A five-sublayer man-machine alternating operation method and system for a wet spraying mechanical arm

Abstract

The present application relates to the field of intelligent control, and proposes a five-layer human-computer alternating operation method and system for wet spraying mechanical arm, which constructs a wet spraying three-dimensional point cloud model of the tunnel, divides the construction layers with different construction requirements, has better environmental adaptability compared with the fixed track or simple layering mode in the prior art, improves the construction quality when facing the complex scene of uneven rock wall and steel arch frame interlacing, avoids the problem that the traditional automatic wet spraying is difficult to deal with complex rock surface, gets rid of the dependence on manual experience, generalizes and reproduces the wet spraying track, improves the construction quality and efficiency, and selects different wet spraying tracks for different construction layers, further improves the construction quality, and the present application improves the wet spraying quality and construction efficiency of the wet spraying mechanical arm operation method.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent control, in particular to a five-layered man-machine alternating operation method and system for a wet spraying mechanical arm. BACKGROUND

[0002] With the rapid development of industrial engineering industry, the requirements of tunnel construction are gradually improved, especially the tunnel wet spraying concrete construction technology, which is used after tunnel blasting or excavation to prevent rock burst and rockfall of the tunnel wall surface. Therefore, the tunnel wet spraying concrete construction has gradually become one of the most important technical links.

[0003] In the prior art, the traditional tunnel wet spraying construction is usually operated by manual operation, but manual operation has the problems of low efficiency and high cost, which is difficult to adapt to the continuous high-intensity tunnel construction, and the manual operation is highly dependent on the personal experience and construction skills of the operator, which cannot guarantee the uniformity of the wet spraying quality, and is prone to uneven spraying and non-standard thickness. In addition, the close-range wet spraying operation by manual operation has safety hazards. The existing mechanical arm wet spraying equipment usually adopts a fixed track or a simple layering mode, which is difficult to adaptively adjust the spraying parameters when facing the complex scenes of the uneven rock wall and the staggered steel arch in the tunnel, resulting in high concrete rebound rate and serious material waste. Especially in large-section tunnel engineering, the traditional method often prolongs the construction period due to poor process connection.

[0004] Therefore, how to design a wet spraying mechanical arm operation method to avoid the influence of complex construction scenes and complex rock surfaces and improve the wet spraying efficiency and quality has become a problem to be solved. SUMMARY

[0005] Therefore, the present application provides a five-layered man-machine alternating operation method and system for a wet spraying mechanical arm, which constructs a three-dimensional point cloud model of the tunnel wet spraying, divides the construction layers according to different construction requirements, has better environmental adaptability compared with the fixed track or simple layering mode in the prior art, improves the construction quality when facing the complex scenes of the uneven rock wall and the staggered steel arch in the tunnel, and avoids the problem that the traditional automatic wet spraying cannot cope with the complex rock surface by generalizing the wet spraying skills, teaching and automatically reproducing the irregular filling and surface flattening work in the traditional construction scene which needs to be operated by manual operation, thereby avoiding the dependence on manual experience, generalizing and reproducing the wet spraying track, improving the construction quality and efficiency, and selecting different wet spraying tracks for different construction layers to further improve the construction quality. The present application improves the wet spraying quality and construction efficiency of the wet spraying mechanical arm operation method.

[0006] The five-layered man-machine alternating operation method for a wet spraying mechanical arm provided by the present application comprises the following steps:

[0007] scanning a wet spray tunnel to construct a wet spray three-dimensional point cloud model, a construction layer of the wet spray three-dimensional point cloud model comprising a manually wet spray layer and an automatic wet spray layer, the manually wet spray layer comprising a manual rock surface filling layer, a manual leveling base layer and a manual leveling surface layer, and the automatic wet spray layer comprising an automatic filling base layer and an automatic filling core layer;

[0008] performing shape feature comparison according to the wet spray three-dimensional point cloud model to select a construction mode of each manually wet spray layer, the shape feature comparison being based on a wet spray construction database, the wet spray construction database comprising historical wet spray three-dimensional point cloud model data and wet spray skill data, and the construction mode comprising a teaching mode and a reproduction mode;

[0009] performing layered wet spray processing according to the construction mode to complete wet spray construction, the layered wet spray processing being based on the wet spray skill data in the wet spray construction database.

[0010] In summary, according to the above-mentioned five-layer human-computer alternating operation method and system for a wet spraying mechanical arm, by constructing a wet spraying three-dimensional point cloud model of the tunnel and dividing the construction layers according to different construction requirements, compared with the fixed track or simple layering mode used in the prior art, better environmental adaptability is achieved, and when facing the complex scene of uneven rock walls and steel arches in the tunnel, the construction quality is improved. The wet spraying skill generalization is performed, the irregular filling and surface leveling work in the traditional construction scene which needs manual operation is taught and automatically reproduced, the problem that the traditional automatic wet spraying is difficult to deal with complex rock surfaces is avoided, the dependence on manual experience is eliminated, the wet spraying track is generalized and reproduced, the construction quality and efficiency are improved, and different wet spraying tracks are selected according to different construction layers, which further improves the construction quality. The present application improves the wet spraying quality and construction efficiency of the wet spraying mechanical arm operation method. Specifically, the tunnel to be wet sprayed is scanned to construct a wet spraying three-dimensional point cloud model. The construction layer of the wet spraying three-dimensional point cloud model includes a manually wet sprayable layer and an automatic wet sprayable layer. The manually wet sprayable layer includes a manual rock surface filling layer, a manual leveling base layer, and a manual leveling surface layer. The automatic wet sprayable layer includes an automatic filling base layer and an automatic filling core layer. Compared with the fixed track or simple layering mode used in the prior art, better environmental adaptability is achieved, and when facing the complex scene of uneven rock walls and steel arches in the tunnel, the construction quality is improved. Shape feature comparison is performed according to the wet spraying three-dimensional point cloud model to select the construction mode of each manually wet sprayable layer. The shape feature comparison is based on a wet spraying construction database. The wet spraying construction database includes historical wet spraying three-dimensional point cloud model data and wet spraying skill data. The construction mode includes a teaching mode and a reproduction mode. The irregular filling and surface leveling work in the traditional construction scene which needs manual operation is taught and automatically reproduced, the problem that the traditional automatic wet spraying is difficult to deal with complex rock surfaces is avoided, the dependence on manual experience is eliminated, the wet spraying track is generalized and reproduced, the construction quality and efficiency are improved, and the construction quality is further improved. The present application improves the wet spraying quality and construction efficiency of the wet spraying mechanical arm operation method.

[0011] Further, the step of scanning the tunnel to be wet sprayed to construct a wet spraying three-dimensional point cloud model specifically includes:

[0012] The tunnel to be wet sprayed is pre-sprayed and three-dimensionally scanned to construct a wet spraying three-dimensional point cloud model of the current tunnel to be wet sprayed;

[0013] The wet spraying three-dimensional point cloud model is subjected to hierarchical processing to be divided into a manually wet spraying layer and an automatic wet spraying layer, the manually wet spraying layer includes a manual rock surface filling layer, a manual leveling base layer and a manual leveling surface layer, and the automatic wet spraying layer includes an automatic filling base layer and an automatic filling core layer;

[0014] The three-dimensional space layer containing all residual rock pits after the pre-spraying treatment is divided into a manual rock surface filling layer, the three-dimensional space layer between the manual rock surface filling layer and the tunnel steel arch layer is divided into an automatic filling base layer and a manual leveling base layer, the three-dimensional space layer proportion of the automatic filling base layer and the manual leveling base layer is divided according to a preset automatic filling threshold, the automatic filling base layer is connected with the manual rock surface filling layer, the manual leveling base layer is connected with the tunnel steel arch layer, the three-dimensional space layer of the tunnel steel arch layer is divided into an automatic filling core layer, and the three-dimensional space layer between the tunnel steel arch layer and the design surface layer is divided into a manual leveling surface layer;

[0015] The residual rock pit area in the manual rock surface filling layer area is subjected to depth detection, and it is judged whether the depth difference value of the residual rock pit area and the construction reference surface is greater than or equal to a preset difference threshold, if it is judged that the depth difference value of the residual rock pit area and the construction reference surface is greater than or equal to the preset difference threshold, the residual rock pit area is set as a priority filling area, the priority filling area is subjected to difference filling during construction, and the difference filling stops at the construction reference surface.

[0016] Further, the step of comparing the shape features of all manually wet spraying layers in the wet spraying three-dimensional point cloud model with the historical wet spraying three-dimensional point cloud model data in the wet spraying construction database, specifically includes:

[0017] The shape features of all manually wet spraying layers in the wet spraying three-dimensional point cloud model are compared with the historical wet spraying three-dimensional point cloud model data in the wet spraying construction database;

[0018] The similarity of the manually wet spraying layer and the historical wet spraying three-dimensional point cloud model data is judged, if the similarity is less than a preset similarity threshold, the construction mode of the manually wet spraying layer is adjusted to a teaching mode, and if the similarity is greater than or equal to the preset similarity threshold, the construction mode of the manually wet spraying layer is adjusted to a reproduction mode;

[0019] The construction mode of all automatic wet spraying layers in the wet spraying three-dimensional point cloud model is set to an automatic mode.

[0020] Further, the teaching mode specifically includes:

[0021] Call the manual wet spraying record of the operator to obtain manual wet spraying trajectory information and manual wet spraying process information, the manual wet spraying trajectory information including spray head pose information and trajectory timestamp information, the spray head pose information including spray head space coordinate information and spray head space angle information, the manual wet spraying process information including wet spraying flow information and spraying agent information;

[0022] Perform coordinate alignment processing according to the spray head pose information, the coordinate alignment processing determining a conversion matrix of a trolley base coordinate system and a sensor coordinate system based on a calibration board, and performing data time synchronization processing according to the trajectory timestamp information;

[0023] Perform point cloud coordinate correspondence of the manual wet spraying trajectory, the point cloud coordinate correspondence searching for a nearest neighbor point in a wet spraying three-dimensional point cloud model based on the spray head pose information;

[0024] Perform point cloud normal vector calculation, extract a radius neighborhood point set of each point cloud to perform local surface fitting, and then calculate a neighborhood point covariance matrix to perform eigenvalue decomposition, a feature vector of a minimum eigenvalue obtained by the eigenvalue decomposition being a point cloud normal vector, perform direction consistency processing according to point cloud global normal vector consistency filtering, and perform curvature weighted iterative optimization;

[0025] Perform point cloud curvature calculation, extract a local surface patch and perform local surface fitting according to the least square method, then calculate a curvature tensor according to a quadratic surface coefficient, and obtain path curvature according to normal curvature of the manual wet spraying trajectory in the manual wet spraying trajectory information;

[0026] Extract key parameters, the key parameters including a reference spraying distance, a normal vector deviation angle, an average normal vector direction, a maximum curvature and a curvature change rate of the trajectory, and key manual intervention points, the key manual intervention points including trajectory inflection points and construction area joint points, and a specific algorithm of the reference spraying distance being as follows:

[0027] ,

[0028] wherein, the reference spraying distance is represented by d, the number of points is represented by n, the point serial number is represented by i, the manual wet spraying trajectory point is represented by P, the nearest point cloud point of the manual wet spraying trajectory point is represented by Pn;

[0029] Generate the key parameters into wet spraying skill data according to a task parameterization algorithm, and store the wet spraying skill data into a wet spraying construction database.

[0030] Further, the reproduction mode specifically includes:

[0031] According to the wet spraying skill data in the wet spraying construction database, the teaching trajectory of the current construction layer is obtained, the teaching trajectory is generated based on the manual wet spraying trajectory information of the teaching mode, and the reproduction trajectory point cloud coordinates are aligned according to the teaching trajectory The reproduction trajectory point cloud coordinates are aligned with the teaching trajectory point cloud coordinates based on an iterative closest point algorithm.

[0032] According to the reproduction trajectory point cloud coordinates, the reproduction trajectory is generated, and the specific algorithm of the reproduction trajectory generation is as follows:

[0033] ,

[0034] Among them, represents the reproduction trajectory point, represents the teaching trajectory point, represents that the reproduction trajectory keeps the reference spraying distance in the normal vector direction, represents the spraying distance component of the teaching trajectory.

[0035] According to the curvature of the reproduction trajectory, the adaptive speed regulation is performed to obtain the adaptive reproduction trajectory speed, and the specific algorithm of the adaptive speed regulation is as follows:

[0036] ,

[0037] Among them, represents the adaptive reproduction trajectory speed, represents the speed of the teaching trajectory, represents the curvature of the reproduction trajectory.

[0038] According to the reproduction trajectory and the adaptive reproduction trajectory speed, the reproduction wet spraying construction is performed.

[0039] Further, the automatic mode specifically includes:

[0040] The wet spraying skill data in the wet spraying construction database and the automatic wet spraying layer data of the wet spraying three-dimensional point cloud model are called;

[0041] According to the automatic wet spraying parameter setting, the automatic wet spraying parameter includes the spraying distance, the spraying amount, the up-down swing angle, the left-right swing angle and the mechanical arm moving speed;

[0042] According to the wet spraying skill data in the wet spraying construction database and the wet spraying three-dimensional point cloud model, the automatic wet spraying is performed, the wet spraying surface of the automatic wet spraying is divided into a plurality of same spraying blocks, the center of each spraying block is taken as a spraying point, and the specific algorithm of the automatic wet spraying is as follows:

[0043] ,

[0044] ,

[0045] ,

[0046] ,

[0047] wherein, and represent the width and length of the wet spray block, represents the spray distance, represents the left-right swing angle, represents the up-down sweep angle, represents the up-down brush range of the end of the mechanical arm, represents the mechanical arm movement speed, represents the spray amount, represents the spray rebound rate, represents the thickness of the layer to be sprayed;

[0048] The present application implements detection of the current automatic wet spray layer flow, and when the wet spray flow is greater than or equal to a construction critical threshold value, three-dimensional scanning is performed and a wet spray three-dimensional point cloud model is updated, and it is determined whether the current construction surface needs to be leveled, and the construction critical threshold value is 90% of the total wet spray flow required for the current layer construction.

[0049] Further, the step of performing layered wet spray processing according to the construction mode to complete the wet spray construction specifically includes:

[0050] performing layered wet spray processing according to the construction mode;

[0051] when the layer to be sprayed in the construction mode is a manual rock surface filling layer, the wet spray track is from bottom to top and left-right alternate pit filling construction, when the layer to be sprayed in the construction mode is a manual leveling base layer, the wet spray track of the wall surface area is left-right alternate "arch" shape upward construction, the left-right alternate distance of the "arch" shape is one meter, the wet spray track of the vault area is "loop" shape construction, the "loop" shape construction is wet spray sequence from the outer ring to the inner ring, when the layer to be sprayed in the construction mode is a manual leveling layer, the wet spray track of the wall surface area is small spiral winding upward construction between two arches in the tunnel steel arch layer, the wet spray track of the vault area is "loop" shape construction until the steel arch of the tunnel steel arch layer is completely covered, and the "loop" shape construction is wet spray sequence from the outer ring to the inner ring.

[0052] The present application provides a five-layered human-computer alternating operation system for a wet spray mechanical arm, which comprises:

[0053] The construction layer division module is used for scanning a wet spraying tunnel to be sprayed to construct a wet spraying three-dimensional point cloud model, and the construction layer of the wet spraying three-dimensional point cloud model comprises a manually wet spraying layer and an automatically wet spraying layer, the manually wet spraying layer comprises a manual rock surface filling layer, a manual leveling base layer and a manual leveling surface layer, and the automatically wet spraying layer comprises an automatic filling base layer and an automatic filling core layer.

[0054] The construction mode division module is used for comparing shape features according to the wet spraying three-dimensional point cloud model to select a construction mode of each manually wet spraying layer, the shape feature comparison is based on a wet spraying construction database, the wet spraying construction database comprises historical wet spraying three-dimensional point cloud model data and wet spraying skill data, and the construction mode comprises a teaching mode and a reproduction mode.

[0055] The construction implementation module is used for performing layered wet spraying processing according to the construction mode to complete wet spraying construction, and the layered wet spraying processing is based on the wet spraying skill data in the wet spraying construction database.

[0056] The application further provides a storage medium, which stores one or more programs, and the programs are executed by a processor to implement the five-layered man-machine alternating operation method for a wet spraying mechanical arm.

[0057] The application further provides a computer device, which comprises a memory and a processor, wherein:

[0058] The memory is used for storing a computer program;

[0059] The processor is used for executing the computer program stored in the memory to implement the five-layered man-machine alternating operation method for a wet spraying mechanical arm. BRIEF DESCRIPTION OF DRAWINGS

[0060] Figure 1 A flow chart of the five-layered man-machine alternating operation method for a wet spraying mechanical arm is provided for the first embodiment of the application;

[0061] Figure 2 A structural schematic diagram of the five-layered man-machine alternating operation system for a wet spraying mechanical arm is provided for the second embodiment of the application;

[0062] Figure 3 A layered schematic diagram of the wet spraying three-dimensional point cloud model is provided for the application.

[0063] The following specific embodiments will further illustrate the application in combination with the above drawings. DETAILED DESCRIPTION

[0064] For the purpose of promoting an understanding of the principles of the application, reference will now be made to the embodiments illustrated in the drawings. There is shown in the drawings several embodiments of the application. It is expressly understood that the drawings are only for the purpose of illustration and are not intended to limit the present application in any in any way. In fact, it will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, it is to be understood that the application disclosed herein is only to be limited by the scope of the appended claims, and not the embodiments that have been specifically enumerated hereinabove.

[0065] It should be noted that when an element as a "set" in another element, it can be directly on another element or also exist in the middle element. When an element is considered to be "connected" to another element, it can be directly connected to another element or there can be a middle element. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0066] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0067] Referring to Figure 1 , a flow chart of a five-layered man-machine alternating operation method for a wet spraying mechanical arm according to the first embodiment of the present application is shown. The five-layered man-machine alternating operation method for a wet spraying mechanical arm includes steps S01 to S03, wherein:

[0068] Step S01: Scanning the tunnel to be wet sprayed to construct a wet spraying three-dimensional point cloud model;

[0069] It should be noted that in this embodiment, the construction layer of the wet spraying three-dimensional point cloud model includes a manually wet sprayable layer and an automatically wet sprayable layer. The manually wet sprayable layer includes a manual rock surface filling layer, a manual leveling base layer and a manual leveling surface layer. The automatically wet sprayable layer includes an automatic filling base layer and an automatic filling core layer. For specific layering, please refer to Figure 3 ;

[0070] Pre-spraying the tunnel to be wet sprayed and performing three-dimensional scanning to construct a wet spraying three-dimensional point cloud model of the current tunnel to be wet sprayed;

[0071] Layering the wet spraying three-dimensional point cloud model to divide it into a manually wet sprayable layer and an automatically wet sprayable layer. The manually wet sprayable layer includes a manual rock surface filling layer, a manual leveling base layer and a manual leveling surface layer. The automatically wet sprayable layer includes an automatic filling base layer and an automatic filling core layer;

[0072] The three-dimensional space layer containing all the residual rock pits after the pre-spraying treatment is divided into a manual rock surface filling layer, the three-dimensional space layer between the manual rock surface filling layer and the tunnel steel arch layer is divided into an automatic filling base layer and a manual flattening base layer, the three-dimensional space layer proportion of the automatic filling base layer and the manual flattening base layer is divided according to a preset automatic filling threshold, the automatic filling base layer is connected with the manual rock surface filling layer, the manual flattening base layer is connected with the tunnel steel arch layer, the three-dimensional space layer of the tunnel steel arch layer is divided into an automatic filling core layer, and the three-dimensional space layer between the tunnel steel arch layer and the design surface layer is divided into a manual flattening surface layer;

[0073] The depth of the residual rock pit area in the manual rock surface filling layer area is detected, and it is determined whether the depth difference between the residual rock pit area and the construction reference surface is greater than or equal to a preset difference threshold. If it is determined that the depth difference between the residual rock pit area and the construction reference surface is greater than or equal to the preset difference threshold, the residual rock pit area is set as a priority filling area, the preset difference threshold is obtained according to historical wet spraying three-dimensional point cloud model data, the priority filling area is filled in the construction, and the filling is stopped at the construction reference surface.

[0074] Step S02: According to the shape feature comparison of the wet spraying three-dimensional point cloud model, the construction mode of each manually wet spraying layer is selected;

[0075] It should be noted that in the embodiment, the shape feature comparison is based on a wet spraying construction database, the wet spraying construction database includes historical wet spraying three-dimensional point cloud model data and wet spraying skill data, and the construction mode includes a teaching mode and a reproduction mode;

[0076] The shape features of all manually wet spraying layers in the wet spraying three-dimensional point cloud model are compared with the historical wet spraying three-dimensional point cloud model data in the wet spraying construction database;

[0077] According to the similarity of the manually wet spraying layer and the historical wet spraying three-dimensional point cloud model data, if the similarity is less than a preset similarity threshold, the construction mode of the manually wet spraying layer is adjusted to the teaching mode, and if the similarity is greater than or equal to the preset similarity threshold, the construction mode of the manually wet spraying layer is adjusted to the reproduction mode;

[0078] The construction mode of all the automatic wet spraying layers in the wet spraying three-dimensional point cloud model is set to an automatic mode;

[0079] The teaching mode specifically includes:

[0080] Call the manual wet spraying record of the operator to obtain manual wet spraying trajectory information and manual wet spraying process information, the manual wet spraying trajectory information including spray head pose information and trajectory timestamp information, the spray head pose information including spray head space coordinate information and spray head space angle information, the manual wet spraying process information including wet spraying flow information and spraying agent information;

[0081] Perform coordinate alignment processing according to the spray head pose information, the coordinate alignment processing determining a conversion matrix of a trolley base coordinate system and a sensor coordinate system based on a calibration board, and performing data time synchronization processing according to the trajectory timestamp information;

[0082] Perform point cloud coordinate correspondence of the manual wet spraying trajectory, the point cloud coordinate correspondence searching for a nearest neighbor point in a wet spraying three-dimensional point cloud model based on the spray head pose information;

[0083] Perform point cloud normal vector calculation, extract a radius neighborhood point set of each point cloud to perform local surface fitting, and then calculate a neighborhood point covariance matrix to perform eigenvalue decomposition, a feature vector of a minimum eigenvalue obtained by the eigenvalue decomposition being a point cloud normal vector, perform direction consistency processing according to point cloud global normal vector consistency filtering, and perform curvature weighted iterative optimization;

[0084] Perform point cloud curvature calculation, extract a local surface patch and perform local surface fitting according to the least square method, then calculate a curvature tensor according to a quadratic surface coefficient, and obtain path curvature according to normal curvature of the manual wet spraying trajectory in the manual wet spraying trajectory information;

[0085] Extract key parameters, the key parameters including a reference spraying distance, a normal vector deviation angle, an average normal vector direction, a maximum curvature and a curvature change rate of the trajectory, and key manual intervention points, the key manual intervention points including trajectory inflection points and construction area joint points, and a specific algorithm of the reference spraying distance being as follows:

[0086] ,

[0087] wherein, the reference spraying distance is represented by d, the number of points is represented by n, the point serial number is represented by i, the manual wet spraying trajectory point is represented by P, the nearest point cloud point of the manual wet spraying trajectory point is represented by Pn;

[0088] Generate the key parameters into wet spraying skill data according to a task parameterization algorithm, and store the wet spraying skill data into a wet spraying construction database;

[0089] The reproduction mode specifically includes:

[0090] According to the wet spraying skill data in the wet spraying construction database, the teaching trajectory of the current construction layer is obtained, and the teaching trajectory is generated based on manual wet spraying trajectory information of the teaching mode. According to the teaching trajectory, the reproduction trajectory point cloud coordinates are aligned The reproduction trajectory point cloud coordinates are aligned with the teaching trajectory point cloud coordinates based on the iterative closest point algorithm.

[0091] According to the reproduction trajectory point cloud coordinates, the reproduction trajectory is generated, and the specific algorithm of the reproduction trajectory generation is as follows:

[0092] ,

[0093] Among them, represents the reproduction trajectory point, represents the teaching trajectory point, represents that the reproduction trajectory keeps the reference spraying distance along the normal vector direction, represents the spraying distance component of the teaching trajectory.

[0094] According to the curvature of the reproduction trajectory, the adaptive speed regulation is performed to obtain the adaptive reproduction trajectory speed, and the specific algorithm of the adaptive speed regulation is as follows:

[0095] ,

[0096] Among them, represents the adaptive reproduction trajectory speed, represents the speed of the teaching trajectory, represents the curvature of the reproduction trajectory.

[0097] According to the reproduction trajectory and the adaptive reproduction trajectory speed, the reproduction wet spraying construction is performed.

[0098] The automatic mode specifically includes:

[0099] The wet spraying skill data in the wet spraying construction database and the automatic wet spraying layer data of the wet spraying three-dimensional point cloud model are called.

[0100] According to the automatic wet spraying parameter setting, the automatic wet spraying parameter includes the spraying distance, the spraying amount, the up-down swing angle, the left-right swing angle and the mechanical arm moving speed.

[0101] According to the wet spraying skill data in the wet spraying construction database and the wet spraying three-dimensional point cloud model, the automatic wet spraying is performed, the wet spraying surface of the automatic wet spraying is divided into a plurality of same spraying blocks, the center of each spraying block is taken as a spraying point, and the specific algorithm of the automatic wet spraying is as follows:

[0102] ,

[0103] ,

[0104] ,

[0105] ,

[0106] wherein, and represent the width and length of the wet spray block, represents the spray distance, represents the left-right swing angle, represents the up-down sweep angle, represents the up-down brush range of the end of the mechanical arm, represents the mechanical arm moving speed, represents the spray amount, represents the spray rebound rate, represents the layer thickness to be sprayed;

[0107] The wet spray flow of the current automatic wet spray layer is detected, and when the wet spray flow is greater than or equal to a construction critical threshold value, a three-dimensional scan is performed and a wet spray three-dimensional point cloud model is updated, and it is judged whether the current construction surface needs to be leveled. The construction critical threshold value is 90% of the total wet spray flow required for the current layer construction.

[0108] Step S03: performing layered wet spray processing according to the construction mode to complete the wet spray construction.

[0109] It should be noted that in the embodiment, the layered wet spray processing is based on the wet spray skill data in the wet spray construction database, and the layered wet spray processing is performed according to the construction mode.

[0110] When the layer to be sprayed of the construction mode is a manual rock surface filling layer, the wet spray track is from bottom to top and left-right alternate filling pit construction, when the layer to be sprayed of the construction mode is a manual leveling base layer, the wet spray track of the wall surface area is left-right alternate "arch" shape upward construction, the left-right alternate distance of the "arch" shape is one meter, the wet spray track of the vault area is "loop" shape construction, the "loop" shape construction is the wet spray sequence from the outer ring to the inner ring, when the layer to be sprayed of the construction mode is a manual leveling layer, the wet spray track of the wall surface area is a small spiral winding upward between the two arches in the tunnel steel arch layer, the wet spray track of the vault area is "loop" shape construction until the steel arch of the tunnel steel arch layer is completely covered, and the "loop" shape construction is the wet spray sequence from the outer ring to the inner ring.

[0111] In summary, according to the above-mentioned five-layer human-computer alternating operation method and system for a wet spraying mechanical arm, by constructing a wet spraying three-dimensional point cloud model of the tunnel and dividing the construction layers according to different construction requirements, compared with the fixed track or simple layering mode used in the prior art, better environmental adaptability is achieved, and when facing the complex scene of uneven rock walls and steel arches in the tunnel, the construction quality is improved. The wet spraying skill generalization is performed, the irregular filling and surface leveling work in the traditional construction scene which needs manual operation is taught and automatically reproduced, the problem that the traditional automatic wet spraying is difficult to deal with complex rock surfaces is avoided, the dependence on manual experience is eliminated, the wet spraying track is generalized and reproduced, the construction quality and efficiency are improved, and different wet spraying tracks are selected according to different construction layers, which further improves the construction quality. The wet spraying quality and construction efficiency of the wet spraying mechanical arm operation method are improved. Specifically, the tunnel to be wet sprayed is scanned to construct a wet spraying three-dimensional point cloud model. The construction layers of the wet spraying three-dimensional point cloud model include manually wet sprayable layers and automatic wet sprayable layers. The manually wet sprayable layers include a manual rock surface filling layer, a manual leveling base layer, and a manual leveling surface layer. The automatic wet sprayable layers include an automatic filling base layer and an automatic filling core layer. Compared with the fixed track or simple layering mode used in the prior art, better environmental adaptability is achieved, and when facing the complex scene of uneven rock walls and steel arches in the tunnel, the construction quality is improved. Shape feature comparison is performed according to the wet spraying three-dimensional point cloud model to select the construction mode of each manually wet sprayable layer. The shape feature comparison is based on a wet spraying construction database. The wet spraying construction database includes historical wet spraying three-dimensional point cloud model data and wet spraying skill data. The construction mode includes a teaching mode and a reproduction mode. The irregular filling and surface leveling work in the traditional construction scene which needs manual operation is taught and automatically reproduced, the problem that the traditional automatic wet spraying is difficult to deal with complex rock surfaces is avoided, the dependence on manual experience is eliminated, the wet spraying track is generalized and reproduced, the construction quality and efficiency are improved, and different wet spraying tracks are selected according to different construction layers, which further improves the construction quality. The wet spraying quality and construction efficiency of the wet spraying mechanical arm operation method are improved.

[0112] Referring to Figure 2 , a structure schematic diagram of a five-layer human-computer alternating operation system for a wet spraying mechanical arm according to the second embodiment of the present application is shown. The system includes:

[0113] A construction layer division module 10 is configured to scan a tunnel to be wet sprayed to construct a wet spraying three-dimensional point cloud model. The construction layers of the wet spraying three-dimensional point cloud model include manually wet sprayable layers and automatic wet sprayable layers. The manually wet sprayable layers include a manual rock surface filling layer, a manual leveling base layer, and a manual leveling surface layer. The automatic wet sprayable layers include an automatic filling base layer and an automatic filling core layer.

[0114] The construction mode division module 20 is configured to compare shape features according to the wet spraying three-dimensional point cloud model to select a construction mode of each manually wet spraying layer, the shape feature comparison is based on a wet spraying construction database, the wet spraying construction database comprises historical wet spraying three-dimensional point cloud model data and wet spraying skill data, and the construction mode comprises a teaching mode and a reproduction mode.

[0115] The construction implementation module 30 is configured to perform layered wet spraying processing according to the construction mode to complete wet spraying construction, and the layered wet spraying processing is based on the wet spraying skill data in the wet spraying construction database.

[0116] The application further provides a computer storage medium, which stores one or more programs, and the programs are executed by a processor to implement the five-layered man-machine alternating operation method for a wet spraying mechanical arm.

[0117] The application further provides a computer device, which comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to implement the five-layered man-machine alternating operation method for a wet spraying mechanical arm.

[0118] Those skilled in the art can understand that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a list of executable instructions for implementing the logic function, which can be specifically implemented in any computer readable medium for use by or in conjunction with an instruction execution system, device or apparatus, such as a computer-based system, a system including a processor or other system that can fetch and execute instructions from the instruction execution system, device or apparatus. For the purpose of the present description, the "computer readable medium" can be any device that can contain a storage, communication, propagation or transmission of a program for use by or in conjunction with an instruction execution system, device or apparatus.

[0119] More specific examples (a non-exhaustive list) of the computer readable medium include the following: an electrical connection having one or more wires (electrical devices), a portable computer diskette (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium can even be paper or other suitable medium on which the program can be printed, because the program can be electronically obtained, for example, by optical scanning of the paper or other medium, followed by electronic conversion, interpretation or processing, if necessary, in other suitable ways, and then stored in a computer memory.

[0120] It should be understood that portions of the application can be implemented in hardware, software, firmware, or combinations thereof. In the embodiments described above, the various steps or methods can be implemented, in part, or in whole, in software or firmware that is stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, the implementation can be with any one or a combination of the following technologies, which are all well-known in the art: a discrete logic circuit having logic gates for implementing logic functions upon an application of data signals; an application specific integrated circuit having appropriate combinational logic gates; a programmable gate array (PGA); a field programmable gate array (FPGA), and the like.

[0121] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the application. In the specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0122] The above-described embodiments only express several implementation manners of the application, which are described in a more specific and detailed manner, but cannot be understood as a limitation on the patent scope of the application. It should be noted that, for those skilled in the art, several modifications and improvements can be made without departing from the concept of the application, which are all within the protection scope of the application. Therefore, the patent protection scope of the application should be subject to the appended claims.

Claims

1. A five-layer human-machine alternating operation method for a wet spraying robotic arm, characterized in that, include: Scan the tunnel to be wet sprayed to construct a three-dimensional point cloud model of wet spraying. The construction layers of the three-dimensional point cloud model of wet spraying include a manually wet spraying layer and an automatically wet spraying layer. The manually wet spraying layer includes a manually filled rock surface layer, a manually leveled base layer and a manually leveled surface layer. The automatically wet spraying layer includes an automatically filled base layer and an automatically filled core layer. The step of scanning the tunnel to be wet-sprayed to construct a three-dimensional point cloud model of the wet-spraying process specifically includes: The tunnel to be wet-sprayed is pre-sprayed and three-dimensional scanned to construct a three-dimensional point cloud model of the current wet-sprayed tunnel. The wet spraying 3D point cloud model is layered to be divided into a manual wet spraying layer and an automatic wet spraying layer. The manual wet spraying layer includes a manual rock surface filling layer, a manual leveling base layer, and a manual leveling surface layer. The automatic wet spraying layer includes an automatic filling base layer and an automatic filling core layer. The three-dimensional spatial layer containing all residual rock pits after pre-spraying is divided into a manual rock surface filling layer. The three-dimensional spatial layer between the manual rock surface filling layer and the tunnel steel arch layer is divided into an automatic filling base layer and a manual leveling base layer. The ratio of the three-dimensional spatial layers of the automatic filling base layer and the manual leveling base layer is divided according to a preset automatic filling threshold. The automatic filling base layer is connected to the manual rock surface filling layer, and the manual leveling base layer is connected to the tunnel steel arch layer. The three-dimensional spatial layer of the tunnel steel arch layer is divided into an automatic filling core layer, and the three-dimensional spatial layer between the tunnel steel arch layer and the designed surface layer is divided into a manual leveling surface layer. The depth of the residual rock pit area in the manual rock surface filling layer area is detected to determine whether the depth difference between the residual rock pit area and the construction reference surface is greater than or equal to a preset difference threshold. If the depth difference between the residual rock pit area and the construction reference surface is greater than or equal to the preset difference threshold, the residual rock pit area is set as a priority filling area. The preset difference threshold is obtained based on historical wet spraying three-dimensional point cloud model data. The priority filling area is filled during construction, and the filling stops when the difference reaches the construction reference surface. Shape feature comparison is performed based on the wet spraying 3D point cloud model to select the construction mode for each manually sprayable layer. The shape feature comparison is based on the wet spraying construction database, which includes historical wet spraying 3D point cloud model data and wet spraying skill data. The construction mode includes teaching mode and reproduction mode. Layered wet spraying is performed according to the construction mode to complete the wet spraying construction. The layered wet spraying is based on wet spraying skill data in the wet spraying construction database. The step of performing layered wet spraying according to the construction mode to complete the wet spraying construction specifically includes: Layered wet spraying treatment shall be carried out according to the construction mode; When the layer to be sprayed in the construction mode is a manual rock surface filling layer, the wet spraying trajectory is to fill the deep pit from bottom to top, alternating left and right. When the layer to be sprayed in the construction mode is a manual leveling base layer, the wet spraying trajectory of the wall area is to work upwards in an alternating left and right "bow" shape, with the left and right alternation distance of the "bow" shape being one meter. The wet spraying trajectory of the arch top area is to work in a "return" shape, with the "return" shape being the wet spraying sequence from the outer circle to the inner circle. When the layer to be sprayed in the construction mode is a manual leveling surface layer, the wet spraying trajectory of the wall area is to work upwards in a small spiral circle between the two arches in the tunnel steel arch frame layer. The wet spraying trajectory of the arch top area is to work in a "return" shape until the steel arch frame of the tunnel steel arch frame layer is completely covered, with the "return" shape being the wet spraying sequence from the outer circle to the inner circle.

2. The five-layer human-machine alternating operation method for a wet spraying robotic arm according to claim 1, characterized in that, The step of comparing shape features based on the wet spraying 3D point cloud model to select the construction mode for each manually sprayable layer specifically includes: The shape features of all manually sprayable layers in the wet spraying 3D point cloud model are compared with historical wet spraying 3D point cloud model data in the wet spraying construction database. The similarity between the manually sprayable wet spraying layer and the historical wet spraying 3D point cloud model data is used to determine whether the similarity is less than a preset similarity threshold. If the similarity is less than a preset similarity threshold, the construction mode of the manually sprayable wet spraying layer is adjusted to the teaching mode. If the similarity is greater than or equal to the preset similarity threshold, the construction mode of the manually sprayable wet spraying layer is adjusted to the reproduction mode. Set the construction mode of all automatic wet spraying layers in the wet spraying 3D point cloud model to automatic mode.

3. The five-layer human-machine alternating operation method for a wet spraying robotic arm according to claim 2, characterized in that, The teaching mode specifically includes: The manual wet spraying record of the operator is retrieved to obtain manual wet spraying trajectory information and manual wet spraying process information. The manual wet spraying trajectory information includes nozzle position information and trajectory timestamp information. The nozzle position information includes nozzle spatial coordinate information and nozzle spatial angle information. The manual wet spraying process information includes wet spraying flow rate information and spraying agent information. The coordinate alignment process is performed based on the nozzle pose information. The coordinate alignment process is based on the calibration plate to determine the transformation matrix between the trolley base coordinate system and the sensor coordinate system. Data time synchronization is performed based on the trajectory timestamp information. The point cloud coordinates of the manual wet spraying trajectory are mapped, and the point cloud coordinates are mapped by searching for the nearest neighbor point in the three-dimensional point cloud model of wet spraying based on the nozzle pose information. Point cloud normal vectors are calculated, and the radius neighborhood point set of each point cloud is extracted for local surface fitting. Then, the neighborhood point covariance matrix is ​​calculated for eigenvalue decomposition. The eigenvector of the smallest eigenvalue obtained by the eigenvalue decomposition is the point cloud normal vector. Direction consistency processing is performed based on the consistency filtering of the global normal vector of the point cloud, and curvature weighted iterative optimization is performed. Point cloud curvature calculation is performed, local surface patches are extracted and local surface fitting is performed using the least squares method, curvature tensor is calculated based on quadratic surface coefficients, and path curvature is obtained based on the normal curvature of the wet spray trajectory in the manual wet spray trajectory information. Key parameters are extracted, including the baseline spraying distance, normal vector deviation angle, average normal vector direction, maximum trajectory curvature and rate of change of curvature, and key manual intervention points, including trajectory inflection points and construction area joint points. The specific algorithm for the baseline spraying distance is as follows: ， in, Indicates the reference spraying distance. Indicates the number of points. Represents the point ordinal number. Indicates the manual wet spray trajectory points. This represents the nearest point cloud point of the manually sprayed wet trajectory. The key parameters are used to generate wet spraying skill data based on the task parameterization algorithm and stored in the wet spraying construction database.

4. The five-layer human-machine alternating operation method for a wet spraying robotic arm according to claim 2, characterized in that, The reproduction mode specifically includes: The teaching trajectory of the current construction layer is obtained based on the wet spraying skill data in the wet spraying construction database. The teaching trajectory is generated based on the manual wet spraying trajectory information of the teaching mode. The point cloud coordinates of the reproduced trajectory are aligned based on the teaching trajectory. The point cloud coordinates of the reproduced trajectory are aligned with the point cloud coordinates of the teaching trajectory based on the iterative nearest point algorithm. The reconstructed trajectory is generated based on the point cloud coordinates of the reconstructed trajectory. The specific algorithm for generating the reconstructed trajectory is as follows: ， in, Indicates the points where the trajectory is reproduced. Indicates the teaching trajectory points, This indicates that the reference spraying distance is maintained along the normal vector direction of the reproduced trajectory. The spraying distance component represents the teaching trajectory; Adaptive speed adjustment is performed based on the curvature of the reproduced trajectory to obtain an adaptive reproduced trajectory speed. The specific algorithm for adaptive speed adjustment is as follows: ， in, Indicates the adaptive trajectory reproduction speed. Indicates the speed of the taught trajectory. The curvature representing the reproduced trajectory; Wet spraying construction is performed based on the reproduction trajectory and the adaptive reproduction trajectory speed.

5. The five-layer human-machine alternating operation method for a wet spraying robotic arm according to claim 2, characterized in that, The automatic mode specifically includes: Retrieve wet spraying skill data and automatic wet spraying layer data from the wet spraying construction database and the wet spraying 3D point cloud model; Automatic wet spraying parameters are set based on the wet spraying skill data. The automatic wet spraying parameters include spraying distance, spray volume, up-and-down sweeping angle, left-and-right swinging angle, and robotic arm movement speed. Automatic wet spraying is performed based on wet spraying skill data and a 3D point cloud model of wet spraying in the wet spraying construction database. The wet spraying surface of the automatic wet spraying is divided into multiple identical spraying blocks, with the center of each spraying block serving as the spraying point. The specific algorithm for automatic wet spraying is as follows: ， ， ， ， in, and This indicates the width and length of the wet spray block. Indicates the spray distance. Indicates the angle of left and right swing. Indicates the vertical sweep angle. This indicates the range of vertical brushing motion at the end of the robotic arm. Indicates the speed at which the robotic arm moves. Indicates the injection volume. Indicates the shotcrete rebound rate. Indicates the thickness of the layer to be sprayed; The wet spraying flow rate of the current automatic wet spraying layer is detected in real time. When the wet spraying flow rate is greater than or equal to the construction critical threshold, a three-dimensional scan is performed and the three-dimensional point cloud model of the wet spraying is updated. It is also determined whether the current construction surface needs to be leveled. The construction critical threshold is 90% of the total wet spraying flow rate required for the current layer construction.

6. A five-layer human-machine alternating operation system for a wet spraying robotic arm, used to execute the five-layer human-machine alternating operation method for a wet spraying robotic arm as described in any one of claims 1-5, characterized in that, include: The construction layer division module is used to scan the tunnel to be wet sprayed in order to construct a three-dimensional point cloud model of wet spraying. The construction layers of the three-dimensional point cloud model of wet spraying include a manually wet spraying layer and an automatically wet spraying layer. The manually wet spraying layer includes a manually filled rock surface layer, a manually leveled base layer and a manually leveled surface layer. The automatically wet spraying layer includes an automatically filled base layer and an automatically filled core layer. The construction mode division module is used to perform shape feature comparison based on the wet spraying 3D point cloud model to select the construction mode for each manually sprayable layer. The shape feature comparison is based on the wet spraying construction database, which includes historical wet spraying 3D point cloud model data and wet spraying skill data. The construction modes include teaching mode and reproduction mode. The construction implementation module is used to perform layered wet spraying treatment according to the construction mode to complete the wet spraying construction. The layered wet spraying treatment is based on wet spraying skill data in the wet spraying construction database.

7. A storage medium, characterized in that, The storage medium stores one or more programs that, when executed by a processor, implement the five-layer human-machine alternating operation method for a wet spraying robotic arm as described in any one of claims 1-5.

8. A computer device, characterized in that, The computer device includes a memory and a processor, wherein: The memory is used to store computer programs; When the processor executes the computer program stored in the memory, it implements the five-layer human-machine alternating operation method for a wet spraying robotic arm as described in any one of claims 1-5.

Images