Mine steel wire rope detection system based on multi-modal data detection

Abstract

The invention relates to the technical field of mine safety detection, and discloses a mine steel wire rope detection system based on multi-modal data detection. According to the mine steel wire rope detection system based on multi-modal data detection, by integrating multiple paths of electromagnetic sensors and a high-precision 3D laser scanning technology, electromagnetic signals and surface contour data of a steel wire rope can be collected in real time, comprehensive monitoring of internal and external defects of the steel wire rope is achieved, and compared with a traditional detection technology, the detection system has the advantages that the detection efficiency is high; the system overcomes the limitation of a single-path detection probe, more accurate and quantitative defect information can be provided, operators are helped to recognize potential safety hazards in time, in addition, generated structured data and detailed detection reports can visually display the health state of the steel wire rope, and the safety of the steel wire rope is improved. And an alarm mechanism can be triggered according to the risk level of the defect, so that maintenance measures are taken in time, the risk of accidents is reduced, and safety and high efficiency of mine operation are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of mine safety detection, and in particular to a mine wire rope detection system based on multimodal data detection. Background Art

[0002] In mining operations, wire ropes are essential equipment for hoisting, transportation, and traction. Due to long-term use and complex working environments, wire ropes are susceptible to various forms of damage, including wear, corrosion, and wire breakage. These defects are often difficult to detect visually, and due to factors such as load fluctuations and environmental influences during use, defects can rapidly intensify, leading to potential safety hazards. Therefore, regular and comprehensive wire rope inspection and maintenance to ensure safety and performance are key tasks in mine management.

[0003] However, existing wire rope inspection technologies face numerous challenges. For example, the limited magnetization degree of traditional magnetizers limits the results obtained through electromagnetic inspection. This is particularly true when detecting internal defects in wire ropes, where the use of a single-path inspection probe often fails to provide a comprehensive and accurate picture of the defect status. Electromagnetic technology often struggles to provide quantitative numerical results when inspecting for rust and wear, leading to a lack of sufficient basis for assessing the overall health of the wire rope. Furthermore, according to the Wire Rope Standard (GB Standard), diameter inspection is considered an important basis for judging wire rope performance. However, relying solely on diameter inspection cannot fully reflect the actual condition of the wire rope. In particular, in the presence of internal or external defects, changes in diameter may not immediately reveal potential safety issues. This inspection method also suffers from a low level of visualization, making it difficult to provide intuitive information to operators, which in turn hinders the ability to take timely maintenance measures. Summary of the Invention

[0004] (1) Technical problems solved In response to the shortcomings of the existing technology, the present invention provides a wire rope detection system for mining based on multimodal data detection. By integrating multi-channel electromagnetic sensors and high-precision 3D laser scanning technology, it can collect the electromagnetic signals and surface profile data of the wire rope in real time, and realize comprehensive monitoring of internal and external defects of the wire rope. Compared with traditional detection technology, this system overcomes the limitations of single-channel inspection probes, and can provide more accurate and quantitative defect information to help operators identify potential safety hazards in a timely manner. In addition, the generated structured data and detailed inspection reports can not only intuitively display the health status of the wire rope, but also trigger the alarm mechanism according to the risk level of the defect, so as to take maintenance measures in time, reduce the risk of accidents, and ensure the safety and efficiency of mining operations. This comprehensive detection method significantly improves the visualization of wire rope detection and provides a scientific basis for mine safety management.

[0005] (2) Technical solution To achieve the above objectives, the present invention provides the following technical solutions: a wire rope detection system for mining based on multimodal data detection, comprising a wire rope multi-channel electromagnetic sensor acquisition module, a wire rope multi-channel 3D laser acquisition module, a wire rope flaw detection and identification data processing module, and a wire rope flaw detection alarm reporting module; The wire rope multi-channel electromagnetic sensor acquisition module is used to arrange multiple electromagnetic sensors around the wire rope to collect the electromagnetic signals of the wire rope in real time, convert the analog signals into digital signals through an analog-to-digital converter, and transmit the processed digital signals to the wire rope flaw detection and identification data processing module after standard formatting; The wire rope multi-channel 3D laser acquisition module is used to use a high-precision 3D laser scanner to comprehensively scan the wire rope, obtain surface profile data, calculate the diameter, cross-sectional shape and surface texture of the wire rope, generate wire rope 3D model format data, and transmit the generated wire rope 3D model format data to the wire rope flaw detection and identification data processing module; The wire rope flaw detection and identification data processing module is used to receive data from the wire rope multi-channel electromagnetic sensor acquisition module and the wire rope multi-channel 3D laser acquisition module, identify wire rope defects and generate a defect parameter list through comprehensive analysis and data fusion processing, generate structured data based on the processing results, and transmit it to the wire rope flaw detection alarm reporting module; The wire rope flaw detection alarm reporting module is used to generate a detailed inspection report based on the output results of the wire rope flaw detection identification data processing module, calculate the risk level of defects and set the wire rope alarm mechanism, issue an alarm signal in a timely manner, and store the inspection report and alarm signal in the database for subsequent query and analysis.

[0006] Preferably, the formula for converting the analog signal into a digital signal is as follows: In the formula, Indicates the The digital signal value of the samples, Indicates the sampling time point The analog voltage value, 、 are the minimum and maximum range values ​​of the analog input signal, Indicates the number of ADC bits.

[0007] Preferably, the formula for applying standard formatting to the processed digital signal is as follows: In the formula, represents the standardized digital signal, represents the original digital signal, Represents the minimum value of the original digital signal, Indicates the maximum value of the original digital signal.

[0008] Preferably, the formula for calculating the diameter of the wire rope is as follows: In the formula, Indicates the diameter of the wire rope, Indicates the The spatial coordinates of the contour points, represents the coordinates of the center of the fitted circle, represents the distance from a point to the center of the circle, Represents the maximum value function.

[0009] Preferably, the formula for calculating the cross-sectional shape of the steel wire rope is as follows: In the formula, represents the objective function, Indicates the The two-dimensional coordinates of the contour points, represents the coordinates of the center point of the fitted ellipse, represents the length of the major semi-axis of the ellipse, represents the length of the minor semi-axis of the ellipse, Indicates the total number of points.

[0010] Preferably, the formula for calculating the surface texture of the wire rope is as follows: In the formula, Indicates the grayscale of the wire rope surface. , represents the gray level index, Represents the gray-level co-occurrence matrix elements.

[0011] Preferably, the three-dimensional model of the steel wire rope is defined as follows: In the formula, represents the coordinates of the wire rope point on the surface, Represents an index, represents the order of the control point, Indicates the About The basis functions of Indicates the About The basis functions of Represents a point on the control point grid, which is used to define the shape of the surface. The surface is formed by linearly combining the positions of the basis functions.

[0012] Preferably, the steel wire rope defects are defined by the following defect classification model: In the formula, represents the output of the defect classification model, represents the candidate category, Indicates the category used to select the maximum probability. Indicates that given a feature vector After, category The probability of Indicates a normal defect type.

[0013] Preferably, the risk level calculation formula of the defect is as follows: In the formula, Indicates the risk level of the defect, Indicates the Defect parameters, Indicates the maximum allowable value of the defect parameter, Indicates the defect parameter weight assigned according to the defect type.

[0014] Preferably, the triggering conditions for setting the wire rope alarm mechanism are as follows: When the risk level of the defect System risk threshold When the alarm is triggered.

[0015] Compared with the existing technology, the present invention provides a mining wire rope detection system based on multimodal data detection, which has the following beneficial effects: By integrating multi-channel electromagnetic sensors and high-precision 3D laser scanning technology, the present invention can collect the electromagnetic signals and surface profile data of the wire rope in real time, and realize comprehensive monitoring of the internal and external defects of the wire rope. Compared with traditional detection technology, this system overcomes the limitations of single-channel inspection probes and can provide more accurate and quantitative defect information to help operators identify potential safety hazards in a timely manner. In addition, the generated structured data and detailed inspection reports can not only intuitively display the health status of the wire rope, but also trigger the alarm mechanism through the risk level of the defect, so as to take maintenance measures in time, reduce the risk of accidents, and ensure the safety and efficiency of mining operations. This comprehensive detection method significantly improves the visualization of wire rope detection and provides a scientific basis for mine safety management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1Schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] In order to solve the problem that the existing magnetizer has limited magnetization degree and the detection accuracy of the single-path inspection probe is limited and cannot accurately reflect the defect status, a mining wire rope inspection system based on multimodal data detection is proposed. Figure 1 The system includes a wire rope multi-channel electromagnetic sensor acquisition module, a wire rope multi-channel 3D laser acquisition module, a wire rope flaw detection and identification data processing module, and a wire rope flaw detection alarm reporting module; To achieve real-time monitoring of wire ropes, multiple highly sensitive electromagnetic sensors (such as Hall sensors or induction coil arrays) are arranged on the surface of the wire rope and in its vicinity. These sensors can continuously monitor changes in the electromagnetic field of the wire rope and promptly capture defect signals such as cracks, broken wires, and corrosion. The analog voltage signal detected by the sensor is pre-amplified and filtered before being sampled by a high-speed analog-to-digital converter (ADC). The continuous analog signal is converted into a discrete digital signal. During the signal conversion process, the original analog signal is normalized using the following formula: in, It is The analog signal value of the sampling point, and are the lowest and highest voltage values ​​of the sensor's operating range (obtained after calibration), The function of this formula is to linearly map the analog signal to the digital range, ensuring that the digital value of each sampling point is between 0 and The normalized digital signal is further transmitted to the wire rope flaw detection and identification data processing module. The combination of multimodal feature fusion and machine learning algorithm helps to accurately identify the type, location and severity of wire rope defects and realize early fault warning. This method ensures the standardization and comparability of multi-channel signals, improves the stability and anti-interference ability of detection, strengthens the real-time data processing capability, and provides reliable technical support for the safe operation of wire ropes. In order to achieve comprehensive and detailed inspection and condition assessment of the wire rope, high-precision 3D laser scanning technology is used. Professional high-precision 3D laser scanners are arranged around the wire rope. Through multi-angle and multi-distance scanning methods, the complex geometric contour data of the wire rope surface is fully captured. After the acquisition is completed, the original point cloud is filtered, registered and reconstructed using a point cloud processing algorithm to remove noise and redundant information. The triangular mesh reconstruction technology is used to generate high-precision 3D model data. The maximum distance between the point set in the model and the center line or reference point of the wire rope is calculated. The formula is as follows: This distance measures the maximum deviation of the wire rope, facilitating the identification of areas of deformation, wear, or fracture. It also quantitatively analyzes the diameter, cross-sectional shape, and surface texture of the wire rope, thereby obtaining detailed geometric feature information. Next, a parameterized B-spline kernel function is used to expand the point cloud data into a parameter space, forming a continuous 3D surface model: in, and are basis functions along the two parameter directions, The corresponding control points describe the smooth changes and detailed features of the wire rope surface. Using the generated three-dimensional model data, the surface texture features such as the contrast in the gray-level co-occurrence matrix index can be extracted. The formula is: here, It represents the joint probability of the gray value pairs in the gray level co-occurrence matrix, reflecting the intensity of the change in surface texture, which helps to identify the severity of surface damage or defects. In addition, a distance transformation formula is introduced to evaluate the With the target point The distance is expressed as: Among them, the parameters and The horizontal and vertical scale coefficients are adjusted separately to measure the offset deformation of the target point relative to the center point. Combining geometric distance, surface texture and deformation indicators, this system realizes multi-dimensional and multi-scale wire rope defect detection, greatly improving the comprehensiveness, accuracy and intelligence level of detection, ensuring the safe operation and maintenance efficiency of wire ropes. To achieve intelligent detection and fault diagnosis of wire ropes, the wire rope flaw detection and identification data processing module plays a core role in the system. Its main task is to receive and analyze electromagnetic signals collected by multiple electromagnetic sensors and surface profile data acquired by multiple 3D laser scanners. By fusing multimodal data and adopting advanced data fusion algorithms (such as Kalman filtering, Bayesian fusion, or deep learning fusion networks), information complementation and enhancement are achieved, thereby obtaining more comprehensive and reliable wire rope status characteristics. Then, using the extracted multidimensional feature vectors and using trained defect classification models, such as machine learning models based on random forests, support vector machines (SVMs), or deep neural networks (DNNs), the posterior probability corresponding to each category (normal or multi-class defects) is calculated: Then, according to the maximum a posteriori probability principle, the prediction results of the defect category are obtained: This process essentially involves probabilistic inference in a multimodal feature space, automatically determining whether the wire rope has defects and the specific type of defect (such as cracks, corrosion, broken wires, etc.). Based on the identification, the system also generates a detailed defect parameter list, including structured parameters such as the defect's location, size, shape, and severity, to facilitate subsequent diagnosis and maintenance decisions. In addition, the detection results are encapsulated into standardized structured data and transmitted to the wire rope flaw detection alarm reporting module for immediate warning and maintenance scheduling. This workflow realizes the effective integration of multi-source and multi-modal information and intelligent decision-making, greatly improving the accuracy and real-time performance of defect identification, and providing reliable protection for the safe operation of the wire rope. The wire rope flaw detection alarm reporting module plays a key role in the monitoring system. Its main function is to generate detailed inspection reports and calculate the risk level of defects based on the structured inspection data provided by the wire rope flaw detection identification module. It also ensures timely response to potential safety hazards by setting a reasonable alarm mechanism. Specifically, the system first calculates the risk index for each potential defect or abnormal point by combining the multi-dimensional characteristics of the defect severity, location, size, etc. using the risk assessment model. The index is the weight of each defect. Maximum safety value of the corresponding defect The sum of products: in, Indicates the importance or risk factor of different defect characteristics. The model parameters obtained through training reflect the impact of each defect on the overall safety status of the wire rope. Representative The system uses the preset risk threshold to determine the maximum hazard parameter of each defect (such as crack length, depth or corrosion thickness, etc.). , determine the degree of risk: like ⇒ Triggering an alarm means that once the risk value exceeds the safety warning line, the system immediately issues an alarm signal, activating audible and visual alarms or remote notifications, prompting maintenance personnel to take timely action. Simultaneously, the inspection report details the defect location, parameters, risk level, and alarm events, and stores all data in a database to facilitate subsequent trend analysis, fault diagnosis, and maintenance scheduling. This solution utilizes a multi-dimensional risk assessment model to achieve accurate and intelligent early warning, effectively reducing the occurrence of wire rope failures and ensuring safe operation. This provides a reliable basis for decision-making and full-process monitoring for wire rope maintenance.

[0019] Example 1: By applying the present invention to conduct wire rope flaw detection risk assessment: First, the defect parameters of the wire rope, including crack length and corrosion depth, are obtained through on-site inspection equipment. A high-speed, high-definition camera combined with an image processing algorithm continuously captures images of the wire rope surface while it is in operation. An edge detection neural network is then used to automatically segment and measure the cracks in the image, obtaining crack length data. For example, in one inspection, image analysis revealed a crack length of 12 mm. The corrosion area of ​​the wire rope is scanned in three dimensions or ultrasonically inspected using a laser scanner or ultrasonic testing instrument to measure the depth of the corrosion area. During the inspection, it was determined that the corrosion depth of the wire rope was 3 mm. Next, to facilitate risk assessment, the parameters obtained from the test are compared with the maximum allowable values ​​of industry standards or design specifications to establish normalized parameters: The maximum permissible length of cracks is specified by national or industry standards (such as ISO and GB standards) and is 20 mm; The maximum permissible corrosion depth, as determined by relevant standards or design requirements, is 5 mm; When performing risk calculations, we combined expert experience and statistical data to assign weights to different defect parameters. Crack length has a greater impact on safety, so its weight coefficient is set to 0.6, and the corrosion depth weight is set to 0.4. The risk level calculation formula of the application defect according to the present invention is: According to the system's preset risk threshold of 1.5, determine whether the risk value exceeds the standard: like , that is, the risk exceeds 1.5, the system automatically triggers the early warning alarm, emits sound and light or remote safety warning information to prompt maintenance personnel to take corresponding measures; In the above example, the calculated result is 1.67, which exceeds the preset threshold. Therefore, the system will issue an alarm signal, indicating that there is a major potential defect in the wire rope and there is a risk of breakage or failure. Example 2: By applying the present invention to conduct wire rope flaw detection risk assessment: First, the defect parameters of the wire rope are collected through a variety of detection equipment: Crack length: A high-definition camera combined with an image recognition algorithm is used to capture and analyze cracks on the surface of the wire rope and extract the crack length. In this test, the crack length was 16 mm, far below the industry's maximum allowable value of 20 mm. Corrosion depth: Using a laser scanner or ultrasonic detector, the depth of the corroded area was measured and the corrosion depth was 4 mm, which is close to the maximum allowable value but does not exceed the limit; Industry standards or design specifications stipulate: The maximum permissible value of cracks is 20 mm, and the maximum permissible value of corrosion depth is 5 mm; Based on empirical analysis, crack length has a greater impact on structural safety, so it is given a weight coefficient of 0.6; corrosion depth has a smaller impact, and its weight coefficient is 0.4; The risk level calculation formula of the application defect according to the present invention is: According to the system's preset risk threshold of 1.5, determine whether the risk value exceeds the standard: Since the risk index It is less than the preset alarm threshold (1.5), so the system determines that the current state of the wire rope is safe and does not trigger an early warning; In this embodiment, the defect parameters obtained through on-site detection show that the risk of the wire rope is low and the risk index does not exceed the threshold. Therefore, the system will not issue an early warning signal to the maintenance personnel, ensuring normal safety monitoring without false alarms.

[0020] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A mining wire rope detection system based on multimodal data detection, characterized by: It includes a wire rope multi-channel electromagnetic sensor acquisition module, a wire rope multi-channel 3D laser acquisition module, a wire rope flaw detection and identification data processing module, and a wire rope flaw detection alarm reporting module; The wire rope multi-channel electromagnetic sensor acquisition module is used to arrange multiple electromagnetic sensors around the wire rope to collect the electromagnetic signals of the wire rope in real time, convert the analog signals into digital signals through an analog-to-digital converter, and transmit the processed digital signals to the wire rope flaw detection and identification data processing module after standard formatting; The wire rope multi-channel 3D laser acquisition module is used to use a high-precision 3D laser scanner to comprehensively scan the wire rope, obtain surface profile data, calculate the diameter, cross-sectional shape and surface texture of the wire rope, generate wire rope 3D model format data, and transmit the generated wire rope 3D model format data to the wire rope flaw detection and identification data processing module; The wire rope flaw detection and identification data processing module is used to receive data from the wire rope multi-channel electromagnetic sensor acquisition module and the wire rope multi-channel 3D laser acquisition module, identify wire rope defects and generate a defect parameter list through comprehensive analysis and data fusion processing, generate structured data based on the processing results, and transmit it to the wire rope flaw detection alarm reporting module; The wire rope flaw detection alarm reporting module is used to generate a detailed inspection report based on the output results of the wire rope flaw detection identification data processing module, calculate the risk level of defects and set the wire rope alarm mechanism, issue an alarm signal in a timely manner, and store the inspection report and alarm signal in the database for subsequent query and analysis.

2. The mining wire rope detection system based on multimodal data detection according to claim 1, characterized in that: The formula used to convert the analog signal to a digital signal is as follows: In the formula, Indicates the The digital signal value of the samples, Indicates the sampling time point The analog voltage value, 、 are the minimum and maximum range values ​​of the analog input signal, Indicates the number of ADC bits.

3. The mining wire rope detection system based on multimodal data detection according to claim 2, characterized in that: The formula for applying the standard formatting to the processed digital signal is as follows: In the formula, represents the standardized digital signal, represents the original digital signal, Represents the minimum value of the original digital signal, Indicates the maximum value of the original digital signal.

4. The mining wire rope detection system based on multimodal data detection according to claim 3, characterized in that: The formula for calculating the diameter of the wire rope is as follows: In the formula, Indicates the diameter of the wire rope, Indicates the The spatial coordinates of the contour points, represents the coordinates of the center of the fitted circle, represents the distance from a point to the center of the circle, Represents the maximum value function.

5. The mining wire rope detection system based on multimodal data detection according to claim 4, characterized in that: The formula for calculating the cross-sectional shape of the wire rope is as follows: In the formula, represents the objective function, Indicates the The two-dimensional coordinates of the contour points, represents the coordinates of the center point of the fitted ellipse, represents the length of the major semi-axis of the ellipse, represents the length of the minor semi-axis of the ellipse, Indicates the total number of points.

6. The mining wire rope detection system based on multimodal data detection according to claim 5, characterized in that: The formula for calculating the surface texture of the wire rope is as follows: In the formula, Indicates the grayscale of the wire rope surface. , represents the gray level index, Represents the gray-level co-occurrence matrix elements.

7. The mining wire rope detection system based on multimodal data detection according to claim 6, characterized in that: The three-dimensional model of the wire rope is defined as follows: In the formula, represents the coordinates of the wire rope point on the surface, Represents an index, represents the order of the control point, Indicates the About The basis functions of Indicates the About The basis functions of Represents a point on the control point grid, which is used to define the shape of the surface. The surface is formed by linearly combining the positions of the basis functions.

8. The mining wire rope detection system based on multimodal data detection according to claim 7, characterized in that: The wire rope defects are defined by the following defect classification model: In the formula, represents the output of the defect classification model, represents the candidate category, Indicates the category used to select the maximum probability. Indicates that given a feature vector After, category The probability of Indicates a normal defect type.

9. The mining wire rope detection system based on multimodal data detection according to claim 8, characterized in that: The formula for calculating the risk level of the defect is as follows: In the formula, Indicates the risk level of the defect, Indicates the Defect parameters, Indicates the maximum allowable value of the defect parameter, Indicates the defect parameter weight assigned according to the defect type.

10. The mining wire rope detection system based on multimodal data detection according to claim 9, characterized in that: The triggering conditions for setting the wire rope alarm mechanism are as follows: When the risk level of the defect System risk threshold When the alarm is triggered.

Images