utilizes the Time Difference of Arrival (TDOA) algorithm or finite element simulation-assisted inversion technology to deduce the propagation path of the vibration energy within the cable tray structure. Based on this, the system can reversely trace the path to the most likely starting excitation point, which is the fault source mapping area. For example, in an industrial plant, if a section of a bridge has a local stiffness difference due to loose connections, when external vibration excitation acts on this area, it will trigger a nonlinear vibration response and propagate around the bridge structure. At this time, each piezoelectric sensor will capture the abnormal vibration signal in turn. The system can accurately identify the area where the vibration first occurs by performing spatiotemporal correlation analysis on the bridge abnormal vibration period identification sequence corresponding to these signals, and then lock in the potential structural fault source area, providing a spatial positioning basis for subsequent weak link assessment.

[0026] Step S4: calculating the structural stress concentration of the cable tray based on the fault source area to obtain a distribution map of weak links of the cable tray.

[0027] Specifically, the calculation of the structural stress concentration of the cable tray based on the fault source mapping area is to further analyze the stress state of the bridge structure in the area from a mechanical perspective on the basis of the known starting area of ​​abnormal vibration propagation, identify possible local strength weaknesses, and thus construct a distribution map of weak links in the bridge. This step combines the spatial position information of the fault source mapping area with the structural geometric model of the cable tray, and combines finite element simulation technology or structural mechanics analysis methods to simulate the stress distribution in the area under known external excitation, and focus on identifying areas with higher stress concentration coefficients, which usually correspond to potential risk points such as structural mutations, missing connectors or material fatigue. The system visualizes the stress concentration values ​​of each key node according to the spatial topological relationship, and finally forms a distribution map of weak links in the bridge with spatial indicative significance, providing a quantitative basis for subsequent fault level determination. For example, in an industrial plant, when the local stiffness of a certain section of bridge is reduced due to loose bolts or cracked welds, the area will produce obvious stress redistribution after being excited by vibration. The system calculates the structural stress concentration of the fault source mapping area and can identify specific locations with high stress concentration, such as beam connections or near bracket support points, and then marks these locations as high-risk areas in the bridge weak link distribution map, providing maintenance personnel with accurate repair and reinforcement references.

[0028] Step S5, based on the weak link distribution map of the cable tray, the fault level of the cable tray is determined to obtain the fault level, and based on the fault level, a cable tray maintenance decision suggestion is obtained, which includes an emergency repair location, preventive replacement parts, and reinforcement plan.

[0029] Specifically, the fault level assessment for the cable tray based on the weak link distribution map is designed to convert the spatial distribution information of structural stress concentration areas into a fault risk level with engineering guidance, thereby generating corresponding maintenance decision recommendations. This step comprehensively evaluates the stress concentration level, crack growth trend, and load-bearing capacity degradation at key locations in the weak link distribution map. Combined with pre-defined fault classification criteria (such as stress concentration factor, fatigue damage value, and failure probability), the cable tray structure is classified into different fault levels, such as low risk, medium risk, and high risk. In practice, the system first determines whether the stress concentration factor of each point in the weak link distribution map exceeds a certain percentage threshold of the material yield strength (e.g., 80%). If the maximum principal stress at a point reaches 280 MPa, while the material yield strength is 350 MPa, the stress level at that point accounts for 80%, marking it as a high-risk point. The system then further refines the fault level by combining factors such as the crack growth rate and remaining life prediction results at that point. For cable tray support nodes identified as high-risk, the system includes them in a list of emergency repair locations. For components at medium risk but still capable of carrying a certain load, it recommends inclusion in a preventive replacement plan or regular monitoring. For areas where local stiffness has decreased but has not reached a critical state, reinforcement solutions are recommended, such as adding supports or local welding reinforcement. For example, in an industrial plant, when a section of cable tray experiences local stress concentration and the initiation of microcracks due to loose bolts at the connection flange, the system identifies this area as a high-risk weak point through the cable tray's weak link distribution map and determines its fault level to be "serious." It then automatically generates a cable tray maintenance decision recommendation: the flange connection is listed as an emergency repair location, and it is recommended that the system be shut down for inspection and repair immediately. The area should be reinforced with welding, and adjacent support structures should be prevented from being replaced to prevent cascading failures. This process achieves closed-loop management from structural status perception to operation and maintenance strategy output, improving the safety and maintenance efficiency of cable tray operation.

[0030] In a specific embodiment, the time window segmentation and abnormality identification of the bridge structure dynamic response data to obtain a bridge abnormal vibration period identification sequence includes the following steps: Performing time domain segmentation on the dynamic response data of the bridge structure by using an adaptive sliding window technology to obtain multiple time window sequences, and performing frequency domain decomposition on the dynamic response data of the bridge structure based on the time window sequences to obtain a time-frequency feature matrix; Performing singular spectrum analysis on the dynamic response data of the bridge structure based on the time-frequency characteristic matrix to obtain a bridge vibration modal sequence, and extracting nonlinear features in the bridge vibration modal sequence through Hilbert-Huang transform to obtain bridge vibration nonlinear features; Based on a preset bridge frame abnormal vibration discrimination threshold, detecting whether there is an abnormality in the nonlinear characteristics of the bridge frame vibration, and if so, obtaining a preliminary abnormal vibration period candidate set; Based on the preliminary abnormal vibration period candidate set, wavelet packet entropy analysis is performed on the dynamic response data of the bridge structure to obtain a multi-scale entropy value sequence, and the abnormality degree of the multi-scale entropy value sequence is identified by fuzzy c-means clustering to obtain a bridge abnormal vibration period identification sequence, wherein the bridge abnormal vibration period identification sequence includes the amplitude mutation time point, continuous vibration duration, and vibration attenuation period.

[0031] Specifically, the time-window segmentation and anomaly identification of the bridge structure dynamic response data to obtain a sequence of abnormal bridge vibration period identifiers is a critical link in the entire cable tray fault diagnosis process. This step aims to identify engineering-significant abnormal vibration events by performing refined time-frequency analysis and feature extraction on the bridge structure dynamic response data collected by the piezoelectric sensor array. These events are then concretized in the form of a sequence of abnormal bridge vibration period identifiers, including key information such as the anomaly timestamp, duration, and severity index. This provides an accurate temporal and spatial location basis for subsequent vibration propagation path tracking. In actual implementation, the system first uses adaptive sliding window technology to perform time-domain segmentation on the continuously collected bridge structure dynamic response data. By setting a reasonable window length (e.g., 10 seconds per segment) and overlap ratio (e.g., 50%), the original signal is divided into multiple time window sequences. This design not only captures transient vibration behavior but also accounts for long-term trend changes. The vibration data within each time window is then converted to the frequency domain for analysis. Using fast Fourier transforms (FFTs) or other spectral analysis methods, a corresponding time-frequency feature matrix is ​​generated, revealing the energy distribution of the vibration signal across different frequency components. This step helps identify potential non-stationary characteristics in the structural response. Based on this, the system performs singular spectrum analysis (SSA) on the obtained time-frequency feature matrix to extract the characteristics of the bridge structure under different vibration modes, generating a bridge vibration modal sequence. This modal sequence reflects the primary vibration modes that the structure may exhibit under different excitation conditions, such as low-frequency oscillations and high-frequency local resonances. To further characterize the nonlinear behavior in the vibration signal, the system further processes the bridge vibration modal sequence using the Hilbert-Huang Transform (HHT) to extract the inherent nonlinear features, such as transient frequency fluctuations and increased energy fluctuations. The resulting nonlinear features are then output. Next, the system detects these nonlinear features based on a preset threshold for abnormal bridge vibration, determining whether they deviate from normal operation. If a characteristic parameter within a certain time window exceeds a set threshold (for example, the energy density in a certain frequency band exceeds three standard deviations of the historical mean), the time period is marked as a preliminary abnormal vibration period candidate set. This process ensures that the system can sensitively identify potential abnormal behavior while avoiding excessive false positives that affect the efficiency of subsequent analysis. To further quantify the actual severity of these candidate abnormal events, the system performs wavelet packet entropy analysis on the dynamic response data of the bridge structure corresponding to the preliminary abnormal vibration period candidate set, calculates its entropy values ​​at different scales, and generates a multi-scale entropy value sequence. The higher the entropy value, the greater the complexity and uncertainty of the vibration signal within the period, which generally corresponds to a more severe structural anomaly.Finally, the system uses the Fuzzy C-Means Clustering (FCM) algorithm to classify the multi-scale entropy value sequence. Based on the clustering results of the entropy distribution, each abnormal event is classified into a certain level. The system then outputs a sequence of abnormal bridge vibration period identifiers, including the specific abnormal timestamp (e.g., 14:32:15, May 28, 2025), the duration of the abnormality (e.g., 7.2 seconds), and the abnormality severity index (e.g., a normalized entropy value of 0.87 indicates a high abnormality). For example, in industrial plants, cable trays often carry a large number of high-voltage cables and span multiple floors. When a section of the cable tray suffers a localized loss of stiffness due to loose bolts, it can produce significant nonlinear vibration responses when subjected to external excitation (e.g., equipment startup or wind loads). In this case, the dynamic response data of the cable tray structure collected by the piezoelectric sensor array will exhibit sudden increases in amplitude, shifts in spectral energy distribution, and transient frequency instability. Through the aforementioned series of processing steps, the system first uses an adaptive sliding window to segment the data. It then extracts the time-frequency feature matrix and performs singular spectrum analysis to identify changes in the main vibration modes. The Hilbert-Huang transform then extracts nonlinear features, identifying a significant energy fluctuation near a certain point in time that exceeds a preset anomaly threshold, thus entering a preliminary set of candidate abnormal vibration periods. Subsequent wavelet packet entropy analysis reveals that the entropy value of this period reaches 0.91, indicating highly complex and unpredictable vibration behavior. Fuzzy c-means clustering further confirms this as a high-level anomaly, ultimately marking it as a typical event in the bridge abnormal vibration period identification sequence: the anomaly timestamp is 14:32:15 on May 28, 2025, the duration is 6.8 seconds, and the anomaly severity index is 0.91. This result not only provides a precise starting point for subsequent vibration propagation path tracing but also provides a scientific basis for timely intervention and maintenance strategy development by maintenance personnel. In summary, this step achieves efficient identification and quantitative description of structural abnormal events from raw vibration data by introducing a variety of advanced signal processing and data analysis technologies, fully demonstrating the advancement and practicality of this method in intelligent fault diagnosis.

[0032] In a specific embodiment, the step of tracing the vibration propagation path of the cable tray based on the abnormal vibration period identification sequence of the cable tray to obtain the fault source area includes: Based on the abnormal vibration period identification sequence of the bridge frame, time difference estimation is performed on the dynamic response data of the bridge frame structure to obtain a vibration wave arrival time difference matrix, and cross-correlation function peak detection is performed on the vibration wave arrival time difference matrix to obtain a vibration propagation delay sequence; Based on the vibration propagation delay sequence, the cable tray is subjected to wave velocity field modeling to obtain a wave velocity distribution diagram of the cable tray structure; and based on the wave velocity distribution diagram of the cable tray structure, the vibration propagation delay sequence is subjected to wave front trajectory reconstruction to obtain a vibration wave front propagation trajectory; Based on the vibration wavefront propagation trajectory, analyzing the vibration energy attenuation degree in the dynamic response data of the bridge structure, generating a vibration energy gradient field, and calculating the vibration energy convergence point in the vibration energy gradient field; The fault area of ​​the cable tray is mapped based on the vibration energy convergence point to obtain the fault source area.

[0033] Specifically, tracing the vibration propagation path of the cable tray based on the abnormal vibration time period identification sequence to determine the fault source region is the core step in the entire cable tray fault diagnosis method for fault location and spatial tracing. This step aims to construct a vibration propagation model from the onset of the abnormal vibration event to the structural response by analyzing the dynamic response data of the bridge structure collected by multiple piezoelectric sensor nodes at key locations on the bridge structure, combining information such as time synchronization, time difference of arrival, and energy propagation path. Ultimately, it locates the spatial region where the initial excitation source causing the abnormal behavior is located—i.e., the fault source region.

[0034] In its implementation, the system first uses the abnormal timestamps, durations, and severity indexes in the abnormal vibration period sequence to identify representative vibration events and extract the corresponding dynamic response data of the cable tray structure as the basis for subsequent analysis. Because the piezoelectric sensor array is deployed at key stress points and connections on the cable tray, different nodes generate vibration response signals with time differences when subjected to the same external stimulus (such as mechanical shock or resonance caused by local loosening). The system then estimates the time differences between these signals and calculates the arrival time differences of the vibration waves between each sensor node, forming a vibration arrival time difference matrix. For example, in a specific abnormal vibration event, a sensor at end A of the cable tray records the onset of the abnormal vibration at 14:32:15, while a sensor at end B, 10 meters away, records the same vibration event at 14:32:16.2. This indicates a vibration arrival time difference of 1.2 seconds. The system then performs cross-correlation function peak detection on the obtained vibration time difference arrival matrix to more accurately identify the moments of strongest correlation between vibration signals between different sensor nodes. This further confirms the actual propagation delay of the vibration wave and generates a vibration propagation delay sequence. This process helps eliminate the influence of noise interference and non-structural propagation paths, ensuring the accuracy of subsequent modeling. For example, if the cross-correlation function between nodes A and C reaches its maximum value at a lag of 1.8 seconds during a vibration event, it indicates that the vibration wave takes 1.8 seconds to propagate from A to C. Next, based on this vibration propagation delay sequence and incorporating the geometric parameters and material properties of the cable tray, the system constructs a wave velocity distribution map for the cable tray structure. This map reflects the variations in vibration wave propagation velocity across different regions of the cable tray structure. Typically, regions with uniform metal material and intact structures exhibit higher wave velocities (e.g., approximately 3000 m / s), while regions with defects such as cracks, corrosion, or loose connections exhibit decreased wave velocities (e.g., below 2500 m / s). By comparing the actual propagation delays between nodes with the theoretical wave velocities, potential abnormalities within the structure can be identified. On this basis, the system further reconstructs the wavefront trajectory of the vibration propagation delay sequence, simulates the propagation path of the vibration wave in the bridge structure, and generates a vibration wavefront propagation trajectory. This trajectory not only reflects the propagation direction of the vibration energy in space, but also reveals whether there are structural damping anomalies or energy reflection phenomena. For example, in one monitoring, it was found that the vibration wavefront of a certain section of the bridge showed obvious deflection and diffusion after passing through a certain connecting flange, which may mean that there is a problem of local stiffness reduction or loose connection in this area. In order to further determine the convergence trend of vibration energy, the system also analyzes the vibration energy attenuation in the dynamic response data of the bridge structure, and combines the amplitude change curve of the sensor node with the propagation path information to construct a vibration energy gradient field.This gradient field describes how vibration energy varies with spatial position. While energy intensity typically decays with distance from the excitation source, energy concentration may occur in certain localized areas. For example, the system detected that during an abnormal event on a cable tray section, the energy values ​​recorded by several sensor nodes near the middle support point were significantly higher than those of surrounding nodes, and the decay rate was significantly slower, indicating that this area may be a focal point for vibration energy. Finally, based on the generated vibration energy gradient field, the system identifies these focal points and maps them to the actual spatial coordinate system of the cable tray, ultimately determining the fault source area. For example, in an industrial plant, when cracking welds on a cable tray section reduces local structural stiffness, the vibration waves exhibit significant energy concentration in this area. Through the aforementioned process, the system identifies this area as a flange connection near the spatial coordinates (X=3.2m, Y=4.5m, Z=2.1m) and marks it as a high-risk fault source area for inspection and resolution by maintenance personnel. In summary, this step achieves the spatiotemporal tracing and fault location of abnormal vibration events in cable tray structures by integrating multiple technical means such as time difference estimation, wave velocity modeling, and energy gradient analysis. This not only improves the accuracy of fault identification but also provides solid data support for subsequent stress concentration assessment and maintenance decision-making, fully demonstrating the advanced nature and practicality of this method in intelligent structural health monitoring.

[0035] In a specific embodiment, the calculation of the structural stress concentration of the cable tray based on the fault source area to obtain a distribution map of weak links of the cable tray includes: Performing stress field calculation on the cable tray based on the fault source area to obtain a stress distribution matrix of the cable tray nodes, and performing stress gradient analysis on the stress distribution matrix of the cable tray nodes to obtain a stress concentration area diagram of the cable tray; Performing local structural analysis on the bridge stress concentration area map by finite element meshing to obtain the bridge local stress field distribution, and extracting singular feature points in the bridge local stress field distribution to obtain a bridge structure dangerous point sequence; Based on the bridge structure danger point sequence, a stiffness degradation analysis is performed on the bridge support structure in the cable bridge to obtain degradation assessment data of the bridge support structure, and fatigue life estimation is performed on the degradation assessment data of the bridge support structure using a stress intensity factor to obtain a fatigue damage map of the bridge structure, wherein the fatigue damage map of the bridge structure includes crack growth rate, number of stress cycles, and material strength degradation rate; Based on the fatigue damage map of the bridge structure, the load-bearing capacity of the bridge support structure is evaluated to obtain the load-bearing capacity result of the bridge structure, and based on the load-bearing capacity result of the bridge structure, the failure mode of the bridge support structure is identified to obtain the distribution map of the weak links of the bridge.

[0036] Specifically, the calculation of the structural stress concentration of the cable tray based on the fault source area to obtain a distribution map of weak links in the cable tray is a key step in achieving structural strength assessment and failure risk prediction in the entire cable tray fault diagnosis process. This step combines the spatial positioning information of the fault source area with structural mechanics analysis, and with the help of various technical means such as finite element simulation, stress gradient analysis, and fatigue life estimation, ultimately forms a distribution map of weak links in the cable tray with spatial resolution, providing a scientific basis for subsequent fault level determination and maintenance decisions. In the specific implementation process, the system first calculates the stress field of the cable tray based on the fault source area to obtain the stress state of the cable tray structure under abnormal vibration excitation. Since the fault source area usually corresponds to a location with an abnormally strong structural response, the system establishes a local finite element model on this basis, and combines the dynamic response data of the cable tray structure collected by the piezoelectric sensor to invert the stress distribution of the structure in different directions, thereby generating a stress distribution matrix for the cable tray node. For example, during one monitoring session, a flange connection (coordinates X=3.2m, Y=4.5m) was identified as the fault source. By modeling the stress values ​​of multiple nodes within this area, the system determined that the average maximum principal stress at each node reached 280 MPa, significantly higher than the 190 MPa in the surrounding area, indicating significant stress concentration. The system then performed stress gradient analysis on the resulting bridge node stress distribution matrix. By comparing the stress change rates between adjacent nodes, the system identified areas of high stress concentration and generated a bridge stress concentration map. This map displays the stress concentration coefficients at different locations within the bridge structure as a heat map, with darker colors indicating higher stress concentration. For example, near the flange connection, the system detected a stress gradient of 60 MPa per meter between two adjacent nodes, significantly higher than the approximately 10 MPa per meter in the normal structural area. This indicates a significant stress abrupt change in this area, making it a high potential starting point for structural damage. To further refine the analysis, the system uses finite element meshing to perform local structural modeling of the high stress concentration areas in the bridge stress concentration area diagram. Using a finer meshing method (such as reducing the unit size from the original 10cm to 2cm), the system conducts refined simulation analysis of the local area, thereby obtaining a more accurate distribution of the local stress field of the bridge. On this basis, the system extracts singular feature points, that is, locations with extremely high stress values ​​or drastically changing stress gradients, to form a sequence of dangerous points in the bridge structure. For example, in one analysis, the system identified three consecutive stress peak points at the edge of the flange connection bolt hole, with maximum principal stresses reaching 310MPa, 325MPa, and 338MPa, respectively, and arranged linearly, indicating a possible crack initiation trend.Next, the system performs a stiffness degradation analysis on the cable tray support structure based on the sequence of critical points in the cable tray structure. This analysis compares the stiffness parameters between the structure's normal and current states to assess whether the support structure has degraded due to long-term loads. For example, a section of cable tray was originally designed for a stiffness of 120 kN / mm. After multiple abnormal vibration events, its current stiffness was measured to be only 90 kN / mm, a 25% decrease. This indicates that the support structure in this area has experienced a certain degree of stiffness degradation, impacting its overall load-bearing capacity. To further assess the structural lifespan of this area, the system introduces the concept of stress intensity factors (SIFs) to estimate fatigue life based on the degradation assessment data of the cable tray support structure, thereby generating a fatigue damage map for the cable tray structure. This map includes not only the crack growth rate (e.g., 0.05 mm / 1,000 cycles) and the number of stress cycles (e.g., cumulative vibration cycles exceeding 100,000) for each region, but also records the material strength degradation rate (e.g., the yield strength has dropped from the original design of 350 MPa to the current 290 MPa). For example, at the crossbeam connection of a certain bridge section, the system simulated and found that the crack growth rate in this area was approximately 0.03mm / thousand cycles. If calculated based on the current vibration frequency, the crack length is expected to increase by approximately 9mm within six months, reaching the critical failure size. Finally, the system assesses the load-bearing capacity of the bridge support structure based on the fatigue damage map of the bridge structure. This involves comprehensively considering factors such as the current structure's residual strength and the integrity of the load transfer path to determine whether it still meets safe operation requirements. Based on the assessment results, the system further performs failure mode identification, identifying possible structural failure modes such as fracture, instability, and disengagement, and generates a distribution map of the bridge's weak links. For example, in one assessment, the load-bearing capacity assessment results of a certain bridge support arm showed that its ultimate load-bearing capacity had dropped from the designed value of 80kN to 60kN, a 25% decrease. The system also identified shear failure as the primary failure mode, thus marking it as a high-risk weak link and placing it on the priority repair list. In summary, this step realizes a closed-loop analysis of the entire process from fault source location to structural strength assessment by integrating various analytical methods such as structural mechanics modeling, finite element simulation, fatigue life estimation and load-bearing capacity assessment. It can not only accurately identify stress concentration areas in the bridge structure, but also quantitatively predict its potential failure risks, providing solid technical support for the intelligent operation and maintenance of power facilities. For example, in an industrial plant, when a section of the bridge causes local stress concentration due to loose connectors, the system can identify the specific dangerous point location through the above process, and predict its crack propagation trend and load-bearing capacity changes, and finally mark it as a key monitoring area in the distribution map of weak links in the bridge, providing a scientific basis for maintenance personnel to formulate targeted reinforcement, replacement or repair measures.

[0037] In a specific embodiment, the stiffness degradation analysis of the bridge support structure in the cable tray is performed based on the bridge structure dangerous point sequence to obtain degradation assessment data of the bridge support structure, including: By means of nonlinear dynamics, the stiffness of the bridge support structure in the cable bridge is calculated based on the dangerous point sequence of the bridge structure, and a bridge support point elastic coefficient matrix is ​​obtained. A dynamic response analysis of the bridge support point elastic coefficient matrix is ​​performed to obtain a bridge support stiffness attenuation curve; Based on the bridge support stiffness attenuation curve, a buckling stability analysis is performed on the bridge support structure to obtain a critical load value of the bridge support structure, and based on the critical load value of the bridge support structure, a bearing capacity calculation is performed through elastic-plastic mechanics to obtain a bridge support strength margin diagram; Performing cumulative damage calculation on the bridge support strength margin diagram through finite element fatigue analysis to obtain a bridge support structure damage state quantity, and performing structural reliability assessment based on the bridge support structure damage state quantity to obtain a bridge support failure probability distribution; A life cycle analysis is performed on the bridge support structure based on the bridge support failure probability distribution to obtain a remaining life estimate of the bridge support structure, and degradation assessment data of the bridge support structure is evaluated based on the remaining life estimate.

[0038] Specifically, the stiffness degradation analysis of the bridge support structure in the cable bridge based on the bridge structure dangerous point sequence is performed to obtain the degradation assessment data of the bridge support structure, which is an important step in achieving the quantitative assessment of the health status of the cable bridge structure. This step systematically reveals the performance evolution law of the bridge support structure under long-term vibration excitation by integrating multidisciplinary methods such as nonlinear dynamics, elastic-plastic mechanics, finite element fatigue analysis and reliability engineering, and finally outputs structural degradation assessment results with predictive significance, providing a scientific basis for subsequent maintenance strategies. In the specific implementation process, the system first uses nonlinear dynamics methods, combined with key node information extracted from the bridge structure dangerous point sequence, to model the elastic response characteristics of the bridge support structure and calculate the elastic coefficient matrix of each support point. This matrix reflects the local stiffness performance of different support points under dynamic loads. For example, during a monitoring session, three high stress concentration points (i.e., critical points in the bridge structure) were identified near a bridge flange connection. By fitting the vibration displacement-force response curves at these locations, the system determined their corresponding elastic moduli to be 0.85 kN / mm, 0.76 kN / mm, and 0.69 kN / mm, respectively. These values ​​are significantly lower than the normal range of 1.2 kN / mm, indicating a significant decrease in stiffness at these locations. Based on this, the system then performs a dynamic response analysis on the elastic moduli matrix of the bridge support points, simulating the bridge structure's behavior under typical external excitations (such as wind vibration and equipment operation vibration). This generates a bridge support stiffness degradation curve. This curve, plotted with time on the horizontal axis and support stiffness on the vertical axis, illustrates the stiffness degradation trend of the support structure over time. For example, over the past six months, the stiffness of a particular bridge support point has gradually decreased from an initial value of 1.2 kN / mm to the current value of 0.7 kN / mm, with an average monthly decrease of approximately 0.083 kN / mm, indicating a continuous deterioration in its structural performance. Subsequently, based on the above-mentioned bridge support stiffness attenuation curve, the system further conducted a buckling stability analysis on the bridge support structure to determine whether it is likely to suffer instability failure when subjected to the ultimate load. Through finite element simulation technology, the system calculates the critical load value of the support structure in its current state, that is, the maximum external force that the structure can withstand before buckling. For example, the original design critical load was 45 kN, but the current critical load after stiffness degradation is only 32 kN, a decrease of 29%, indicating that the bearing capacity of the structure has decreased significantly. In order to further evaluate the safety margin of the structure, the system introduced an elastic-plastic mechanics model, calculated the bearing capacity based on the critical load value of the bridge support structure, and generated a bridge support strength margin diagram. The map shows the proportion of additional load that each support point can still withstand in the current state in the form of spatial distribution.For example, if the design bearing capacity of a support point is 50 kN and the current maximum bearing capacity is 38 kN, its strength margin is (50 - 38) / 50 × 100% = 24%, indicating a 24% safety margin at this point, but still relatively low and requiring attention. Next, the system uses finite element fatigue analysis to calculate the cumulative damage of the bridge support strength margin diagram. This considers the fatigue effects of the structure under periodic vibration excitation and assesses the extent of microcrack initiation and propagation within the material, ultimately generating a damage state quantity for the bridge support structure. For example, after experiencing 100,000 cumulative vibration cycles, the damage state quantity of a certain support structure reaches 0.68 (a full value of 1 indicates complete failure), indicating that the structure has entered the mid-stage of fatigue damage. Based on this damage state quantity, the system further performs a structural reliability assessment. Using methods such as Monte Carlo simulation, the system calculates the probability of failure of the bridge support structure within a certain period of time and generates a bridge support failure probability distribution. For example, for a key support point, the system simulated its failure probability within the next year under different operating conditions. The results showed a 12.3% failure probability, far exceeding the generally permitted safety threshold of 5%, indicating a high risk of failure. Finally, based on the bridge support failure probability distribution, the system conducted a lifecycle analysis of the bridge support structure, estimating its remaining useful life by comprehensively considering its current damage state, load history, and environmental factors. This yielded an estimated remaining useful life for the bridge support structure. For example, a support structure is expected to maintain stable operation for 14 months in its current state before entering a high-risk failure period. Therefore, replacement or reinforcement is recommended within 12 months. In summary, this step constructs a comprehensive bridge support structure degradation assessment system through a combination of nonlinear dynamic modeling, stiffness decay analysis, buckling stability assessment, strength margin calculation, fatigue damage simulation, and failure probability prediction. This system not only accurately reflects the current mechanical state of the support structure but also provides a scientific forecast of its future performance evolution. For example, in an industrial plant, when the local stiffness of a certain section of bridge is reduced due to loose connection bolts, the system can identify characteristics such as the decrease in the elastic coefficient of the support point, the decrease in critical load, and the reduction in strength margin through the above process, and estimate its remaining life and failure probability based on this. Ultimately, it will be marked as a high-risk object in the degradation assessment data of the bridge support structure, providing clear data support for operation and maintenance personnel to formulate preventive maintenance or structural reinforcement plans.

[0039] In a specific embodiment, performing a life cycle analysis on the bridge support structure based on the bridge support failure probability distribution to obtain an estimated remaining life of the bridge support structure includes: The failure criterion analysis of the bridge support failure probability distribution is performed using damage accumulation theory to obtain a support component damage evolution curve, and critical failure points in the support component damage evolution curve are identified to obtain a critical failure state set of the bridge support structure, wherein the critical failure state set includes a crack growth critical value, a material strength attenuation rate, and a structural deformation limit; Performing a stress history analysis on the bridge support structure based on the failure critical state set to obtain a stress spectrum function of the bridge support structure, and performing cyclic load statistics on the stress spectrum function of the bridge support structure using a rain flow counting technique to obtain a fatigue damage spectrum of the bridge support structure; Analyzing crack propagation of the bridge support structure based on a fatigue damage spectrum of the bridge support structure to obtain a crack propagation rate curve, and performing fracture mechanics calculation based on the crack propagation rate curve to obtain a life prediction diagram of the bridge support structure; A reliability analysis is performed on the life prediction diagram to obtain a reliability curve, and the estimated remaining life of the bridge support structure is evaluated based on the reliability curve using a preset probabilistic statistical technique, wherein the estimated remaining life of the bridge support structure includes the structural failure time, the maintenance and replacement cycle, and the safe operation range.

[0040] Specifically, the life cycle analysis of the cable tray support structure based on the cable tray support failure probability distribution is performed to obtain an estimated remaining life of the cable tray support structure. This is a key technical step in achieving structural life prediction and operation and maintenance decision support in cable tray fault diagnosis methods. This step systematically reveals the performance degradation process of the cable tray support structure under complex loads by integrating multi-dimensional assessment methods such as damage accumulation theory, fracture mechanics models, stress spectrum analysis, and reliability engineering. Ultimately, it outputs an estimated remaining life of the cable tray support structure with practical engineering value, including key parameters such as structural failure time, maintenance and replacement cycle, and safe operating range. In the specific implementation process, the system first models the historical load response data of the cable tray support structure using damage accumulation theory. Combined with the failure trend information in the cable tray support failure probability distribution, it analyzes the damage evolution behavior of the support components under long-term vibration excitation and generates a support component damage evolution curve. This curve, with time as the horizontal axis and the accumulated damage as the vertical axis, shows the entire process of the structure from its initial state to a state close to failure. For example, for a section of a bridge support structure, the system draws a damage evolution curve based on vibration monitoring data and fatigue analysis results from the past year. This curve shows that the structure's current cumulative damage is 0.62 (a full value of 1 indicates complete failure) and identifies the point at which it is about to enter a rapid damage phase. The system then further identifies critical failure points in the damage evolution curve—those turning points where the structure transitions from stable operation to a high-risk failure state—to construct a critical failure state set for the bridge support structure. This set includes several key indicators, such as the crack growth threshold (for example, a crack length exceeding 3 mm triggers rapid growth), material strength decay rate (for example, yield strength drops below 75% of the original design value), and structural deformation limit (for example, maximum deflection exceeds 80% of the allowable value). These parameters together form the basis for determining whether the support structure remains within the safe operating range. For example, the system detects that the crack length of a support point has reached 2.7 mm and is expected to exceed the critical value of 3 mm within the next two months, thus marking it as a high-risk critical state object. Next, based on the above-mentioned critical failure state set, the system conducts a stress history analysis on the bridge support structure, that is, reconstructs the dynamic stress change process experienced by the support structure through historical vibration data, and generates a stress spectrum function of the bridge support structure. This function describes the frequency and duration of different stress levels during the service life of the structure. For example, the system statistically concluded that the peak stress borne by a certain support structure in the past year was mainly concentrated between 200 and 250 MPa, accounting for 65% of the total number of stress cycles, while high stress events exceeding 280 MPa accounted for only 8%, but had a significant impact on structural fatigue. In order to further quantify the degree of fatigue damage, the system uses rain flow counting technology to process the stress spectrum function of the bridge support structure, extract the number of cycles under each stress level, and form a fatigue damage spectrum of the bridge support structure.For example, the system statistically determined that the support structure had undergone a total of 98,000 effective stress cycles over the past year, 12,000 of which exceeded the fatigue limit, indicating a high degree of fatigue damage. Based on this fatigue damage spectrum, the system analyzed the crack growth behavior of the bridge support structure and calculated the crack growth rate using a linear elastic fracture mechanics model, generating a crack growth rate curve. This curve reflects the growth trend of crack length with service time. For example, the system's simulation results showed that as the crack length increased from 2.5mm to 3.5mm, the growth rate increased from 0.02mm per day to 0.15mm per day, indicating that the structure is about to enter the accelerated failure stage. The system then performed fracture mechanics calculations based on this crack growth rate curve, taking into account material properties, loading conditions, and environmental factors, to predict the overall service life of the structure and generate a life prediction graph for the bridge support structure. This graph, with time as the horizontal axis and crack length or remaining life as the vertical axis, visually illustrates the life evolution trend of the structure. For example, the system predicts that the remaining life of a certain support structure is currently approximately 14 months. If no maintenance measures are taken, structural failure is expected in 16 months due to cracks penetrating the primary bearing surface. Finally, the system performs reliability analysis on this life prediction graph, using probabilistic statistical models such as the Weibull distribution or exponential distribution to assess the probability of failure within a specific future timeframe and generate a reliability curve. For example, the system analysis concludes that the failure probability of this support structure is 18.7% within the next 12 months, rising to 45.3% within the next 18 months, indicating a rapid decline in reliability. Based on this reliability curve, the system uses pre-defined probabilistic statistical techniques (such as confidence interval estimation and Monte Carlo simulation) to estimate the specific remaining life of the bridge support structure. This includes the structural failure time (e.g., expected failure date: August 2026), the maintenance and replacement period (e.g., reinforcement or replacement recommended by April 2026), and the safe operating range (e.g., the current structure can safely operate under existing conditions until June 2026). For example, in an industrial plant, when a section of bridge suffers a decrease in local stiffness and crack initiation due to loose connection bolts, the system can accurately identify the crack propagation trend, fatigue damage level, and failure probability through the above process. Based on this, it provides a clear estimate of the remaining life and maintenance window recommendations, providing strong support for operation and maintenance personnel to formulate scientific and reasonable maintenance plans. In summary, this step achieves an accurate estimation of the life of the bridge support structure through systematic damage modeling, stress spectrum analysis, crack propagation prediction, and reliability assessment. It not only reveals the degradation patterns of structural performance, but also provides a quantitative basis for the safe operation and intelligent maintenance of power facilities, fully demonstrating the advancement and practicality of this method in modern structural health monitoring and life management.

[0041] In a specific embodiment, analyzing the crack propagation of the bridge support structure based on the fatigue damage spectrum of the bridge support structure to obtain a crack propagation rate curve includes: Calculating the crack tip stress field distribution of the bridge support structure based on the fatigue damage spectrum of the bridge support structure, and performing plastic zone correction based on the crack tip stress field distribution to obtain a crack propagation driving force sequence; Calibrate fatigue crack growth parameters of the bridge support structure based on the crack growth driving force sequence to obtain a material fatigue constant matrix, and perform stress ratio effect analysis on the material fatigue constant matrix to obtain a crack growth threshold curve; Predicting a crack propagation path based on the crack propagation threshold curve using fracture mechanics criteria, and performing crack tip strain field analysis based on the crack propagation path to obtain a crack propagation velocity field, wherein the crack propagation velocity field includes a crack propagation direction angle, a propagation rate gradient, and a critical propagation length; Based on the crack propagation velocity field, the crack propagation integration of the bridge support structure is performed to obtain the crack length increment distribution, and based on the crack length increment distribution, a periodic accumulation calculation is performed to obtain a crack propagation rate curve; wherein, the crack propagation rate curve includes a crack propagation acceleration period, a stable propagation interval and a rapid propagation critical point.

[0042] Specifically, the crack propagation of the bridge support structure is analyzed based on the fatigue damage spectrum of the bridge support structure to obtain a crack propagation rate curve, which is the core technical link for realizing structural life prediction and failure evolution simulation in the cable bridge fault diagnosis process. This step systematically reveals the crack evolution process of the bridge support structure under complex loads by combining fracture mechanics, material fatigue properties and numerical simulation methods, and finally outputs a crack propagation rate curve with engineering significance, including key stages such as the crack propagation acceleration period, stable propagation interval and rapid propagation critical point. In the specific implementation process, the system first calculates the stress cycle characteristics experienced by the bridge support structure during its service based on the fatigue damage spectrum of the bridge support structure, and further derives the stress field distribution at the crack tip. This distribution describes the stress concentration state of the crack front area under different load conditions, and is the key basis for judging whether the crack has propagated. For example, in a certain section of a bridge support structure, the system inverted the maximum principal stress at the crack tip based on its vibration monitoring data over the past year and found that the average value was 280 MPa, with periodic fluctuations, and the maximum fluctuation amplitude reached ±35 MPa, indicating that the area was in a typical fatigue loading state. Subsequently, the system performed a plastic zone correction based on the above crack tip stress field distribution, that is, considering the influence of local plastic deformation of the material near the crack tip due to high stress concentration on the crack propagation behavior, thereby more accurately evaluating the crack propagation driving force. This correction process usually uses Neuber's law or finite element elastic-plastic analysis methods to convert elastic stress into actual crack propagation driving force, forming a crack propagation driving force sequence. For example, the system identified a support point with a crack length of 2.4 mm. After plastic correction, its crack propagation driving force increased from the original ΔK = 18 MPa·√m to ΔK = 21 MPa·√m, indicating that its crack propagation trend is increasing. Based on this crack propagation driving force sequence, the system calibrates fatigue crack growth parameters for the bridge support structure. Specifically, the system obtains the S-N curve and da / dN-ΔK relationship curve for the relevant material from experimental data or material manuals, and constructs a material fatigue constant matrix. This matrix includes key parameters such as the Paris zone slope m, threshold value ΔKth, and fracture toughness KIC. For example, for a bridge support structure made of Q235 steel, its material fatigue constant matrix shows a Paris slope m = 3.2, threshold value ΔKth = 15 MPa·√m, and fracture toughness KIC = 60 MPa·√m. To further improve model accuracy, the system analyzes the stress ratio effect of the material fatigue constant matrix. This analysis considers the influence of different stress ratios R (minimum stress / maximum stress) on crack propagation behavior, specifically correcting for crack closure effects, thereby generating a crack growth threshold curve.For example, when the stress ratio R increases from 0.1 to 0.5, the system detects that the crack propagation threshold ΔKth decreases from 15 MPa·√m to 12 MPa·√m, indicating that cracks are more likely to propagate under higher stress ratios. Next, the system uses fracture mechanics criteria (such as the maximum circumferential tensile stress criterion or the energy release rate criterion) to predict the crack propagation path based on the crack propagation threshold curve, simulating the propagation direction and morphological changes of the crack in the bridge support structure. Simultaneously, the system performs strain field analysis on the crack tip region, extracting strain gradient information during crack propagation and generating a crack propagation velocity field. This velocity field includes not only the crack propagation direction angle (e.g., a deviation of approximately 15° from the principal stress direction), the propagation rate gradient (e.g., an increase in the propagation rate of approximately 0.02 mm / cycle for each millimeter of crack length increase), but also the critical propagation length (e.g., the crack enters a rapid propagation phase after exceeding 4.5 mm in length). Finally, the system performs a crack growth integral on the bridge support structure based on the crack growth velocity field. This involves calculating the change in crack length after each load cycle through a cycle-by-cycle accumulation method, generating a crack length increment distribution. For example, in one simulation, the system calculated that the crack length grew from 2.0 mm to 4.0 mm over approximately 70,000 effective stress cycles. The first 30,000 cycles saw a relatively gentle growth rate (approximately 0.015 mm / cycle), while the subsequent 40,000 cycles saw a gradual increase in growth rate to over 0.035 mm / cycle due to increased stress concentration. Based on this crack length increment distribution, the system further performs cycle-by-cycle cumulative calculations to produce a complete crack growth rate curve. The curve clearly shows the three typical stages of crack propagation: the initial accelerated crack propagation period (e.g., when the crack length increases from 2.0 mm to 2.8 mm, the expansion rate increases from 0.01 mm / cycle to 0.02 mm / cycle), the mid-term stable expansion range (e.g., when the crack length increases from 2.8 mm to 3.8 mm, the expansion rate remains between 0.02 and 0.025 mm / cycle), and the late rapid expansion critical point (e.g., after the crack length exceeds 4.0 mm, the expansion rate rapidly rises to above 0.05 mm / cycle, entering the unstable expansion stage). For example, in an industrial plant, when a section of a bridge frame loses local stiffness due to loose connection bolts and cracks initiate, the system can identify the crack's initial position, expansion direction, and rate change pattern through the above process, and draw a crack propagation rate curve accordingly. For example, the system predicts that a crack will expand from its current size of 2.5mm to 4.2mm within the next nine months, entering a phase of rapid expansion. It recommends completing reinforcement or replacement within six months to avoid sudden structural failure. In summary, this step achieves full-process simulation and quantitative assessment of the crack growth behavior of the bridge support structure by integrating fracture mechanics modeling, fatigue parameter calibration, crack growth path prediction, and rate integral analysis.It can not only accurately predict the development trend of cracks, but also provide scientific data support for the safe operation and intelligent maintenance of power facilities, fully demonstrating the advancement and practicality of this method in modern structural health monitoring and life management.

[0043] The above describes the cable tray fault diagnosis method based on the sensor network in the embodiment of the present invention. The following describes the cable tray fault diagnosis device based on the sensor network in the embodiment of the present invention. Figure 2 In one embodiment of the present invention, a cable tray fault diagnosis device based on a sensor network includes: The monitoring module 21 is used to monitor the vibration of the cable bridge through a piezoelectric sensor array arranged at key nodes of the cable bridge to obtain dynamic response data of the bridge structure; The segmentation module 22 is used to segment the bridge structure dynamic response data into time windows and identify abnormalities to obtain a bridge abnormal vibration period identification sequence, wherein the bridge abnormal vibration period identification sequence includes the amplitude mutation time point, continuous vibration duration, and vibration attenuation period; A tracking module 23 is configured to track the vibration propagation path of the cable tray based on the abnormal vibration period identification sequence of the cable tray to obtain a fault source area; A calculation module 24 is configured to calculate the structural stress concentration of the cable tray based on the fault source area to obtain a distribution map of weak links of the cable tray; The judgment module 25 is used to judge the fault level of the cable tray based on the distribution map of weak links of the cable tray, obtain the fault level, and obtain a cable tray maintenance decision suggestion based on the fault level, including emergency repair location, preventive replacement parts, and reinforcement plan.

[0044] In this embodiment, for the specific implementation of each unit in the above device embodiment, please refer to the above method embodiment, which will not be repeated here.

[0045] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided, wherein the internal structure of the computer device can be as follows: Figure 3As shown. The computer device includes a processor, memory, display screen, input device, network interface and database connected via a system bus. The processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0046] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0047] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-described method when executed by a processor. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0048] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware using a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media provided herein and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM.

[0049] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, article, or method comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, apparatus, article, or method. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, apparatus, article, or method comprising the element.

[0050] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A cable tray fault diagnosis method based on a sensor network, characterized in that: The following steps are involved: Vibration monitoring of the cable bridge is performed by using a piezoelectric sensor array arranged at key nodes of the cable bridge to obtain dynamic response data of the bridge structure; The bridge structure dynamic response data is segmented into time windows and anomalies are marked to obtain a bridge abnormal vibration period identification sequence, wherein the bridge abnormal vibration period identification sequence includes a moment of amplitude mutation, a continuous vibration duration, and a vibration attenuation period; Tracing the vibration propagation path of the cable tray based on the abnormal vibration period identification sequence of the cable tray to obtain the fault source area; Calculating the structural stress concentration of the cable tray based on the fault source area to obtain a distribution map of weak links of the cable tray; The cable tray is subjected to a fault level determination based on the weak link distribution map of the cable tray to obtain a fault level, and a cable tray maintenance decision suggestion is obtained based on the fault level, wherein the cable tray maintenance decision suggestion includes an emergency repair location, preventive replacement components, and a reinforcement plan.

2. The cable tray fault diagnosis method based on sensor network according to claim 1 is characterized in that: The step of segmenting the bridge structure dynamic response data into time windows and marking anomalies to obtain an abnormal bridge vibration period identification sequence includes the following steps: Performing time domain segmentation on the dynamic response data of the bridge structure by using an adaptive sliding window technology to obtain multiple time window sequences, and performing frequency domain decomposition on the dynamic response data of the bridge structure based on the time window sequences to obtain a time-frequency feature matrix; Performing singular spectrum analysis on the dynamic response data of the bridge structure based on the time-frequency characteristic matrix to obtain a bridge vibration modal sequence, and extracting nonlinear features in the bridge vibration modal sequence through Hilbert-Huang transform to obtain bridge vibration nonlinear features; Based on a preset bridge frame abnormal vibration discrimination threshold, detecting whether there is an abnormality in the nonlinear characteristics of the bridge frame vibration, and if so, obtaining a preliminary abnormal vibration period candidate set; Based on the preliminary abnormal vibration period candidate set, wavelet packet entropy analysis is performed on the dynamic response data of the bridge structure to obtain a multi-scale entropy value sequence, and the abnormality degree of the multi-scale entropy value sequence is identified by fuzzy c-means clustering to obtain a bridge abnormal vibration period identification sequence, wherein the bridge abnormal vibration period identification sequence includes the amplitude mutation time point, continuous vibration duration, and vibration attenuation period.

3. The cable tray fault diagnosis method based on sensor network according to claim 1 is characterized in that: Tracing the vibration propagation path of the cable tray based on the abnormal vibration period identification sequence of the cable tray to obtain the fault source area includes: Based on the abnormal vibration period identification sequence of the bridge frame, time difference estimation is performed on the dynamic response data of the bridge frame structure to obtain a vibration wave arrival time difference matrix, and cross-correlation function peak detection is performed on the vibration wave arrival time difference matrix to obtain a vibration propagation delay sequence; Based on the vibration propagation delay sequence, the cable tray is subjected to wave velocity field modeling to obtain a wave velocity distribution diagram of the cable tray structure; and based on the wave velocity distribution diagram of the cable tray structure, the vibration propagation delay sequence is subjected to wave front trajectory reconstruction to obtain a vibration wave front propagation trajectory; Based on the vibration wavefront propagation trajectory, analyzing the vibration energy attenuation degree in the dynamic response data of the bridge structure, generating a vibration energy gradient field, and calculating the vibration energy convergence point in the vibration energy gradient field; The fault area of ​​the cable tray is mapped based on the vibration energy convergence point to obtain the fault source area.

4. The cable tray fault diagnosis method based on sensor network according to claim 1 is characterized in that: The calculation of the structural stress concentration of the cable tray based on the fault source area to obtain a distribution map of weak links of the cable tray includes: Performing stress field calculation on the cable tray based on the fault source area to obtain a stress distribution matrix of the cable tray nodes, and performing stress gradient analysis on the stress distribution matrix of the cable tray nodes to obtain a stress concentration area diagram of the cable tray; Performing local structural analysis on the bridge stress concentration area map by finite element meshing to obtain the bridge local stress field distribution, and extracting singular feature points in the bridge local stress field distribution to obtain a bridge structure dangerous point sequence; Based on the bridge structure danger point sequence, a stiffness degradation analysis is performed on the bridge support structure in the cable bridge to obtain degradation assessment data of the bridge support structure, and fatigue life estimation is performed on the degradation assessment data of the bridge support structure using a stress intensity factor to obtain a fatigue damage map of the bridge structure, wherein the fatigue damage map of the bridge structure includes crack growth rate, number of stress cycles, and material strength degradation rate; Based on the fatigue damage map of the bridge structure, the load-bearing capacity of the bridge support structure is evaluated to obtain the load-bearing capacity result of the bridge structure, and based on the load-bearing capacity result of the bridge structure, the failure mode of the bridge support structure is identified to obtain the distribution map of the weak links of the bridge.

5. The cable tray fault diagnosis method based on sensor network according to claim 4 is characterized in that: The performing of stiffness degradation analysis on the bridge support structure in the cable bridge based on the bridge structure dangerous point sequence to obtain degradation assessment data of the bridge support structure includes: By means of nonlinear dynamics, the stiffness of the bridge support structure in the cable bridge is calculated based on the dangerous point sequence of the bridge structure, and a bridge support point elastic coefficient matrix is ​​obtained. A dynamic response analysis of the bridge support point elastic coefficient matrix is ​​performed to obtain a bridge support stiffness attenuation curve; Based on the bridge support stiffness attenuation curve, a buckling stability analysis is performed on the bridge support structure to obtain a critical load value of the bridge support structure, and based on the critical load value of the bridge support structure, a bearing capacity calculation is performed through elastic-plastic mechanics to obtain a bridge support strength margin diagram; Performing cumulative damage calculation on the bridge support strength margin diagram through finite element fatigue analysis to obtain a bridge support structure damage state quantity, and performing structural reliability assessment based on the bridge support structure damage state quantity to obtain a bridge support failure probability distribution; A life cycle analysis is performed on the bridge support structure based on the bridge support failure probability distribution to obtain a remaining life estimate of the bridge support structure, and degradation assessment data of the bridge support structure is evaluated based on the remaining life estimate.

6. The cable tray fault diagnosis method based on sensor network according to claim 5 is characterized in that: The performing of a life cycle analysis on the bridge support structure based on the bridge support failure probability distribution to obtain an estimated remaining life of the bridge support structure includes: The failure criterion analysis of the bridge support failure probability distribution is performed using damage accumulation theory to obtain a support component damage evolution curve, and critical failure points in the support component damage evolution curve are identified to obtain a critical failure state set of the bridge support structure, wherein the critical failure state set includes a crack growth critical value, a material strength attenuation rate, and a structural deformation limit; Performing a stress history analysis on the bridge support structure based on the failure critical state set to obtain a stress spectrum function of the bridge support structure, and performing cyclic load statistics on the stress spectrum function of the bridge support structure using a rain flow counting technique to obtain a fatigue damage spectrum of the bridge support structure; Analyzing crack propagation of the bridge support structure based on a fatigue damage spectrum of the bridge support structure to obtain a crack propagation rate curve, and performing fracture mechanics calculation based on the crack propagation rate curve to obtain a life prediction diagram of the bridge support structure; A reliability analysis is performed on the life prediction diagram to obtain a reliability curve, and the estimated remaining life of the bridge support structure is evaluated based on the reliability curve using a preset probabilistic statistical technique, wherein the estimated remaining life of the bridge support structure includes the structural failure time, the maintenance and replacement cycle, and the safe operation range.

7. The cable tray fault diagnosis method based on sensor network according to claim 6 is characterized in that: The crack growth of the bridge support structure is analyzed based on the fatigue damage spectrum of the bridge support structure to obtain a crack growth rate curve, including: Calculating the crack tip stress field distribution of the bridge support structure based on the fatigue damage spectrum of the bridge support structure, and performing plastic zone correction based on the crack tip stress field distribution to obtain a crack propagation driving force sequence; Calibrate fatigue crack growth parameters of the bridge support structure based on the crack growth driving force sequence to obtain a material fatigue constant matrix, and perform stress ratio effect analysis on the material fatigue constant matrix to obtain a crack growth threshold curve; Predicting a crack propagation path based on the crack propagation threshold curve using fracture mechanics criteria, and performing crack tip strain field analysis based on the crack propagation path to obtain a crack propagation velocity field, wherein the crack propagation velocity field includes a crack propagation direction angle, a propagation rate gradient, and a critical propagation length; Based on the crack propagation velocity field, the crack propagation integration of the bridge support structure is performed to obtain the crack length increment distribution, and based on the crack length increment distribution, a periodic accumulation calculation is performed to obtain a crack propagation rate curve; wherein, the crack propagation rate curve includes a crack propagation acceleration period, a stable propagation interval and a rapid propagation critical point.

8. A cable tray fault diagnosis device based on a sensor network, characterized in that: include: A monitoring module is used to monitor the vibration of the cable bridge through a piezoelectric sensor array arranged at key nodes of the cable bridge to obtain dynamic response data of the bridge structure; A segmentation module is used to segment the dynamic response data of the bridge structure into time windows and identify abnormalities to obtain a bridge abnormal vibration period identification sequence, wherein the bridge abnormal vibration period identification sequence includes the moment of amplitude mutation, continuous vibration duration, and vibration attenuation period; A tracking module, configured to track the vibration propagation path of the cable tray based on the abnormal vibration period identification sequence of the cable tray to obtain a fault source area; A calculation module, configured to calculate the structural stress concentration of the cable tray based on the fault source area to obtain a distribution map of weak links of the cable tray; A determination module is used to determine the fault level of the cable tray based on the distribution map of weak links in the tray, obtain the fault level, and obtain a maintenance decision suggestion for the tray based on the fault level, including an emergency repair location, preventive replacement parts, and reinforcement plan.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: 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 having a computer program stored thereon, 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