Rope clip operation risk analysis system and method for cableway safety

Abstract

The invention relates to the technical field of cableway safety, and discloses a cableway safety-oriented rope clip operation risk analysis system and method, and the method comprises the steps: carrying out the abnormality judgment based on first wear data and second wear data corresponding to texture features and dynamic trajectory features; aiming at the safety of the rope clip, a multi-modal data fusion technology is adopted, and external deformation and internal stress change of equipment are comprehensively captured; potential risks can be effectively identified through collaborative analysis of image features and physical signals, and limitation of a single data source is avoided; in addition, an adaptive standardized parameter mechanism is introduced, a standard value is dynamically adjusted, robustness is enhanced, and false alarms are reduced; on the basis of physical rules and statistical characteristics, interpretable risk scores and rules are constructed, and it is ensured that diagnostic logic is transparent and traceable; through setting of different risk levels, quick response and long-term early warning under emergency conditions are taken into consideration, and the safety and operation and maintenance efficiency of cableway operation are improved.

Description

Technical Field

[0001] This invention relates to the field of cableway safety technology, and more specifically, to a system and method for analyzing the operational risks of cable grippers for cableway safety. Background Technology

[0002] Cable grips are an important safety device used in cableway systems. Their main function is to ensure the safety and stability of cableway transportation. By securing and supporting the cableway cables, cable grips prevent the cableway from becoming loose or slipping during operation, thereby ensuring the normal operation of the cableway and the safety of passengers. This equipment is typically high in strength and durability, and can adapt to the challenges of various weather and working environments, ensuring reliability even under high loads and extreme conditions.

[0003] However, traditional methods for analyzing the operational risks of cable clamps suffer from four major shortcomings: First, fragmented multi-source data leads to blind spots in perception. Relying solely on images or vibration signals cannot simultaneously capture the correlation between external deformation and internal stress, easily overlooking hidden risks such as internal fatigue or clamping block anomalies. Second, fixed threshold judgments are prone to failure; static thresholds cannot adapt to the slow changes in equipment status over time, easily generating false alarms or missed alarms. Third, deep learning models rely on large amounts of labeled data and lack interpretability; their black-box nature makes it difficult to meet the requirements of transparency in diagnostic logic in industrial scenarios. Fourth, single risk assessment and response are lagging; binary judgments or single thresholds lack dynamic grading mechanisms. These problems result in incomplete risk coverage, high false alarm rates, and opaque decision-making in traditional methods, making it difficult to meet the requirements of cableway safety for high reliability, interpretability, and graded response. Summary of the Invention

[0004] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a system and method for analyzing the operational risks of cableway grippers for cableway safety.

[0005] To achieve the above objectives, the present invention provides the following technical solution: Firstly, a method for analyzing the operational risks of cableway grippers for cableway safety is provided, the method comprising: S101. Collect the original image sequence and structural parameters of the cable holder, optimize the original image sequence and structural parameters respectively, generate segmented images and feature datasets, and align the segmented images and feature datasets. S102. Analyze the aligned segmented image, extract texture features and dynamic trajectory features from the aligned segmented image, and make anomaly judgment based on the first wear data and the second wear data corresponding to the texture features and dynamic trajectory features. S103. Extract vibration signal features, acoustic emission signal features and temperature sequence from the aligned feature dataset, and calculate vibration kurtosis, acoustic emission frequency and temperature difference respectively. Make anomaly judgment based on vibration kurtosis, acoustic emission frequency and temperature difference. S104. Standardize the texture variance, closure delay frame number, acoustic emission frequency, and temperature sequence. Then, weight the three types of standardized data to calculate the comprehensive risk score, determine the risk level, and continuously adjust the standardization parameters.

[0006] Furthermore, the anomaly determination based on the first wear data and the second wear data corresponding to texture features and dynamic trajectory features includes: The clamping block region of the gripper in the aligned segmented image is converted into texture features. The texture variance of the texture features is calculated. The gray-level co-occurrence matrix is ​​extracted from the texture features to obtain the contrast and correlation values. The anomaly detection rule is: if the texture variance is greater than the texture variance threshold, then wear risk is marked. If the contrast ratio is less than n and the correlation value fluctuates, it is judged as an abnormal surface fatigue. The variance threshold is the historical mean plus twice the standard deviation.

[0007] Furthermore, the anomaly determination based on the first wear data and the second wear data corresponding to texture features and dynamic trajectory features also includes: For two consecutive segmented images, optical flow jitter detection is performed, and the standard deviation of the angular velocity of the clamping block region is calculated. Identify the starting frame and closing frame of the clamping block closure, count the number of closing delay frames, introduce the centroid coordinates of the left and right clamping blocks, and calculate their corresponding Euclidean distance and phase difference; The anomaly detection rule is: if the standard deviation of angular velocity is greater than m, it is considered a machine malfunction. If the number of closure delay frames is greater than the mean of the number of closure delay frames plus twice the standard deviation of the number of closure delay frames, a closure delay warning will be triggered. If the Euclidean distance is greater than a or the phase difference is greater than b, then the synchronization of the left and right clamping blocks is determined to be ineffective.

[0008] Furthermore, the anomaly determination based on vibration kurtosis, acoustic emission frequency, and temperature difference includes: The triaxial vibration acceleration signal is extracted from the aligned feature dataset, Fourier transform is performed to obtain the spectrum, and the frequency domain energy ratio of the main frequency band is calculated. Simultaneously, the vibration kurtosis and waveform distortion rate are calculated using the following formulas:

[0009] In the formula: For the nth vibration acceleration sample value, This is the average value of the vibration acceleration. The standard deviation of the vibration acceleration;

[0010] In the formula: A k Let A1 be the FFT amplitude of the kth harmonic, and A1 be the amplitude of the dominant frequency. Acquire the health mode data of the cable clamp and perform cross-correlation analysis with the current vibration mode to obtain the cross-correlation coefficient; The anomaly judgment rule is: if the frequency domain energy ratio of the main frequency band is less than the historical average -10%, it is considered as stiffness degradation; If the vibration kurtosis or waveform distortion rate is greater than the corresponding threshold, it indicates that impact vibration has occurred. If the cross-correlation coefficient is less than the cross-correlation threshold, the structure is considered abnormal.

[0011] Furthermore, the logic for standardizing the texture variance, closure delay frame count, acoustic emission frequency, and temperature sequence is as follows: For texture variance and closure delay frames, respectively, the corresponding normalization parameters are used for normalization; For the acoustic emission frequency and temperature sequence, the historical maximum acoustic emission frequency and the temperature safety threshold are used as standardized parameters, respectively.

[0012] Furthermore, the formula for calculating the comprehensive risk score is as follows:

[0013] In the formula: , , These are the weights of texture variance, the sum of closure delay frames, acoustic emission frequency, and temperature sequence, respectively. The sub-weights are the texture variance and the number of frames with closure delay. For the normalized texture variance and closure delay frames, For acoustic emission frequency, This is the highest acoustic emission frequency in history. Given the current temperature difference, This is the temperature safety threshold.

[0014] Furthermore, the continuous adjustment of the standardized parameters includes: At intervals T, the historical mean and standard deviation of texture variance and closure delay frame count are calculated, and the standardized parameters corresponding to texture variance and closure delay frame count are updated. The update formulas for the historical mean and standard deviation are as follows:

[0015]

[0016] In the formula: This is the nth historical sample value.

[0017] Secondly, a risk analysis system for the operation of cableway grippers is provided for cableway safety. This system is based on the aforementioned risk analysis method for cableway gripper operation, and includes: The data acquisition module collects the original image sequence and structural parameters of the cable holder, optimizes the original image sequence and structural parameters respectively, generates segmented images and feature datasets, and aligns the segmented images and feature datasets. The image feature module analyzes the aligned segmented image, extracts texture features and dynamic trajectory features from the aligned segmented image, and makes anomaly determination based on the first wear data and the second wear data corresponding to the texture features and dynamic trajectory features. The data feature module extracts vibration signal features, acoustic emission signal features, and temperature sequence from the aligned feature dataset, and calculates vibration kurtosis, acoustic emission frequency, and temperature difference respectively. Anomaly determination is then made based on vibration kurtosis, acoustic emission frequency, and temperature difference. The risk analysis module standardizes texture variance, closure delay frame count, acoustic emission frequency, and temperature sequence, then weights the three types of standardized data to calculate a comprehensive risk score, determine the risk level, and continuously adjust the standardization parameters.

[0018] Thirdly, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the above-described method for analyzing the operating risk of cableway grippers for cableway safety.

[0019] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed, implements the above-described method for analyzing the operational risks of cableway grippers for cableway safety.

[0020] Compared with the prior art, the beneficial effects of the present invention are as follows: This application discloses a risk analysis system and method for cableway grip operation, including: analyzing aligned segmented images, extracting texture features and dynamic trajectory features from the aligned segmented images, and determining anomalies based on the first and second wear data corresponding to the texture features and dynamic trajectory features; this invention, for the safety of the grip, employs multimodal data fusion technology, comprehensively capturing the external deformation and internal stress changes of the equipment through dual-channel data acquisition of image and physical data; the collaborative analysis of image features and physical signals can effectively identify potential risks, avoiding the limitations of a single data source; in addition, an adaptive standardization parameter mechanism is introduced to dynamically adjust standard values, enhance robustness, and reduce false alarms; based on physical rules and statistical characteristics, an interpretable risk score and rules are constructed to ensure transparent and traceable diagnostic logic; finally, a hierarchical decision-making mechanism is adopted to balance risk response speed and judgment accuracy, and by setting different risk levels, it takes into account both rapid response in emergency situations and long-term early warning, improving the safety and maintenance efficiency of cableway operation. Attached Figure Description

[0021] Figure 1 A flowchart of a method for analyzing the operational risks of cableway grippers for cableway safety provided by the present invention; Figure 2 A schematic diagram of the module structure of a cable gripper operation risk analysis system for cableway safety provided by the present invention; Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention; Figure 4 A flowchart of S104 in the cableway safety-oriented cable gripper operation risk analysis method provided by the present invention; Figure 5 The present invention provides a data analysis flowchart for a method of analyzing the operational risks of cableway grippers for cableway safety. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] Example 1 Please see Figure 1 , Figure 4 and Figure 5 As shown in the figure, this embodiment discloses a method for analyzing the operational risks of cableway grippers for cableway safety. The method includes: S101: Collect the original image sequence and structural parameters of the cable holder, optimize the original image sequence and structural parameters respectively, generate segmented images and feature datasets, and align the segmented images and feature datasets; In this embodiment, the original image sequence is acquired by installing high-speed industrial cameras on both sides of the clamping device. The cameras have a resolution of 1024×768 and a frame rate of ≥120fps, ensuring that the lens axis is perpendicular to the direction of movement of the clamping block.

[0024] Meanwhile, an infrared fill light with a wavelength of 850nm is fixed next to the camera, and the reflection from the metal surface is eliminated by a diffuser.

[0025] For the original image sequence, this embodiment performs optimization processing through background subtraction, edge enhancement, and binarization segmentation.

[0026] Background subtraction is an image processing technique used to separate foreground objects from static backgrounds in video or image sequences. By comparing the current frame with the background model, fixed background areas are removed, and only dynamically changing foreground objects are retained.

[0027] Edge enhancement is a processing step that improves the contrast of object contours in an image, making edges clearer. A common method is the gradient operator, which aims to highlight object boundaries, facilitating subsequent feature extraction or object detection.

[0028] Binarization segmentation is the process of converting an image into black and white. Typically, pixels are divided into target and background regions by setting a threshold. For example, the Otsu algorithm can be used to automatically determine the optimal threshold, making the outline of the clamping block clearly distinguishable against a complex background, which is convenient for shape analysis or size measurement.

[0029] Background subtraction can extract dynamic foregrounds, edge enhancement strengthens object contour details, and binarization segmentation further simplifies image structure. These three methods are often used together to extract clear targets from complex scenes, such as detecting the motion state of cableway clamping blocks. The above methods are all existing technologies and will not be elaborated on further. In other implementations, other technologies can be used for optimization, and this application does not limit them.

[0030] Meanwhile, the structural parameters are composed of data acquired by vibration sensors, acoustic emission sensors, and temperature sensors. When acquiring structural parameters, an absolute timestamp is added to the sensor data, and then the image frame timestamp is matched with the sensor data timestamp to achieve the effect of aligning and segmenting the image and feature dataset.

[0031] S102: Analyze the aligned segmented image, extract texture features and dynamic trajectory features from the aligned segmented image, and make anomaly judgment based on the first wear data and the second wear data corresponding to the texture features and dynamic trajectory features. It should be understood that the anomaly determination based on the first wear data and the second wear data corresponding to texture features and dynamic trajectory features includes: The clamping block region of the gripper in the aligned segmented image is converted into texture features, and the texture variance of the texture features is calculated. The gray-level co-occurrence matrix is ​​extracted from the texture features to obtain the contrast and correlation values, which are calculated using the following formula:

[0032]

[0033] In the formula: i and j are the gray values ​​of adjacent pixels in the gray-level co-occurrence matrix. Normalized probability (the frequency of adjacent occurrences of gray values ​​i and j). , The mean of gray values ​​i and j; The standard deviation of gray values ​​i and j; The anomaly detection rule is: if the texture variance is greater than the texture variance threshold, then wear risk is marked. If the contrast ratio is less than n and the correlation value fluctuates, it is determined to be an abnormal surface fatigue. In this embodiment, n is 0.45 and the correlation value fluctuation means that the absolute value of the difference between adjacent frames is greater than 0.02. The variance threshold is the historical mean plus twice the standard deviation.

[0034] For example, the anomaly determination based on the first wear data and the second wear data corresponding to texture features and dynamic trajectory features further includes: For two consecutive segmented images, optical flow jitter detection is performed, and the standard deviation of the angular velocity of the clamping block region is calculated. The calculation formula for optical flow jitter detection is as follows:

[0035] In the formula: The rate of change of brightness. The rate of change of image brightness over time The smoothness of the velocity field is controlled, with a value of 100. This is the motion velocity vector of each pixel in the image.

[0036] Identify the start and end frames of the clamping block closure, count the number of closure delay frames, and introduce the centroid coordinates of the left and right clamping blocks, which is (x... L ,y L ) and (x R ,y R ), calculate the corresponding Euclidean distance and phase difference, Euclidean distance D= The phase lookup is performed by extracting the phase of the motion period through Fourier transform, which is an existing technology and will not be elaborated on here. The anomaly detection rule is: if the standard deviation of angular velocity is greater than m, where m is 2.5 rad / s 2 This is considered a machine lag; If the number of closure delay frames is greater than the mean of the number of closure delay frames plus twice the standard deviation of the number of closure delay frames, a closure delay warning will be triggered. If the Euclidean distance is greater than a or the phase difference is greater than b, where a is 3 and b is 10°, then the synchronization of the left and right clamping blocks is determined to be ineffective.

[0037] S103: Extract vibration signal features, acoustic emission signal features and temperature sequence from the aligned feature dataset, and calculate vibration kurtosis, acoustic emission frequency and temperature difference respectively. Based on vibration kurtosis, acoustic emission frequency and temperature difference, anomaly determination is made. Furthermore, the anomaly determination based on vibration kurtosis, acoustic emission frequency, and temperature difference includes: The triaxial vibration acceleration signal is extracted from the aligned feature dataset, and the spectrum is obtained by performing a Fourier transform. The frequency domain energy ratio of the main frequency band is calculated, which is the sum of the energy of the main frequency band divided by the sum of the energy of the entire frequency band. Simultaneously, the vibration kurtosis and waveform distortion rate are calculated using the following formulas:

[0038] In the formula: For the nth vibration acceleration sample value, This is the average value of the vibration acceleration. The standard deviation of the vibration acceleration;

[0039] In the formula: A k Let A1 be the FFT amplitude of the kth harmonic, and A1 be the amplitude of the dominant frequency. The specific steps for determining anomalies in acoustic emission frequencies are as follows: The number of Hits per unit time is counted, i.e., the acoustic emission frequency and energy value, and the stress index is calculated. The anomaly rule is as follows: If the number of hits is greater than 200 / s or the energy value is greater than 5000aJ, it indicates crack propagation; If the stress index is greater than 1.5 times the benchmark value for 3 consecutive seconds, an alarm will be triggered.

[0040] The formula for calculating the stress index is as follows:

[0041] In the formula: Counts is the number of events, Duration is the duration, and Energy is the accumulated energy value; The energy value is the integral of the square of the voltage over time, that is:

[0042] In the formula: It is a voltage signal that varies with time; The specific steps for anomaly detection in temperature sequences are as follows: Calculate the temperature difference ΔT between the left and right clamps and the heating rate dT / dt. The anomaly rule is as follows: If ΔT > 3℃ and lasts for more than 10 seconds, it indicates an off-center load.

[0043] If dT / dt > 2℃ / s and the vibration / acoustic emission characteristics are abnormal, an emergency risk is identified.

[0044] Acquire the health mode data of the cable clamp and perform cross-correlation analysis with the current vibration mode to obtain the cross-correlation coefficient; The anomaly judgment rule is: if the frequency domain energy ratio of the main frequency band is less than the historical average -10%, it is considered as stiffness degradation; If the vibration kurtosis or waveform distortion rate is greater than the corresponding threshold, it indicates that impact vibration has occurred. If the cross-correlation coefficient is less than the cross-correlation threshold, the structure is considered abnormal.

[0045] S104: The texture variance, closure delay frame number, acoustic emission frequency and temperature sequence are standardized, and then the three types of standardized data are weighted to calculate the comprehensive risk score, determine the risk level, and continuously adjust the standardization parameters. It should be noted that the logic for standardizing the texture variance, closure delay frame count, acoustic emission frequency, and temperature sequence is as follows: For texture variance and closure delay frames, respectively, the corresponding normalization parameters are used for normalization; For the acoustic emission frequency and temperature sequence, the historical maximum acoustic emission frequency and the temperature safety threshold are used as standardized parameters, respectively.

[0046] The specific process is as follows: Normalization of texture variance and closure delay frames:

[0047] In the formula: For the current eigenvalue, This is the historical average. The historical standard deviation; The acoustic emission frequency and temperature sequence were normalized using Min-Max normalization:

[0048] In the formula: These are the historical maximum / minimum values; In summary, the formula for calculating the comprehensive risk score is as follows:

[0049] In the formula: , , These are the weights of texture variance, the sum of closure delay frames, acoustic emission frequency, and temperature sequence, respectively. The sub-weights are the texture variance and the number of frames with closure delay. For the normalized texture variance and closure delay frames, For acoustic emission frequency, This is the highest acoustic emission frequency in history. Given the current temperature difference, The temperature safety threshold is set; the sub-weights between texture variance and closure delay frame number are 0.6 and 0.4, respectively.

[0050] The specific rules for determining the risk level are as follows: High-risk conditions: Condition 1: Acoustic emission Hits > 300 / s and vibration kurtosis > 6.

[0051] Condition 2: Temperature rise rate dT / dt > 3℃ / s and risk score > 0.8.

[0052] Medium risk conditions: Condition 1: The main frequency energy ratio decreases by 10%-15% and the energy value is >3000aJ.

[0053] Condition 2: Risk score > 0.5 and closure delay > mean + 1.5σ.

[0054] Low-risk conditions: Condition 1: Minor anomaly of a single feature Meanwhile, its judgment logic is as follows: for each time t, the rule conditions are judged in order of priority. If the high-risk condition is met, it is marked as high-risk; otherwise, if the medium-risk condition is met, it is marked as medium-risk; otherwise, if the low-risk condition is met, it is marked as low-risk; otherwise, it is marked as normal.

[0055] In this embodiment, , , The values ​​are 0.4, 0.5, and 0.1 respectively.

[0056] As a concrete example, see below: Assume the basic data are: closing delay frames. The value is 9, the historical mean is 8, and the standard deviation is 2. The texture variance was 0.17, the historical mean was 0.15, and the standard deviation was 0.025. Hits = 300 / s, historical maximum is 500 / s Temperature difference ΔT =2.8℃, the safety threshold is 3℃.

[0057] Normalization of closing delay frame count:

[0058] Normalization of texture variance:

[0059] Therefore, we can conclude that:

[0060] In summary:

[0061] Multi-feature anomaly detection: Closure delay: Historical threshold +2 =12, =9 < 12, no delay warning triggered; Texture variance: Historical threshold +2 =0.2, =0.17 < 0.2, wear warning not triggered; Hits count assessment: Hits count = 300 / s > 200 / s, triggering crack propagation warning; Temperature difference: Temperature difference 2.8℃ < 3℃, no off-center load warning triggered.

[0062] As one specific implementation method, the continuous adjustment of standardized parameters includes: At intervals T, the historical mean and standard deviation of texture variance and closure delay frame count are calculated, and the standardized parameters corresponding to texture variance and closure delay frame count are updated. The update formulas for the historical mean and standard deviation are as follows:

[0063]

[0064] In the formula: This is the nth historical sample value.

[0065] Assume there are 24 historical samples of closure delay data in the past 24 hours (1 sample per hour), the current sample size is 10, the historical mean is 7.8, the historical standard deviation is 2.2, and the historical variance is 4.84.

[0066] Update the mean:

[0067] Update variance and standard deviation:

[0068]

[0069] Example 2 Please see Figure 2 As shown, based on the same inventive concept, this embodiment discloses a risk analysis system for the operation of cableway grippers for cableway safety. For details not covered in this embodiment, please refer to the relevant sections of Embodiment 1. The system includes: The data acquisition module collects the original image sequence and structural parameters of the cable holder, optimizes the original image sequence and structural parameters respectively, generates segmented images and feature datasets, and aligns the segmented images and feature datasets. The image feature module analyzes the aligned segmented image, extracts texture features and dynamic trajectory features from the aligned segmented image, and makes anomaly determination based on the first wear data and the second wear data corresponding to the texture features and dynamic trajectory features. The data feature module extracts vibration signal features, acoustic emission signal features, and temperature sequence from the aligned feature dataset, and calculates vibration kurtosis, acoustic emission frequency, and temperature difference respectively. Anomaly determination is then made based on vibration kurtosis, acoustic emission frequency, and temperature difference. The risk analysis module standardizes texture variance, closure delay frame count, acoustic emission frequency, and temperature sequence, then weights the three types of standardized data to calculate a comprehensive risk score, determine the risk level, and continuously adjust the standardization parameters.

[0070] Example 3 Please see Figure 3 As shown, this embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the cable gripper operation risk analysis method for cableway safety provided by the above methods.

[0071] Since the electronic device described in this embodiment is the electronic device used to implement the method for analyzing the operation risk of a cableway safety gripper as described in this application embodiment, those skilled in the art can understand the specific implementation and various variations of the electronic device in this embodiment based on the method for analyzing the operation risk of a cableway safety gripper as described in this application embodiment. Therefore, how the electronic device implements the method in this application embodiment will not be described in detail here. Any electronic device used by those skilled in the art to implement the method for analyzing the operation risk of a cableway safety gripper as described in this application embodiment falls within the scope of protection of this application.

[0072] Example 4 This embodiment discloses a computer-readable storage medium, including a memory, a processor, and a computer program stored on the memory and running on the processor. When the processor executes the computer program, it implements the cable gripper operation risk analysis method for cableway safety provided by the above methods.

[0073] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters, weights, and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0074] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired or wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0075] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0076] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0077] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only one method, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0078] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0079] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0080] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0081] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for analyzing the operational risks of cableway grippers for cableway safety, characterized in that, The method includes: S101. Collect the original image sequence and structural parameters of the cable holder, optimize the original image sequence and structural parameters respectively, generate segmented images and feature datasets, and align the segmented images and feature datasets. S102. Analyze the aligned segmented image, extract texture features and dynamic trajectory features from the aligned segmented image, and make anomaly judgment based on the first wear data and the second wear data corresponding to the texture features and dynamic trajectory features. S103. Extract vibration signal features, acoustic emission signal features and temperature sequence from the aligned feature dataset, and calculate vibration kurtosis, acoustic emission frequency and temperature difference respectively. Make anomaly judgment based on vibration kurtosis, acoustic emission frequency and temperature difference. S104. Standardize the texture variance, closure delay frame number, acoustic emission frequency, and temperature sequence. Then, weight the three types of standardized data to calculate the comprehensive risk score, determine the risk level, and continuously adjust the standardization parameters.

2. The method for analyzing the operational risks of cableway grippers according to claim 1, characterized in that, The anomaly determination based on the first and second wear data corresponding to texture features and dynamic trajectory features includes: The clamping block region of the gripper in the aligned segmented image is converted into texture features. The texture variance of the texture features is calculated. The gray-level co-occurrence matrix is ​​extracted from the texture features to obtain the contrast and correlation values. The anomaly detection rule is: if the texture variance is greater than the texture variance threshold, then wear risk is marked. If the contrast ratio is less than n and the correlation value fluctuates, it is judged as an abnormal surface fatigue. The variance threshold is the historical mean plus twice the standard deviation.

3. The method for analyzing the operational risks of cableway grippers according to claim 2, characterized in that, The anomaly determination based on the first and second wear data corresponding to texture features and dynamic trajectory features also includes: For two consecutive segmented images, optical flow jitter detection is performed, and the standard deviation of the angular velocity of the clamping block region is calculated. Identify the starting frame and closing frame of the clamping block closure, count the number of closing delay frames, introduce the centroid coordinates of the left and right clamping blocks, and calculate their corresponding Euclidean distance and phase difference; The anomaly detection rule is: if the standard deviation of angular velocity is greater than m, it is considered a machine malfunction. If the number of closure delay frames is greater than the mean of the number of closure delay frames plus twice the standard deviation of the number of closure delay frames, a closure delay warning will be triggered. If the Euclidean distance is greater than a or the phase difference is greater than b, then the synchronization of the left and right clamping blocks is determined to be ineffective.

4. The method for analyzing the operational risks of cableway grippers according to claim 1, characterized in that, The anomaly determination based on vibration kurtosis, acoustic emission frequency, and temperature difference includes: The triaxial vibration acceleration signal is extracted from the aligned feature dataset, Fourier transform is performed to obtain the spectrum, and the frequency domain energy ratio of the main frequency band is calculated. Simultaneously, the vibration kurtosis and waveform distortion rate are calculated using the following formulas: In the formula: For the nth vibration acceleration sample value, This is the average value of the vibration acceleration. The standard deviation of the vibration acceleration; In the formula: A k Let A1 be the FFT amplitude of the kth harmonic, and A1 be the amplitude of the dominant frequency. Acquire the health mode data of the cable clamp and perform cross-correlation analysis with the current vibration mode to obtain the cross-correlation coefficient; The anomaly judgment rule is: if the frequency domain energy ratio of the main frequency band is less than the historical average -10%, it is considered as stiffness degradation; If the vibration kurtosis or waveform distortion rate is greater than the corresponding threshold, it indicates that impact vibration has occurred. If the cross-correlation coefficient is less than the cross-correlation threshold, the structure is considered abnormal.

5. The method for analyzing the operational risks of cableway grippers according to claim 1, characterized in that, The logic for standardizing texture variance, closure delay frame count, acoustic emission frequency, and temperature sequence is as follows: For texture variance and closure delay frames, respectively, the corresponding normalization parameters are used for normalization; For the acoustic emission frequency and temperature sequence, the historical maximum acoustic emission frequency and the temperature safety threshold are used as standardized parameters, respectively.

6. The method for analyzing the operational risks of cableway grippers according to claim 1, characterized in that, The formula for calculating the comprehensive risk score is as follows: In the formula: , , These are the weights of texture variance, the sum of closure delay frames, acoustic emission frequency, and temperature sequence, respectively. The sub-weights are the texture variance and the number of frames with closure delay. For the normalized texture variance and closure delay frames, For acoustic emission frequency, This is the highest acoustic emission frequency in history. Given the current temperature difference, This is the temperature safety threshold.

7. The method for analyzing the operational risks of cableway grippers according to claim 6, characterized in that, The continuous adjustment of standardized parameters includes: At intervals T, the historical mean and standard deviation of texture variance and closure delay frame count are calculated, and the standardized parameters corresponding to texture variance and closure delay frame count are updated. The update formulas for the historical mean and standard deviation are as follows: In the formula: This is the nth historical sample value.

8. A risk analysis system for cableway gripper operation oriented towards cableway safety, characterized in that, It is implemented based on the method for analyzing the operational risks of cableway grippers for cableway safety as described in any one of claims 1 to 7, and the system includes: The data acquisition module collects the original image sequence and structural parameters of the cable holder, optimizes the original image sequence and structural parameters respectively, generates segmented images and feature datasets, and aligns the segmented images and feature datasets. The image feature module analyzes the aligned segmented image, extracts texture features and dynamic trajectory features from the aligned segmented image, and makes anomaly determination based on the first wear data and the second wear data corresponding to the texture features and dynamic trajectory features. The data feature module extracts vibration signal features, acoustic emission signal features, and temperature sequence from the aligned feature dataset, and calculates vibration kurtosis, acoustic emission frequency, and temperature difference respectively. Anomaly determination is then made based on vibration kurtosis, acoustic emission frequency, and temperature difference. The risk analysis module standardizes texture variance, closure delay frame count, acoustic emission frequency, and temperature sequence, then weights the three types of standardized data to calculate a comprehensive risk score, determine the risk level, and continuously adjust the standardization parameters.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the cable gripper operation risk analysis method for cableway safety as described in claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed, implements the cable gripper operation risk analysis method for cableway safety as described in claims 1-7.

Images