Automatic alignment method and system for upper anchor rod equipment based on lifting manipulator

Abstract

The invention relates to the technical field of anchor rod automation, and discloses an anchor rod feeding equipment automatic alignment method and system based on a lifting manipulator, and the method comprises the steps: configuring a visual sensor on the lifting manipulator of anchor rod feeding equipment, and collecting visual information; carrying out preliminary identification on the visual information; according to the result of the preliminary identification, performing visual positioning on a preset area for mounting the anchor rod, and determining the mounting angle of the anchor rod according to the positioning result; according to the positioning result and the mounting angle, the anchor rods are aligned; and the state of the anchor rod is judged in real time, and if the alignment requirement is not met, alignment operation is conducted again. Manual intervention is reduced through automatic operation, and construction safety and consistency are improved. On the whole, the anchor rod mounting quality and reliability are greatly improved, and the method is suitable for various engineering scenes.

Description

Technical Field

[0001] The present invention relates to the field of anchor bolt automation technology, and in particular to an automatic alignment method and system for upper anchor bolt equipment based on a lifting robot. Background Art

[0002] In modern engineering construction, anchor rods are widely used as an important supporting structure in tunnels, mines, and slope reinforcement. However, traditional anchor rod installation methods usually rely on manual alignment, which has problems such as insufficient precision, low efficiency, and poor safety. Especially under complex geological conditions, the angle and position of anchor rod installation are difficult to control accurately, which often leads to deviation, angle error, and even installation failure. This not only affects the construction quality, but also increases the subsequent maintenance costs. In response to the above problems, with the development of artificial intelligence and automation technology, automatic anchor rod alignment technology combined with lifting robots and visual recognition has become an emerging solution. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] Therefore, the technical problem solved by the present invention is that the existing anchor rod method cannot achieve accurate automation and has poor accuracy in positioning and installation.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an automatic alignment method of an upper anchor rod device based on a lifting robot, comprising: A visual sensor is configured on the lifting robot of the upper anchor bolt equipment to collect visual information; Performing preliminary recognition on the visual information; Based on the result of the preliminary identification, visually locate the predetermined area for anchor bolt installation, and determine the installation angle of the anchor bolt based on the positioning result; Align the anchor rods according to the positioning results and installation angles; The anchor bolt status is judged in real time. If the alignment requirements are not met, re-alignment is performed; The alignment includes, based on the positioning result, determining the position of the anchor rod according to the installation angle; after determining the position of the anchor rod, performing an anchoring action.

[0006] As a preferred solution of the method for automatically aligning the upper anchor rod equipment based on the lifting robot arm of the present invention, the visual information includes: in the site, the actual area where the anchor rod needs to be installed is demarcated as the predetermined area, and the predetermined area is marked; through the real-time image information collected by the visual sensor, whether there is a mark in the image is identified; When the predetermined area completely enters the image frame, the acquisition result is recorded.

[0007] As a preferred solution of the automatic alignment method of the upper anchor rod device based on the lifting robot arm of the present invention, the preliminary identification includes screening images in the sampling results and identifying the screened images; The screening process includes: analyzing the clarity to screen out images whose clarity meets the preset conditions and whose proportion of the predetermined area in the picture is higher than τ; performing secondary screening on the screened images to calculate the actual distance A between the center of the predetermined area and the center of the picture, and selecting the image with the smallest A; if there are multiple results of the secondary screening, selecting the image with the highest clarity from the multiple secondary screening results as the final screening result; in, Indicates the preset ratio threshold; , a represents the distance between the center of the predetermined area and the center of the picture in the image, represents the actual horizontal width of the predetermined area, Indicates the horizontal width of the predetermined area in the figure.

[0008] As a preferred solution of the automatic alignment method of the upper anchor rod device based on the lifting robot arm of the present invention, wherein: the recognition of the filtered image includes extracting the edges in the image using the Canny algorithm, connecting the broken edges using morphological operations, and forming a closed area; Recognition based on convolutional neural network architecture; Input: the result of the preliminary identification; Output: coordinate results of visual positioning; The convolutional neural network architecture includes a feature extraction layer, a region division layer, and a coordinate positioning layer; The feature extraction layer extracts the features of each closed area, obtains a feature map and inputs it into the area division layer; the area division layer identifies the feature types and distribution density in the feature map and divides the feature area; the coordinate positioning layer selects the area in the map of the divided feature area and locates the center of the selected area; Among them, the feature extraction layer, region division layer, and coordinate positioning layer have independent functions, and the three layers can be trained separately, and finally the recognition is completed through collaboration; After the recognition is completed, the coordinate results are mapped to the positioning position of the actual site, the alignment behavior of the anchor installation is continuously monitored, and the positioning position of the actual site is mapped to the real-time monitoring screen, and adjustments are made until the anchor is completed.

[0009] As a preferred solution of the automatic alignment method of the upper anchor rod device based on the lifting robot arm of the present invention, wherein: the installation angle includes matching the positioning result in the design drawing, obtaining the angle between the anchor rod and the anchoring plane in the drawing as angle 1; The anchoring geology is analyzed and the angle 1 is adjusted to obtain the actual installation angle.

[0010] As a preferred solution of the automatic alignment method of the upper anchor rod device based on the lifting robot arm of the present invention, the analysis of the anchoring geology includes obtaining a three-dimensional virtual model of the geological structure and simulating the penetration process of the anchor rod in the virtual model; assuming that in the same medium, the angle of the anchor rod will not change during the penetration process, and the anchor rod head will deviate at the junction of the two media, so that the angle of the anchor rod changes; Performing angle analysis on the end of the anchor rod according to the angle change to obtain an adjustment angle for the angle 1; In the three-dimensional geological structure virtual model, the edges of different media are divided: for any two connected media B and C, the survey signals of B and C are obtained respectively, and at the connecting part of B and C, the positions where the survey signal intensities of B and C are equal are fitted to obtain the boundary line of the edges of B and C, and all the boundary lines are drawn to obtain the division results of the edges of different media; In the three-dimensional geological structure virtual model, it is assumed that the anchor rod is penetrated at an angle of 1, and when reaching any boundary line, it deflects, and the deflection angle is δ; the force on the anchor rod is analyzed by using mechanical analysis software, so as to obtain the offset angle of the end of the anchor rod compared with the angle 1; The offset angle is analyzed in real time. When the offset angle exceeds a threshold, the anchor bolt is predicted to fail, and the automatic alignment of the upper anchor bolt device at the current position is canceled; when the anchor bolt depth does not meet the requirement and the offset angle does not exceed the threshold, the prediction is continued; when the anchor bolt depth meets the requirement and the offset angle does not exceed the threshold, it is determined that the current position can complete the anchor bolt, and the final offset angle is recorded as the adjustment angle; Superimpose the adjustment angle and angle 1 to obtain the installation angle; in, is the deflection angle, which indicates the angle deflection when the anchor head reaches the boundary line; the relationship between the deflection angle and the parameter is fitted using the regression method ; f(...) represents the function used for fitting; It indicates the angle between the anchor head and the boundary line when it reaches the boundary line. It indicates the parameters of the medium where the anchor head is located before reaching the boundary line; It indicates the parameters of the medium where the anchor head is located after reaching the boundary line; Represents the external force applied during the penetration of the anchor.

[0011] As a preferred solution of the automatic alignment method of the upper anchor rod equipment based on the lifting robot arm described in the present invention, the real-time judgment of the anchor rod status includes using a visual sensor to obtain the actual angle between the anchor rod and the anchoring plane. If the actual angle exceeds a preset maximum reference value, it is judged that the alignment requirement is not met; otherwise, it is judged that the alignment requirement is met.

[0012] An automatic alignment system for upper anchor rod equipment based on a lifting robot using any method described in the present invention, characterized in that: The collection unit is equipped with a visual sensor on the lifting robot of the upper anchor equipment to collect visual information; A recognition unit, which performs preliminary recognition on the visual information; A positioning unit, which visually locates a predetermined area for anchor bolt installation according to the result of the preliminary identification, and determines an installation angle of the anchor bolt according to the positioning result; The execution unit aligns the anchor rod according to the positioning result and the installation angle; the anchor rod status is judged in real time, and if the alignment requirements are not met, the re-alignment operation is performed.

[0013] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein: the processor implements the steps of any one of the methods of the present invention when executing the computer program.

[0014] A computer-readable storage medium stores a computer program, wherein: when the computer program is executed by a processor, the steps of any one of the methods of the present invention are implemented.

[0015] Beneficial effects of the present invention: The automatic alignment method of the upper anchor rod equipment based on the lifting robot provided by the present invention realizes high-precision automatic alignment of the anchor rod by combining the lifting robot, visual recognition and geological model analysis. Its beneficial effects include: improving the accuracy of anchor rod installation and significantly reducing the installation failure rate caused by angle deviation; improving construction efficiency through intelligent image recognition and dynamic adjustment; optimizing the installation angle of the anchor rod in combination with the geological virtual model to adapt to complex geological conditions; automated operation reduces manual intervention and improves construction safety and consistency. Overall, the present invention greatly improves the quality and reliability of anchor rod installation and is suitable for a variety of engineering scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0017] Figure 1 An overall flow chart of an automatic alignment method for upper anchor rod equipment based on a lifting robot provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0019] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides an automatic alignment method for an upper anchor rod device based on a lifting robot, comprising: S1: A visual sensor is configured on the lifting robot of the upper anchor equipment to collect visual information.

[0020] The visual information includes, in the site, demarcating the actual area where the anchor rods need to be installed as the predetermined area, and marking the predetermined area; identifying whether there is a mark in the image through the real-time image information collected by the visual sensor; when the predetermined area completely enters the image screen, recording the collection result.

[0021] It is important to delineate and mark the predetermined area where the anchor rod needs to be installed on the site. The target position for anchor rod installation can be quickly located by real-time image acquisition and recognition by the visual sensor. By ensuring that the predetermined area is completely in the picture and recording the results, the installation position can be initially located, providing high-quality initial data support for subsequent precise identification and alignment operations. The purpose of this design is to reduce errors in the traditional manual positioning process, optimize the installation process of anchor rods, and lay a solid foundation for automated installation in complex construction environments.

[0022] S2: Performing preliminary recognition on the visual information.

[0023] The preliminary identification includes screening images in the sampling results and identifying the screened images; wherein the screening process includes analyzing the clarity and screening out images whose clarity meets preset conditions and whose proportion of the predetermined area in the picture is higher than τ; performing secondary screening on the screened images, calculating the actual distance A between the center of the predetermined area and the center of the picture, and selecting the image with the smallest A; if there are multiple results of the secondary screening, selecting the image with the highest clarity from the multiple secondary screening results as the final screening result.

[0024] in, Indicates the preset ratio threshold; , a represents the distance between the center of the predetermined area and the center of the picture in the image, represents the actual horizontal width of the predetermined area, Indicates the horizontal width of the predetermined area in the figure.

[0025] This preset condition is a preset value. In the design of this embodiment, the clarity is first quantified using existing means; the preset condition here is to take the average of the top 20% of the sample clarity of the training set. If the clarity of the top 20% average is not met, resampling is performed.

[0026] The identification of the filtered image includes extracting the edges in the image using the Canny algorithm and connecting the broken edges using morphological operations to form a closed area. Identification based on the convolutional neural network architecture: Input: the result of the preliminary identification.

[0027] Output: coordinate results of visual positioning.

[0028] It should be noted that the general requirements for anchor rods are: for broken and uneven slopes, loose pumice and rock debris must be removed, cavities must be filled with mortared stone slabs, and the gaps on the slope surface must be sealed. The slope is flat and dense after trimming. That is to say, the actual position of the anchor rod is a position that has been processed separately in an area. Then, when anchoring, it is necessary to find this position. According to the needs of the anchor rod, different training sets are used. If the entire predetermined area is in compliance, it will be simplified in the second layer of the neural network, thereby simplifying the calculation amount, and directly locating the relative position of the preset area through the calculation of the third layer. If a part of the entire predetermined area does not meet the requirements, the area can be identified through the second layer, and then the positioning selection can be made. The convolutional neural network architecture includes a feature extraction layer, a region division layer, and a coordinate positioning layer. The alignment includes, on the positioning result, determining the position of the anchor rod according to the installation angle; after determining the position of the anchor rod, performing the anchoring action.

[0029] The feature extraction layer extracts the features of each closed area, and obtains a feature map which is input into the area division layer; the area division layer identifies the feature types and distribution density in the feature map and divides the feature areas; the coordinate positioning layer selects the area in the map of the divided feature areas and locates the area at the center of the selected area.

[0030] Feature extraction layer: Extract key features of each closed area (such as edges, textures, shapes, etc.) and generate feature maps. Use convolution operations to extract edge features: ; in is the input image, is the convolution kernel.

[0031] Use nonlinear activation functions (such as ReLU) to process features and improve network expression capabilities: ; Use the pooling operation to reduce the size of the feature map, reduce the amount of calculation, and retain the main features: ; Output a low-resolution, high-semantic feature map that represents the characteristics of each closed region in the predetermined area.

[0032] Region division layer: Based on the results of the feature extraction layer, the feature types and distribution density of the region are analyzed, and the regions that meet and do not meet the anchor requirements are divided. Classify the regions in the image and identify which regions meet the anchor requirements. Use a convolutional or fully connected layer to output the category C of each region: ; Filtered Area Chart , including markings for areas that meet anchor installation requirements.

[0033] The coordinate positioning layer locates the specific anchor position in the divided feature area. The coordinate regression model is used to accurately predict the position of the point: (x, y) = Regressor (Fr).

[0034] Among them, the feature extraction layer, the area division layer, and the coordinate positioning layer have independent functions, and the three layers can be trained separately, and finally the recognition is completed through collaboration. After the recognition is completed, the coordinate results are mapped to the positioning position of the actual site, the alignment behavior of the anchor installation is continuously monitored, and the positioning position of the actual site is mapped to the real-time monitoring screen, and the anchor is adjusted until it is completed.

[0035] S3: Based on the result of the preliminary identification, visual positioning is performed on the predetermined area for anchor bolt installation, and the installation angle of the anchor bolt is determined based on the positioning result.

[0036] The installation angle includes matching the positioning result in the design drawing, obtaining the angle between the anchor rod and the anchoring plane in the drawing as angle 1; analyzing the anchoring geology, adjusting the angle 1, and obtaining the actual installation angle.

[0037] It should be said that in the plan, before anchoring, the area where anchors are needed needs to be pre-processed so that the processed area can be consistent with the anchor plane in the drawing. By processing the slope, the angle between the actual slope and the horizontal position can be presented as a fixed value. However, the angle 1 obtained in the drawing is an ideal value, and the final anchor result should be within the range of this ideal value, so the actual installation angle can be obtained after adjustment. Among them, it is very simple to obtain the design angle between the anchor and the slope on the drawing, which can be completed through angle measurement. After aligning the slope in the drawing, the anchor position can be directly locked according to the alignment position, and the actual slope should be a flat surface after processing. Then when the anchor is anchored, the actual angle can be determined by the angle between the anchor and the actual slope.

[0038] When anchoring, it is necessary to conduct geological surveys in advance and analyze the geological conditions of anchoring before anchoring. The analysis of the anchoring geology includes obtaining a three-dimensional virtual model of the geological structure and simulating the penetration process of the anchor in the virtual model; assuming that in the same medium, the angle of the anchor will not change during the penetration process, and the anchor head will be offset at the junction of the two media, so that the angle of the anchor changes. According to the angle change, the angle of the end of the anchor is analyzed to obtain the adjustment angle of the angle 1, and the data information such as the deflection, vibration and displacement of the anchor due to force at the junction of the two media is recorded.

[0039] Among them, "angle change" is completed by mechanical analysis software through the technical means of finite element analysis. "Recording the data information of the deflection, vibration and displacement of the anchor rod due to the force at the junction of two media" is for the technical personnel to observe when analyzing the adjustment process. The anchor rod process is simulated by mechanical analysis software, and the force condition of the anchor rod after the anchor rod is impacted by the external medium is analyzed. Time is accumulated according to the force condition until the anchor rod passes through the medium junction. The position change before and after anchoring into the "medium junction" is recorded to obtain displacement data; by comparing the angle change before and after anchoring into the "medium junction", the deflection data can be obtained; by analyzing the force analysis of the anchor rod head and the drilling power during anchoring, the vibration data can be obtained.

[0040] It should be said that the establishment of a three-dimensional geological structure virtual model is a key link in simulating the anchor penetration process. The model needs to accurately reflect the stratum structure, medium properties and distribution of geological interfaces to facilitate subsequent mechanical analysis and anchor angle adjustment calculations. In order to build such a model, it is necessary to first obtain three-dimensional geological structure data, then perform modeling and data processing, and finally form a three-dimensional virtual environment that can be used for analysis. Three-dimensional geological data can be obtained through a variety of means, mainly including geophysical detection, drilling surveys, geological radar scanning and remote sensing data. The following are common data collection methods: (1) Seismic wave detection: Principle: Seismic waves are emitted into the ground through a seismic source (such as explosives or vibrators), and the speed difference of seismic waves propagating between different media is used to build a three-dimensional model of the underground geological structure.

[0041] Seismic reflection or refraction methods are used to collect geological data. The propagation time, amplitude, and frequency of seismic waves are recorded, and the distribution of different underground geological layers is inverted.

[0042] (2) Borehole survey: Principle: Drill multiple boreholes in different areas and use sensors to record information such as stratum structure, lithology parameters, groundwater distribution, etc.

[0043] Data acquisition uses the following methods: Electrical logging: measuring the resistivity of the rock formation and identifying different media.

[0044] Sonic logging: Measures the speed of sound waves in rock formations to determine density and bedding.

[0045] Density logging: obtain the density distribution of rock formations and infer the hardness of the medium.

[0046] (3) Geological radar: Principle: Use high-frequency electromagnetic waves to detect changes in underground media and analyze reflected signals to obtain shallow geological information.

[0047] The GPR antenna is used to transmit electromagnetic waves, receive reflected signals from geological layers, and analyze the boundary positions of different media.

[0048] (4) Remote sensing technology: Principle: Use satellite images, drone aerial surveys, LiDAR and other technologies to infer underground geological information from surface data.

[0049] Spectral analysis: Analyze the surface reflectance spectrum to identify different rock types. LiDAR scanning: Accurately measure terrain undulations and infer underground structures.

[0050] Furthermore, after obtaining geological data, it is necessary to use computer software to construct a three-dimensional virtual geological model. The main process is as follows: Data preprocessing: Data cleaning: remove noise and outliers to ensure the accuracy of seismic, well logging, GPR and remote sensing data. Coordinate unification: convert different data sources (drilling, seismic, radar scanning, etc.) into a unified three-dimensional coordinate system (such as UTM coordinate system).

[0051] 3D mesh modeling: Use inversion algorithms to convert geological data into three-dimensional spatial structures. Common methods include: Seismic Tomography: Reconstruct a three-dimensional geological model based on the distribution of seismic wave velocity. Kriging Interpolation: Use borehole data for spatial interpolation to construct a three-dimensional grid of the underground medium. Point cloud data modeling: Point cloud data obtained by LiDAR scanning or GPR can be used to build detailed surface models.

[0052] Geological boundary extraction, for example: Based on seismic data: using the characteristics of seismic reflection layers to determine the interface between different media. Based on well logging data: analyzing borehole logging results, identifying lithology changes, and drawing geological layer sections.

[0053] 3D visualization: Use 3D modeling software (such as Leapfrog, GOCAD, Surpac) for geological visualization modeling: Generate a 3D geological model to show the spatial distribution of different strata. Define the properties of different media in the model (elastic modulus, density, Poisson's ratio, etc.). Combine mechanical analysis software (such as ANSYS, Abaqus) to simulate the force of anchor bolts.

[0054] Furthermore, the constructed 3D geological virtual model can be used for anchor construction simulation: The initial installation angle of the anchor bolt (angle 1) is defined in the model, and the drilling process of the anchor bolt is simulated.

[0055] Set mechanical parameters: set the friction, support and resistance of each medium to simulate the stress conditions of the anchor in different geological conditions.

[0056] Simulate the anchor penetration process: In a single medium, the angle remains unchanged. When the anchor reaches the medium boundary, calculate the force mutation and predict the deflection angle δ. Record the displacement, vibration and force data of the anchor as a basis for construction adjustments.

[0057] Correct installation angle: The final angle of the anchor end is calculated through simulation, and the anchor construction angle is adjusted to ensure stability.

[0058] First, in the three-dimensional geological structure virtual model, the edges of different media are divided: for any two connected media B and C, the survey signals of B and C are obtained respectively, and in the connected part of B and C, the positions where the survey signal intensities of B and C are equal are fitted to obtain the boundary line of the edges of B and C, and all the boundary lines are drawn to obtain the division results of the edges of different media.

[0059] In the three-dimensional geological structure virtual model, it is assumed that the anchor rod penetrates at an angle of 1 and deflects when reaching any boundary line. The deflection angle is ; Use mechanical analysis software to analyze the forces on the anchor rod, so as to obtain the offset angle of the end of the anchor rod compared with angle 1. It should be noted that by comparing the angle of the anchor rod before anchoring, and the angle between the anchor rod position and the slope after the mechanical analysis software simulates anchoring, the offset angle can be obtained by subtracting the two.

[0060] The offset angle is analyzed in real time using mechanical analysis software. When the offset angle exceeds a threshold, anchor failure is predicted and the automatic alignment of the upper anchor device at the current position is canceled. When the anchor depth does not meet the requirement and the offset angle does not exceed the threshold, the prediction continues. When the anchor depth meets the requirement and the offset angle does not exceed the threshold, it is determined that the current position can complete the anchoring and the final offset angle is recorded as the adjustment angle.

[0061] Among them, there are many professional mechanical analysis software that can be used to analyze the stress of the rod, especially for structural mechanics and material mechanics problems. Mechanical analysis software can use the following software: ANSYS, Abaqus, SolidWorksSimulation, etc. Through the finite element analysis method, the predicted results are directly output through the software.

[0062] The adjustment angle is superimposed on angle 1 to obtain the installation angle. is the deflection angle, which indicates the angle deflection when the anchor head reaches the boundary line; the relationship between the deflection angle and the parameter is fitted using the regression method ; f(...) represents the fitting function, which can be done by linear regression, support vector machine (SVM) or neural network. It indicates the angle between the anchor head and the boundary line when it reaches the boundary line. It indicates the parameters of the medium where the anchor head is located before reaching the boundary line; It indicates the parameters of the medium where the anchor head is located after reaching the boundary line; Represents the external force applied during the penetration of the anchor.

[0063] It is important to carry out three-dimensional modeling and virtual simulation of geological conditions, accurately identify the distribution and properties of the junction of multiple media, and provide data support for the dynamic adjustment of the anchor angle. During the process of anchor penetration, the anchor head may be offset at the junction of two media. The deflection angle is predicted using a three-dimensional geological virtual model, and it is superimposed with the initial angle (angle 1) to calculate the actual installation angle. Through real-time analysis, the installation angle is dynamically adjusted to adapt to broken geology or uneven media conditions to avoid installation failure or excessive errors. Among them, "dynamic adjustment of installation angle" represents an iterative process, which outputs the final installation angle by continuously taking the "actual installation angle" as input and adjusting it. Ensuring the final installation angle is the most stable solution.

[0064] Through mechanical analysis software (such as ANSYS, Abaqus, etc.), the finite element analysis method is used to calculate the force and deflection angle of the anchor in real time, ensuring that the feasibility of installation can be quickly evaluated under complex geological conditions. When the anchor depth does not meet the requirements, the prediction analysis is continuously performed; when the deviation angle exceeds the threshold, the installation operation at the current position is terminated in time to reduce trial and error time and resource waste.

[0065] Regression methods (such as linear regression, SVM or neural network) are used to fit the relationship between the anchor deflection angle and medium parameters and external forces, to achieve intelligent prediction of the deflection angle, and to provide generalization capabilities for anchor installation under different site conditions. Dynamic monitoring of the anchor installation process, real-time adjustment of angle and depth parameters, and reduction of human intervention can achieve efficient and automated anchor construction.

[0066] By setting the deflection angle threshold and real-time prediction, when the anchor bolt offset exceeds the threshold, the anchor bolt alignment is terminated in time to avoid anchor bolt installation failure or construction risks due to large errors. The final adjustment angle is recorded in real time to provide a reference for subsequent construction and improve construction safety in geologically complex areas.

[0067] S4: Align the anchor rods according to the positioning results and installation angle.

[0068] S5: The anchor status is judged in real time. If the alignment requirements are not met, re-alignment is performed.

[0069] Specifically, the actual angle between the anchor rod and the anchoring plane is obtained by using a visual sensor. If the actual angle exceeds a preset maximum reference value, it is determined that the alignment requirement is not met; otherwise, it is determined that the alignment requirement is met.

[0070] On the other hand, the present embodiment further provides an automatic alignment system for upper anchor rod equipment based on a lifting robot, which includes: The collection unit is equipped with a visual sensor on the lifting robot of the upper anchor equipment to collect visual information.

[0071] The recognition unit performs preliminary recognition on the visual information.

[0072] The positioning unit visually locates the predetermined area for anchor rod installation according to the result of the preliminary identification, and determines the installation angle of the anchor rod according to the positioning result.

[0073] The execution unit aligns the anchor rod according to the positioning result and the installation angle; the anchor rod status is judged in real time, and if the alignment requirements are not met, the re-alignment operation is performed.

[0074] Embodiment 2 is an embodiment of the present invention, which provides a method for real-time status diagnosis of a hydraulic system based on an automatic alignment method of an upper anchor rod device of a lifting robot.

[0075] Multiple sensors (displacement sensor, vibration acceleration sensor, acceleration sensor, etc.) are configured on the robot arm and hydraulic system to collect displacement information and various acceleration information.

[0076] During the alignment installation, data information is transmitted to the hydraulic system in real time; automatic data detection, automatic processing, calculation and storage of parameters (pressure, flow, acceleration, vibration, displacement, etc.) are realized, which is convenient for adjusting the angle of the anchor robot and monitoring the working status of the hydraulic system and signal collection; The information data of the hydraulic system operation is analyzed as a linear process, the data change rules are explored, data sets are created, and a state space model based on machine learning is constructed. The training data can be used to diagnose whether the hydraulic system is abnormal in real time.

[0077] For the condition monitoring of hydraulic system, the machine learning K-Means method is used to perform cluster analysis on the data of the hydraulic system operation process; the data is processed by Fourier basis function transformation, EM algorithm and Kalman filtering method to establish a state space model.

[0078] When collecting sensor data, when the data collection frequency is high and the number of sampling points is large, the obtained data will show certain functional characteristics in the data space. The linear data analysis method can perform unequally spaced data sampling when obtaining observation data. For discrete data samples with different sampling rates, they can be converted into linear data by using interpolation or smoothing methods.

[0079] Based on the linear data analysis method, discrete time series data objects are expressed in a functional way: ; Where: is the function value of the original data sequence at the kth sampling point; is the fitting error corresponding to the data point, which often refers to the disturbance factors, errors or other exogenous factors in the observed data; The fitted sequence can be expressed as a function .

[0080] The general steps of linear data analysis are: Step 1: Expand the discrete data based on the basis function smoothing method.

[0081] Step 2: Add a penalty term to smooth the fitting function.

[0082] When using the basis function smoothing method to fit discrete data, in order to avoid overfitting of the function curve and excessive consideration of local fluctuations of the data that cannot accurately express the main characteristics of the original data, the roughness penalty factor is introduced into the fitting process, and the penalty term is added to control the curvature of the fitting curve, that is, to control the degree of fitting of the basis function to the original discrete data, so that its representation is more reasonable.

[0083] Step 3: Calculate the coefficient vector using the least squares method.

[0084] The specific process of K-means clustering algorithm: Step 1: Use the sparrow optimization algorithm to select K cluster centroids: .

[0085] Step 2: Calculate each data point x and the centroid set in the data object separately The distance between each centroid in the data point x is divided into the class closest to the centroid, as shown in formula (1-1): (1-1); Where i = 1, 2, ..., N; j = 1, 2, ..., K and ; Represents the distance between the data point and the centroid, calculated using the Euclidean distance formula.

[0086] Step 3: Recalculate the centroid of each cluster, as shown in formula (1-2): (1-2); in, express The number of data points in .

[0087] Step 4: Repeat steps 2 and 3 until the algorithm converges.

[0088] CatBoost algorithm is used to diagnose abnormal operation status of hydraulic system.

[0089] According to the feature importance ranking of CatBoost, the optimal feature subset is determined to judge the severity or cause of the fault. The steps are as follows: Step 1: Import the original data such as displacement, pressure and vibration sensors collected from the hydraulic system, and divide the original experimental data into training set A and test set B through random sampling and other methods. Both training sets A and B contain different operating states of the same number of components, and perform maximum and minimum processing on all samples.

[0090] Step 2: On the training set, use the Catboost method to rank the importance of all features and determine the relevance ranking of the features.

[0091] Step 3: Screen the feature variables to ensure recognition accuracy and determine the feature set.

[0092] Step 4: On the feature subset trained in the previous step, a Catboost classification model is constructed and the model's ability to accurately identify fault types is evaluated through the test set.

[0093] Step 5: According to the preliminary diagnostic effect of the model, adjust the parameters of the Catboost classification model until the expected effect is achieved.

[0094] Step 6: On the premise of meeting the iteration conditions, store the current optimal model parameters, and use these parameters to analyze the test data to ultimately obtain accurate classification diagnosis results.

[0095] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0096] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0097] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0098] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0099] Example 3 is an embodiment of the present invention, which provides an automatic alignment method for upper anchor rod equipment based on a lifting robot. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0100] The experimental site selected a broken and uneven simulated slope area. The foundation conditions of the slope were trimmed to form multiple potential anchor bolt installation areas. The rock mass conditions of the slope were obtained through survey tools, and a three-dimensional geological structure virtual model was constructed to predict the angle deflection.

[0101] Test equipment and materials: Lifting robot equipped with vision sensor (model: G-RobotX2).

[0102] Independently developed 3D geological model simulation platform.

[0103] Mechanical analysis software (ANSYS).

[0104] High-resolution camera (resolution: 1920×1080).

[0105] During the test, the following steps are performed in sequence: Visual information collection and preprocessing: The lifting robot is installed at the predetermined test site to collect visual information of the set slope area. The visual sensor uses a high-resolution camera to capture real-time images, uses the Canny algorithm to extract image edges, and connects broken edges through morphological operations to form multiple closed areas. After screening, images with high clarity, a large proportion of the predetermined area, and the smallest distance between the center of the picture and the center of the predetermined area are selected from the visual information as the basis for subsequent processing.

[0106] Predetermined area positioning and installation angle determination: The filtered image is input into the convolutional neural network for recognition, the feature extraction layer extracts the regional edge and texture features, the regional division layer marks the qualified areas with higher feature density, and the coordinate positioning layer outputs the coordinates of the center point of the area that meets the installation conditions. Subsequently, the initial installation angle (angle 1) obtained from the design drawings is matched with the three-dimensional geological virtual model to simulate the angle deflection of the anchor at different depths, calculate the adjustment angle, and finally determine the actual installation angle.

[0107] Simulation and data recording of anchor penetration process: The anchor is gradually penetrated at the actual installation angle, and the force and deflection angle are monitored in real time using mechanical analysis software. The deviation angle is recorded every 1 meter. When the deviation angle does not exceed the threshold and the anchor depth reaches the requirement, the installation is considered successful, and the final deviation angle is recorded as the basis for adjustment; if the deviation angle exceeds the threshold, the installation is terminated and the coordinates of the failure point are recorded.

[0108] Through experimental tests, the present invention can accurately complete the alignment without the need for manual correction.

[0109] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for automatically aligning an upper anchor rod device based on a lifting robot, characterized in that: include: A visual sensor is configured on the lifting robot of the upper anchor bolt equipment to collect visual information; Performing preliminary recognition on the visual information; Based on the result of the preliminary identification, visually locate the predetermined area for anchor bolt installation, and determine the installation angle of the anchor bolt based on the positioning result; Align the anchor rods according to the positioning results and installation angles; The anchor bolt status is judged in real time. If the alignment requirements are not met, re-alignment is performed; The alignment includes, based on the positioning result, determining the position of the anchor rod according to the installation angle; after determining the position of the anchor rod, performing an anchoring action.

2. The automatic alignment method of the upper anchor rod equipment based on the lifting robot according to claim 1 is characterized in that: The visual information includes, in the site, demarcating the actual area where the anchor rod needs to be installed as the predetermined area, and marking it in the predetermined area; Using the real-time image information collected by the visual sensor, identifying whether there is a logo in the image; When the predetermined area completely enters the image frame, the acquisition result is recorded.

3. The automatic alignment method of the upper anchor rod equipment based on the lifting robot according to claim 2 is characterized in that: The preliminary recognition includes screening images in the sampling results and identifying the screened images; The screening process includes: analyzing the clarity to screen out images whose clarity meets the preset conditions and whose proportion of the predetermined area in the picture is higher than τ; performing secondary screening on the screened images to calculate the actual distance A between the center of the predetermined area and the center of the picture, and selecting the image with the smallest A; if there are multiple results of the secondary screening, selecting the image with the highest clarity from the multiple secondary screening results as the final screening result; in, Indicates the preset ratio threshold; , a represents the distance between the center of the predetermined area and the center of the picture in the image, represents the actual horizontal width of the predetermined area, Indicates the horizontal width of the predetermined area in the figure.

4. The automatic alignment method of the upper anchor rod equipment based on the lifting robot according to claim 3 is characterized in that: The identifying of the screened image includes extracting edges in the image using a Canny algorithm, connecting broken edges using a morphological operation, and forming a closed area; Recognition based on convolutional neural network architecture; Input: the result of the preliminary identification; Output: coordinate results of visual positioning; The convolutional neural network architecture includes a feature extraction layer, a region division layer, and a coordinate positioning layer; The feature extraction layer extracts the features of each closed area, obtains a feature map and inputs it into the area division layer; the area division layer identifies the feature types and distribution density in the feature map and divides the feature area; the coordinate positioning layer selects the area in the map of the divided feature area and locates the center of the selected area; Among them, the feature extraction layer, region division layer, and coordinate positioning layer have independent functions, and the three layers can be trained separately, and finally the recognition is completed through collaboration; After the recognition is completed, the coordinate results are mapped to the positioning position of the actual site, the alignment behavior of the anchor installation is continuously monitored, and the positioning position of the actual site is mapped to the real-time monitoring screen, and adjustments are made until the anchor is completed.

5. The automatic alignment method of the upper anchor rod equipment based on the lifting robot according to claim 4 is characterized in that: The installation angle includes matching the positioning result in the design drawing, obtaining the angle between the anchor rod and the anchoring plane in the drawing as angle 1; The anchoring geology is analyzed and the angle 1 is adjusted to obtain the actual installation angle.

6. The automatic alignment method of the upper anchor rod equipment based on the lifting robot according to claim 5 is characterized in that: The analysis of anchoring geology includes obtaining a three-dimensional virtual model of geological structure and simulating the penetration process of the anchor rod in the virtual model; assuming that in the same medium, the angle of the anchor rod will not change during the penetration process, and the anchor rod head will deviate at the junction of the two media, so that the angle of the anchor rod will change; Performing angle analysis on the end of the anchor rod according to the angle change to obtain an adjustment angle for the angle 1; In the three-dimensional geological structure virtual model, the edges of different media are divided: for any two connected media B and C, the survey signals of B and C are obtained respectively, and at the connecting part of B and C, the positions where the survey signal intensities of B and C are equal are fitted to obtain the boundary line of the edges of B and C, and all the boundary lines are drawn to obtain the division results of the edges of different media; In the three-dimensional geological structure virtual model, it is assumed that: the anchor rod is penetrated at an angle of 1, and when reaching any boundary line, it deflects, and the deflection angle is δ; The force on the anchor rod is analyzed using mechanical analysis software to obtain the offset angle of the anchor rod end compared to angle 1; The offset angle is analyzed in real time. When the offset angle exceeds a threshold, the anchor bolt is predicted to fail, and the automatic alignment of the upper anchor bolt device at the current position is canceled; when the anchor bolt depth does not meet the requirement and the offset angle does not exceed the threshold, the prediction is continued; when the anchor bolt depth meets the requirement and the offset angle does not exceed the threshold, it is determined that the current position can complete the anchor bolt, and the final offset angle is recorded as the adjustment angle; Superimpose the adjustment angle and angle 1 to obtain the installation angle; in, is the deflection angle, which indicates the angle deflection that occurs when the anchor head reaches the junction line; Use regression method to fit the relationship between deflection angle and parameters ; f(...) represents the function used for fitting; It indicates the angle between the anchor head and the boundary line when it reaches the boundary line. It indicates the parameters of the medium where the anchor head is located before reaching the boundary line; It indicates the parameters of the medium where the anchor head is located after reaching the boundary line; Represents the external force applied during the penetration of the anchor.

7. The method for automatically aligning the upper anchor rod equipment based on the lifting robot according to claim 6, characterized in that: The real-time determination of the state of the anchor rod includes obtaining the actual angle between the anchor rod and the anchoring plane using a visual sensor, and if the actual angle exceeds a preset maximum reference value, determining that the alignment requirement is not met; Otherwise, it is judged that the alignment requirement is met.

8. An automatic alignment system for upper anchor bolt equipment based on a lifting robot using the method according to any one of claims 1 to 7, characterized in that: The collection unit is equipped with a visual sensor on the lifting robot of the upper anchor equipment to collect visual information; A recognition unit, which performs preliminary recognition on the visual information; A positioning unit, which visually locates a predetermined area for anchor bolt installation according to the result of the preliminary identification, and determines an installation angle of the anchor bolt according to the positioning result; The execution unit aligns the anchor rod according to the positioning result and the installation angle; the anchor rod status is judged in real time, and if the alignment requirements are not met, the re-alignment operation is performed.

9. A computer device comprising: A memory and a processor; the memory stores a computer program, wherein the processor implements the steps of any method as claimed in claim 1 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images