CN115773128A - Cutting control method and control system of heading machine and heading machine - Google Patents
Cutting control method and control system of heading machine and heading machine Download PDFInfo
- Publication number
- CN115773128A CN115773128A CN202310095079.XA CN202310095079A CN115773128A CN 115773128 A CN115773128 A CN 115773128A CN 202310095079 A CN202310095079 A CN 202310095079A CN 115773128 A CN115773128 A CN 115773128A
- Authority
- CN
- China
- Prior art keywords
- automatic
- operation data
- heading machine
- program
- execution
- 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.)
- Granted
Links
- 238000005520 cutting process Methods 0.000 title claims abstract description 100
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000006399 behavior Effects 0.000 claims abstract description 114
- 238000012549 training Methods 0.000 claims abstract description 57
- 238000012360 testing method Methods 0.000 claims abstract description 26
- 230000002093 peripheral effect Effects 0.000 claims abstract description 10
- 238000001931 thermography Methods 0.000 claims description 15
- 238000011161 development Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 2
- 230000008447 perception Effects 0.000 abstract description 9
- 230000000875 corresponding effect Effects 0.000 description 48
- 230000005641 tunneling Effects 0.000 description 11
- 230000001276 controlling effect Effects 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000013178 mathematical model Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000010721 machine oil Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21D—SHAFTS; TUNNELS; GALLERIES; LARGE UNDERGROUND CHAMBERS
- E21D9/00—Tunnels or galleries, with or without linings; Methods or apparatus for making thereof; Layout of tunnels or galleries
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21D—SHAFTS; TUNNELS; GALLERIES; LARGE UNDERGROUND CHAMBERS
- E21D9/00—Tunnels or galleries, with or without linings; Methods or apparatus for making thereof; Layout of tunnels or galleries
- E21D9/10—Making by using boring or cutting machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/60—Software deployment
- G06F8/65—Updates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mining & Mineral Resources (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Environmental & Geological Engineering (AREA)
- Artificial Intelligence (AREA)
- Geology (AREA)
- Medical Informatics (AREA)
- Geochemistry & Mineralogy (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Stored Programmes (AREA)
- Excavating Of Shafts Or Tunnels (AREA)
Abstract
The application discloses a cutting control method and a cutting control system of a heading machine and the heading machine, relates to the technical field of heading machines, and solves the problems that the existing method lacks perception of peripheral conditions, once sudden conditions occur, tasks cannot be continuously executed, and cutting efficiency is low. The method comprises the following steps: determining manual operation data and automatic operation data corresponding to each execution behavior in a plurality of execution behaviors; training the obtained automatic cutting program based on manual operation data and automatic operation data corresponding to each execution behavior, and updating program parameters of the automatic cutting program; responding to the running request of the heading machine, acquiring running test data carried by the running request of the heading machine, and inputting the running test data into an automatic target cutting program; and acquiring a cutting control instruction output by the target automatic cutting program so as to control the heading machine to execute cutting operation according to the cutting control instruction.
Description
Technical Field
The application belongs to the technical field of tunneling machines, and particularly relates to a cutting control method and a cutting control system of a tunneling machine and the tunneling machine.
Background
The heading machine is a common mechanical device used for heading roadways on mines, engineering tunnels and urban underground engineering. Particularly in the coal industry, a heading machine is often used for underground operation, and the working environment has great potential safety hazard.
In the prior art, a manual operation heading machine or a positioning automatic cutting technology is often adopted for executing operation tasks, and for the manual operation heading machine, people are mostly adopted to sit on the heading machine to manually drive the heading machine for heading work, so that the potential safety hazard of the people is strong; for the positioning automatic cutting technology, the output action of the heading machine needs to be planned in advance, corresponding actions are executed according to a time flow during operation, but the program of the technology is solidified, the peripheral condition is not sensed, once an emergency occurs, tasks cannot be executed continuously, and the cutting efficiency is low.
Disclosure of Invention
In view of the above, the invention provides a cutting control method and a control system of a heading machine and the heading machine, and mainly aims to solve the problems that the existing method lacks perception of peripheral conditions, once an emergent condition occurs, tasks cannot be executed continuously, and the cutting efficiency is low.
According to a first aspect of the application, a cutting control method of a heading machine is provided, which comprises the following steps:
acquiring a plurality of execution behaviors of the heading machine, and determining manual operation data and automatic operation data corresponding to each execution behavior in the plurality of execution behaviors;
acquiring an automatic cutting program of the heading machine, training the automatic cutting program based on manual operation data and automatic operation data corresponding to each execution behavior, and updating program parameters of the automatic cutting program to obtain a target automatic cutting program;
responding to a running request of the heading machine, acquiring running test data carried by the running request of the heading machine, and inputting the running test data into the target automatic cutting program;
and acquiring a cutting control instruction output by the target automatic cutting program so as to control the heading machine to execute cutting operation according to the cutting control instruction.
Optionally, before the obtaining of the plurality of execution behaviors of the heading machine, the method further includes:
acquiring an initial manual operation data set for operating a manual cutting program, and extracting at least one first data category included in the initial manual operation data set;
classifying a plurality of initial manual operation data included in the initial manual operation data set based on the at least one first data category to obtain a classified initial manual operation data set;
slicing the classified initial manual operation data set to obtain a sliced initial manual operation data set;
acquiring a first time point for executing a manual cutting task each time, and marking initial manual operation data corresponding to the sliced initial manual operation data set by adopting the first time point to obtain a sorted manual operation data set; and the number of the first and second groups,
acquiring an initial automatic operation data set for operating an automatic cutting program, and extracting at least one second data category included in the initial automatic operation data set;
classifying a plurality of initial automatic operation data included in the initial automatic operation data set based on the at least one second data category to obtain a classified initial automatic operation data set;
slicing the classified initial automatic operation data set to obtain a sliced initial automatic operation data set;
and acquiring a second time node for executing the automatic cutting task each time, and marking the initial automatic operation data corresponding to the sliced initial automatic operation data set by adopting the second time node to obtain the sorted automatic operation data set.
Optionally, before the obtaining a plurality of execution behaviors of the heading machine, the method further includes:
acquiring manual execution data which is acquired by controlling the heading machine based on each piece of the sorted manual behavior data in the sorted manual operation data set, and acquiring a manual execution data set;
determining a plurality of execution behaviors and manual operation data corresponding to each execution behavior in the plurality of execution behaviors by adopting a behavior recognition algorithm based on the sorted manual operation data set and the manual execution data set;
acquiring automatic execution data which is acquired by controlling the heading machine based on each piece of arranged automatic behavior data in the arranged automatic operation data set;
determining automatic execution data corresponding to each execution behavior of the plurality of execution behaviors.
Optionally, the training the automatic cutting program based on the manual operation data and the automatic operation data corresponding to each execution behavior, and updating the program parameters of the automatic cutting program to obtain the target automatic cutting program includes:
inputting the manual operation data corresponding to each execution behavior into the automatic cutting program, controlling the heading machine to acquire first automatic execution data corresponding to each execution behavior, comparing the automatic execution data indicated by the same execution behavior with the first automatic execution data, updating program parameters of the automatic cutting program, and determining at least one target manual operation data meeting preset conditions as training data of the next round;
and determining the preset training times, inputting training data obtained in the previous round into an updated automatic cutting program in each round of training, and continuously updating program parameters of the automatic cutting program until the training round reaches the preset training times to obtain the target automatic cutting program.
Optionally, the comparing the automatic execution data indicated by the same execution behavior with the first automatic execution data, updating the program parameters of the automatic cutting program, and determining at least one target manual operation data meeting a preset condition as the training data of the next round includes:
calculating a difference between the automatically executed data and the first automatically executed data indicated by the same execution behavior;
acquiring a preset threshold, if the difference is smaller than the preset threshold, finely adjusting program parameters of the automatic cutting program, and determining target manual operation data corresponding to the same execution behavior;
and acquiring the at least one target manual operation data as training data of the next round.
Optionally, the method further comprises:
and if the difference is larger than the preset threshold, replacing the program parameters of the automatic cutting program by using the program parameters of the manual cutting program.
Optionally, after obtaining the target automatic cutting program, the method further includes:
and uploading the target program parameters of the automatic target cutting program to a cloud server, so that other heading machines update the program parameters of the automatic target cutting program by using the target program parameters.
According to a second aspect of the present application, there is provided a cutting control system of a heading machine, comprising:
the determining module is used for acquiring a plurality of execution behaviors of the heading machine, and determining manual operation data and automatic operation data corresponding to each execution behavior in the plurality of execution behaviors;
the training module is used for acquiring an automatic cutting program of the heading machine, training the automatic cutting program based on manual operation data and automatic operation data corresponding to each execution behavior, and updating program parameters of the automatic cutting program to obtain a target automatic cutting program;
the running module is used for responding to a running request of the heading machine, obtaining running test data carried by the running request of the heading machine and inputting the running test data into the target automatic cutting program;
and the cutting module is used for acquiring a cutting control instruction output by the target automatic cutting program so as to control the heading machine to execute cutting operation according to the cutting control instruction.
Optionally, the system further comprises: an acquisition module;
the acquisition module comprises: a laser ranging unit, a millimeter wave radar unit, an infrared thermal imaging unit and a total station positioning unit, wherein,
the laser ranging unit is used for acquiring absolute distance data between the peripheral wall of the heading machine and the heading machine body;
the millimeter wave radar unit is used for acquiring surface shape data of the peripheral wall of the heading machine;
the infrared thermal imaging unit is used for acquiring heat source data around the development machine;
and the total station positioning unit is used for acquiring absolute position data of the heading machine on a working face.
According to a third aspect of the present application there is provided a heading machine comprising a cutting control system of a heading machine according to any of the second aspects above.
According to the technical scheme, the method for controlling the cutting of the heading machine comprises the steps of firstly obtaining a plurality of execution behaviors of the heading machine, determining manual operation data and automatic operation data corresponding to each execution behavior in the plurality of execution behaviors, then obtaining an automatic cutting program of the heading machine, training the automatic cutting program based on the manual operation data and the automatic operation data corresponding to each execution behavior, updating program parameters of the automatic cutting program to obtain a target automatic cutting program, then responding to a heading machine operation request, obtaining operation test data carried by the heading machine operation request, inputting the operation test data into the target automatic cutting program, finally obtaining a cutting control instruction output by the target automatic cutting program to control the heading machine to execute cutting operation according to the cutting control instruction, improving the perception capability of the heading machine on the surrounding situation by training the automatic cutting program of the heading machine, and improving the accuracy of the cutting operation according to the trained cutting program when a cutting task is executed.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
figure 1 illustrates a flow diagram of a method of cutting control of a heading machine according to an embodiment of the present application;
figure 2 illustrates a flow diagram of a method of cutting control of a heading machine according to another embodiment of the present application;
figure 3 illustrates a schematic structural view of a cutting control system of a heading machine according to an embodiment of the present application;
figure 4 illustrates a schematic structural view of a cutting control system of a heading machine according to an embodiment of the present application;
figure 5 illustrates a schematic structural view of a cutting control system of a heading machine according to an embodiment of the present application;
figure 6 illustrates a schematic structural view of a cutting control system of a heading machine according to an embodiment of the present application;
figure 7 illustrates a schematic structural view of a cutting control system of a heading machine according to an embodiment of the present application;
fig. 8 shows a schematic structural diagram of a mathematical model constructed by binocular vision units in an acquisition module of a cutting control system of a heading machine according to an embodiment of the application;
figure 9 illustrates a system architecture diagram of a roadheader of a cutting control system of the roadheader according to an embodiment of the present application;
fig. 10 shows a schematic diagram of a three-dimensional point cloud chart constructed by a cutting control system of a heading machine based on distance data acquired by binocular vision units in an acquisition module according to an embodiment of the application.
Detailed Description
Various aspects and features of the present application are described herein with reference to the drawings.
It will be understood that various modifications may be made to the embodiments of the present application. Accordingly, the foregoing description should not be construed as limiting, but merely as exemplifications of embodiments. Those skilled in the art will envision other modifications within the scope and spirit of the application.
The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the application and, together with a general description of the application given above and the detailed description of the embodiments given below, serve to explain the principles of the application.
These and other characteristics of the present application will become apparent from the following description of preferred forms of embodiment, given as non-limiting examples, with reference to the attached drawings.
It is also to be understood that although the present application has been described with reference to some specific examples, those skilled in the art are able to ascertain many other equivalents to the practice of the present application.
The above and other aspects, features and advantages of the present application will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.
Specific embodiments of the present application are described hereinafter with reference to the accompanying drawings; however, it is to be understood that the disclosed embodiments are merely exemplary of the application, which can be embodied in various forms. Well-known and/or repeated functions and constructions are not described in detail to avoid obscuring the application of unnecessary or unnecessary detail. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present application in virtually any appropriately detailed structure.
The specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," which may each refer to one or more of the same or different embodiments in accordance with the application.
Example 1
The cutting control method of the heading machine provided by the embodiment of the application can be applied to a control system of the heading machine shown in fig. 9, specifically, as shown in fig. 9, the heading machine comprises an acquisition module and a control system, when a data acquisition request is received, the control system generates a control instruction and sends the control instruction to the acquisition module, and the acquisition module executes related operations based on the received control instruction and uploads the acquired data to the control system.
The embodiment of the application provides a cutting control method of a heading machine, as shown in fig. 1, the method comprises the following steps:
101. the method comprises the steps of obtaining a plurality of execution behaviors of the heading machine, and determining manual operation data and automatic operation data corresponding to each execution behavior in the plurality of execution behaviors.
102. And acquiring an automatic cutting program of the heading machine, training the automatic cutting program based on manual operation data and automatic operation data corresponding to each execution behavior, and updating program parameters of the automatic cutting program to obtain a target automatic cutting program.
103. And responding to the running request of the heading machine, acquiring running test data carried by the running request of the heading machine, and inputting the running test data into the target automatic cutting program.
104. And acquiring a cutting control instruction output by the target automatic cutting program so as to control the heading machine to execute cutting operation according to the cutting control instruction.
The method includes the steps of firstly obtaining a plurality of execution behaviors of the heading machine, determining manual operation data and automatic operation data corresponding to each execution behavior in the plurality of execution behaviors, then obtaining an automatic cutting program of the heading machine, training the automatic cutting program based on the manual operation data and the automatic operation data corresponding to each execution behavior, updating program parameters of the automatic cutting program to obtain a target automatic cutting program, then responding to a heading machine operation request, obtaining operation test data carried by the heading machine operation request, inputting the operation test data into the target automatic cutting program, and finally obtaining a cutting control instruction output by the target automatic cutting program to control the heading machine to execute cutting operation according to the cutting control instruction.
The embodiment of the application provides a cutting control method of a heading machine, as shown in fig. 2, the method comprises the following steps:
201. the method comprises the steps of obtaining an initial manual operation data set and an initial automatic operation data set, obtaining the manual operation data set based on the initial manual operation data set, and obtaining the automatic operation data set based on the initial automatic operation data set.
In the embodiment of the application, for a manual cutting program of a heading machine, firstly, a control system of the heading machine acquires an initial manual operation data set for operating the manual cutting program, and extracts at least one first data category included in the initial manual operation data set, then, the control system classifies a plurality of initial manual operation data included in the initial manual operation data set based on the at least one first data category to obtain the classified initial manual operation data set, then, slices the classified initial manual operation data set to obtain the sliced initial manual operation data set, and finally, a first time point for executing a manual cutting task each time is acquired, and the initial manual operation data corresponding to the sliced initial manual operation data set is labeled by the first time point to obtain the sorted manual operation data set.
Further, for the automatic cutting program, firstly, an initial automatic operation data set used for operating the automatic cutting program is obtained, at least one second data category included in the initial automatic operation data set is extracted, then, a plurality of initial automatic operation data included in the initial automatic operation data set are classified based on the at least one second data category, the classified initial automatic operation data set is obtained, then, the classified initial automatic operation data set is sliced, the sliced initial automatic operation data set is obtained, finally, a second time node for executing the automatic cutting task each time is obtained, the second time node is adopted to label the corresponding initial automatic operation data in the sliced initial automatic operation data set, and the sorted automatic operation data set is obtained.
It should be noted that, in the embodiment of the present application, the first data category and the second data category are both data that can be generated when the heading machine operates, for example, the cutting head operating current, the hydraulic pressure when the heading machine oil pump operates, and the like.
202. Automatic execution data corresponding to each execution behavior in the plurality of execution behaviors is obtained.
In the embodiment of the application, based on the sorted manual operation data set, the control system controls the heading machine to collect manual execution data and obtain the collected manual execution data, wherein each sorted manual operation data in the sorted manual operation data set corresponds to one manual execution data, the manual execution data set is constructed based on all the manual execution data, then based on the sorted manual operation data set and the manual execution data set, a plurality of execution behaviors and manual operation data corresponding to each execution behavior in the plurality of execution behaviors are determined by adopting a behavior recognition algorithm, and meanwhile, based on the sorted automatic operation data set, the control system controls the heading machine to collect automatic execution data and obtain the collected automatic execution data, wherein each sorted automatic behavior data in the sorted automatic operation data set corresponds to one automatic execution data and the automatic execution data corresponding to each execution behavior in the plurality of execution behaviors are determined.
Specifically, in the actual application process, the sorted manual operation data sets and the manual execution data corresponding to each sorted manual data in the sorted manual operation data sets are uploaded to the database, then a data mining algorithm is executed, the same data in the database are automatically classified to determine what the current data is, and the data description of the current manual mark, namely the area and the centroid of the data in each dimension, is extracted and defined as the set of the behavior recognition P (a).
Further, data generated in the automatic clipping program is extracted into a database, the automatic clipping program is applied to obtain P (B), the closer the joint probability of P (A) and P (B) is to 1, the more the P (B) and the marked behavior P (A) are executed, the same content of P (B) and the marked behavior P (A) is represented, and therefore the marked known behavior of P (B) can be determined.
It should be noted that, in the practical application process, the operation effect of the manual cutting program is often better than that of the automatic cutting program, and when two events or data occur simultaneously, the two events or data can be represented by P (a, B), that is, the data of the position category is determined by using the data set training model of the known category.
The manual execution data and the automatic execution data are at least one of absolute distance data between a wall body around the heading machine and a heading machine body, acquired by a laser ranging unit of the heading machine, a millimeter wave radar unit, surface shape data of the wall body around the heading machine, acquired by an infrared thermal imaging unit, heat source data around the heading machine, and absolute position data of the heading machine on a working face, acquired by a total station positioning unit.
203. The method comprises the steps of obtaining a plurality of execution behaviors of the heading machine, and determining manual operation data and automatic operation data corresponding to each execution behavior in the plurality of execution behaviors.
204. Training the obtained automatic cutting program based on the manual operation data and the automatic operation data corresponding to each execution behavior, and updating program parameters of the automatic cutting program to obtain the target automatic cutting program.
In the embodiment of the application, after an automatic cutting program is obtained, manual operation data corresponding to each execution behavior is input into the automatic cutting program, a heading machine is controlled to collect first automatic execution data corresponding to each execution behavior, then the automatic execution data indicated by the same execution behavior is compared with the first automatic execution data, program parameters of the automatic cutting program are updated, and at least one target manual operation data meeting preset conditions is determined to be used as training data of the next round; and then determining the preset training times, inputting the training data obtained in the previous round into the updated automatic cutting program in each round of training, and continuously updating the program parameters of the automatic cutting program until the training rounds reach the preset training times to obtain the target automatic cutting program.
Further, comparing the automatic execution data indicated by the same execution behavior with the first automatic execution data, updating program parameters of the automatic cutting program, and determining at least one target manual operation data meeting preset conditions as training data of the next round, specifically comprising: the method comprises the steps of firstly calculating a difference value between automatic execution data indicated by the same execution behavior and first automatic execution data, then obtaining a preset threshold value, finely adjusting program parameters of an automatic cutting program if the difference value is smaller than the preset threshold value, determining target manual operation data corresponding to the same execution behavior, finally obtaining at least one target manual operation data as training data of the next round, and replacing the program parameters of the automatic cutting program by the program parameters of the manual cutting program if the difference value is larger than the preset threshold value.
205. And uploading target program parameters of the target automatic cutting program to a cloud server.
In the embodiment of the application, after the target automatic cutting program is acquired, the control system can upload the target program parameters of the target automatic cutting program to the cloud server, so that other tunneling machines can update the program parameters of the automatic cutting program by using the uploaded target program parameters, and the automatic cutting operation of the other tunneling machines is optimized.
206. And responding to the running request of the heading machine, acquiring running test data carried by the running request of the heading machine, and inputting the running test data into the target automatic cutting program.
In the embodiment of the application, after the target automatic cutting program is obtained, the running test data carried by the running request of the heading machine is obtained in response to the running request of the heading machine, and the running test data is input into the target automatic cutting program.
207. And acquiring a cutting control instruction output by the target automatic cutting program so as to control the heading machine to execute cutting operation according to the cutting control instruction.
The method includes the steps of firstly obtaining an initial manual operation data set and an initial automatic operation data set, obtaining a manual operation data set and an automatic operation data set based on the initial manual operation data set and the initial automatic operation data set, then obtaining automatic execution data corresponding to each execution behavior in a plurality of execution behaviors, determining manual operation data and automatic operation data corresponding to each execution behavior in the plurality of execution behaviors, training an obtained automatic cutting program based on the manual operation data and the automatic operation data corresponding to each execution behavior, updating program parameters of the automatic cutting program to obtain a target automatic cutting program, uploading target program parameters of the target automatic cutting program to a cloud server, finally responding to a tunneling machine operation request, obtaining operation test data carried by the tunneling machine operation request, inputting the operation test data to the target automatic cutting program, obtaining cutting control instructions output by the target automatic cutting program, controlling the tunneling machine to execute cutting operation according to the cutting control instructions, and improving perception of the tunneling machine to the situation of the cutting program through the automatic cutting program of the tunneling machine, and improving the accuracy of cutting operation when the cutting task is executed.
Example 2
The embodiment of the application provides a cutting control system of a heading machine, as shown in fig. 3, including: a determination module 301, a training module 302, an execution module 303, and a cutting module 304.
The determining module 301 is configured to acquire a plurality of execution behaviors of the heading machine, and determine manual operation data and automatic operation data corresponding to each execution behavior in the plurality of execution behaviors;
the training module 302 is configured to acquire an automatic cutting program of the heading machine, train the automatic cutting program based on manual operation data and automatic operation data corresponding to each execution behavior, and update program parameters of the automatic cutting program to obtain a target automatic cutting program;
the operation module 303 is configured to respond to a heading machine operation request, acquire operation test data carried in the heading machine operation request, and input the operation test data to the target automatic cutting program;
the cutting module 304 is configured to obtain a cutting control instruction output by the target automatic cutting program, so as to control the heading machine to perform cutting operation according to the cutting control instruction.
As a preferred implementation of the embodiment of the present application, in a specific application scenario, as shown in fig. 4, the system further includes: an acquisition module 305;
the collection module includes: a laser ranging unit, a millimeter wave radar unit, an infrared thermal imaging unit and a total station positioning unit, wherein,
the laser ranging unit is used for acquiring absolute distance data between the peripheral wall of the heading machine and the heading machine body;
the millimeter wave radar unit is used for acquiring surface shape data of the peripheral wall of the development machine;
the infrared thermal imaging unit is used for acquiring heat source data around the development machine;
and the total station positioning unit is used for acquiring absolute position data of the heading machine on the working face.
In the embodiment of the application, the determining module is connected with the collecting module, after the collecting module collects the target data, the target data can be sent to the confirming module, namely, after the laser ranging unit, the millimeter wave radar unit, the infrared thermal imaging unit and the total station positioning unit acquire the corresponding data, the corresponding data are respectively sent to the confirming module, in the process of specific application, the collecting module can further comprise a binocular vision unit, the binocular vision unit is used for identifying the shape, the distance and the current position of the tunneling working face, whether the material piling and the dust state exist or not, the heading machine is endowed with forward perception, and the perceived data are sent to the confirming module, wherein a mathematical model constructed by the binocular vision unit is shown in fig. 8, and the heading machine works with the mathematical model, and the heading machine can be used for determining the forward perception data according to the position of the laser ranging unit, the millimeter wave radar unit, the laser ranging unit, the millimeter wave radar unit and the total station positioning unit, and the total station positioning unit are used for acquiring the corresponding dataDistance of front working face
Can be expressed as:
equation 1:
，
wherein,z(1,1) is the distance from the upper left coordinate point of the overlaid image in figure 8 to the binocular vision unit,z(n1) is the distance from the upper right coordinate point of the overlaid image of FIG. 8 to the binocular visual unit,z(1,m) The distance from the lower left coordinate point of the overlaid image in figure 8 to the binocular visual unit,z(n,m) The distance from the lower right coordinate point of the overlaid image in figure 8 to the binocular visual unit,bis the baseline distance of the two vision cameras,fis the focal length of the camera and,X L for the width of the image captured by the left camera,X R the width of the image acquired by the right camera.
The depth change of the working surface can be estimated according to formula 1.
It should be noted that, in the practical application process, the distance Z between the heading machine and the front working face is acquired by using the binocular vision unit during working 0 The specific obtaining method is shown as formula 1, and in order to avoid ambiguity in the subsequent process, in the following process, the distance between the heading machine and the front working face during working is usedFMeans that Z in formula 1 is 0 By replacement withFBased on distanceFA three-dimensional point cloud picture is constructed, point cloud abstract features are extracted by adopting a machine learning algorithm and a deep learning algorithm based on the three-dimensional point cloud picture, the point cloud is segmented by a semantic segmentation model based on the three-dimensional point cloud abstract features, and the final segmentation result is shown in fig. 10, for example, in the embodiment of the application, the three-dimensional point cloud picture is finally segmented into three parts, each part represents an actual visual area, wherein X, Y and Z coordinates of points in the three-dimensional point cloud picture are respectively represented as:
equation 2:
，
wherein,Bis the baseline distance in the three-dimensional point cloud graph,dispis a parallax value of (u,v) Is the corresponding pixel coordinate.
Further, the laser ranging unit can establish the relative distance between the heading machine and the working face when the heading machine moves back and forthLTime axis when moving relativelytThe two are combined to establish a dimension time axis before and after the development machine during manual cutting, and the dimension time axisL t Can be expressed as:
equation 3:
，
wherein,n1 is the timestamp of the last manual runtime.
Further, the millimeter wave radar unit can construct the perception of the heading machine on the left and right positions to position the dimension point cloud of the perception Y of the heading machine on the left and right positions and the time t, and the dimension point cloud is expressed as:
equation 4:
。
further, the infrared thermal imaging unit is used for constructing a thermal imaging point cloud dimension matrix W of the cutting head when the cutting head moves, and the thermal imaging point cloud dimension matrix W is expressed as follows as the coordinate system of the binocular vision unit:
equation 5:
。
wherein,w(1,1) is the distance from the upper left coordinate point of the superimposed image to the infrared thermal imaging unit,w(1,m) The distance from the lower left coordinate point of the superimposed image to the infrared thermal imaging unit,w(n1) is the distance from the coordinate point on the upper right of the superposed image to the infrared thermal imaging unit,w(n,m) Is the distance from the lower right coordinate point of the superposed image to the infrared thermal imaging unit.
Further, the total station positioning unit is used for establishing an absolute position V of the heading machine in the roadway during manual cutting, wherein the absolute position V is represented as:
equation 6:
。
wherein x is the coordinate location of left and right movement of the total station description equipment, y is the coordinate location of front and back movement of the total station description equipment, and z is the coordinate location of high and low movement of the total station description equipment.
All absolute positions combined
。
As a preferred implementation of the embodiment of the present application, in a specific application scenario, as shown in fig. 5, the system further includes: a first data processing module 306 and a second data processing module 307.
The first data processing module 306 is configured to acquire an initial manual operation data set for operating a manual cutting program, and extract at least one first data category included in the initial manual operation data set; classifying a plurality of initial manual operation data included in the initial manual operation data set based on at least one first data category to obtain a classified initial manual operation data set; slicing the classified initial manual operation data set to obtain a sliced initial manual operation data set; acquiring a first time point for executing a manual cutting task each time, and marking initial manual operation data corresponding to the sliced initial manual operation data set by using the first time point to obtain a sorted manual operation data set;
the second data processing module 307 is configured to obtain an initial automatic operation data set for operating the automatic cutting program, and extract at least one second data category included in the initial automatic operation data set; classifying a plurality of initial automatic operation data included in the initial automatic operation data set based on at least one second data category to obtain a classified initial automatic operation data set; slicing the classified initial automatic operation data set to obtain a sliced initial automatic operation data set; and acquiring a second time node for executing the automatic cutting task each time, and labeling the initial automatic operation data corresponding to the sliced initial automatic operation data set by adopting the second time node to obtain a sorted automatic operation data set.
As a preferred implementation of the embodiment of the present application, in a specific application scenario, as shown in fig. 6, the system further includes: a behavior recognition module 308.
The behavior identification module 308 is configured to acquire manual execution data acquired by controlling the heading machine based on each piece of organized manual behavior data in the organized manual operation data set, and acquire a manual execution data set; based on the sorted manual operation data set and the manual execution data set, determining a plurality of execution behaviors by adopting a behavior recognition algorithm and manual operation data corresponding to each execution behavior in the plurality of execution behaviors; acquiring automatic execution data acquired by controlling the heading machine based on each sorted automatic behavior data in the sorted automatic operation data set; automatic execution data corresponding to each execution behavior in the plurality of execution behaviors is determined.
In a specific application scenario, the training module 302 is further configured to: inputting manual operation data corresponding to each execution behavior into an automatic cutting program, controlling a heading machine to collect first automatic execution data corresponding to each execution behavior, comparing the automatic execution data indicated by the same execution behavior with the first automatic execution data, updating program parameters of the automatic cutting program, and determining at least one target manual operation data meeting preset conditions as training data of the next round; and determining the preset training times, inputting the training data obtained in the previous training round into the updated automatic cutting program in each training round, and continuously updating the program parameters of the automatic cutting program until the training round reaches the preset training times to obtain the target automatic cutting program.
In a specific application scenario, the training module 302 is further configured to: calculating a difference between the automatically executed data and the first automatically executed data indicated by the same execution behavior; acquiring a preset threshold, if the difference is smaller than the preset threshold, finely adjusting program parameters of the automatic cutting program, and determining target manual operation data corresponding to the same execution behavior; and acquiring at least one target manual operation data as training data of the next round.
In a specific application scenario, the training module 302 is further configured to: and if the difference value is larger than the preset threshold value, replacing the program parameters of the automatic cutting program by the program parameters of the manual cutting program.
As a preferred implementation of the embodiment of the present application, in a specific application scenario, as shown in fig. 7, the system further includes: a transmission module 309.
The transmission module 309 is configured to upload the target program parameters of the target automatic cutting program to the cloud server, so that the other heading machines update the program parameters of the automatic cutting program thereof by using the target program parameters.
The cutting control system provided by the embodiment of the application comprises a determining module, a plurality of executing behaviors of the heading machine, manual operation data and automatic operation data corresponding to each executing behavior in the plurality of executing behaviors, an automatic cutting program of the heading machine is obtained through a training module, the automatic cutting program is trained based on the manual operation data and the automatic operation data corresponding to each executing behavior, program parameters of the automatic cutting program are updated, a target automatic cutting program is obtained, then, in response to a heading machine operation request, operation test data carried by the heading machine operation request are obtained through the operating module, the operation test data are input into the target automatic cutting program, finally, a cutting control instruction output by the target automatic cutting program is obtained through the cutting module, the heading machine is controlled to execute cutting operation according to the cutting control instruction, the perception capability of the heading machine on the peripheral condition is improved through training of the automatic cutting program of the heading machine, and the accuracy rate of the cutting operation is improved when a cutting task is executed.
Example 3
The embodiment of the application provides a heading machine, which comprises the cutting control system of the heading machine.
The heading machine comprises the cutting control system of the heading machine, the sensing capability of the heading machine to the surrounding conditions is improved by training the automatic cutting program of the heading machine, and the accuracy of cutting operation is improved when a cutting task is executed.
The above embodiments are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present application and such modifications and equivalents should also be considered to be within the scope of the present application.
Claims (10)
1. A cutting control method of a heading machine is characterized by comprising the following steps:
acquiring a plurality of execution behaviors of the heading machine, and determining manual operation data and automatic operation data corresponding to each execution behavior in the plurality of execution behaviors;
acquiring an automatic cutting program of the heading machine, training the automatic cutting program based on manual operation data and automatic operation data corresponding to each execution behavior, and updating program parameters of the automatic cutting program to obtain a target automatic cutting program;
responding to a running request of the heading machine, acquiring running test data carried by the running request of the heading machine, and inputting the running test data into the target automatic cutting program;
and acquiring a cutting control instruction output by the target automatic cutting program so as to control the heading machine to execute cutting operation according to the cutting control instruction.
2. The method of claim 1, wherein prior to said obtaining a plurality of performance activities of the roadheader, the method further comprises:
acquiring an initial manual operation data set for operating a manual cutting program, and extracting at least one first data category included in the initial manual operation data set;
classifying a plurality of initial manual operation data included in the initial manual operation data set based on the at least one first data category to obtain a classified initial manual operation data set;
slicing the classified initial manual operation data set to obtain a sliced initial manual operation data set;
acquiring a first time point for executing a manual cutting task each time, and marking initial manual operation data corresponding to the sliced initial manual operation data set by adopting the first time point to obtain a sorted manual operation data set; and the number of the first and second groups,
acquiring an initial automatic operation data set for operating an automatic cutting program, and extracting at least one second data category included in the initial automatic operation data set;
classifying a plurality of initial automatic operation data included in the initial automatic operation data set based on the at least one second data category to obtain a classified initial automatic operation data set;
slicing the classified initial automatic operation data set to obtain a sliced initial automatic operation data set;
and acquiring a second time node for executing the automatic cutting task each time, and labeling the initial automatic operation data corresponding to the sliced initial automatic operation data set by adopting the second time node to obtain a sorted automatic operation data set.
3. The method of claim 2, wherein prior to said obtaining a plurality of performance activities of the roadheader, the method further comprises:
acquiring manual execution data which is acquired by controlling the heading machine based on each piece of the sorted manual behavior data in the sorted manual operation data set, and acquiring a manual execution data set;
determining a plurality of execution behaviors and manual operation data corresponding to each execution behavior in the plurality of execution behaviors by adopting a behavior recognition algorithm based on the sorted manual operation data set and the manual execution data set;
acquiring automatic execution data which is acquired by controlling the heading machine based on each piece of arranged automatic behavior data in the arranged automatic operation data set;
determining automatic execution data corresponding to each execution behavior of the plurality of execution behaviors.
4. The method according to claim 1, wherein the training of the automatic cutting program based on the manual operation data and the automatic operation data corresponding to each execution behavior and the updating of the program parameters of the automatic cutting program to obtain the target automatic cutting program comprises:
inputting the manual operation data corresponding to each execution behavior into the automatic cutting program, controlling the heading machine to acquire first automatic execution data corresponding to each execution behavior, comparing the automatic execution data indicated by the same execution behavior with the first automatic execution data, updating program parameters of the automatic cutting program, and determining at least one target manual operation data meeting preset conditions as training data of the next round;
and determining the preset training times, inputting the training data obtained in the previous training round into an updated automatic cutting program in each training round, and continuously updating the program parameters of the automatic cutting program until the training round reaches the preset training times to obtain the target automatic cutting program.
5. The method according to claim 4, wherein the step of comparing the automatic execution data indicated by the same execution behavior with the first automatic execution data, updating the program parameters of the automatic cutting program, and determining at least one target manual operation data satisfying a preset condition as the training data of the next round comprises:
calculating a difference between the automatically executed data and the first automatically executed data indicated by the same execution behavior;
acquiring a preset threshold, if the difference is smaller than the preset threshold, finely adjusting program parameters of the automatic cutting program, and determining target manual operation data corresponding to the same execution behavior;
and acquiring the at least one target manual operation data as training data of the next round.
6. The method of claim 5, further comprising:
and if the difference is larger than the preset threshold, replacing the program parameters of the automatic cutting program by using the program parameters of the manual cutting program.
7. The method of claim 1, wherein after obtaining the target automatic cutting program, the method further comprises:
and uploading the target program parameters of the automatic target cutting program to a cloud server, so that other heading machines update the program parameters of the automatic target cutting program by using the target program parameters.
8. A cutting control system of a heading machine, comprising:
the determining module is used for acquiring a plurality of execution behaviors of the heading machine, and determining manual operation data and automatic operation data corresponding to each execution behavior in the plurality of execution behaviors;
the training module is used for acquiring an automatic cutting program of the heading machine, training the automatic cutting program based on manual operation data and automatic operation data corresponding to each execution behavior, and updating program parameters of the automatic cutting program to obtain a target automatic cutting program;
the operation module is used for responding to a heading machine operation request, acquiring operation test data carried by the heading machine operation request, and inputting the operation test data into the target automatic cutting program;
and the cutting module is used for acquiring a cutting control instruction output by the target automatic cutting program so as to control the heading machine to execute cutting operation according to the cutting control instruction.
9. The cutting control system of a heading machine of claim 8, further comprising: an acquisition module;
the acquisition module comprises: a laser ranging unit, a millimeter wave radar unit, an infrared thermal imaging unit and a total station positioning unit, wherein,
the laser ranging unit is used for acquiring absolute distance data between the peripheral wall of the heading machine and the heading machine body;
the millimeter wave radar unit is used for acquiring surface shape data of the peripheral wall of the development machine;
the infrared thermal imaging unit is used for acquiring heat source data around the development machine;
and the total station positioning unit is used for acquiring absolute position data of the heading machine on a working face.
10. A heading machine, characterized by comprising a cutting control system of the heading machine according to any one of claims 8-9.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310095079.XA CN115773128B (en) | 2023-02-10 | 2023-02-10 | Cutting control method and system of heading machine and heading machine |
| PCT/CN2024/070396 WO2024164770A1 (en) | 2023-02-10 | 2024-01-03 | Cutting control method and system for roadheader and roadheader |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310095079.XA CN115773128B (en) | 2023-02-10 | 2023-02-10 | Cutting control method and system of heading machine and heading machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115773128A true CN115773128A (en) | 2023-03-10 |
| CN115773128B CN115773128B (en) | 2023-05-19 |
Family
ID=85393448
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310095079.XA Active CN115773128B (en) | 2023-02-10 | 2023-02-10 | Cutting control method and system of heading machine and heading machine |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115773128B (en) |
| WO (1) | WO2024164770A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024164770A1 (en) * | 2023-02-10 | 2024-08-15 | 三一重型装备有限公司 | Cutting control method and system for roadheader and roadheader |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114233312A (en) * | 2021-11-17 | 2022-03-25 | 中铁工程装备集团隧道设备制造有限公司 | Free section cutting control system and control method for cantilever excavator |
| CN114856604A (en) * | 2022-05-09 | 2022-08-05 | 中国铁建重工集团股份有限公司 | Tunneling machine control method, device, equipment and storage medium |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7061891B2 (en) * | 2018-02-21 | 2022-05-02 | 清水建設株式会社 | Operation estimation device and operation estimation method |
| CN109630154B (en) * | 2019-01-24 | 2023-08-25 | 华能西藏雅鲁藏布江水电开发投资有限公司 | Tunneling robot for tunneling and remote mobile terminal command system |
| CN110852423B (en) * | 2019-11-12 | 2023-01-24 | 中铁工程装备集团有限公司 | Tunnel boring machine excavation performance and control parameter prediction method based on transfer learning |
| CN111173510A (en) * | 2020-03-14 | 2020-05-19 | 天地科技股份有限公司 | Intelligent control method and system for fully mechanized mining equipment for complex condition working face |
| CN111622763A (en) * | 2020-04-23 | 2020-09-04 | 中国铁建重工集团股份有限公司 | Direction adjusting control method and system for vertical shaft heading machine, vertical shaft heading machine and storage medium |
| CN112163316A (en) * | 2020-08-31 | 2021-01-01 | 同济大学 | Tunneling parameter prediction method of hard rock tunnel boring machine based on deep learning |
| CN112926643A (en) * | 2021-02-22 | 2021-06-08 | 广东数程科技有限公司 | Modeling method, device, computer equipment and medium based on divisible data |
| CN115773128B (en) * | 2023-02-10 | 2023-05-19 | 三一重型装备有限公司 | Cutting control method and system of heading machine and heading machine |
-
2023
- 2023-02-10 CN CN202310095079.XA patent/CN115773128B/en active Active
-
2024
- 2024-01-03 WO PCT/CN2024/070396 patent/WO2024164770A1/en unknown
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114233312A (en) * | 2021-11-17 | 2022-03-25 | 中铁工程装备集团隧道设备制造有限公司 | Free section cutting control system and control method for cantilever excavator |
| CN114856604A (en) * | 2022-05-09 | 2022-08-05 | 中国铁建重工集团股份有限公司 | Tunneling machine control method, device, equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024164770A1 (en) * | 2023-02-10 | 2024-08-15 | 三一重型装备有限公司 | Cutting control method and system for roadheader and roadheader |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115773128B (en) | 2023-05-19 |
| WO2024164770A1 (en) | 2024-08-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | A critical review of vision-based occupational health and safety monitoring of construction site workers | |
| CN111666921B (en) | Vehicle control method, apparatus, computer device, and computer-readable storage medium | |
| CN116630394B (en) | Multi-mode target object attitude estimation method and system based on three-dimensional modeling constraint | |
| CN115773128B (en) | Cutting control method and system of heading machine and heading machine | |
| CN113914407B (en) | Excavator excavation tunnel accurate control system based on BIM and machine vision | |
| CN113746936B (en) | VR and AR distributed cooperation fully-mechanized coal mining face intelligent monitoring system | |
| CN116310843B (en) | Coal rock identification method, device, readable storage medium and heading machine | |
| EP3913527A1 (en) | Method and device for performing behavior prediction by using explainable self-focused attention | |
| CN111444891A (en) | Unmanned rolling machine operation scene perception system and method based on airborne vision | |
| CN113982690A (en) | Control method, device and system based on anchoring and protecting operation and tunneling, anchoring and protecting all-in-one machine | |
| CN116259002A (en) | Human body dangerous behavior analysis method based on video | |
| KR102396330B1 (en) | System and method for establishing recovery of runway based on image, ai and reinforcement learning at war | |
| JP2020013480A (en) | Vehicle recognition system and vehicle recognition method | |
| CN117392611A (en) | Site safety monitoring method, system, equipment and storage medium | |
| CN112785564A (en) | Pedestrian detection tracking system and method based on mechanical arm | |
| CN117423157A (en) | Mine abnormal video action understanding method combining migration learning and regional invasion | |
| CN116398134A (en) | Coal cutter cutting planning method and equipment based on inspection and perception | |
| CN110531774A (en) | Obstacle Avoidance, device, robot and computer readable storage medium | |
| CN109000634A (en) | A kind of based reminding method and system of navigation object travelling route | |
| Roberts et al. | Annotating 2D imagery with 3D kinematically configurable assets of construction equipment for training pose-informed activity analysis and safety monitoring algorithms | |
| CN105243665A (en) | Robot biped positioning method and apparatus | |
| Jiang et al. | Computer vision-based methods applied to construction processes: A literature review | |
| Li et al. | A vision-based end pose estimation method for excavator manipulator | |
| CN212873508U (en) | Unmanned rolling machine operation scene perception system based on airborne vision | |
| Zhang et al. | Semantic segmentation of point clouds of field obstacle-crossing terrain for multi-legged rescue equipment based on random forest |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |