Anchor rod / cable axial force intelligent detection method and system

Abstract

The embodiment of the invention relates to the technical field of advanced manufacturing and intelligent sensing of mine safety equipment, and discloses an anchor rod / cable axial force intelligent detection method and system, and the method comprises the steps: collecting original point cloud data and environment temperature data of a passive random deformation device connected with an anchor rod / cable; the method comprises the following steps: preprocessing original point cloud data through an analysis system, and performing feature extraction on the preprocessed point cloud data to obtain key point cloud data capable of reflecting structural features and deformation states of a passive random deformation device; on the basis of the key point cloud data and standard point cloud data in a standard model, the free end displacement of the passive random deformation device is obtained; calling calibration parameters under the environment temperature data from a temperature deformation pressure three-dimensional mapping database; determining the initial axial force of the anchor rod / cable based on the calibration parameters and the free end displacement; and under the condition that the relation between the initial axial force and the designed axial force meets the preset condition, the initial axial force is stored as the target axial force of the anchor rod / cable.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of advanced manufacturing and intelligent sensing technology of mine safety equipment, and relates to, but is not limited to, an anchor rod / cable axial force intelligent detection method and system. BACKGROUND

[0002] Current anchor rod / cable axial force detection mainly relies on electronic force gauges (such as vibrating wire sensors) or stress wave devices, which have three major bottlenecks: the failure rate of electronic devices in the underground high-humidity, strong-shock, and strong-electromagnetic interference environment is over 30%, and the reliability is poor; the cost of single-point detection is relatively high, and it is difficult to achieve large-scale deployment of tens of thousands of anchor rods underground; the resolution of existing mechanical pressure gauges (such as pointer type) is insufficient 5 kilonewtons, and cannot meet the precision requirements of roof separation micro-change early warning. These problems result in less than 15% coverage of underground support quality detection, forming a huge safety hazard and seriously threatening mine safety production. SUMMARY

[0003] Therefore, the embodiments of the present application provide an anchor rod / cable axial force intelligent detection method and system to solve the problems of high detection cost and low detection precision.

[0004] The technical scheme of the embodiments of the present application is as follows: In a first aspect, the embodiments of the present application provide an anchor rod / cable axial force intelligent detection method applied to an intelligent detection system, the intelligent detection system comprising a passive random deformation device, intelligent detection equipment, and an analysis system, and the method comprising: The original point cloud data and the environmental temperature data of the passive random deformation device connected with the anchor rod / cable are collected by the intelligent detection equipment, the passive random deformation device is used to convert the axial force of the anchor rod / cable into mechanical deformation that can be captured by the intelligent detection equipment; The original point cloud data is preprocessed by the analysis system to obtain preprocessed point cloud data, and the preprocessed point cloud data is feature extracted to obtain key point cloud data, the key point cloud data being point cloud data that can reflect the structural features and deformation state of the passive random deformation device; The free end displacement of the passive random deformation device is obtained by the analysis system based on the key point cloud data and standard point cloud data in a standard model, the standard point cloud data being point cloud data when the passive random deformation device is in an original state without force; The calibration parameters under the environmental temperature data are called from a temperature deformation pressure three-dimensional mapping database by the analysis system; based on the calibration parameters and the free end displacement, the initial axial force of the anchor rod / cable is determined; In a case where a relationship between the initial axial force and a design axial force meets a preset condition, the analysis system stores the initial axial force as a target axial force of the anchor rod / cable.

[0005] In a second aspect, the embodiments of the present application provide an anchor rod / cable axial force intelligent detection system, which comprises a passive state deformation device, an intelligent detection device and an analysis system, wherein: The intelligent detection device is configured to collect original point cloud data and environmental temperature data of the passive state deformation device connected to the anchor rod / cable, and the passive state deformation device is configured to convert an axial force of the anchor rod / cable into a mechanical deformation that can be captured by the intelligent detection device. The analysis system is configured to pre-process the original point cloud data to obtain pre-processed point cloud data, and extract features from the pre-processed point cloud data to obtain key point cloud data, which is point cloud data capable of reflecting structural features and deformation states of the passive state deformation device. The analysis system is further configured to obtain a free end displacement of the passive state deformation device based on the key point cloud data and standard point cloud data in a standard model, and the standard point cloud data is point cloud data of the passive state deformation device in an original state without force. The analysis system is further configured to call calibration parameters under the environmental temperature data from a temperature deformation pressure three-dimensional mapping database, and determine an initial axial force of the anchor rod / cable based on the calibration parameters and the free end displacement. The analysis system is further configured to store the initial axial force as a target axial force of the anchor rod / cable in a case where a relationship between the initial axial force and a design axial force meets a preset condition.

[0006] The technical solutions provided by the embodiments of the present application have at least the following beneficial effects: The original point cloud data and the environmental temperature data are collected by the intelligent detection device, and the analysis system performs a series of operations such as pre-processing and feature extraction, so that the axial force of the anchor rod / cable can be automatically and intelligently detected without manual complex measurement and calculation, thereby improving the detection efficiency and accuracy and reducing the detection cost. The environmental temperature data are collected, and the calibration parameters are called from the temperature deformation pressure three-dimensional mapping database, so that the influence of temperature change on the measurement result can be compensated, thereby improving the adaptability and measurement accuracy of the detection method under different environmental conditions. The passive state deformation device is used to convert the axial force of the anchor rod / cable into a mechanical deformation, and then the point cloud data are collected for analysis, so that the indirect measurement method can avoid some difficulties that may be encountered when directly measuring the axial force, such as inconvenient sensor installation and low measurement accuracy, thereby further reducing the detection complexity and improving the detection accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can be obtained from these drawings without creative labor. Figure 1 A flowchart of an anchor rod / cable axial force intelligent detection method provided by the embodiments of the present application; Figure 2 A component structure diagram of an anchor rod / cable axial force intelligent detection system provided by the embodiments of the present application; Figure 3 A general component and working scene profile diagram of an anchor rod / cable axial force intelligent detection system provided by the embodiments of the present application; Figure 4 A structure plan view of a passive adaptive morphing device provided by the embodiments of the present application; Figure 5 A general structure diagram of an intelligent explosion-proof inspection robot provided by the embodiments of the present application. DETAILED DESCRIPTION

[0008] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments. The following embodiments are used to illustrate the present application, but not to limit the scope of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0009] In the following description, “some embodiments” are described, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” can be the same subset or different subset of all possible embodiments, and can be combined with each other without conflict.

[0010] It should be noted that the terms “first\second\third” involved in the embodiments of the present application are only to distinguish similar objects, and do not represent a specific order of the objects. It can be understood that “first\second\third” can be interchanged with a specific order or sequence as allowed, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0011] Those skilled in the art can understand that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art in the field of embodiments of the present application. It should also be understood that terms such as those defined in a general dictionary have meanings consistent with those in the context of the prior art and should not be interpreted in an idealized or overly formal sense unless specifically defined as such herein.

[0012] The embodiments of the present application provide an anchor rod / cable axial force intelligent detection method, which is applied to an electronic device. The electronic device includes but is not limited to a mobile phone, a notebook computer, a tablet computer, a palm Internet device, a multimedia device, a streaming media device, a mobile Internet device, a wearable device or other types of electronic devices. The function realized by the method can be realized by calling program code in the processor of the electronic device, and of course the program code can be saved in a computer storage medium. Therefore, the electronic device at least includes a processor and a storage medium. The processor can be used for processing the anchor rod / cable axial force intelligent detection process, and the storage can be used for storing the data required in the anchor rod / cable axial force intelligent detection process and the generated data.

[0013] Figure 1 A flowchart of an anchor rod / cable axial force intelligent detection method provided by the embodiments of the present application is shown in the figure. The method is applied to an intelligent detection system, which includes a passive state deformation device, intelligent detection equipment and an analysis system. As shown in the figure, the method at least includes the following steps: Figure 1 Step S110, acquiring original point cloud data and environmental temperature data of the passive state deformation device connected with the anchor rod / cable by the intelligent detection equipment. The passive state deformation device is used to convert the axial force of the anchor rod / cable into mechanical deformation that can be captured by the intelligent detection equipment. ​The anchor rod / cable is the core supporting component of underground engineering such as a mine and a tunnel, and the "axial force" (i.e., the pulling force borne by the anchor rod / cable) directly determines the safety of the support. If the axial force is too large, the anchor rod may be broken and the support may fail. If the axial force is too small, the anchor rod / cable cannot play a role in fixing the surrounding rock. The passive dynamic deformation device connected to the anchor rod / cable serves as the pressure sensing front end of the intelligent detection system and is used to convert the axial force borne by the anchor rod / cable into mechanical deformation that can be observed. The passive dynamic deformation device is designed to be all-mechanical and passive, which can completely eliminate electrical signal interference and circuit failure. Point cloud data is obtained by intelligent detection equipment to obtain the three-dimensional coordinates of numerous points on the surface of the passive dynamic deformation device, forming a three-dimensional model of the passive dynamic deformation device. Since the mechanical deformation of the passive dynamic deformation device may be subtle, ordinary two-dimensional photos cannot accurately measure the deformation, but point cloud data can accurately calculate the displacement and deformation size (such as how many millimeters the free end moves) of the passive dynamic deformation device by comparing the three-dimensional models before and after deformation. Since temperature can affect mechanical deformation, environmental temperature data can be collected to correct the influence of temperature on deformation in subsequent axial force calculation.

[0014] In step S120, the original point cloud data is preprocessed by the analysis system to obtain preprocessed point cloud data, and feature extraction is performed on the preprocessed point cloud data to obtain key point cloud data. The key point cloud data is point cloud data that can reflect the structural characteristics and deformation state of the passive dynamic deformation device. The original point cloud data may have defects such as data redundancy, insufficient accuracy, and scattered information, so the original point cloud data can be preprocessed by denoising, registration, downsampling, and completion to eliminate interference and unify the format.

[0015] In one embodiment, preprocessing the original point cloud data can include denoising filtering and downsampling. The purpose of denoising filtering is to remove outlier points and noise points caused by underground dust, water mist, and laser scattering. The analysis system can use at least one of a statistical filtering algorithm and a radius filtering algorithm. Statistical filtering calculates the average distance of each point to all neighboring points. Assuming that the distance distribution of the entire point cloud conforms to a Gaussian distribution, points with a distance exceeding ±3 times the standard deviation of the mean value are considered outliers and are removed. This method can effectively filter obvious isolated noise. Radius filtering traverses each point in the point cloud and counts the number of neighboring points within a given radius sphere. If the number of neighboring points is lower than a predetermined threshold, the point is determined to have too low a density and is removed as noise. This method can clean up scattered noise floating outside the main point cloud.

[0016] The purpose of downsampling is to reduce the number of point clouds under the premise of ensuring the shape accuracy of the point cloud model through the voxel grid downsampling algorithm. The algorithm divides the three-dimensional space into tiny cubes (voxels) and replaces all points in each voxel with the center of gravity of all points in the voxel. This can significantly reduce the data volume and complexity of subsequent calculations while maintaining geometric features, improving processing efficiency.

[0017] The preprocessed point cloud data contains all the structure points of the passive state deformation device. From all the structure points, key point cloud data that can directly associate structure features and deformation states can be extracted. The point cloud data associated with the structure features are the landmark structure points of the passive state deformation device. The positions of these points are fixed and serve as the reference anchor points for judging deformation, such as the center of the bolt hole at the fixed end of the passive state deformation device connected to the anchor rod / cable, the edge points of the deformation reference surface designed for the passive state deformation device, etc. The point cloud data associated with the deformation state are the active deformation parts of the passive state deformation device. The positions of these points change with the axial force and are the core observation points for calculating the deformation amount, such as the vertex of the free deformation end of the passive state deformation device, the key contour points of the elastic deformation section of the passive state deformation device, etc.

[0018] In step S130, the analysis system obtains the free end displacement of the passive state deformation device based on the key point cloud data and standard point cloud data in the standard model. The standard point cloud data is the point cloud data when the passive state deformation device is in the original state without force. The key point cloud data is the corresponding point cloud data when the passive state deformation device is in the stressed state and can be used as the observation object after deformation. The standard point cloud data is the corresponding point cloud data when the passive state deformation device is in the original state without force and can be used as the reference template before deformation. By comparing the key point cloud data and the standard point cloud data, the free end displacement of the passive state deformation device can be calculated.

[0019] In step S140, the analysis system calls the calibration parameters under the environmental temperature data from the temperature deformation pressure three-dimensional mapping database. Based on the calibration parameters and the free end displacement, the initial axial force of the anchor rod / cable is determined. The analysis system, also known as an intelligent computing and analysis system or an intelligent analysis system, has edge computing capabilities and can realize real-time data processing and intelligent decision-making. It can inverse calculate the initial axial force based on the relationship model between the free end displacement and the axial force calibrated in the laboratory. FThe model error is <±2%. The relationship model includes the calibration parameters, which may include material coefficients k and b, where k represents the stiffness coefficient and b represents the correction parameter to offset the zero drift error of the system.

[0020] The temperature-deformation-pressure three-dimensional mapping database stores multiple calibration curves at different temperatures. These calibration curves establish a meaningful correspondence between the core output parameters of the calibrated equipment (usually signals related to deformation / displacement, such as free end displacement) and the input standard axial force at a specific temperature. They serve as the core basis for transforming abstract equipment signals into quantifiable physical quantities (force, displacement) and form the foundation for establishing the "temperature-deformation-pressure three-dimensional mapping database." By automatically calling the calibration curves for the corresponding temperature zones in the database and calculating the initial axial force based on the free end displacement, systematic errors caused by thermal expansion and contraction can be completely eliminated.

[0021] Step S150: When the relationship between the initial axial force and the design axial force meets the preset conditions, the analysis system stores the initial axial force as the target axial force of the anchor rod / cable.

[0022] Among them, the design axial force is the core reference for determining the ideal stress value or safe stress range in the early stage of the project based on the support requirements, material strength, and usage scenarios of the anchor bolts / cables. For example, it is the reasonable tensile force range that this type of anchor bolt should withstand in mine support. It is the benchmark for the analysis system to judge whether the initial axial force is qualified. The analysis system will pre-set a preset condition. The essence of this condition is the reasonable deviation range between the initial axial force and the design axial force. If the relationship between the initial axial force and the design axial force meets the preset condition, it means that the initial axial force is within the reasonable deviation range, and that the current stress state of the anchor bolt / cable meets the project requirements. Therefore, this initial axial force can be stored as the target axial force as a valid data record for subsequent monitoring or archiving.

[0023] In the above embodiments, the intelligent detection equipment collects raw point cloud data and ambient temperature data, and the analysis system performs a series of operations such as preprocessing and feature extraction. This enables automatic and intelligent detection of the axial force of the anchor bolt / cable, eliminating the need for complex manual measurements and calculations, thus improving detection efficiency and accuracy and reducing detection costs. Collecting ambient temperature data and calling calibration parameters from the temperature deformation pressure three-dimensional mapping database compensates for the impact of temperature changes on the measurement results, improving the adaptability and measurement accuracy of the detection method under different environmental conditions. Utilizing a passive, adaptive deformation device to convert the axial force of the anchor bolt / cable into mechanical deformation, and then analyzing the collected point cloud data, this indirect measurement method avoids some difficulties that may be encountered when directly measuring axial force, such as inconvenient sensor installation and low measurement accuracy, further reducing detection complexity and improving detection accuracy.

[0024] In some embodiments, the analysis system can be equipped with dedicated data visualization and interaction software for intuitive, multi-dimensional presentation of detection results through a graphical user interface, and provide deep data analysis functions. The graphical user interface (GUI) design includes the following core modules: Macro roadway axial force distribution cloud map: The system main interface displays the roadway model from a two-dimensional or three-dimensional overhead angle, and uses heat map (cloud map) technology to render the axial force distribution of the anchor rod / cable in real time. Different force value intervals are clearly marked with different colors (for example, blue represents the safe range, yellow represents the warning range, and red represents the dangerous range), so that the operator can grasp the overall stress health status of the entire roadway support system at a glance.

[0025] Multi-dimensional data comprehensive dashboard: includes customizable dynamic trend charts that update and display the average axial force of a specific anchor rod / cable or region over time in the form of line graphs or bar graphs; and lists all detection point numbers, real-time axial forces, design axial forces, deviation percentages, detection times, and states (normal / early warning / alarm) in table form, supports sorting by force value, deviation, and other key fields, and facilitates quick positioning of focus points.

[0026] Intelligent alarm and early warning center: When the system identifies axial force abnormalities, the interface alerts through multiple modalities: on the distribution cloud map, the icon of the abnormal point changes to red and flashes continuously; in the data list, the row record is displayed with a high-light red background; at the same time, the system can trigger an audible prompt to ensure timely detection of hidden dangers. Alarm information is automatically recorded in the log, and an alarm report containing detailed information such as point, time, and force value can be generated.

[0027] Deep data interaction and diagnosis functions: allow the operator to directly call up the detailed detection archives of the anchor rod / cable by clicking on the anchor rod icon on the distribution cloud map or the entry in the data list. The archives page displays the full chain of data for this detection in a hierarchical manner, providing the possibility for result verification and deep analysis, including a rotatable and scalable original point cloud three-dimensional model, key point cloud data identified by the algorithm displayed in a highlighted color, a side-by-side display of the current state and the standard model to visually display the displacement calculation basis, and all metadata such as the environmental temperature and the calibration curve used in this detection. This functional design greatly enhances the transparency of the detection process and the credibility of the results, providing a reliable tool for professionals to conduct deep diagnosis and decision support.

[0028] In some embodiments, the intelligent detection system further includes a laboratory calibration system, and the method further includes: In step S101, the laboratory calibration system is used to apply axial force to the passive state deformation device according to a preset gradient at multiple environmental temperatures in a simulated mine environment, and the intelligent detection equipment is used to synchronously collect the free end displacement of the passive state deformation device under the corresponding axial force. In step S102, the laboratory calibration system is used to construct a relationship between the free end displacement and the axial force under different environmental temperatures based on the environmental temperature, the axial force and the free end displacement. In step S103, the laboratory calibration system is used to store the relationship into the temperature deformation pressure three-dimensional mapping database.

[0029] The simulated mine environment can be a temperature of 5-40°C (simulated underground temperature fluctuation), and the humidity is 95% RH (relative humidity). The preset gradient can be 10 kN. The temperature deformation pressure three-dimensional mapping database can be established by performing graded loading calibration (for example, loading from 0 kN to 300 kN with a gradient of 10 kN) in the simulated mine environment, and multiple calibration curves under different temperatures can be stored.

[0030] To construct a universal calibration database, the calibration experiment needs to cover all typical working postures of the bourdon tube in the well. Key, graded loading calibration needs to be performed when the bourdon tube is in the'vertical suspension' (simulating installation on the two sides of the roadway) and 'horizontal placement' (simulating installation on the roof of the roadway) two extreme postures. This is to accurately quantify the influence of the self-weight and internal hydraulic oil column pressure of the bourdon tube on the free end displacement under different postures, and to include this system error into the calibration model. Then, the standard digital pressure calibrator is used to load the passive state deformation device from 0 kN to 300 kN according to a preset gradient (for example, 10 kN), and the intelligent detection equipment is used to synchronously collect the free end displacement ΔL of the bourdon tube. Based on the environmental temperature, the axial force F and the free end displacement ΔL, the ΔL-F relationship under different temperature and different installation posture combinations is constructed, thereby establishing a complete and high-precision temperature-deformation-pressure three-dimensional mapping database, which is embedded into the analysis system.

[0031] In one embodiment, in the environmental simulation cabin, the temperature is controlled (5°C, 10°C, 25°C, 40°C), the standard digital pressure calibrator is used to perform graded loading on the entire state deformation device, the laser scanning displacement ΔL and the actual load F are synchronously collected, the ΔL-F relationship under different temperatures is constructed, and is stored in the temperature deformation pressure three-dimensional mapping database and embedded into the intelligent computing system of the robot. The ΔL-F relationship can be expressed as F = k ·ΔL + b， wherein, F represents the axial force, Δ L represents the free end displacement ，k represents the stiffness coefficient, b represents the correction parameter for offsetting the system zero drift error.

[0032] In the above embodiment, the passive state deformation device is calibrated in a simulated mine environment by a laboratory calibration system, and the accurate relationship between the free end displacement and the axial force under different environmental temperatures can be obtained. This provides a reliable basis for subsequent calculation of the axial force according to the displacement in actual engineering, ensuring the accuracy of the measurement results; the calibration in the simulated mine environment takes into account various complex conditions that may be encountered in actual engineering, so that the detection method can better adapt to special environments such as mines in actual application, improving the practicality of the detection method; the constructed relationship is stored in a temperature deformation pressure three-dimensional mapping database, providing rich reference data for analysis of the system, facilitating quick calling and querying in actual detection, and improving the efficiency and accuracy of detection.

[0033] In some embodiments, to achieve a more comprehensive and forward-looking evaluation of the working state of the anchor rod / cable and the stability of the roadway, the analysis system can also construct a multi-source data fusion and joint analysis model. This model deeply fuses the core detection data of the present application with other monitoring data of the roadway to form a comprehensive judgment.

[0034] Specifically, the analysis system takes the point cloud data of the passive state deformation device and the axial force data obtained by inversion thereof as the core input; at the same time, multi-source heterogeneous data from other sensors are integrated through a data interface, mainly including surrounding rock surface deformation point cloud data reflecting the overall convergence of the roadway (which can be synchronously obtained by a laser scanner of the inspection robot), and stope pressure data from a mine pressure monitoring system, etc.

[0035] The system utilizes a machine learning model (such as gradient boosting decision tree, long short-term memory network, etc.) to jointly train and learn the above multi-source data. The model aims to mine the deep non-linear correlation and potential law between the parameters such as axial force change, surrounding rock deformation rate, and stope mine pressure intensity. Through this model, the analysis system can realize two major advanced functions: first, joint early warning, that is, when the model identifies that the axial force is within the safety threshold, but the surrounding rock deformation accelerates and the stope mine pressure significantly increases, etc. Dangerous coupling mode, a higher risk level of early warning can be given in advance, overcoming the lag of single parameter judgment; second, trend prediction, the analysis system can predict the change trend of the anchor rod axial force and the stability of the support system in the future based on the current multi-source data sequence, providing decision basis for active maintenance. This multi-factor fusion analysis mechanism significantly improves the comprehensiveness, accuracy and forward-looking of the entire intelligent detection system in evaluating the safety state of the roadway.

[0036] In some embodiments, the step S120 of "performing feature extraction on the pre-processed point cloud data to obtain key point cloud data" includes: Step S1201, based on a curvature extreme point recognition algorithm, performing feature extraction on the pre-processed point cloud data to obtain key point cloud data.

[0037] The curvature extreme point recognition algorithm is used to locate the special points with the most drastic curvature change (i.e. curvature extreme points) in the point cloud, which are often the core markers reflecting the structural features of the object. Therefore, the key point cloud data that can accurately describe the morphology and deformation of the passive state deformation device is selected from a large number of regular point clouds. The curvature extreme points can include the vertex of a C-shaped arc (the point with the maximum curvature), the fixed end edge of the device connected to the anchor rod (the point with a sudden change in curvature), and the corner point of the free end (the point with the most drastic change in structural morphology), etc. In the processing of point cloud data, the curvature extreme point recognition algorithm can be used to accurately locate the feature points of the passive state deformation device before and after deformation, which can be used as a reference for displacement calculation, thereby improving the anti-interference ability and accuracy.

[0038] Compared with the feature extraction algorithm based on the normal direction and the feature extraction algorithm based on region growing, the curvature extreme point recognition algorithm has higher sensitivity to local deformation features and faster calculation efficiency. The passive dynamic deformation device comprises a ring pressure-bearing device and a Borda tube connected through a high-pressure resistant hose. To significantly improve the recognition accuracy and robustness of the free end feature point in the point cloud data, the free end of the Borda tube is provided with a special feature enhancement structure. The structure is a convex projection (for example, a small sphere, a micro-cone platform or a cross prism) with a regular and unique three-dimensional shape which is integrally formed with the pipe body. This design can create a stable and high-contrast geometric feature in the laser point cloud, so that the intelligent analysis system can quickly and accurately lock the geometric center of the structure as the displacement calculation reference through the feature extraction algorithm (such as curvature extreme point recognition) regardless of surface contamination and environmental interference.

[0039] In the above embodiments, the curvature extreme point recognition algorithm is used for feature extraction of the preprocessed point cloud data, which can quickly and accurately find the key point cloud data reflecting the structural features and deformation state of the passive dynamic deformation device, reduce the workload and redundant data of data processing, improve the efficiency and accuracy of data processing, and enhance the reliability and stability of feature extraction.

[0040] In some embodiments, the step S130 of "obtaining the free end displacement of the passive dynamic deformation device based on the key point cloud data and the standard point cloud data in the standard model" comprises the following steps: In step S1301, based on the point cloud registration algorithm, the preprocessed point cloud data is matched with the standard point cloud data, and the free end feature points in the matched key point cloud data are compared with the free end feature points in the standard point cloud data in space coordinates. The point cloud registration algorithm can be used to match the preprocessed point cloud data with the standard point cloud data, and accurately extract the displacement ΔL of the free end of the Borda tube. The point cloud registration algorithm can be an ICP (Iterative Closest Point) algorithm.

[0041] The ICP algorithm includes finding the nearest point pair, calculating the optimal transformation matrix, and iterative optimization until convergence. In finding the nearest point pair, for each point in the pre-processed point cloud data, the spatial distance nearest point in the standard point cloud data can be found to form a set of corresponding point pairs; in calculating the optimal transformation matrix, based on the corresponding point pairs, a rigid body transformation matrix containing translation and rotation parameters is calculated by mathematical methods (such as least squares method), which can make the pre-processed point cloud data translate and rotate in space to minimize the overall distance of the corresponding point pairs with the standard point cloud data (i.e. the sum of the Euclidean distances of all corresponding point pairs is minimized); in iterative optimization until convergence, the pre-processed point cloud data is spatially transformed by the rigid body transformation matrix to approach the standard point cloud data, and then the steps of finding the nearest point pair and calculating the optimal transformation matrix are repeated, and when the overall distance error of the point cloud between two iterations is less than a preset threshold, or the number of iterations reaches an upper limit, the algorithm stops, at this time the pre-processed point cloud data and the standard point cloud data are accurately aligned, and the registration is completed.

[0042] In step S1302, the displacement of the free end of the passive dynamic deformation device is determined based on the coordinate comparison result.

[0043] In the process of determining the displacement of the free end of the passive dynamic deformation device based on the point cloud registration algorithm, the actual displacement of the free end of the Borden tube is calculated as the coordinate difference between the free end feature point in the matched key point cloud data and the free end feature point in the standard point cloud data in the target direction (such as the axial direction or the radial direction), because the pre-processed point cloud data and the standard point cloud data after registration are in the same coordinate system.

[0044] It should be noted that, in order to ensure the accuracy and reliability of the intelligent detection result of the axial force, potential errors in the system can be systematically analyzed and corresponding precision protection and correction measures can be implemented in the process of determining the displacement of the free end of the passive dynamic deformation device based on the point cloud registration algorithm. The errors mainly come from data acquisition errors and algorithm processing errors.

[0045] The data acquisition error is mainly caused by environmental factors and sensor performance limitations. Specifically, environmental noise such as downhole dust and water mist can interfere with laser propagation, resulting in noise and data loss in the original point cloud data; at the same time, the measurement accuracy (such as ±0.01 mm) of the laser scanner itself constitutes the basic error limit of the system. To correct such errors, the present application can take targeted measures in the point cloud preprocessing stage: effectively eliminate outliers by statistical filtering and radius filtering algorithm; and through multi-frame data fusion technology based on time series, i.e. continuously collecting and superimposing multiple frames of point cloud data under stable scanning state, which is equivalent to increasing the number and density of effective point cloud data, thereby significantly smoothing random errors and improving signal-to-noise ratio.

[0046] The algorithm processing error is mainly caused by the limitation of the point cloud registration process. A multi-stage fine registration strategy is adopted: first, in the feature extraction stage, the robustness of the curvature extreme point identification algorithm is enhanced to ensure that the key point cloud data used for registration is more representative and stable; second, before calling the ICP algorithm, a coarse registration based on feature descriptors is introduced to provide a good initial pose for subsequent fine registration and avoid local convergence; finally, in the ICP iteration process, a weighted nearest neighbor search strategy can be used to give higher weight to high-quality points, thereby improving the calculation accuracy of the final displacement ΔL.

[0047] In the above embodiments, the point cloud data after preprocessing is matched with the standard point cloud data based on the point cloud registration algorithm, and then the displacement of the free end is determined by comparing the spatial coordinates of the feature points of the free end. This method can fully utilize the spatial information of the point cloud data, improve the accuracy and precision of the displacement measurement; the point cloud registration algorithm and the coordinate comparison process can be automatically realized by a computer program without human intervention, reducing human error and improving the automation and efficiency of the measurement.

[0048] In some embodiments, the method further comprises: determining, by the analysis system, that the relationship between the initial axial force and the design axial force meets a preset condition when the initial axial force is greater than a first proportion threshold of the design axial force and less than a second proportion threshold of the design axial force; wherein the first proportion threshold is less than 100%, and the second proportion threshold is greater than 100%.

[0049] wherein the preset condition can be that the initial axial force is between the first proportion threshold and the second proportion threshold of the design axial force, the first proportion threshold is less than 100%, for example, it can be 80%, 85%, 90%, etc., and the second proportion threshold is greater than 100%. For example, it can be 105%, 110%, 115%, etc.; when the preset condition is met, it means that the initial axial force is within a reasonable deviation range.

[0050] In the above embodiments, by setting the first proportion threshold and the second proportion threshold, the relationship between the initial axial force and the design axial force can be reasonably evaluated. When the initial axial force is within this reasonable range, it is determined that it meets the preset condition, indicating that the stress state of the anchor rod / cable is normal, providing an effective basis for engineering safety. This evaluation method can timely determine whether the axial force of the anchor rod / cable meets the design requirements, avoiding safety hazards in engineering structures caused by excessive or insufficient axial force, and ensuring the safety and stability of the engineering.

[0051] In some embodiments, the method further comprises: Step S160: Abnormal alarm is performed by the analysis system when the initial axial force is less than the first proportional threshold of the design axial force or greater than the second proportional threshold of the design axial force.

[0052] In the case where the initial axial force is less than the first proportional threshold of the design axial force or greater than the second proportional threshold of the design axial force, it is indicated that the preset condition is not met, that is, the initial axial force is out of the reasonable deviation range, indicating that the current stress state is abnormal, and the analysis system will perform an abnormal alarm to remind the worker to troubleshoot the problem.

[0053] The embodiments of the application can realize intelligent evaluation and early warning. The robot locally and in real time calculates the axial force value, and transmits the result to the ground monitoring center through the downhole industrial ring network / 5G network. The system software automatically generates a roadway axial force distribution cloud diagram, and intelligently judges based on the set threshold (such as 85% and 110% of the design load) to perform real-time sound and light alarm and accurate positioning on the anchor rod / cable with force value decay exceeding the limit or overload.

[0054] In the above embodiments, when the initial axial force is less than the first proportional threshold or greater than the second proportional threshold, an abnormal alarm is performed, which can timely remind the worker that the stress state of the anchor rod / cable is abnormal, so that the worker can take timely measures for processing, such as checking the installation of the anchor rod / cable, reinforcing, etc., to avoid the occurrence of safety accidents. The abnormal alarm mechanism can effectively improve the safety and reliability of the project, and through timely discovery and processing of the axial force abnormality, the stability and safety of the engineering structure are ensured.

[0055] The embodiments of the application provide an algorithm data processing and axial force inversion method, which comprises: Step S1, start single-point detection; Wherein, the detection process for a single anchor rod / cable can be started; Step S2, collect original point cloud data and read the environment temperature T; Wherein, the three-dimensional point cloud data (i.e. original point cloud data containing the spatial form information of the Bogen tube) of the Bogen tube on the current anchor rod / cable can be obtained through a laser scanner or the like, and the environment temperature T at the time of detection can be recorded through a temperature sensor.

[0056] Step S3, point cloud preprocessing is performed on the original point cloud data; Wherein, the original point cloud data can be preprocessed, such as noise reduction and outlier removal, to realize cleaning of the original point cloud data, remove interference information, and retain effective data.

[0057] Step S4, feature extraction; Among them, the key feature points (i.e. key point cloud data) of the Bourdon tube can be located based on the curvature extreme point identification algorithm.

[0058] Step S5, point cloud matching, matching the real-time point cloud with the standard model; Among them, the ICP algorithm can be used to spatially align the currently detected preprocessed point cloud data with the standard point cloud data when it is not under force, so as to obtain the matched real-time point cloud data and standard point cloud data.

[0059] Step S6: Calculate the displacement ΔL at the free end; In the process of matching real-time point cloud data and standard point cloud data, the spatial coordinates of the free end feature points in the key point cloud data and the free end feature points in the standard point cloud data are compared, and the distance difference between the two is calculated, which is the displacement ΔL of the free end.

[0060] Step S7: Input temperature T, call the temperature-pressure-deformation mapping database, and query the calibration parameters k and b corresponding to temperature T; The temperature-pressure-deformation mapping database is a three-dimensional temperature-deformation-pressure mapping database. Based on the ambient temperature T read in step S2, the rigidity coefficient of the Bourdon tube at that temperature can be retrieved from the pre-established temperature-pressure-deformation mapping database. k and zero drift correction parameters b , k and b These parameters, obtained through laboratory calibration (the values ​​vary at different temperatures), are used to establish the correspondence between "displacement ΔL" and "axial force F". F = k ·Δ L + b ).

[0061] Step S8: Axial force inversion calculation, output the current anchor / cable axial force value F; The displacement Δ obtained in step S6 can be used as an example. L Substitute the result obtained in step S7 k and b The parameters are used to calculate the actual axial force of the current anchor bolt / cable using a formula. F .

[0062] Step S9, Intelligent Judgment and Decision-Making; Among them, the calculated axial force F Compare with preset thresholds (85% and 110% of the design value) to determine whether the current anchor / cable force is normal. If F < 85% of the design value or F > 110% of the design value, then execute step S10. If F is between 85% and 110% of the design value, then execute step S11. Step S10, abnormal alarm; When F exceeds the threshold range, an abnormal response is triggered, and the location of the anchor / cable (e.g., tunnel coordinates) and the current force value are recorded locally. F (i.e., axial force), and upload it to the monitoring center; Step S11: Data is stored and uploaded normally; Among them, when F When within the normal range, the test data (location, force value) of the anchor / cable should be used. F The data (such as detection time and temperature T) is stored locally and simultaneously uploaded to the monitoring center for archiving and subsequent analysis.

[0063] Step S11: This test is complete. Prepare for the next test point.

[0064] Once the inspection process for a single anchor rod / cable is completed, the robot or system switches to the "ready state" and prepares to move to the next inspection point (the next anchor rod / cable), repeating steps S1-S11 to achieve batch inspection.

[0065] Based on the foregoing embodiments, this application further provides an intelligent detection system for axial force of anchor bolts / cables. The system includes various modules and units included in each module, which can be implemented by a processor in an electronic device; of course, it can also be implemented by specific logic circuits. In the implementation process, the processor can be a central processing unit (CPU), a microprocessor (MPU), a digital signal processor (DSP), or a field programmable gate array (FPGA), etc.

[0066] Figure 2 This application provides a schematic diagram of the composition structure of an intelligent detection system for axial force of anchor bolts / cables, as shown in the embodiments of this application. Figure 2 As shown, the system 200 includes: a passive adaptive deformation device 201, an intelligent detection equipment 202, and an analysis system 203, wherein: The intelligent detection equipment 202 is used to collect the original point cloud data and ambient temperature data of the passive following deformation device 201 connected to the anchor bolt / cable. The passive following deformation device 201 is used to convert the axial force of the anchor bolt / cable into mechanical deformation that can be captured by the intelligent detection equipment 202. The analysis system 203 is used to preprocess the original point cloud data to obtain preprocessed point cloud data, and to extract features from the preprocessed point cloud data to obtain key point cloud data. The key point cloud data is point cloud data that can reflect the structural features and deformation state of the passive following deformation device 201. The analysis system 203 is also used to obtain the free end displacement of the passive following deformation device 201 based on the key point cloud data and the standard point cloud data in the standard model. The standard point cloud data is the point cloud data of the passive following deformation device 201 when it is in the original state without force. The analysis system 203 is also used to retrieve calibration parameters from the temperature deformation pressure three-dimensional mapping database under the ambient temperature data; and to determine the initial axial force of the anchor / cable based on the calibration parameters and the free end displacement. The analysis system 203 is also used to store the initial axial force as the target axial force of the anchor rod / cable when the relationship between the initial axial force and the design axial force meets the preset conditions.

[0067] In some embodiments, the passive adaptive deformation device 201 includes an annular pressure bearing device and a Bourdon tube connected by a high-pressure resistant hose; the internal cavity of the annular pressure bearing device is filled with hydraulic oil, and the high-pressure resistant hose, the annular pressure bearing device, and the Bourdon tube form a hydraulic circuit; an overload relief valve is integrated in the hydraulic circuit to protect the Bourdon tube when the hydraulic pressure is greater than a preset opening threshold of the relief valve. The annular pressure-bearing device is used to bear the axial force of the anchor rod / cable and convert the axial force into hydraulic pressure; The high-pressure resistant hose is used to transmit hydraulic pressure to the Bourdon tube through the hydraulic circuit, so as to deform the Bourdon tube and generate free end displacement.

[0068] like Figure 3 As shown, the anchor bolts are driven into the rock strata (rock strata 1, rock strata 2, rock strata 3) to reinforce the tunnel and prevent the rock strata from collapsing. The axial force of the anchor bolts is a key indicator for measuring the support effect and needs to be tested regularly.

[0069] The annular pressure-bearing device, serving as a pressure interface, can be directly embedded between the anchor bolt tray and the nut. It can be made of 316L (Low Carbon) stainless steel with a wall thickness of 3 mm. Its internal cavity is filled with high-viscosity silicone-based hydraulic oil (viscosity index ≥180), exhibiting good chemical stability and viscosity-temperature characteristics. The annular pressure-bearing device can be embedded between the anchor bolt tray and the locking nut, similar to a washer. The Bourdon tube is reliably fixed to the adjacent roadway wall using a mounting bracket, ensuring its free end is unobstructed for easy laser scanning.

[0070] As shown in Figure 4 , the Bourdon tube can be a C-shaped Bourdon tube, and the annular pressure-bearing device can be communicated with the C-shaped Bourdon tube through a high-pressure-resistant hose capable of bearing a pressure of 60 megapascals (MPa). When the anchor rod is subjected to an axial force, the C-shaped Bourdon tube will be deformed, and the deformation amount of the C-shaped Bourdon tube has a corresponding relationship with the axial force of the anchor rod. The profile of the C-shaped Bourdon tube after deformation is shown by a dashed line in Figure 4 , an anti-overload relief valve is integrated in the hydraulic circuit, and the opening threshold can be set to 350 kN, which can effectively protect the core sensitive element, the Bourdon tube, from damage caused by impact load.

[0071] The C-shaped Bourdon tube as the core deformation element has a material and structure that are precisely designed and optimized. The material is preferably 174PH (Precipitation Hardening) stainless steel (UNSS17400, the official standardized grade of 174PH stainless steel), which is subjected to double aging treatment of solid solution + H1150 (the material after solid solution is reheated to about 1150 degrees Fahrenheit), to obtain excellent comprehensive mechanical properties: yield strength ≥ 1100 MPa, elongation ≥ 15%, elastic modulus E ≈ 196 gigapascals (GPa), to ensure that the C-shaped Bourdon tube has extremely high linearity, fatigue life and environmental adaptability (corrosion resistance and impact resistance) in the elastic deformation range. The structural parameters are as follows: C-shaped structure, curvature radius R = 8 mm, and pipe wall thickness t = 0.5 mm ± 0.02 mm. The parameter combination is calculated by a mechanical formula ΔL = (P * R3 * (1 - v2)) / (E * t * b) * K to ensure that the free end of the C-shaped Bourdon tube can produce a linear displacement of 0.1 mm to 5 mm within the axial force input range of 20-300 kN, and the sensitivity is as high as 0.1 kN corresponding to about 0.01 mm deformation, which accurately matches the laser scanning resolution. In the above formula, ΔL represents the target deformation amount (i.e., the displacement amount of the free end) of the C-shaped Bourdon tube under the action of the axial force, P represents the axial force, v represents the Poisson's ratio of the material of the C-shaped Bourdon tube, i.e., the transverse deformation coefficient of the material, which reflects the proportional relationship between the axial elongation / shortening and the transverse contraction / expansion of the material when the material is subjected to an axial force; E represents the elastic modulus of the material of the C-shaped Bourdon tube, b represents the pipe wall width of the C-shaped Bourdon tube; K represents a correction coefficient, t is the pipe wall thickness, and R is the curvature radius.

[0072] In some embodiments, the intelligent detection equipment is an autonomous mobile inspection robot carrying an explosion-proof laser scanner and an infrared temperature measurement module.

[0073] In the embodiments of the present application, the intelligent detection equipment can be integrated into an automatic mobile platform to realize unmanned intelligent inspection, as shown in Figure 5As shown, the autonomous mobile inspection robot 51 (i.e. Figure 3 The inspection robot in the autonomous mobile inspection robot 51 adopts a tracked mobile chassis, is powered by an explosion-proof lithium battery pack, and is integrated with an explosion-proof servo mechanical arm. The explosion-proof laser scanner (also referred to as a laser scanning device) and an infrared temperature measurement module are fixed at the end of the mechanical arm, automatic identification, alignment and scanning are realized by a robot control system, the laser radar computing unit can perform preliminary processing on the point cloud data collected by the laser scanner, the laser scanner can be a line laser scanner, and a carbon fiber explosion-proof sleeve is sleeved outside the linkage circuit of the mechanical arm to protect the circuit from damage from the external environment. Figure 5 As shown, the bourdon tube deflection measurement point refers to a specific position for measuring the linear displacement of the axis or median surface of the bourdon tube in the perpendicular direction to the original axis when the bourdon tube deforms under pressure.

[0074] In one embodiment, the robot adopts an explosion-proof tracked mobile chassis (protection level IP67, in line with the GB3836.1 2021 explosion-proof standard), has strong obstacle crossing ability (climbing angle ≥ 15°), is powered by an explosion-proof lithium battery pack, and has a continuous running time of ≥ 8 hours. The robot body is equipped with a 2-3 degree of freedom explosion-proof servo mechanical arm. The end of the mechanical arm is integrated and fixed with an explosion-proof line laser scanner and an infrared temperature measurement module. The wavelength of the explosion-proof line laser scanner is 650 nanometers (unit: nm), the scanning frequency is 50 hertz (unit: Hz), and the measurement accuracy is 0.01 mm. The infrared temperature measurement module is used for real-time non-contact measurement of the surface temperature of the bourdon tube for subsequent algorithm compensation.

[0075] After the robot is in place, the control mechanical arm is deep, the laser scanning point or visual auxiliary is used, the bourdon tube is automatically identified and accurately positioned, the scanner is adjusted to the best scanning distance (for example, it can be 300 mm) and angle, the scanning is triggered, and high-density point cloud data (for example, the point distance can be 0.1 mm) is generated.

[0076] In one embodiment, as shown in Figure 5 The operation and maintenance personnel issue an inspection task at the ground dispatch center. The intelligent inspection robot is automatically awakened and travels along the preset path. After reaching each detection point, the mechanical arm is automatically controlled to complete the identification, alignment, scanning and temperature measurement actions, and single-point data acquisition and calculation are completed within 3 seconds. The intelligent detection equipment integrates laser SLAM (Simultaneous Localization and Mapping) and UWB (Ultra-Wideband) precise positioning technology, so that the robot can autonomously plan a path, avoid obstacles, and accurately move to the predetermined anchor rod detection point.

[0077] In some embodiments, the analysis system is an embedded industrial computer embedded in the autonomous mobile inspection robot.

[0078] wherein, as shown in Figure 5 The autonomous mobile inspection robot is built-in embedded with an explosion-proof industrial computer, carries a multi-core processor, and can serve as a hardware basis for algorithm running. The embedded industrial computer can complete the calculation of axial force and result judgment in real time in the scanning field.

[0079] In some embodiments, the intelligent detection system further comprises a laboratory calibration system, The laboratory calibration system is configured to apply axial force to the passive state deformation device according to a preset gradient under a plurality of environmental temperatures in a simulated mine environment by using a standard digital pressure calibrator, and to synchronously collect the free end displacement of the passive state deformation device under the corresponding axial force by using the intelligent detection equipment. The laboratory calibration system is further configured to construct a relationship between the free end displacement and the axial force under different environmental temperatures based on the environmental temperature, the axial force, and the free end displacement, and to store the relationship in the temperature deformation pressure three-dimensional mapping database.

[0080] In some embodiments, the analysis system 203 is further configured to perform feature extraction on the preprocessed point cloud data based on a curvature extreme point recognition algorithm to obtain key point cloud data.

[0081] In some embodiments, the analysis system 203 is further configured to match the preprocessed point cloud data with the standard point cloud data based on a point cloud registration algorithm, to select free end feature points in the key point cloud data after matching, and to compare the free end feature points with the standard point cloud data in spatial coordinates. Based on the coordinate comparison result, the free end displacement of the passive state deformation device is determined.

[0082] In some embodiments, the analysis system 203 is further configured to determine that the relationship between the initial axial force and the design axial force satisfies a preset condition when the initial axial force is greater than a first proportion threshold of the design axial force and less than a second proportion threshold of the design axial force. The first proportion threshold is less than 100%, and the second proportion threshold is greater than 100%.

[0083] In some embodiments, the analysis system 203 is further configured to perform abnormal alarm when the initial axial force is less than the first proportion threshold of the design axial force or greater than the second proportion threshold of the design axial force.

[0084] In the embodiments of the present application, through the deep integration of pure mechanical state deformation device and optical non-contact scanning, intelligent algorithm and robot technology, the environmental adaptability limit of electronic devices is broken through, a zero-circuit, high-reliability, ultra-low-cost, high-precision and large-scale unmanned intelligent inspection axial force monitoring system and method are provided, the sensor front end is all-mechanical passive structure, there is no any circuit element, the electronic sensor failure problem caused by the harsh environment in the well is fundamentally solved, and the failure rate is reduced by more than 90% compared with the existing electronic sensor. The zero electronic device has ultra-high reliability. The laser detection system is integrated in the explosion-proof inspection robot, realizing the full autonomy, large-scale and grid operation of the anchor rod axial force detection, and the detection efficiency and human-machine safety are revolutionarily improved. The single-point state deformation device has a low manufacturing cost, so that the full-coverage monitoring of the ten thousand anchor rods in the well becomes possible; at the same time, the laser measurement accuracy is 0.01 mm, combined with the precise algorithm, the total error of axial force inversion is less than or equal to ±3% (compared with the hydraulic jack). Through infrared temperature measurement and three-dimensional calibration database, intelligent coupling compensation of temperature mechanical behavior is realized, and the long-term measurement stability and accuracy in the complex environment are significantly improved.

[0085] It should be pointed out that the description of the above device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0086] It should be understood that the "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of each process does not mean the execution order, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The sequence number of the above embodiments of the present application is only for description, not representing the advantages and disadvantages of the embodiments.

[0087] It should be noted that in this document, the term "comprising" or "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or device including the element.

[0088] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. The above described device embodiments are merely exemplary. For example, the division of the units is merely logical function division, and there can be other division manners in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling, or direct coupling or communication connection between the components can be indirect coupling or communication connection through some interfaces, devices, or units, and can be electrical, mechanical, or in other forms.

[0089] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units; they can be located in one place, or distributed on a plurality of network units; and some or all of the units can be selected as needed to achieve the purposes of the embodiments of the present application. In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be realized in the form of hardware, or in the form of hardware plus software functional units.

[0090] Alternatively, the integrated units described above can be stored in a computer readable storage medium in the form of software functional modules if they are realized in the form of software functional modules and sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present application essentially or the parts that contribute to the related art can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing an apparatus to perform all or part of the methods described in the embodiments of the present application. The foregoing storage medium includes: a mobile storage device, a ROM, a magnetic disk, or an optical disk, and various media that can store program codes.

[0091] The methods disclosed in several method embodiments provided by the present application can be combined arbitrarily without conflict to obtain new method embodiments. The features disclosed in several method or device embodiments provided by the present application can be combined arbitrarily without conflict to obtain new method embodiments or device embodiments.

[0092] The above describes only the embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for intelligent detection of axial force in anchor bolts / cables, characterized in that, The method is applied to an intelligent detection system, which includes a passive adaptive deformation device, intelligent detection equipment, and an analysis system. The intelligent detection equipment collects the original point cloud data and ambient temperature data of the passive following deformation device connected to the anchor bolt / cable. The passive following deformation device is used to convert the axial force of the anchor bolt / cable into mechanical deformation that can be captured by the intelligent detection equipment. The original point cloud data is preprocessed by the analysis system to obtain preprocessed point cloud data. Feature extraction is performed on the preprocessed point cloud data to obtain key point cloud data. The key point cloud data is point cloud data that can reflect the structural features and deformation state of the passive following deformation device. The analysis system obtains the free end displacement of the passive following deformation device based on the key point cloud data and the standard point cloud data in the standard model. The standard point cloud data is the point cloud data of the passive following deformation device when it is in the original state without force. The analysis system retrieves calibration parameters from the environmental temperature data from the temperature deformation pressure three-dimensional mapping database; based on the calibration parameters and the free end displacement, the initial axial force of the anchor / cable is determined. When the relationship between the initial axial force and the design axial force meets the preset conditions, the analysis system stores the initial axial force as the target axial force of the anchor / cable.

2. The method according to claim 1, characterized in that, The intelligent detection system also includes a laboratory calibration system, and the method further includes: In a simulated mine environment, the passive following deformation device was subjected to axial force according to a preset gradient using a standard digital pressure calibrator under multiple ambient temperatures through the laboratory calibration system. The displacement of the free end of the passive following deformation device under the corresponding axial force was simultaneously collected by the intelligent detection equipment. Based on the ambient temperature, the axial force, and the free end displacement, the laboratory calibration system constructs the relationship between the free end displacement and the axial force under different ambient temperatures. The relation is stored in the temperature deformation pressure three-dimensional mapping database through the laboratory calibration system.

3. The method according to claim 1, characterized in that, The step of extracting features from the preprocessed point cloud data to obtain key point cloud data includes: Based on the curvature extreme point identification algorithm, feature extraction is performed on the preprocessed point cloud data to obtain key point cloud data.

4. The method according to claim 1, characterized in that, The process of obtaining the free end displacement of the passive adaptive deformation device based on the key point cloud data and the standard point cloud data in the standard model includes: Based on the point cloud registration algorithm, the preprocessed point cloud data is matched with the standard point cloud data, and the free end feature points in the matched key point cloud data are compared with the free end feature points in the standard point cloud data in terms of spatial coordinates. Based on the coordinate comparison results, the displacement of the free end of the passive adaptive deformation device is determined.

5. The method according to claim 1, characterized in that, The method further includes: The analysis system determines that the relationship between the initial axial force and the design axial force satisfies a preset condition when the initial axial force is greater than a first proportional threshold of the design axial force and less than a second proportional threshold of the design axial force. Wherein, the first ratio threshold is less than 100%, and the second ratio threshold is greater than 100%.

6. The method according to claim 5, characterized in that, The method further includes: The analysis system will issue an alarm if the initial axial force is less than the first proportional threshold of the design axial force or greater than the second proportional threshold of the design axial force.

7. An intelligent detection system for axial force of anchor bolts / cables, characterized in that, The intelligent detection system includes a passive adaptive deformation device, intelligent detection equipment, and an analysis system, wherein: The intelligent detection equipment is used to collect the original point cloud data and ambient temperature data of the passive following deformation device connected to the anchor bolt / cable. The passive following deformation device is used to convert the axial force of the anchor bolt / cable into mechanical deformation that can be captured by the intelligent detection equipment. The analysis system is used to preprocess the original point cloud data to obtain preprocessed point cloud data, and to extract features from the preprocessed point cloud data to obtain key point cloud data. The key point cloud data is point cloud data that can reflect the structural features and deformation state of the passive following deformation device. The analysis system is also used to obtain the free end displacement of the passive following deformation device based on the key point cloud data and the standard point cloud data in the standard model. The standard point cloud data is the point cloud data of the passive following deformation device when it is in the original state without force. The analysis system is also used to retrieve calibration parameters from the temperature deformation pressure three-dimensional mapping database under the ambient temperature data; and to determine the initial axial force of the anchor / cable based on the calibration parameters and the free end displacement. The analysis system is also used to store the initial axial force as the target axial force of the anchor / cable when the relationship between the initial axial force and the design axial force meets preset conditions.

8. The intelligent detection system according to claim 7, characterized in that, The passive adaptive deformation device includes an annular pressure-bearing device and a Bourdon tube connected by a high-pressure resistant hose; the internal cavity of the annular pressure-bearing device is filled with hydraulic oil, and the high-pressure resistant hose, the annular pressure-bearing device, and the Bourdon tube constitute a hydraulic circuit; The annular pressure-bearing device is used to bear the axial force of the anchor rod / cable and convert the axial force into hydraulic pressure; The high-pressure resistant hose is used to transmit the hydraulic pressure to the Bourdon tube through the hydraulic circuit, so as to deform the Bourdon tube and generate a free end displacement. The hydraulic circuit integrates an overload relief valve to protect the Bourdon tube when the hydraulic pressure exceeds the preset opening threshold of the relief valve.

9. The intelligent detection system according to claim 7 or 8, characterized in that, The intelligent inspection equipment is an autonomous mobile inspection robot equipped with an explosion-proof laser scanner and an infrared temperature measurement module.

10. The intelligent detection system according to claim 9, characterized in that, The analysis system is an embedded industrial control computer embedded inside the autonomous mobile inspection robot.

Images