CN113421283A - Automatic hoisting method and device for shield machine segments - Google Patents
Automatic hoisting method and device for shield machine segments Download PDFInfo
- Publication number
- CN113421283A CN113421283A CN202110889812.6A CN202110889812A CN113421283A CN 113421283 A CN113421283 A CN 113421283A CN 202110889812 A CN202110889812 A CN 202110889812A CN 113421283 A CN113421283 A CN 113421283A
- Authority
- CN
- China
- Prior art keywords
- segment
- positioning
- clamped
- hole
- coordinates
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000011218 segmentation Effects 0.000 claims abstract description 23
- 230000002159 abnormal effect Effects 0.000 claims abstract description 18
- 238000006073 displacement reaction Methods 0.000 claims abstract description 16
- 238000003062 neural network model Methods 0.000 claims abstract description 15
- 238000007781 pre-processing Methods 0.000 claims description 20
- 238000005070 sampling Methods 0.000 claims description 14
- 238000004891 communication Methods 0.000 claims description 11
- 230000009467 reduction Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000009471 action Effects 0.000 description 15
- 230000005641 tunneling Effects 0.000 description 9
- 238000010276 construction Methods 0.000 description 7
- 230000032258 transport Effects 0.000 description 4
- 238000009434 installation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007569 slipcasting Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/215—Motion-based segmentation
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21D—SHAFTS; TUNNELS; GALLERIES; LARGE UNDERGROUND CHAMBERS
- E21D11/00—Lining tunnels, galleries or other underground cavities, e.g. large underground chambers; Linings therefor; Making such linings in situ, e.g. by assembling
- E21D11/04—Lining with building materials
- E21D11/08—Lining with building materials with preformed concrete slabs
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21D—SHAFTS; TUNNELS; GALLERIES; LARGE UNDERGROUND CHAMBERS
- E21D11/00—Lining tunnels, galleries or other underground cavities, e.g. large underground chambers; Linings therefor; Making such linings in situ, e.g. by assembling
- E21D11/40—Devices or apparatus specially adapted for handling or placing units of linings or supporting units for tunnels or galleries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Engineering & Computer Science (AREA)
- Mining & Mineral Resources (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Structural Engineering (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Lining And Supports For Tunnels (AREA)
Abstract
The invention relates to an automatic hoisting method and device for shield machine segments, which comprises the following steps: acquiring a segment image and constructing a coordinate system; performing 3D point cloud depth analysis on the image after the example segmentation to determine an original coordinate of the 3D point cloud in a coordinate system, and determining a candidate central point coordinate of a positioning round hole and a candidate positioning coordinate of a grouting hole from the original coordinate; determining the standard hole spacing between the positioning round hole and the grouting hole according to the type of the pipe piece, and eliminating abnormal point clouds which cannot meet the standard hole spacing in the candidate central point coordinates and the candidate positioning coordinates; inputting the coordinates from which the abnormal point clouds are removed into a hole positioning neural network model to obtain target central point coordinates, calculating an average value of original coordinates of the 3D point clouds in a preset range of the target central point coordinates, and calculating a connecting line of the target central point coordinates and the average value and an included angle between the target central point coordinates and a Z axis; determining the rotation and displacement directions of the positioning pin according to the target central point coordinates and the included angles of the positioning round holes; and controlling the positioning pin to clamp the duct piece according to the rotation and displacement directions.
Description
Technical Field
The disclosure relates to the technical field of tunnel construction, in particular to an automatic hoisting method and device for segments of a shield tunneling machine.
Background
Shield construction operation is usually subaerial, receives the restriction of construction space restriction and tunnel segment weight, and manpower installation effectiveness is lower, therefore usually based on hoisting device handling tunnel segment, with tunnel segment hoist to the mounted position, implements the installation by the manpower again. For example, the transport vechicle transports the tunnel segment in the tunnel, snatchs the segment by field constructor manual operation segment lifting device to the segment after will snatching lifts by crane transports to the operation region of feeding the mascerating machine, is carried the tunnel segment by other field constructor to the end of feeding the mascerating machine, so that can load the tunnel segment to the concatenation region of erector with operation feeding the mascerating machine.
In the relevant scene, set up the location round hole at the tunnel section of jurisdiction usually, based on the location round hole, snatch the tunnel section of jurisdiction through the locating pin, perhaps use the vacuum chuck device to absorb the tunnel section of jurisdiction, the sucking disc of vacuum chuck device often damages, has increased equipment cost. And the locating pin snatchs the tunnel section of jurisdiction, often confuses location round hole and injected hole, causes to snatch the tunnel section of jurisdiction from the injected hole, leads to the injected hole wearing and tearing, and it is fixed to be difficult to slip casting smoothly.
Content of patent
In order to solve the problems that in the related art, a positioning pin grabs a tunnel segment, a positioning round hole is confused with a grouting hole, the tunnel segment is grabbed from the grouting hole, and the grouting hole is abraded, the shield machine segment automatic lifting method and the shield machine segment automatic lifting device are provided.
According to a first aspect of the embodiments of the present disclosure, there is provided an automatic hoisting method for segments of a shield tunneling machine, the method including:
acquiring a segment image of a segment to be clamped, taking the leftmost corner of the segment to be clamped represented by the segment image as a coordinate origin, taking any straight line connected with the coordinate origin as an X axis, taking the straight line passing through the coordinate origin and perpendicular to the X axis outwards as a Y axis, and taking an XY plane passing through the coordinate origin and perpendicular to the X axis and the Y axis upwards as a Z axis, so as to construct a three-dimensional coordinate system;
carrying out example segmentation on the segment image, carrying out 3D point cloud depth analysis on each image area subjected to example segmentation, determining the original coordinates of each 3D point cloud in the three-dimensional coordinate system, and determining candidate central point coordinates of the positioning round hole to be clamped with the segment and candidate positioning coordinates of the grouting hole from the original coordinates of the 3D point cloud on the basis of a down-sampling method;
acquiring a segment type of the segment to be clamped, determining a standard hole distance between the positioning circular hole and the grouting hole according to the segment type, and eliminating abnormal 3D point clouds in the candidate central point coordinate and the candidate positioning coordinate, wherein the abnormal 3D point clouds cannot meet the standard hole distance;
inputting the candidate central point coordinate and the candidate positioning coordinate after the abnormal 3D point cloud is removed into a hole positioning neural network model to obtain a target central point coordinate output by the hole positioning neural network model, calculating an average value of all dimensional coordinates of an original coordinate of the 3D point cloud in a preset range of the target central point coordinate, and calculating a connecting line of the target central point coordinate and a coordinate obtained by calculating the average value of all dimensional coordinates and an included angle between the connecting line and the Z axis;
determining the rotation direction and the displacement direction of a positioning pin of the lifting device according to the target central point coordinate and the included angle of the positioning round hole;
according to the rotating direction and the displacement direction, the positioning pin is controlled to clamp the to-be-clamped duct piece, so that the positioning pin is inserted into the positioning round hole to realize the grabbing of the to-be-clamped duct piece and the lifting of the to-be-clamped duct piece to a target area.
Optionally, before determining candidate coordinates of a center point of a locating circular hole of the segment to be gripped from the original coordinates of the 3D point cloud based on the downsampling method, the method includes:
selecting an image preprocessing method corresponding to the segment type to perform image preprocessing on the segment image;
carrying out positioning round hole image identification recognition on the segment image after the image preprocessing based on Hough transform;
the method for determining candidate central point coordinates of a positioning round hole of the segment to be clamped and candidate positioning coordinates of a grouting hole from the original coordinates of the 3D point cloud based on the down-sampling method comprises the following steps:
determining the positioning hole spacing between the positioning round holes of the duct piece to be clamped and the grouting hole spacing between the grouting holes according to the positioning round hole image identification and the original coordinates of the 3D point cloud based on a down-sampling method;
determining candidate central point coordinates of a positioning round hole of the segment to be clamped at least according to the segment type of the segment to be clamped and the positioning hole interval, and determining candidate positioning coordinates of a grouting hole of the segment to be clamped at least according to the segment type of the segment to be clamped and the grouting hole interval.
Optionally, the method further comprises:
based on the segment image of the segment to be clamped, which is acquired by the image acquisition device, performing image noise reduction on the segment image, and removing interference factors in the segment image;
extracting the positioning mark image of the target duct piece after the image denoising treatment;
fuzzifying and binarizing the positioning identification image to obtain the positioning information of the duct piece to be clamped;
the at least according to treat press from both sides and get the section of jurisdiction type and locating hole interval, confirm treat that press from both sides the candidate central point coordinate of getting the location round hole of section of jurisdiction, and at least according to treat press from both sides and get the section of jurisdiction type and grouting hole interval, confirm treat that press from both sides the candidate location coordinate of the grouting hole of getting the section of jurisdiction, include:
determining candidate central point coordinates of a positioning round hole of the segment to be clamped at least according to the segment type, the positioning information and the positioning hole interval of the segment to be clamped, and determining candidate positioning coordinates of a grouting hole of the segment to be clamped at least according to the segment type, the positioning information and the grouting hole interval of the segment to be clamped.
Optionally, the determining a standard hole distance between the positioning circular hole and the grouting hole according to the segment type includes:
based on the positioning round hole and the grouting hole which are used for clamping the duct piece are in the same straight line, determining the standard hole distance between the positioning round hole and the grouting hole according to the type of the duct piece.
Optionally, the method further comprises:
generating a grabbing success signal under the condition that the lifting device successfully grabs the segment to be clamped;
sending the grabbing success signal to a feeding machine based on a wireless communication device, so that the feeding machine performs initialization under the condition that the grabbing success signal is received;
and under the condition that the segment to be clamped is hoisted to the target area, generating and sending a release signal to the hoisting device, so that the hoisting device releases and hoists the segment to be clamped to the target area based on the release signal, otherwise, controlling the hoisting device to perform posture adjustment until the release signal is received.
According to a first aspect of the embodiments of the present disclosure, an automatic lifting device for segments of a shield tunneling machine is provided, the device including:
the acquisition module is used for acquiring a segment image of a segment to be clamped, taking the leftmost lower corner of the segment to be clamped represented by the segment image as a coordinate origin, taking any straight line connected with the coordinate origin as an X axis, taking the straight line passing through the coordinate origin and perpendicular to the X axis outwards as a Y axis, and taking an XY plane passing through the coordinate origin and perpendicular to the X axis and the Y axis upwards as a Z axis to construct a three-dimensional coordinate system;
the segmentation module is used for performing example segmentation on the segment image, performing 3D point cloud depth analysis on each image area subjected to example segmentation, determining an original coordinate of each 3D point cloud in the three-dimensional coordinate system, and determining candidate central point coordinates of the positioning round hole of the segment to be clamped and candidate positioning coordinates of the grouting hole from the original coordinates of the 3D point cloud based on a down-sampling method;
the removing module is used for acquiring the segment type of the segment to be clamped, determining the standard hole interval between the positioning circular hole and the grouting hole according to the segment type, and removing the candidate central point coordinate and abnormal 3D point cloud which cannot meet the standard hole interval in the candidate positioning coordinate;
the calculation module is used for inputting the candidate central point coordinates and the candidate positioning coordinates after the abnormal 3D point clouds are removed into the hole positioning neural network model to obtain target central point coordinates output by the hole positioning neural network model, calculating the average value of all dimensional coordinates of original coordinates of the 3D point clouds in the preset range of the target central point coordinates, and calculating a connecting line of the target central point coordinates and coordinates obtained by calculating the average value of all dimensional coordinates and an included angle between the connecting line and the Z axis;
the determining module is used for determining the rotation direction and the displacement direction of a positioning pin of the lifting device according to the target central point coordinate and the included angle of the positioning round hole;
and the control module is used for controlling the positioning pin to clamp the segment to be clamped according to the rotation direction and the displacement direction, so that the positioning pin is inserted into the positioning round hole to realize the grabbing of the segment to be clamped and to lift the segment to be clamped to a target area.
Optionally, the segmentation module is further configured to select an image preprocessing method corresponding to the segment type to perform image preprocessing on the segment image before determining candidate center point coordinates of a positioning round hole of the segment to be gripped from the original coordinates of the 3D point cloud based on the downsampling method;
carrying out positioning round hole image identification recognition on the segment image after the image preprocessing based on Hough transform;
determining the positioning hole spacing between the positioning round holes of the duct piece to be clamped and the grouting hole spacing between the grouting holes according to the positioning round hole image identification and the original coordinates of the 3D point cloud based on a down-sampling method;
determining candidate central point coordinates of a positioning round hole of the segment to be clamped at least according to the segment type of the segment to be clamped and the positioning hole interval, and determining candidate positioning coordinates of a grouting hole of the segment to be clamped at least according to the segment type of the segment to be clamped and the grouting hole interval.
Optionally, the obtaining module is further configured to:
based on the segment image of the segment to be clamped, which is acquired by the image acquisition device, performing image noise reduction on the segment image, and removing interference factors in the segment image;
extracting the positioning mark image of the target duct piece after the image denoising treatment;
fuzzifying and binarizing the positioning identification image to obtain the positioning information of the duct piece to be clamped;
the segmentation module is used for determining candidate central point coordinates of a positioning round hole of the segment to be clamped at least according to the segment type, the positioning information and the positioning hole interval of the segment to be clamped, and determining candidate positioning coordinates of a grouting hole of the segment to be clamped at least according to the segment type, the positioning information and the grouting hole interval of the segment to be clamped.
Optionally, the removing module is configured to determine a standard hole interval between the positioning circular hole and the grouting hole according to the type of the duct piece based on that the positioning circular hole to be clamped with the duct piece and the grouting hole are in the same straight line.
Optionally, the control module is further configured to:
generating a grabbing success signal under the condition that the lifting device successfully grabs the segment to be clamped;
sending the grabbing success signal to a feeding machine based on a wireless communication device, so that the feeding machine performs initialization under the condition that the grabbing success signal is received;
and under the condition that the segment to be clamped is hoisted to the target area, generating and sending a release signal to the hoisting device, so that the hoisting device releases and hoists the segment to be clamped to the target area based on the release signal, otherwise, controlling the hoisting device to perform posture adjustment until the release signal is received.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects: the method comprises the steps of pre-estimating center coordinates of a positioning round hole and a grouting hole by establishing a three-dimensional coordinate system, rejecting abnormal point clouds according to a standard hole interval between the positioning round hole and the grouting hole, determining a target central point coordinate based on a neural network model, determining a rotating direction and a displacement direction of a positioning pin according to the target central point coordinate and an included angle between a connecting line of the target central point coordinate and a coordinate average value target of the 3D point cloud within a preset range and a Z axis, improving accuracy of determining the positioning round hole and accuracy of positioning pin control, avoiding confusion of the positioning round hole and the grouting hole, causing the problem that a tunnel segment is grabbed from the grouting hole and the grouting hole is abraded, further effectively improving the efficiency of shield construction and improving the intelligent level of shield construction.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is a flow chart illustrating a method for automated handling of segments of a shield tunneling machine according to an exemplary embodiment.
Fig. 2 is a flow chart illustrating another method for automated handling of segments for a shield tunneling machine according to an exemplary embodiment.
Fig. 3 is a block diagram illustrating a shield tunneling machine segment automated handling apparatus according to an exemplary embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
Fig. 1 is a flowchart illustrating an automated handling method for segments of a shield tunneling machine according to an exemplary embodiment, which may be used in a splicing system of a shield tunneling machine, as shown in fig. 1, and includes the following steps.
In step S11, acquiring a segment image of a segment to be gripped, and constructing a three-dimensional coordinate system with the leftmost lower corner of the segment to be gripped represented by the segment image as a coordinate origin, any straight line connected with the coordinate origin as an X-axis, any straight line passing through the coordinate origin and perpendicular to the X-axis as an outward Y-axis, and an XY plane passing through the coordinate origin and perpendicular to the X-axis and the Y-axis as an upward Z-axis;
in step S12, performing example segmentation on the segment image, performing 3D point cloud depth analysis on each image area subjected to example segmentation, determining an original coordinate of each 3D point cloud in the three-dimensional coordinate system, and determining candidate central point coordinates of the locating circular hole of the segment to be gripped and candidate locating coordinates of the grouting hole from the original coordinates of the 3D point cloud based on a downsampling method;
in step S13, acquiring a segment type of the segment to be gripped, determining a standard hole distance between the positioning circular hole and the grouting hole according to the segment type, and removing abnormal 3D point clouds in the candidate center point coordinates and the candidate positioning coordinates, where the standard hole distance cannot be met;
in step S14, inputting the candidate center point coordinates and the candidate positioning coordinates from which the abnormal 3D point clouds are removed into a hole positioning neural network model to obtain target center point coordinates output by the hole positioning neural network model, calculating an average value of each dimensional coordinate of the original coordinates of the 3D point clouds within a preset range of the target center point coordinates, and calculating a connecting line between the target center point coordinates and coordinates obtained by calculating the average value of each dimensional coordinate, and an included angle between the connecting line and the Z axis;
in step S15, determining a rotation direction and a displacement direction of a positioning pin of the lifting device according to the target center point coordinates and the included angle of the positioning circular hole;
in step S16, the positioning pin is controlled to clamp the segment to be clamped according to the rotation direction and the displacement direction, so that the positioning pin is inserted into the positioning circular hole to realize the clamping of the segment to be clamped and to hoist the segment to be clamped to a target area.
According to the technical scheme, the three-dimensional coordinate system is established, the central coordinates of the positioning round hole and the grouting hole are estimated, abnormal point cloud is removed according to the standard hole distance between the positioning round hole and the grouting hole, the coordinate of the target central point is determined based on the neural network model, the included angle between the connecting line of the coordinate of the target central point coordinate and the coordinate average value target of the 3D point cloud in the preset range and the Z axis is determined according to the target central point coordinate, the rotating direction and the displacement direction of the positioning pin are determined, the accuracy of determining the positioning round hole and the control accuracy of the positioning pin can be improved, the problem that the tunnel segment is grabbed from the grouting hole and the grouting hole is abraded due to the fact that the positioning round hole and the grouting hole are mixed can be avoided, the shield construction efficiency can be effectively improved, and the intelligent level of shield construction is improved.
On the basis of the above embodiment, before determining the candidate coordinates of the center point of the positioning circular hole of the segment to be gripped from the original coordinates of the 3D point cloud based on the downsampling method, the method includes:
selecting an image preprocessing method corresponding to the segment type to perform image preprocessing on the segment image;
carrying out positioning round hole image identification recognition on the segment image after the image preprocessing based on Hough transform;
the method for determining candidate central point coordinates of a positioning round hole of the segment to be clamped and candidate positioning coordinates of a grouting hole from the original coordinates of the 3D point cloud based on the down-sampling method comprises the following steps:
determining the positioning hole spacing between the positioning round holes of the duct piece to be clamped and the grouting hole spacing between the grouting holes according to the positioning round hole image identification and the original coordinates of the 3D point cloud based on a down-sampling method;
determining candidate central point coordinates of a positioning round hole of the segment to be clamped at least according to the segment type of the segment to be clamped and the positioning hole interval, and determining candidate positioning coordinates of a grouting hole of the segment to be clamped at least according to the segment type of the segment to be clamped and the grouting hole interval.
On the basis of the above embodiment, the method further includes:
based on the segment image of the segment to be clamped, which is acquired by the image acquisition device, performing image noise reduction on the segment image, and removing interference factors in the segment image;
extracting the positioning mark image of the target duct piece after the image denoising treatment;
fuzzifying and binarizing the positioning identification image to obtain the positioning information of the duct piece to be clamped;
the at least according to treat press from both sides and get the section of jurisdiction type and locating hole interval, confirm treat that press from both sides the candidate central point coordinate of getting the location round hole of section of jurisdiction, and at least according to treat press from both sides and get the section of jurisdiction type and grouting hole interval, confirm treat that press from both sides the candidate location coordinate of the grouting hole of getting the section of jurisdiction, include:
determining candidate central point coordinates of a positioning round hole of the segment to be clamped at least according to the segment type, the positioning information and the positioning hole interval of the segment to be clamped, and determining candidate positioning coordinates of a grouting hole of the segment to be clamped at least according to the segment type, the positioning information and the grouting hole interval of the segment to be clamped.
On the basis of the above embodiment, the determining the standard hole pitch between the positioning circular hole and the grouting hole according to the segment type includes:
based on the positioning round hole and the grouting hole which are used for clamping the duct piece are in the same straight line, determining the standard hole distance between the positioning round hole and the grouting hole according to the type of the duct piece.
Optionally, fig. 2 is a flowchart illustrating another automated handling method for segments of a shield tunneling machine according to an exemplary embodiment, where the method further includes:
in step S21, when the lifting device successfully grips the segment to be gripped, a gripping success signal is generated;
in step S22, sending the grabbing success signal to a feeding machine based on a wireless communication device, so that the feeding machine performs initialization when receiving the grabbing success signal;
in step S23, a release signal is generated and sent to the lifting device when the segment to be gripped is lifted to the target area, so that the lifting device releases and lifts the segment to be gripped to the target area based on the release signal, otherwise, the lifting device is controlled to perform posture adjustment until the release signal is received.
When concrete implementation, the section of jurisdiction hoist relies on the locating pin accurate positioning to snatch the section of jurisdiction, and the section of jurisdiction hoist is arranged two intelligent cameras of installation and is adjusted the left and right sides locating pin respectively, and dynamic identification location round hole resolves current section of jurisdiction space coordinate, and the section of jurisdiction snatchs the action is accomplished to accurate adjustment section of jurisdiction hoist gesture. When the segment grabbing action is completed, the wireless communication device is used for carrying out equipment communication, a grabbing completion action signal is sent, the wireless signal receiving device is deployed at the end part of the segment feeding machine, and the signal is received to carry out segment feeding machine automatic action initialization. And releasing the segment lifting appliance to complete the automatic loading action of the segment feeder, and carrying the segments to an assembling area. The segment release signal is sent to the segment lifting tool through the wireless communication device, and the segment lifting tool can carry out next segment lifting action.
The intelligent camera can identify the type of a segment to be grabbed, an appropriate image preprocessing method is selected according to the segment type, image marks after preprocessing are identified through Huogh transformation, the position of a positioning hole is judged at a processor end through the segment type, the positioning hole distance, the prior information that the positioning hole and a grouting hole are located on the same straight line and the like, the action direction and the distance of the lifting appliance are calculated according to the position information and the current positioning hole position information, and an upper computer end sends action information to a PLC (programmable logic controller) to control the action of a lifting appliance executing mechanism.
The segment transport vehicle places segments in a designated area, a camera A installed on a segment lifting appliance identifies segment positioning hole marks, image interference factors are removed through image noise reduction algorithm processing, and effective information of the segment positioning marks is extracted. The image mark is fuzzified, binaryzation is processed and is analyzed the section of jurisdiction spatial position coordinate, the upper computer end carries out analysis processing to the analytic coordinate of camera and sends action instruction and action distance to PLC logic controller, and the control section of jurisdiction hoist carries out the gesture adjustment, can accurately insert the section of jurisdiction locating hole until section of jurisdiction hoist locating pin, accomplishes the automatic action of snatching of section of jurisdiction. The segment grabbing completion signal is sent to the segment carrying device through the wireless communication device by the segment lifting appliance, the segment feeding machine end receives the grabbing completion signal to perform initialization action, the segment lifting appliance performs automatic logic action, the segment carrying device carries the segment action to a target area, and the segment releasing is performed. And transmitting the segment release completion signal to the segment lifting appliance through the wireless communication device, otherwise, adjusting the posture of the lifting appliance.
Based on the same conception, the embodiment of the disclosure also provides an automatic lifting device for the shield segment, which can execute the steps of the lifting method for the shield segment in a software, hardware or software and hardware combined mode. Fig. 3 is a block diagram illustrating a shield segment automated handling apparatus according to an exemplary embodiment, where the shield segment automated handling apparatus 100, as shown in fig. 3, includes: an acquisition module 110, a segmentation module 120, a culling module 130, a calculation module 140, a determination module 150, and a control module 160.
The acquiring module 110 is configured to acquire a segment image of a segment to be clamped, and construct a three-dimensional coordinate system by taking a leftmost corner of the segment to be clamped, which is represented by the segment image, as a coordinate origin, taking any straight line connected to the coordinate origin as an X-axis, taking the straight line passing through the coordinate origin and perpendicular to the X-axis as an outward Y-axis, and taking an XY plane passing through the coordinate origin and perpendicular to the X-axis and the Y-axis as an upward Z-axis;
the segmentation module 120 is configured to perform example segmentation on the segment image, perform 3D point cloud depth analysis on each image area after the example segmentation, determine an original coordinate of each 3D point cloud in the three-dimensional coordinate system, and determine candidate central point coordinates of the positioning circular hole of the segment to be clamped and candidate positioning coordinates of the grouting hole from the original coordinates of the 3D point cloud based on a downsampling method;
the removing module 130 is configured to obtain a segment type of the segment to be clamped, determine a standard hole interval between the positioning circular hole and the grouting hole according to the segment type, and remove the candidate center point coordinate and the abnormal 3D point cloud in the candidate positioning coordinate, where the standard hole interval cannot be met;
the calculation module 140 is configured to input the candidate center point coordinates and the candidate positioning coordinates after the abnormal 3D point cloud is removed into the hole positioning neural network model to obtain target center point coordinates output by the hole positioning neural network model, calculate an average value of each dimensional coordinate of original coordinates of the 3D point cloud within a preset range of the target center point coordinates, and calculate a connection line between the target center point coordinates and coordinates obtained by calculating the average value of each dimensional coordinate, and an included angle between the connection line and the Z axis;
the determining module 150 is used for determining the rotation direction and the displacement direction of the positioning pin of the lifting device according to the target central point coordinate of the positioning round hole and the included angle;
and the control module 160 is used for controlling the positioning pin to clamp the segment to be clamped according to the rotation direction and the displacement direction, so that the positioning pin is inserted into the positioning round hole to realize the grabbing of the segment to be clamped and to lift the segment to be clamped to a target area.
Optionally, the segmentation module 120 is further configured to select an image preprocessing method corresponding to the segment type to perform image preprocessing on the segment image before determining candidate coordinates of a center point of a positioning round hole of the segment to be gripped from the original coordinates of the 3D point cloud based on the downsampling method;
carrying out positioning round hole image identification recognition on the segment image after the image preprocessing based on Hough transform;
determining the positioning hole spacing between the positioning round holes of the duct piece to be clamped and the grouting hole spacing between the grouting holes according to the positioning round hole image identification and the original coordinates of the 3D point cloud based on a down-sampling method;
determining candidate central point coordinates of a positioning round hole of the segment to be clamped at least according to the segment type of the segment to be clamped and the positioning hole interval, and determining candidate positioning coordinates of a grouting hole of the segment to be clamped at least according to the segment type of the segment to be clamped and the grouting hole interval.
Optionally, the obtaining module 110 is further configured to:
based on the segment image of the segment to be clamped, which is acquired by the image acquisition device, performing image noise reduction on the segment image, and removing interference factors in the segment image;
extracting the positioning mark image of the target duct piece after the image denoising treatment;
fuzzifying and binarizing the positioning identification image to obtain the positioning information of the duct piece to be clamped;
the segmentation module 120 is configured to determine, at least according to the segment type of the segment to be clamped, the positioning information and the positioning hole interval, candidate central coordinates of a positioning circular hole of the segment to be clamped, and determine, at least according to the segment type of the segment to be clamped, the positioning information and the grouting hole interval, candidate positioning coordinates of a grouting hole of the segment to be clamped.
Optionally, the removing module is configured to determine a standard hole interval between the positioning circular hole and the grouting hole according to the type of the duct piece based on that the positioning circular hole to be clamped with the duct piece and the grouting hole are in the same straight line.
Optionally, the control module 160 is further configured to:
generating a grabbing success signal under the condition that the lifting device successfully grabs the segment to be clamped;
sending the grabbing success signal to a feeding machine based on a wireless communication device, so that the feeding machine performs initialization under the condition that the grabbing success signal is received;
and under the condition that the segment to be clamped is hoisted to the target area, generating and sending a release signal to the hoisting device, so that the hoisting device releases and hoists the segment to be clamped to the target area based on the release signal, otherwise, controlling the hoisting device to perform posture adjustment until the release signal is received.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. An automatic hoisting method for shield machine segments is characterized by comprising the following steps:
acquiring a segment image of a segment to be clamped, taking the leftmost corner of the segment to be clamped represented by the segment image as a coordinate origin, taking any straight line connected with the coordinate origin as an X axis, taking the straight line passing through the coordinate origin and perpendicular to the X axis outwards as a Y axis, and taking an XY plane passing through the coordinate origin and perpendicular to the X axis and the Y axis upwards as a Z axis, so as to construct a three-dimensional coordinate system;
carrying out example segmentation on the segment image, carrying out 3D point cloud depth analysis on each image area subjected to example segmentation, determining the original coordinates of each 3D point cloud in the three-dimensional coordinate system, and determining candidate central point coordinates of the positioning round hole to be clamped with the segment and candidate positioning coordinates of the grouting hole from the original coordinates of the 3D point cloud on the basis of a down-sampling method;
acquiring a segment type of the segment to be clamped, determining a standard hole distance between the positioning circular hole and the grouting hole according to the segment type, and eliminating abnormal 3D point clouds in the candidate central point coordinate and the candidate positioning coordinate, wherein the abnormal 3D point clouds cannot meet the standard hole distance;
inputting the candidate central point coordinate and the candidate positioning coordinate after the abnormal 3D point cloud is removed into a hole positioning neural network model to obtain a target central point coordinate output by the hole positioning neural network model, calculating an average value of all dimensional coordinates of an original coordinate of the 3D point cloud in a preset range of the target central point coordinate, and calculating a connecting line of the target central point coordinate and a coordinate obtained by calculating the average value of all dimensional coordinates and an included angle between the connecting line and the Z axis;
determining the rotation direction and the displacement direction of a positioning pin of the lifting device according to the target central point coordinate and the included angle of the positioning round hole;
according to the rotating direction and the displacement direction, the positioning pin is controlled to clamp the to-be-clamped duct piece, so that the positioning pin is inserted into the positioning round hole to realize the grabbing of the to-be-clamped duct piece and the lifting of the to-be-clamped duct piece to a target area.
2. The method of claim 1, wherein before determining the coordinates of the candidate center point of the locating circular hole for grasping the segment to be grasped from the original coordinates of the 3D point cloud based on the down-sampling method, the method comprises:
selecting an image preprocessing method corresponding to the segment type to perform image preprocessing on the segment image;
carrying out positioning round hole image identification recognition on the segment image after the image preprocessing based on Hough transform;
the method for determining candidate central point coordinates of a positioning round hole of the segment to be clamped and candidate positioning coordinates of a grouting hole from the original coordinates of the 3D point cloud based on the down-sampling method comprises the following steps:
determining the positioning hole spacing between the positioning round holes of the duct piece to be clamped and the grouting hole spacing between the grouting holes according to the positioning round hole image identification and the original coordinates of the 3D point cloud based on a down-sampling method;
determining candidate central point coordinates of a positioning round hole of the segment to be clamped at least according to the segment type of the segment to be clamped and the positioning hole interval, and determining candidate positioning coordinates of a grouting hole of the segment to be clamped at least according to the segment type of the segment to be clamped and the grouting hole interval.
3. The method of claim 2, further comprising:
based on the segment image of the segment to be clamped, which is acquired by the image acquisition device, performing image noise reduction on the segment image, and removing interference factors in the segment image;
extracting the positioning mark image of the target duct piece after the image denoising treatment;
fuzzifying and binarizing the positioning identification image to obtain the positioning information of the duct piece to be clamped;
the at least according to treat press from both sides and get the section of jurisdiction type and locating hole interval, confirm treat that press from both sides the candidate central point coordinate of getting the location round hole of section of jurisdiction, and at least according to treat press from both sides and get the section of jurisdiction type and grouting hole interval, confirm treat that press from both sides the candidate location coordinate of the grouting hole of getting the section of jurisdiction, include:
determining candidate central point coordinates of a positioning round hole of the segment to be clamped at least according to the segment type, the positioning information and the positioning hole interval of the segment to be clamped, and determining candidate positioning coordinates of a grouting hole of the segment to be clamped at least according to the segment type, the positioning information and the grouting hole interval of the segment to be clamped.
4. The method of claim 1, wherein said determining a standard hole spacing between said positioning round holes and said grouting holes according to said segment type comprises:
based on the positioning round hole and the grouting hole which are used for clamping the duct piece are in the same straight line, determining the standard hole distance between the positioning round hole and the grouting hole according to the type of the duct piece.
5. The method according to any one of claims 1-4, further comprising:
generating a grabbing success signal under the condition that the lifting device successfully grabs the segment to be clamped;
sending the grabbing success signal to a feeding machine based on a wireless communication device, so that the feeding machine performs initialization under the condition that the grabbing success signal is received;
and under the condition that the segment to be clamped is hoisted to the target area, generating and sending a release signal to the hoisting device, so that the hoisting device releases and hoists the segment to be clamped to the target area based on the release signal, otherwise, controlling the hoisting device to perform posture adjustment until the release signal is received.
6. The utility model provides a shield constructs automatic overhead hoist of quick-witted section of jurisdiction which characterized in that, the device includes:
the acquisition module is used for acquiring a segment image of a segment to be clamped, taking the leftmost lower corner of the segment to be clamped represented by the segment image as a coordinate origin, taking any straight line connected with the coordinate origin as an X axis, taking the straight line passing through the coordinate origin and perpendicular to the X axis outwards as a Y axis, and taking an XY plane passing through the coordinate origin and perpendicular to the X axis and the Y axis upwards as a Z axis to construct a three-dimensional coordinate system;
the segmentation module is used for performing example segmentation on the segment image, performing 3D point cloud depth analysis on each image area subjected to example segmentation, determining an original coordinate of each 3D point cloud in the three-dimensional coordinate system, and determining candidate central point coordinates of the positioning round hole of the segment to be clamped and candidate positioning coordinates of the grouting hole from the original coordinates of the 3D point cloud based on a down-sampling method;
the removing module is used for acquiring the segment type of the segment to be clamped, determining the standard hole interval between the positioning circular hole and the grouting hole according to the segment type, and removing the candidate central point coordinate and abnormal 3D point cloud which cannot meet the standard hole interval in the candidate positioning coordinate;
the calculation module is used for inputting the candidate central point coordinates and the candidate positioning coordinates after the abnormal 3D point clouds are removed into the hole positioning neural network model to obtain target central point coordinates output by the hole positioning neural network model, calculating the average value of all dimensional coordinates of original coordinates of the 3D point clouds in the preset range of the target central point coordinates, and calculating a connecting line of the target central point coordinates and coordinates obtained by calculating the average value of all dimensional coordinates and an included angle between the connecting line and the Z axis;
the determining module is used for determining the rotation direction and the displacement direction of a positioning pin of the lifting device according to the target central point coordinate and the included angle of the positioning round hole;
and the control module is used for controlling the positioning pin to clamp the segment to be clamped according to the rotation direction and the displacement direction, so that the positioning pin is inserted into the positioning round hole to realize the grabbing of the segment to be clamped and to lift the segment to be clamped to a target area.
7. The device of claim 6, wherein the segmentation module is further configured to select an image preprocessing method corresponding to the segment type for image preprocessing of the segment image before determining candidate center point coordinates of the locating circular hole for grasping the segment from the original coordinates of the 3D point cloud based on the downsampling method;
carrying out positioning round hole image identification recognition on the segment image after the image preprocessing based on Hough transform;
determining the positioning hole spacing between the positioning round holes of the duct piece to be clamped and the grouting hole spacing between the grouting holes according to the positioning round hole image identification and the original coordinates of the 3D point cloud based on a down-sampling method;
determining candidate central point coordinates of a positioning round hole of the segment to be clamped at least according to the segment type of the segment to be clamped and the positioning hole interval, and determining candidate positioning coordinates of a grouting hole of the segment to be clamped at least according to the segment type of the segment to be clamped and the grouting hole interval.
8. The apparatus of claim 7, wherein the obtaining module is further configured to:
based on the segment image of the segment to be clamped, which is acquired by the image acquisition device, performing image noise reduction on the segment image, and removing interference factors in the segment image;
extracting the positioning mark image of the target duct piece after the image denoising treatment;
fuzzifying and binarizing the positioning identification image to obtain the positioning information of the duct piece to be clamped;
the segmentation module is used for determining candidate central point coordinates of a positioning round hole of the segment to be clamped at least according to the segment type, the positioning information and the positioning hole interval of the segment to be clamped, and determining candidate positioning coordinates of a grouting hole of the segment to be clamped at least according to the segment type, the positioning information and the grouting hole interval of the segment to be clamped.
9. The device of claim 6, wherein the removing module is configured to determine a standard hole distance between the positioning round hole and the grouting hole according to the type of the segment based on that the positioning round hole of the segment to be gripped and the grouting hole are in the same straight line.
10. The apparatus of any of claims 6-9, wherein the control module is further configured to:
generating a grabbing success signal under the condition that the lifting device successfully grabs the segment to be clamped;
sending the grabbing success signal to a feeding machine based on a wireless communication device, so that the feeding machine performs initialization under the condition that the grabbing success signal is received;
and under the condition that the segment to be clamped is hoisted to the target area, generating and sending a release signal to the hoisting device, so that the hoisting device releases and hoists the segment to be clamped to the target area based on the release signal, otherwise, controlling the hoisting device to perform posture adjustment until the release signal is received.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110889812.6A CN113421283A (en) | 2021-08-04 | 2021-08-04 | Automatic hoisting method and device for shield machine segments |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110889812.6A CN113421283A (en) | 2021-08-04 | 2021-08-04 | Automatic hoisting method and device for shield machine segments |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113421283A true CN113421283A (en) | 2021-09-21 |
Family
ID=77718847
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110889812.6A Withdrawn CN113421283A (en) | 2021-08-04 | 2021-08-04 | Automatic hoisting method and device for shield machine segments |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113421283A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113997290A (en) * | 2021-11-17 | 2022-02-01 | 合肥联宝信息技术有限公司 | Control method and equipment for mechanical arm |
| CN114941543A (en) * | 2022-05-31 | 2022-08-26 | 浙江大学高端装备研究院 | RGB-D vision segment grabbing and identifying system, assembling and positioning system and assembling and positioning method |
| CN115063579A (en) * | 2022-08-19 | 2022-09-16 | 西南交通大学 | Train positioning pin looseness detection method based on two-dimensional image and three-dimensional point cloud projection |
-
2021
- 2021-08-04 CN CN202110889812.6A patent/CN113421283A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113997290A (en) * | 2021-11-17 | 2022-02-01 | 合肥联宝信息技术有限公司 | Control method and equipment for mechanical arm |
| CN114941543A (en) * | 2022-05-31 | 2022-08-26 | 浙江大学高端装备研究院 | RGB-D vision segment grabbing and identifying system, assembling and positioning system and assembling and positioning method |
| CN115063579A (en) * | 2022-08-19 | 2022-09-16 | 西南交通大学 | Train positioning pin looseness detection method based on two-dimensional image and three-dimensional point cloud projection |
| CN115063579B (en) * | 2022-08-19 | 2022-11-04 | 西南交通大学 | Train positioning pin looseness detection method based on two-dimensional image and three-dimensional point cloud projection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113421283A (en) | Automatic hoisting method and device for shield machine segments | |
| US11780101B2 (en) | Automated package registration systems, devices, and methods | |
| CN106044570B (en) | It is a kind of that automatic identification equipment and method are hung using the coil of strip of machine vision | |
| KR101699672B1 (en) | Method and system for automatically landing containers on a landing target using a container crane | |
| CN111844019B (en) | Method and device for determining grabbing position of machine, electronic device and storage medium | |
| CN106839985B (en) | The automatic identification localization method of unmanned overhead traveling crane coil of strip crawl | |
| CN112253168B (en) | Automatic assembling method and device for segments of shield tunneling machine | |
| CN110936355B (en) | Mechanical arm guiding system and method based on visual speed measurement positioning | |
| CN107445067A (en) | Container tire crane automatic assembling and disassembling system | |
| CN109977954B (en) | Identification and positioning method and system for electric automobile charging interface | |
| JP5428922B2 (en) | Apparatus and method for supplying workpiece to hanger line | |
| CN113610833A (en) | Material grabbing method and device, electronic equipment and storage medium | |
| CN114029951A (en) | Robot autonomous recognition intelligent grabbing method based on depth camera | |
| CN110950255B (en) | Crane counterweight block alignment detection and control method and equipment and crane | |
| CN118239385A (en) | Intelligent steel coil hoisting system and method based on visual identification | |
| CN113034526B (en) | Grabbing method, grabbing device and robot | |
| CN110533717A (en) | A kind of target grasping means and device based on binocular vision | |
| JP5428921B2 (en) | Work collection device and method from hanger line | |
| JPH08169684A (en) | Position sensing method for article to be suspended by overhead traveling crane | |
| CN109108966B (en) | Reinforcing mesh grabbing control method based on visual identification | |
| CN215565965U (en) | Automatic handling system of section of jurisdiction | |
| CN115592666A (en) | Component positioning method, component positioning device, component positioning system and robot | |
| CN112565616A (en) | Target grabbing method, system and device and readable storage medium | |
| JPH09328291A (en) | Automatic coiling direction recognition method | |
| CN111232845A (en) | Steel coil crane automatic grabbing algorithm based on machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210921 |