Steel wire rope online detection method and device, electronic equipment and storage medium

Abstract

The invention provides a steel wire rope online detection method and device, electronic equipment and a storage medium, and belongs to the technical field of damage detection.The method comprises the steps that a first detection requirement is determined based on the detection emphasis of a target steel wire rope, and a second detection requirement is determined based on scene features of the target steel wire rope; determining a target detection strategy of the target steel wire rope based on the first detection demand and the second detection demand, wherein the target detection strategy comprises a first detection model and a second detection model; and detecting the physical characteristics of the target steel wire rope based on the target detection strategy to obtain a damage state detection result. According to the steel wire rope online detection method and device, the electronic equipment and the storage medium, the efficiency and timeliness of steel wire rope online detection can be improved.

Description

Technical Field

[0001] This disclosure belongs to the field of damage detection technology, and more specifically, relates to an online detection method and device for steel wire ropes, electronic equipment, and storage medium. Background Technology

[0002] In modern industrial production and infrastructure construction, wire ropes, as key load-bearing components, are widely used in cranes, elevators, mining hoisting equipment, and many other fields. Because wire ropes are subjected to high loads, harsh environments, and complex stresses over long periods, they are highly susceptible to defects such as broken wires, wear, and corrosion, which can seriously threaten equipment safety and the lives and property of personnel.

[0003] Wire ropes are high-risk and easily damaged parts in port cranes, and the usual method of manually inspecting ropes by "visual inspection and caliper measurement" is not only inefficient, but also makes it difficult to fully and timely detect subtle internal defects.

[0004] Therefore, there is an urgent need for an efficient online inspection method for steel wire ropes. Summary of the Invention

[0005] The purpose of this disclosure is to provide a method, apparatus, electronic device, and storage medium for online detection of wire ropes, so as to improve the efficiency and timeliness of online detection of wire ropes.

[0006] A first aspect of this disclosure provides an online inspection method for steel wire ropes, comprising: The first inspection requirement is determined based on the inspection focus of the target steel wire rope, and the second inspection requirement is determined based on the scene characteristics of the target steel wire rope. Based on the first detection requirement and the second detection requirement, a target detection strategy for the target steel wire rope is determined, and the target detection strategy includes a first detection model and a second detection model. The physical characteristics of the target wire rope are detected based on the target detection strategy to obtain the damage state detection result.

[0007] A second aspect of this disclosure provides an online wire rope inspection device, comprising: The detection requirement determination module is used to determine the first detection requirement based on the detection focus of the target steel wire rope, and to determine the second detection requirement based on the scene characteristics of the target steel wire rope. The detection strategy determination module is used to determine the target detection strategy for the target wire rope based on the first detection requirement and the second detection requirement. The target detection strategy includes a first detection model and a second detection model. The detection result analysis module is used to detect the physical characteristics of the target wire rope based on the target detection strategy and obtain the damage state detection result.

[0008] A third aspect of this disclosure provides an electronic device 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 steps of the above-described online wire rope detection method.

[0009] A fourth aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described online wire rope detection method.

[0010] The beneficial effects of the online detection method and apparatus for steel wire ropes, electronic equipment, and storage medium provided in this disclosure are as follows: This disclosure, by identifying multiple inspection requirements for the target wire rope, accurately grasps the key points and direction of inspection, avoiding the blindness and inefficiency of traditional inspection methods, thus improving inspection efficiency and ensuring the pertinence and effectiveness of the inspection work. Secondly, the target inspection strategy based on multiple inspection requirements, combining the first and second inspection models, achieves comprehensive and in-depth inspection of the physical characteristics of the wire rope, more accurately reflecting the actual damage state of the wire rope and improving the accuracy and reliability of the inspection. Finally, this disclosure, through online inspection, achieves real-time monitoring and damage early warning of the wire rope, helping to promptly identify and address potential safety hazards, prevent accidents, and thus ensure the safety of production and operations. Therefore, this disclosure can improve the efficiency and timeliness of online wire rope inspection. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic flowchart of an online wire rope testing method provided in an embodiment of the present disclosure; Figure 2 This is a structural block diagram of an online wire rope detection device provided in an embodiment of the present disclosure; Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of the present disclosure. Detailed Implementation

[0013] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of the embodiments of this disclosure. However, those skilled in the art will understand that this disclosure may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this disclosure with unnecessary detail.

[0014] To make the objectives, technical solutions, and advantages of this disclosure clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0015] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of an online wire rope inspection method provided in this disclosure. The method includes: S101: Determine the first inspection requirement based on the inspection focus of the target steel wire rope, and determine the second inspection requirement based on the scene characteristics of the target steel wire rope.

[0016] In this embodiment, the target wire rope is the wire rope that needs to be inspected, which can be the wire rope currently in use on a crane. For example, this embodiment needs to inspect the wire rope used for lifting goods on a port crane. This wire rope is the target wire rope, responsible for frequently lifting heavy objects. Due to the high intensity of the work and the complex environment, real-time inspection is required to ensure safety.

[0017] The testing requirements are for testing the target wire rope in different aspects, including various problems that may occur in the wire rope and dimensions of condition assessment.

[0018] Identify several testing requirements for the target wire rope, including: The focus of the inspection of the target wire rope is determined based on its working state, and the first inspection requirement is determined based on the focus of the inspection of the target wire rope. The scenario characteristics of the target steel wire rope are determined based on its usage scenario, and the second inspection requirement is determined based on the scenario characteristics of the target steel wire rope.

[0019] In this embodiment, the working state of the target wire rope can be determined by whether the surface of the wire rope is protected. The focus of the inspection of the target wire rope is determined based on its working condition, including: If the target wire rope is in a working state where its surface is protected, then the focus of the inspection of the target wire rope should be its interior. If the target wire rope is in a working state where its surface is not protected, then the focus of the inspection of the target wire rope is on its internal and external surfaces.

[0020] The target wire rope has a protective outer layer, such as grease, lubricant, or a protective layer. This outer layer protects the wire rope's surface, reducing wear and corrosion. Therefore, the focus of inspection is on the internal structure, such as the presence of broken wires. However, the presence of the outer layer limits the accuracy of external inspections. Therefore, focusing on the internal structure still allows for accurate analysis of the wire rope's damage, ensuring operational safety.

[0021] Considering that the target wire rope lacks an outer protective layer, damage exists not only internally but also externally due to wear or corrosion. Therefore, the focus of inspection should be on both the internal and external aspects. A comprehensive inspection of both the internal structure and surface of the target wire rope facilitates rapid determination of its damage status and allows for timely maintenance.

[0022] Alternatively, if the target wire rope is used for long-distance hoisting, the focus of the inspection should be on the location of defects in the target wire rope.

[0023] At this point, locating the defect in the target wire rope helps staff understand the development and changes of defects at different locations over different periods, which is beneficial for predicting the service life of the target wire rope or the life cycle of similar target wire ropes.

[0024] The primary inspection requirements are determined based on the inspection focus of the target steel wire rope, including: In response to the fact that the focus of the inspection of the target steel wire rope is on the internal structure, the detection of local defects is taken as the primary inspection requirement; In response to the fact that the inspection focus of the target steel wire rope is on the internal and external aspects, global defect detection is taken as the primary inspection requirement; In response to the fact that the focus of the inspection of the target wire rope is on the location of defects, the detection of the location of defects is taken as the primary inspection requirement.

[0025] The scenario characteristics of the target steel wire rope are determined based on its application scenario, including: If the target wire rope is used in a scenario where the dust level is greater than or equal to the first dust level threshold, then the scenario characteristic of the target wire rope is that the surface detail detection of the target wire rope is limited. If the target wire rope is used in a scenario where the dust level is less than the first dust level threshold, then the scenario characteristic of the target wire rope is that the surface detail detection of the target wire rope is not restricted.

[0026] Considering that dust can adhere to the surface of the steel wire rope and obstruct its movement, thus limiting the detection of surface details of the target steel wire rope, a first dust amount threshold is pre-set to determine whether the dust amount limits the detection of surface details of the target steel wire rope.

[0027] Therefore, in response to the scenario characteristics of the target steel wire rope, which limit the detection of surface details of the target steel wire rope, single detection is regarded as a second detection requirement; In response to the scenario characteristics of the target steel wire rope, which allow for unrestricted surface detail inspection, joint inspection is designated as a second inspection requirement.

[0028] Since the damage condition of the target wire rope is detected, and the detection results are obtained, it is difficult to find a method that can simultaneously and accurately detect both the internal and external aspects of the target wire rope. Therefore, when the surface detail detection of the target wire rope is limited, a certain method or technology can be used to detect the internal aspects of the target wire rope, i.e., single detection; when the surface detail detection of the target wire rope is not limited, a certain method can be used to detect the internal aspects of the target wire rope, and another method can be used to detect the external aspects (surface) of the target wire rope, i.e., combined detection, so that the detection of the target wire rope is more comprehensive.

[0029] The application scenarios of the target steel wire rope can also be considered based on weather conditions, lighting, etc. The corresponding scenario characteristics of the target steel wire rope will also be different. Therefore, based on different scenario characteristics, single detection or joint detection can be selected as the second detection requirement.

[0030] S102: Determine the target detection strategy for the target wire rope based on the first detection requirement and the second detection requirement. The target detection strategy includes the first detection model and the second detection model.

[0031] In this embodiment, multiple testing requirements are determined by step S101, and the testing requirements of the target wire rope are determined from different dimensions or different considerations.

[0032] The target detection strategy is a detection plan determined according to different detection needs, including the detection technology to be used and the detection process, with the aim of comprehensively, accurately and timely detecting the condition of the target wire rope.

[0033] The first and second detection models employ different detection technologies and processes to process and analyze different detection data to obtain results. They are based on different principles or designed to meet different needs.

[0034] In one embodiment of this disclosure, the first detection requirement includes local defect detection, global defect detection, and defect location detection; the second detection requirement includes single detection and combined detection. Based on the first and second inspection requirements, the target inspection strategy for the target wire rope is determined, including: In response to the first detection requirement being local defect detection and the second detection requirement being single detection, the first detection model is used as the target detection strategy for the target wire rope. In response to the first detection requirement being global defect detection or defect location detection, and the second detection requirement being joint detection, the second detection model is used as the target detection strategy for the target wire rope.

[0035] In this embodiment, the key issues encountered by the target wire rope differ under different application scenarios, thus the focus of inspection will also vary. The focus of inspection can be determined based on the protection status or operating characteristics of the target wire rope, including its internal structure, internal and external surfaces, and defect location. The first inspection requirement is the specific inspection direction and requirements defined based on this focus, including local defect detection, global defect detection, and defect location detection. Local defect detection can be internal defect detection; global defect detection can be internal and external defect detection, i.e., detection of defects both inside and on the surface.

[0036] Furthermore, the application scenarios of the target steel wire rope vary, and these scenarios will present different damage risks, thus determining different testing requirements. Scenario characteristics can be determined based on the physical or working environment of the target steel wire rope, and may include surface detail inspection, weather conditions, and corrosion characteristics. The second testing requirement is the specific type and quantity of testing determined based on these scenario characteristics. This second testing requirement includes single testing and combined testing. Single testing involves testing based on a single type of data feature, while combined testing involves testing based on two or more types of data features.

[0037] When the primary inspection requirement is internal defect detection, it's necessary to inspect the target wire rope for internal defects such as broken wires, core corrosion, and internal wear. Because the target wire rope bears heavy loads for extended periods, internal wires can break due to fatigue; detecting internal defects allows for the timely identification of such potential problems. When the primary inspection requirement is internal and external defect detection, it's necessary to inspect not only the internal defects of the target wire rope but also external defects such as wear, corrosion, or scratches on its surface. For example, the wire ropes of port cranes are susceptible to damage both internally and externally in humid and salty environments; internal and external defect detection provides a comprehensive assessment of the target wire rope's condition. When the primary inspection requirement is defect location detection, it's necessary to pinpoint the location of any existing defects on the target wire rope. Regardless of whether the defect is internal or external, accurately identifying its location is crucial for subsequent maintenance or replacement decisions, allowing for targeted reinforcement or repair measures.

[0038] Therefore, when the first inspection requirement is internal defect detection or internal / external defect detection, the inspection results for the target wire rope include the type and extent of damage. When the second inspection requirement is defect location detection, the inspection results for the target wire rope include not only the type and extent of damage, but also the location of damage.

[0039] When the second detection requirement is a single detection, detection can be performed based on a single type of data feature; when the second detection requirement is a joint detection, detection can be performed based on two or more types of data features.

[0040] When the first inspection requirement is internal defect detection and the second inspection requirement is single inspection, since only internal defects of the target wire rope need to be detected and a single inspection method is used, the first inspection model can efficiently and directly inspect the target wire rope. Therefore, the first inspection model can be used as the target inspection strategy.

[0041] When the first detection requirement is internal and external defect detection, and the second detection requirement is joint detection, since the internal and external defects of the target wire rope need to be detected, a single detection cannot meet the requirements and joint detection is necessary. In this case, the second detection model can comprehensively detect the target wire rope, so the second detection model can be used as the target detection strategy.

[0042] When the first detection requirement is defect location detection and the second detection requirement is joint detection, determining the defect location often requires obtaining information from multiple dimensions to accurately locate the defect. Therefore, the second detection model can be used as the target detection strategy.

[0043] S103: Based on the target detection strategy, the physical characteristics of the target wire rope are detected to obtain the damage status detection results.

[0044] In one embodiment of this disclosure, the physical characteristics of the target steel wire rope are detected based on a target detection strategy to obtain damage state detection results, including: In response to the target detection strategy being the first detection model, the physical characteristics of the target wire rope are detected based on the first detection model to determine the damage state detection result; In response to the target detection strategy, a second detection model is used to detect the physical characteristics of the target wire rope and determine the damage status detection result.

[0045] In this embodiment, the target detection strategy can be a first detection model or a second detection model. Physical features can be signal features, texture features, and shape features. Signal features can include amplitude, frequency, and phase, for example, a sudden change in amplitude can indicate a broken wire, and a change in signal frequency can be related to the degree of wear. Texture features can be the surface texture of the target wire rope. Normal wire rope surface textures have a certain regularity, but when damage such as wear or corrosion occurs, the surface texture will change. Shape features can be the uniformity of the target wire rope's diameter, its bending, and its deformation, for example, a decrease in diameter indicates wear, and bending deformation can indicate abnormal external force.

[0046] The collected physical characteristic data is analyzed and processed, and compared with the characteristic data under normal conditions to determine the damage status detection results of the target wire rope. It can also generate a detection report on the damage status of the target wire rope. The report can include whether damage exists, the location and type of damage (such as broken wire, wear, corrosion, etc.), the severity, and suggestions for the subsequent use of the wire rope.

[0047] For example, the currently detected weak magnetic signal characteristics are compared with the weak magnetic signal characteristics of a standard defect-free steel wire rope to determine whether internal defects exist and the type and severity of the defects. Texture and shape features obtained through image analysis are compared with surface images under normal conditions to determine surface damage, such as the presence of rust, the size and location of wear areas, etc.

[0048] As can be seen from the above, this disclosure, by identifying multiple inspection requirements for the target wire rope, can accurately grasp the key points and direction of inspection, avoiding the blindness and inefficiency of traditional inspection methods, thus improving inspection efficiency and ensuring the pertinence and effectiveness of the inspection work. Secondly, the target inspection strategy based on multiple inspection requirements, combined with the first and second inspection models, achieves comprehensive and in-depth inspection of the physical characteristics of the wire rope, more accurately reflecting the actual damage state of the wire rope and improving the accuracy and reliability of the inspection. Finally, this disclosure, through online inspection, achieves real-time monitoring and damage early warning of the wire rope, helping to promptly identify and address potential safety hazards, prevent accidents, and thus ensure the safety of production and operations. Therefore, this disclosure can improve the efficiency and timeliness of online wire rope inspection.

[0049] In one embodiment of this disclosure, the physical characteristics of the target steel wire rope are detected based on a first detection model to determine the damage state detection result, including: The leakage magnetic signal of the target steel wire rope is determined based on weak magnetic field detection; Signal processing is performed on the leakage magnetic signal to obtain the target signal characteristics; The target signal features are analyzed based on the first detection model to determine the damage state detection result.

[0050] In this embodiment, weak magnetic field detection utilizes the principle that after a ferromagnetic material (i.e., the target steel wire rope) is magnetized, internal defects cause changes in the magnetic field distribution, resulting in some magnetic field leakage to the outside of the material, thus generating leakage magnetic field. Based on leakage magnetic field detection, the leakage magnetic field signal generated by the internal defects of the target steel wire rope is acquired, and this signal is used as the raw signal data for judging the damage state of the target steel wire rope.

[0051] For example, when inspecting the wire rope of a crane, a permanent magnet or electromagnet is brought close to the target wire rope to uniformly magnetize it along its axial direction. When a broken wire is present inside the wire rope, the magnetic field at the broken wire will be distorted, generating a leakage magnetic signal. This leakage magnetic signal can be detected by Hall sensors arranged around the wire rope.

[0052] The leakage magnetic signal is the magnetic field signal formed when the target steel wire rope is magnetized, and the magnetic field leaks into the external space due to internal defects. Its characteristics are closely related to the internal defects of the steel wire rope.

[0053] For example, the signal of magnetic field strength change caused by broken wires detected by the Hall sensor is the leakage magnetic signal. If the number of broken wires increases or the length of a single broken wire increases, the amplitude of the leakage magnetic signal will usually increase.

[0054] Weak magnetic field detection utilizes the principle that internal defects in a magnetized steel wire rope cause magnetic field leakage. When a magnetic field is applied to the target steel wire rope to magnetize it, under normal circumstances, the magnetic field distribution inside the rope is relatively uniform. However, if defects such as broken wires, internal wear, or corrosion exist, the magnetic field lines will be distorted at the defect locations, and some of the magnetic field will leak to the outside of the wire rope, forming a leakage magnetic signal. For example, when there is a broken wire inside the steel wire rope, the permeability at the broken wire changes, causing the originally uniformly distributed magnetic field lines to bend and leak at that point, which can then be detected by the detection equipment as a leakage magnetic signal.

[0055] Considering that the leakage magnetic signal obtained from the target wire rope will contain noise and interference and cannot be directly used to accurately determine the damage status, signal processing of the leakage magnetic signal is required.

[0056] In this embodiment, signal processing is performed on the leakage magnetic signal to obtain the target signal characteristics, including: The leakage magnetic signal is filtered and normalized to obtain the preprocessed leakage magnetic signal; Feature extraction is performed on the preprocessed leakage magnetic signal to obtain the target signal features, which include amplitude features, frequency features, and phase features.

[0057] Filtering the magnetic flux leakage signal includes: filtering the magnetic flux leakage signal based on the Recursive Least-squares (RLS) algorithm with a variable forgetting factor, specifically including: Determine the initial parameter estimates Error covariance matrix and forgetting factor ; Leakage magnetic signal samples were received sequentially according to time. ,in, Indicates the The leakage magnetic signal value at any given time; Calculate the gain vector based on the first formula. ; Based on leakage magnetic signal Gain vector The second formula updates the parameter estimates. ; Update the error covariance matrix based on the third formula. ; Based on the updated parameter estimates and input vector Output the first Preprocessed leakage magnetic signal value at time ,in, ; Update the forgetting factor, iterate repeatedly, and execute: calculate the gain vector based on the first formula. The iteration continues until each leakage magnetic signal has been processed, at which point the iteration ends.

[0058] The first formula is:

[0059] in, Indicates the Gain vector at time step Indicates the The error covariance matrix at time t. Indicates the The input vector at time t, Indicates the The forgetting factor of time, This indicates transpose.

[0060] It is an input vector related to the leakage magnetic signal, which can contain the leakage magnetic signal values ​​at the current time and several past times or other related features.

[0061] The second formula is: ; The third formula is: .

[0062] Update the forgetting factor, including: The forgetting factor is dynamically adjusted based on the estimation error to determine the updated forgetting factor.

[0063] The formula for dynamically adjusting the forgetting factor is: ; ; in, Indicates the desired leakage magnetic signal. This indicates the error between the preprocessed leakage magnetic signal and the desired leakage magnetic signal. and These represent the minimum and maximum values ​​of the forgetting factor, respectively. and These represent a first error threshold and a second error threshold, respectively, where the first error threshold is greater than the second error threshold. This represents the adjustment factor.

[0064] When error A large error indicates a sudden change in the signal. In this case, reducing the forgetting factor allows the filter to quickly track the signal change; when the error... A smaller value indicates a relatively stable signal. Increasing the forgetting factor can improve the stability of the filter.

[0065] Normalization can unify each signal into a specific range, eliminating the impact of differences on subsequent feature extraction and analysis, and making the features comparable.

[0066] The first detection model is a model trained on a large amount of experimental data, establishing the relationship between historical signal characteristics and historical wire rope damage states. When the target signal characteristics are input into the first detection model, the model analyzes and judges the target signal characteristics according to the set rules and judgment conditions.

[0067] For example, if the first detection model detects that the signal amplitude exceeds the threshold of the normal range and the frequency fluctuates abnormally, according to the model's preset rules, it can determine that the wire rope has broken wires or significant wear, and determine the damage type, severity, and other information, ultimately generating a damage status detection result. Assuming the first detection model is based on a neural network, the extracted target signal features, such as amplitude and frequency, are used as input data and fed into the pre-trained neural network model. Based on the pre-learned correspondence between signal features and damage status, the neural network determines that the wire rope has broken wires, with three broken wires, and the severity is moderate.

[0068] As can be seen from the above, this embodiment, through weak magnetic field detection technology, can acquire the leakage magnetic signal of the wire rope non-contactly, avoiding secondary damage to the wire rope caused by traditional detection methods. Secondly, by performing fine signal processing on the leakage magnetic signal, key target signal features are extracted, improving the accuracy and reliability of the detection. Finally, by using the first detection model to conduct in-depth analysis of the target signal features, the damage state of the wire rope can be accurately determined, providing a strong basis for timely maintenance and replacement, and effectively ensuring the safety and stability of the wire rope in use.

[0069] In one embodiment of this disclosure, the physical characteristics of the target steel wire rope are detected based on a second detection model to determine the damage state detection result, including: The signal characteristics of the target steel wire rope are determined based on weak magnetic field detection; The surface features of the target steel wire rope are determined based on machine vision recognition. The signal features and surface features are fused to obtain the fused features of the target steel wire rope; The fusion features are analyzed based on the second detection model to determine the damage state detection results.

[0070] In this embodiment, the step of determining the signal characteristics of the target wire rope based on weak magnetic field detection is the same as above, namely, it includes: The leakage magnetic signal of the target steel wire rope is determined based on weak magnetic field detection; The leakage magnetic signal is filtered and normalized to obtain the preprocessed leakage magnetic signal; Feature extraction is performed on the preprocessed leakage magnetic signal to obtain signal features, including amplitude features, frequency features, and phase features.

[0071] Machine vision recognition involves acquiring images of a target wire rope using optical imaging devices (such as cameras), and then analyzing these images using image processing and pattern recognition techniques to identify the surface condition of the wire rope. Machine vision recognition can detect physical features such as wear, corrosion, and scratches on the wire rope surface, supplementing information about its condition.

[0072] Surface features, obtained from machine vision image recognition and analysis, reflect the surface condition of the wire rope, such as the area and shape of worn areas, the degree and location of rust, and the depth and length of scratches. Surface features can visually present the damage to the wire rope surface and help determine the overall damage status.

[0073] In one embodiment of this disclosure, signal features and surface features are fused to obtain the fused features of the target wire rope, including: The correlation coefficient is determined based on signal characteristics and surface characteristics; If the correlation coefficient is greater than or equal to the first correlation threshold, the signal features and surface features are weighted and fused to obtain the fused features of the target steel wire rope. If the correlation coefficient is less than the first correlation threshold, the signal features and surface features are directly spliced ​​together to obtain the fused features of the target wire rope.

[0074] The first relevant threshold can be set based on experience.

[0075] The correlation coefficient can be calculated using the formula for the Pearson correlation coefficient.

[0076] Weighted fusion of signal features and surface features includes: In response to the fact that signal features are more important than surface features, the weight of signal features is increased and the weight of surface features is decreased. Since the importance of signal features is less than that of surface features, the weight of signal features is reduced and the weight of surface features is increased. The weights of the signal features and the surface features are added together to equal 1.

[0077] The signal features and surface features are directly concatenated, that is, the signal feature vector and the surface feature vector are directly concatenated in sequence to form a new feature vector.

[0078] The second detection model is used to analyze the fused features and determine the damage state of the target wire rope. The second detection model can be a trained neural network model. The fused features are used as input. The neural network determines the presence of various damages such as broken wires, wear and corrosion in the wire rope based on the correspondence between the features learned during training and the damage, and gives the location and severity of the damage.

[0079] As can be seen from the above, this embodiment can comprehensively and accurately capture the signal and surface features of the wire rope, and obtain richer fused features through fusion processing, providing more reliable data support for damage state judgment. Simultaneously, using the second detection model to conduct in-depth analysis of the fused features can further improve the accuracy and reliability of damage state detection, helping to promptly identify potential safety hazards and ensure the safe use of the wire rope.

[0080] In one embodiment of this disclosure, the online detection method for steel wire rope further includes: The service life of the target wire rope is assessed based on the damage condition detection results.

[0081] In this embodiment, the damage status detection results may include information such as whether the target wire rope is damaged, the type of damage, the location of the damage, or the severity of the damage.

[0082] The service life of the target wire rope is the period from when the wire rope is put into use until it is damaged or its performance deteriorates and can no longer meet safety and work requirements, requiring replacement or repair, or the number of work cycles that can be completed within this period, etc.

[0083] The damage detection results are evaluated based on a trained multi-layer neural network model to determine the service life of the target wire rope.

[0084] The trained multilayer neural network model is obtained by training the multilayer neural network model based on historical damage state detection results and corresponding historical service life. The damage state detection results (such as the number of broken wires, the degree of wear, etc.) are used as input layer data, and after nonlinear transformation in the hidden layer, the remaining service life of the target wire rope is obtained in the output layer.

[0085] As can be seen from the above, this embodiment can not only accurately determine the damage state, but also assess the service life accordingly, realizing comprehensive monitoring of the wire rope condition and improving detection efficiency and accuracy.

[0086] Corresponding to the wire rope online inspection method in the above embodiment, Figure 2 This is a structural block diagram of an online wire rope inspection device provided according to an embodiment of the present disclosure. For ease of explanation, only the parts relevant to the embodiment of the present disclosure are shown. References Figure 2 The online wire rope inspection device 20 includes: an inspection requirement determination module 21, an inspection strategy determination module 22, and an inspection result analysis module 23.

[0087] Among them, the detection requirement determination module 21 is used to determine the first detection requirement based on the detection focus of the target steel wire rope, and to determine the second detection requirement based on the scene characteristics of the target steel wire rope. The detection strategy determination module 22 is used to determine the target detection strategy of the target wire rope based on the first detection requirement and the second detection requirement. The target detection strategy includes the first detection model and the second detection model. The detection result analysis module 23 is used to detect the physical characteristics of the target wire rope based on the target detection strategy and obtain the damage state detection result.

[0088] In one embodiment of this disclosure, the first detection requirement includes local defect detection, global defect detection, and defect location detection; the second detection requirement includes single detection and combined detection. The detection strategy determination module 22 is further used to respond to the first detection requirement being local defect detection and the second detection requirement being single detection, and to use the first detection model as the target detection strategy for the target wire rope. In response to the first detection requirement being global defect detection or defect location detection, and the second detection requirement being joint detection, the second detection model is used as the target detection strategy for the target wire rope.

[0089] In one embodiment of this disclosure, the detection result analysis module 23 is specifically used to detect the physical characteristics of the target wire rope based on the first detection model in response to the target detection strategy being the first detection model, and to determine the damage state detection result. The target detection strategy is a second detection model. Based on the second detection model, the physical characteristics of the wire rope are detected to determine the damage status detection result.

[0090] In one embodiment of this disclosure, the detection result analysis module 23 is further used to determine the leakage magnetic signal of the target wire rope based on weak magnetic field detection. Signal processing is performed on the leakage magnetic signal to obtain the target signal characteristics; The target signal features are analyzed based on the first detection model to determine the damage state detection result.

[0091] In one embodiment of this disclosure, the detection result analysis module 23 is further used to determine the signal characteristics of the target wire rope based on weak magnetic field detection. The surface features of the target steel wire rope are determined based on machine vision recognition. The signal features and surface features are fused to obtain the fused features of the target steel wire rope; The fusion features are analyzed based on the second detection model to determine the damage state detection results.

[0092] In one embodiment of this disclosure, the detection result analysis module 23 is further used to determine the correlation coefficient based on signal features and surface features; If the correlation coefficient is greater than or equal to the first correlation threshold, the signal features and surface features are weighted and fused to obtain the fused features of the target steel wire rope. If the correlation coefficient is less than the first correlation threshold, the signal features and surface features are directly spliced ​​together to obtain the fused features of the target wire rope.

[0093] In one embodiment of this disclosure, the wire rope online detection device 20 further includes: a service life assessment module; The service life assessment module is used to assess the service life of the target wire rope based on the damage status detection results.

[0094] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of the present disclosure. Figure 3The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of each module / unit in the above-described device embodiments, for example... Figure 2 The functions of modules 21 to 23 are shown.

[0095] It should be understood that, in the embodiments of this disclosure, the processor 301 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0096] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0097] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store device type information.

[0098] In specific implementations, the processor 301, input device 302, and output device 303 described in this disclosure embodiment can execute the implementation methods described in the first and second embodiments of the wire rope online detection method provided in this disclosure embodiment, or they can execute the implementation methods of the electronic device described in this disclosure embodiment, which will not be repeated here.

[0099] In another embodiment of this disclosure, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to implement these processes. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0100] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0101] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. 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 implementation should not be considered beyond the scope of this disclosure.

[0102] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0103] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, 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 couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces or units, or they may be electrical, mechanical, or other forms of connection.

[0104] 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 the embodiments of this disclosure, depending on actual needs.

[0105] Furthermore, the functional units in the various embodiments of this disclosure 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. The integrated unit can be implemented in hardware or as a software functional unit.

[0106] The above are merely specific embodiments of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this disclosure, and these modifications or substitutions should all be covered within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A method for online inspection of steel wire ropes, characterized in that, include: The first inspection requirement is determined based on the inspection focus of the target steel wire rope, and the second inspection requirement is determined based on the scene characteristics of the target steel wire rope. Based on the first detection requirement and the second detection requirement, a target detection strategy for the target steel wire rope is determined, and the target detection strategy includes a first detection model and a second detection model. The physical characteristics of the target wire rope are detected based on the target detection strategy to obtain the damage state detection result.

2. The online inspection method for steel wire rope as described in claim 1, characterized in that, The first detection requirement includes local defect detection, global defect detection, and defect location detection; the second detection requirement includes single detection and combined detection. The target detection strategy for determining the target wire rope based on the first detection requirement and the second detection requirement includes: In response to the first detection requirement being the detection of local defects and the second detection requirement being the detection of a single defect, the first detection model is used as the target detection strategy for the target wire rope. In response to the first detection requirement being either global defect detection or defect location detection, and the second detection requirement being joint detection, the second detection model is used as the target detection strategy for the target wire rope.

3. The online inspection method for steel wire rope as described in claim 1, characterized in that, The step of detecting the physical characteristics of the target wire rope based on the target detection strategy to obtain damage state detection results includes: In response to the target detection strategy being the first detection model, the physical characteristics of the target wire rope are detected based on the first detection model to determine the damage state detection result; In response to the target detection strategy being the second detection model, the physical characteristics of the target wire rope are detected based on the second detection model to determine the damage state detection result.

4. The online inspection method for steel wire rope as described in claim 3, characterized in that, The step of detecting the physical characteristics of the target wire rope based on the first detection model to determine the damage state detection result includes: The leakage magnetic signal of the target wire rope is determined based on weak magnetic field detection; The leakage magnetic signal is processed to obtain the target signal characteristics; The target signal features are analyzed based on the first detection model to determine the damage state detection result.

5. The online inspection method for steel wire rope as described in claim 3, characterized in that, The step of detecting the physical characteristics of the target wire rope based on the second detection model to determine the damage state detection result includes: The signal characteristics of the target steel wire rope are determined based on weak magnetic field detection; The surface features of the target steel wire rope are determined based on machine vision recognition. The signal features and the surface features are fused to obtain the fused features of the target wire rope; The fusion features are analyzed based on the second detection model to determine the damage state detection result.

6. The online inspection method for steel wire rope as described in claim 5, characterized in that, The process of fusing the signal features and the surface features to obtain the fused features of the target wire rope includes: The correlation coefficient is determined based on the signal characteristics and the surface characteristics; If the correlation coefficient is greater than or equal to the first correlation threshold, then the signal features and the surface features are weighted and fused to obtain the fused features of the target steel wire rope; If the correlation coefficient is less than the first correlation threshold, the signal features and the surface features are directly spliced ​​together to obtain the fused features of the target wire rope.

7. The online inspection method for steel wire rope as described in claim 1, characterized in that, Also includes: The service life of the target wire rope is evaluated based on the damage state detection results.

8. An online inspection device for steel wire ropes, characterized in that, include: The detection requirement determination module is used to determine the first detection requirement based on the detection focus of the target steel wire rope, and to determine the second detection requirement based on the scene characteristics of the target steel wire rope. The detection strategy determination module is used to determine the target detection strategy for the target wire rope based on the first detection requirement and the second detection requirement. The target detection strategy includes a first detection model and a second detection model. The detection result analysis module is used to detect the physical characteristics of the target wire rope based on the target detection strategy and obtain the damage state detection result.

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 steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images