CN117483838A - Board drilling method and device based on artificial intelligence - Google Patents
Board drilling method and device based on artificial intelligence Download PDFInfo
- Publication number
- CN117483838A CN117483838A CN202311843587.8A CN202311843587A CN117483838A CN 117483838 A CN117483838 A CN 117483838A CN 202311843587 A CN202311843587 A CN 202311843587A CN 117483838 A CN117483838 A CN 117483838A
- Authority
- CN
- China
- Prior art keywords
- drilling
- plate
- data
- processed
- real
- 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
- 238000005553 drilling Methods 0.000 title claims abstract description 432
- 238000000034 method Methods 0.000 title claims abstract description 79
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 26
- 238000004458 analytical method Methods 0.000 claims abstract description 73
- 230000008569 process Effects 0.000 claims abstract description 52
- 230000007246 mechanism Effects 0.000 claims description 60
- 238000012545 processing Methods 0.000 claims description 44
- 230000007547 defect Effects 0.000 claims description 29
- 230000000704 physical effect Effects 0.000 claims description 19
- 238000013507 mapping Methods 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 5
- 238000003709 image segmentation Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 238000007514 turning Methods 0.000 abstract description 2
- 239000000463 material Substances 0.000 description 25
- 238000004519 manufacturing process Methods 0.000 description 22
- 238000005516 engineering process Methods 0.000 description 9
- 238000012544 monitoring process Methods 0.000 description 7
- 238000013135 deep learning Methods 0.000 description 6
- 238000003754 machining Methods 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 239000002699 waste material Substances 0.000 description 3
- 239000002023 wood Substances 0.000 description 3
- 238000005520 cutting process Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 238000003703 image analysis method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23B—TURNING; BORING
- B23B41/00—Boring or drilling machines or devices specially adapted for particular work; Accessories specially adapted therefor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23B—TURNING; BORING
- B23B47/00—Constructional features of components specially designed for boring or drilling machines; Accessories therefor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q15/00—Automatic control or regulation of feed movement, cutting velocity or position of tool or work
- B23Q15/007—Automatic control or regulation of feed movement, cutting velocity or position of tool or work while the tool acts upon the workpiece
- B23Q15/14—Control or regulation of the orientation of the tool with respect to the work
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
- B23Q17/22—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring existing or desired position of tool or work
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Numerical Control (AREA)
Abstract
The invention relates to the technical field of plate turning, and discloses a plate drilling method and device based on artificial intelligence, which are used for improving the accuracy of plate drilling based on artificial intelligence. The method comprises the following steps: controlling a preset lathe device to drill the plate to be processed through a plurality of target drilling paths, and collecting real-time image data of the plate to be processed in the drilling process in real time; and carrying out drilling parameter analysis on the real-time image data to obtain drilling depth data and drilling position data corresponding to the real-time image data, collecting a drill bit parameter set of the lathe in real time, carrying out drilling deviation analysis on the plate to be processed according to the drilling depth data and the drilling position data to obtain drilling deviation data, carrying out control parameter analysis on the lathe according to the drilling deviation data to obtain target control parameters, and controlling the lathe to carry out drilling control on the plate to be processed according to the target control parameters.
Description
Technical Field
The invention relates to the technical field of plate turning, in particular to a plate drilling method and device based on artificial intelligence.
Background
With the development of manufacturing industry, plate processing is one of important links in the manufacturing process, and has a critical meaning for improving the product quality and the production efficiency. In the traditional plate processing, experience and manual operation are generally relied on, and the problems of low processing efficiency and difficulty in guaranteeing the product quality exist. To address these issues, the use of artificial intelligence technology in the manufacturing industry is becoming a hotspot for research. The technical scheme is based on an artificial intelligence technology, realizes automatic analysis and drilling control of the plate to be processed by methods such as image processing, deep learning and the like, and provides a new solution for improving the automation level and the production efficiency of plate processing.
However, conventional intelligence in sheet processing still presents some challenges. First, the acquisition and analysis of part of the plate attribute information still depend on manual judgment, and an efficient and accurate automatic means is lacked. Second, many automated systems are currently still in need of improvement in terms of real-time and self-adaptability, and in particular, the robustness of the system is still insufficient when handling different types of boards and varying production environments. In addition, the prior art has certain limitations in real-time monitoring and adjustment of the drilling process, which makes it difficult to find and correct deviations in the process in time. Therefore, it is necessary to further improve the automation level and the degree of intellectualization of the sheet processing by introducing more advanced artificial intelligence techniques.
Disclosure of Invention
In view of the above, the embodiment of the invention provides a plate drilling method and device based on artificial intelligence, which are used for improving the accuracy of plate drilling based on artificial intelligence.
The invention provides a plate drilling method based on artificial intelligence, which comprises the following steps: carrying out image scanning on a plate to be processed to obtain image scanning data of the plate to be processed; performing plate attribute information analysis on the plate to be processed according to the image scanning data to obtain plate attribute information of the plate to be processed; inputting the plate attribute information into a preset drilling path planning model to carry out drilling path planning to obtain a plurality of target drilling paths; controlling a preset lathe device to drill the plate to be processed through a plurality of target drilling paths, and collecting real-time image data of the plate to be processed in the drilling process in real time; and carrying out drilling parameter analysis on the real-time image data to obtain drilling depth data and drilling position data corresponding to the real-time image data, and collecting a drill bit parameter set of the lathe in real time, wherein the drill bit parameter set comprises: drill rotational speed and feed rate; and carrying out drilling deviation analysis on the plate to be processed according to the drilling depth data and the drilling position data to obtain drilling deviation data, carrying out control parameter analysis on the lathe according to the drilling deviation data to obtain target control parameters, and controlling the lathe to carry out drilling control on the plate to be processed according to the target control parameters.
In the invention, the step of scanning the image of the plate to be processed to obtain the image scanning data of the plate to be processed comprises the following steps: performing plate corner positioning on the plate to be processed to obtain corner position data of the plate to be processed; extracting plate attribute of the plate to be processed to obtain plate attribute data of the plate to be processed; and calibrating image acquisition parameters of the plate to be processed based on the plate attribute data, wherein the image acquisition parameters comprise: image exposure time, light source intensity, and sampling frequency; carrying out image acquisition area analysis on the plate to be processed through the angular point position data to obtain an image acquisition area of the plate to be processed; and carrying out image scanning on the plate to be processed based on the image acquisition area and the image acquisition parameters to obtain image scanning data of the plate to be processed.
In the invention, the step of analyzing the plate attribute information of the plate to be processed according to the image scanning data to obtain the plate attribute information of the plate to be processed comprises the following steps: performing image enhancement processing on the image scanning data to obtain enhanced image data corresponding to the image scanning data; extracting the texture features of the plate from the enhanced image data to obtain plate texture feature data; performing defect detection on the enhanced image data to obtain a plate defect position corresponding to the enhanced image data; and merging the plate defect positions and the plate texture feature data into the plate attribute information of the plate to be processed.
In the invention, the step of inputting the plate attribute information into a preset drilling path planning model to carry out drilling path planning to obtain a plurality of target drilling paths comprises the following steps: obtaining physical property data of the plate to be processed, wherein the physical property data comprises: plate thickness data, plate hardness data and plate density data; constructing a digital twin body of the plate to be processed according to the physical property data, and constructing drilling paths of the digital twin body to obtain a plurality of candidate drilling paths; inputting the plate texture feature data and the plate defect positions into a plurality of initial layers of the drilling path planning model to sequentially perform forward propagation processing to obtain a plurality of feature vectors; inputting a plurality of feature vectors into a target layer of the drilling path planning model to carry out track coordinate mapping to obtain a plurality of path track coordinate sets; generating a plurality of drilling paths to be processed according to a plurality of path track coordinate sets; and carrying out path data combination on the candidate drilling paths and the drilling paths to be processed to obtain a plurality of target drilling paths.
In the invention, the step of controlling a preset lathe device to drill the plate to be processed through a plurality of target drilling paths and collecting real-time image data of the plate to be processed in the drilling process in real time comprises the following steps: inputting a plurality of target drilling paths into a numerical control module of the lathe device, and planning drilling time of the plurality of target drilling paths through the numerical control module based on preset target operation duration to obtain target drilling time; and controlling the lathe device to drill the plate to be processed based on the target drilling time, and collecting real-time image data of the plate to be processed in the drilling process in real time.
In the invention, the real-time image data is subjected to drilling parameter analysis to obtain drilling depth data and drilling position data corresponding to the real-time image data, and a drill bit parameter set of the lathe is acquired in real time, wherein the drill bit parameter set comprises: drill bit rotational speed and feed rate steps, including: calibrating the drilling position of the real-time image data to obtain drilling position data, wherein the drilling position data comprises a plurality of drilling position coordinates; based on a plurality of drilling position coordinates, performing image segmentation on the real-time image data to obtain segmented image data corresponding to each drilling position coordinate; respectively extracting drilling depths from the segmented image data corresponding to each drilling position coordinate to obtain drilling depths corresponding to each drilling position coordinate, and merging the drilling depths corresponding to each drilling position coordinate into drilling depth data; collecting a drill bit parameter set of the lathe in real time, wherein the drill bit parameter set comprises: drill speed and feed rate.
In the invention, the drilling deviation analysis is performed on the plate to be processed according to the drilling depth data and the drilling position data to obtain drilling deviation data, the control parameter analysis is performed on the lathe according to the drilling deviation data to obtain target control parameters, and the lathe is controlled to perform drilling control steps on the plate to be processed according to the target control parameters, including: respectively carrying out drilling time mapping on the drilling depth corresponding to each drilling position coordinate to obtain the drilling time corresponding to each drilling position coordinate; respectively carrying out standard drilling depth matching on the drilling time corresponding to each drilling position coordinate to obtain standard drilling depth data corresponding to each drilling position coordinate; carrying out drilling deviation analysis on the drilling depth corresponding to each drilling position coordinate and the standard drilling depth data corresponding to each drilling position coordinate to obtain drilling deviation data; and carrying out control parameter analysis on the lathe according to the drilling deviation data to obtain target control parameters, and controlling the lathe to carry out drilling control on the plate to be processed according to the target control parameters.
The invention also provides a plate drilling device based on artificial intelligence, which comprises:
the machine frame is provided with a processing table which is used for placing a plate to be processed;
the scanning mechanism is arranged on the frame, and the acquisition end of the scanning mechanism is arranged opposite to the processing table and is used for scanning images of the plate to be processed to obtain image scanning data of the plate to be processed;
the analysis mechanism is arranged on the frame, is electrically connected with the scanning mechanism and is used for analyzing the plate attribute information of the plate to be processed according to the image scanning data to obtain the plate attribute information of the plate to be processed;
the planning mechanism is arranged on the frame and is electrically connected with the analysis mechanism, and is used for inputting the plate attribute information into a preset drilling path planning model to carry out drilling path planning so as to obtain a plurality of target drilling paths;
the operation mechanism is arranged on the frame, is electrically connected with the planning mechanism, and is used for carrying out drilling operation on the plate to be processed through a plurality of target drilling paths and collecting real-time image data of the plate to be processed in the drilling operation process in real time;
The acquisition mechanism is arranged on the frame and is electrically connected with the operation mechanism, and is used for carrying out drilling parameter analysis on the real-time image data to obtain drilling depth data and drilling position data corresponding to the real-time image data, and acquiring a drill bit parameter set of the lathe in real time, wherein the drill bit parameter set comprises: drill rotational speed and feed rate;
the control mechanism is arranged on the frame, is electrically connected with the acquisition mechanism and the operation mechanism respectively, and is used for carrying out drilling deviation analysis on the plate to be processed according to the drilling depth data and the drilling position data to obtain drilling deviation data, carrying out control parameter analysis on the operation mechanism according to the drilling deviation data to obtain target control parameters, and controlling the operation mechanism to carry out drilling control on the plate to be processed according to the target control parameters.
In the invention, the operation mechanism comprises a transverse moving assembly, a longitudinal moving assembly and a drilling assembly, wherein the transverse moving assembly is connected with the longitudinal moving assembly and used for driving the longitudinal moving assembly and the drilling assembly to synchronously move transversely, the longitudinal moving assembly is used for driving the drilling assembly to longitudinally move, the drilling assembly comprises a rotary motor and a drill bit, the rotary motor is connected with the longitudinal moving assembly, and the drill bit is arranged at the driving end of the rotary motor.
According to the technical scheme provided by the invention, various attribute information of the plate to be processed, including physical properties, texture features and possible defect positions, can be accurately obtained through image scanning and analysis. This helps to build a comprehensive board property model. And generating a plurality of target drilling paths according to the plate attribute information by using a preset drilling path planning model. Such a plan takes into account the multifaceted nature of the sheet material, making the drilling path more adaptable to different sheet material types and process requirements. By acquiring real-time image data in the drilling operation process in real time, drilling depth data, drilling position data and a drill bit parameter set can be timely obtained. This provides the necessary information for real-time monitoring and control, ensuring accuracy and consistency in the drilling process. Drilling parameter analysis obtains drilling depth data and drilling position data through processing the real-time image data. By combining the drill bit parameter set, the influence of drilling parameters can be analyzed, a foundation is provided for subsequent drilling deviation analysis, and parameter optimization is performed when needed. The analysis of the drilling deviation data provides feedback of actual machining conditions, and the control parameter analysis of the lathe can be performed according to the data. By adjusting the control parameters in real time, the deviation in the drilling process can be automatically corrected, and the accuracy and quality of drilling are improved. The whole scheme combines the technologies of image processing, deep learning, real-time control and the like, so that the drilling process is more intelligent. This helps to improve production efficiency, reduce material waste, and ensure consistency and quality stability of production.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for drilling a plate based on artificial intelligence in an embodiment of the invention.
Fig. 2 is a flowchart of analyzing board attribute information of a board to be processed according to image scanning data in an embodiment of the present invention.
Fig. 3 is a schematic diagram of an artificial intelligence-based plate drilling device according to an embodiment of the present invention.
Reference numerals:
301. a frame; 302. a scanning mechanism; 303. an analysis mechanism; 304. a planning mechanism; 305. a working mechanism; 306. a collection mechanism; 307. a control mechanism; 3051. a lateral movement assembly; 3052. a longitudinally moving assembly; 3053. and (5) a drilling assembly.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In addition, the technical features of the different embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
For easy understanding, the following describes a specific flow of the embodiment of the present invention, referring to fig. 1, fig. 1 is a flow chart of a plate drilling method based on artificial intelligence according to the embodiment of the present invention, as shown in fig. 1, including the following steps:
s101, performing image scanning on a plate to be processed to obtain image scanning data of the plate to be processed;
First, a sheet material to be processed is subjected to a comprehensive and detailed image scanning by using a high-performance image scanning device such as an optical scanner or a camera-based. This step is the start-up phase of the entire intelligent borehole, providing the necessary input data for subsequent process control. By combining the scanner with computer vision techniques, image scan data of the sheet material to be processed can be acquired with high accuracy. Subsequently, by means of the image scanning data, a depth analysis of the sheet property information is performed. This step is to extract key board properties from the image, including physical properties, surface texture features, and any possible defects. Taking a deep learning technology as an example, through training a model, the plate attributes of different types can be automatically learned and identified, so that efficient and accurate attribute information extraction is realized. And then, inputting the extracted plate attribute information into a preset drilling path planning model. By this step, a plurality of target drilling paths can be generated according to the actual characteristics of the sheet material and the prescribed production targets. The choice of this model may depend on the type of sheet material faced and the diversity of production environments. For example, a hybrid model may be selected that integrates image processing and deep learning techniques to accommodate variations in different types of sheet materials and production requirements. Finally, after a plurality of target drilling paths are obtained, the drilling operation is carried out on the plate to be processed by controlling a preset lathe device. In the whole drilling process, real-time image data of the plate to be processed are acquired in real time so as to further optimize and adjust the drilling process. Such a real-time data feedback mechanism helps to achieve the accuracy and efficiency of the drilling operation. Through the organic combination of the steps, the intelligent drilling can realize automatic plate processing while efficiently utilizing image information, and the overall efficiency of a production line is improved.
S102, carrying out plate attribute information analysis on the plate to be processed according to the image scanning data to obtain plate attribute information of the plate to be processed;
the image scanning data acquired by advanced image scanning equipment provides a basis for subsequent analysis of the sheet attribute information. First, by using a high-performance optical scanner or camera, high-resolution image data of a sheet to be processed can be acquired, covering fine features and structures of the sheet surface. Subsequently, depth analysis of the sheet property information is performed using the image scanning data. By using computer vision techniques and image processing algorithms, various attributes of the sheet material can be identified and extracted. For example, an algorithm based on deep learning can automatically learn the texture features of the board and distinguish between different types of wood grain or fibrous structures. Meanwhile, the conventional image processing method can be used for detecting the uniformity and color distribution of the surface of the plate, which are important factors affecting the subsequent drilling process. The resulting sheet property information includes physical properties, surface texture features, and any possible defect locations. For example, the physical properties of the sheet material, such as density, hardness, etc., may be analyzed and the texture, color distribution of the surface identified. If a defect, such as a crack, is present, its location can be accurately located and recorded. Such detailed attribute information provides a basis for subsequent borehole path planning, ensuring that an optimized borehole path can be generated based on the actual properties of the sheet material. In this way, the analysis of the image scan data not only provides the necessary inputs for the drilling process, but also provides a reliable basis for the intelligent processing of the production.
S103, inputting the plate attribute information into a preset drilling path planning model to carry out drilling path planning, so as to obtain a plurality of target drilling paths;
specifically, based on the obtained plate attribute information, the plate attribute information is input into a preset drilling path planning model so as to realize intelligent and personalized drilling path planning. This step ensures optimization of the drilling path by taking into account the physical properties, surface texture and defect information in combination to accommodate the varying sheet material and production requirements of different types. For example, if a specific texture or defect exists on the surface of the plate, the drilling path planning model can adjust the drilling path according to the information so as to avoid possible obstacle or defect positions and ensure that the drilling process is smoothly performed. In this way, a plurality of target drilling paths can be generated which take into account the actual properties of the sheet material while meeting production targets. The diversity of these target paths allows for selection on a case-by-case basis to improve the flexibility of production. For example, when processing different kinds of wood, it is possible to generate different drilling paths adapted to each wood grain and hardness to minimize material loss and to improve production efficiency. In summary, the process of incorporating plate attribute information into a borehole path planning model is a key step in achieving personalized and intelligent plate drilling, ensuring that an optimized borehole path can be generated while taking into account multiple factors. The accurate and flexible path planning method is beneficial to improving the efficiency of a production line and the processing quality.
S104, controlling a preset lathe device to perform drilling operation on the plate to be processed through a plurality of target drilling paths, and collecting real-time image data of the plate to be processed in the drilling operation process in real time;
specifically, based on the generated multiple target drilling paths, further implementing control of a preset lathe device to perform intelligent drilling operation on the plate to be processed. In the whole drilling process, image data of the plate to be processed are acquired in real time, so that the accuracy and real-time monitoring of drilling operation are ensured. For example, it is possible to acquire image data of the sheet surface in real time as each drilling step, and use this data to dynamically adjust and optimize the drilling path to ensure adaptation to the complexity and variations of the sheet surface. The acquisition of the real-time image data not only can realize timely feedback on the drilling process, but also is helpful for detecting and correcting any possible abnormal conditions, such as non-uniformity of the surface of the plate or defects. By comparing with the expected target drilling path, the dynamic parameters of the lathe device, such as the feeding speed or the rotating speed of the drill bit, can be adjusted in real time so as to improve the accuracy and efficiency of the drilling operation to the greatest extent. The tightly combined operation flow fully plays the advantages of image data analysis and real-time monitoring, so that highly intelligent drilling operation can be realized under different plates and production environments. Through dynamic adjustment and optimization, the accuracy of operation can be continuously improved in the actual drilling process, and efficient and high-quality plate processing is realized.
S105, carrying out drilling parameter analysis on the real-time image data to obtain drilling depth data and drilling position data corresponding to the real-time image data, and collecting a drill bit parameter set of a lathe in real time, wherein the drill bit parameter set comprises: drill rotational speed and feed rate;
specifically, in intelligent drilling, drilling parameter information can be obtained in real time by precisely analyzing real-time image data. Firstly, carrying out depth analysis on the real-time image data, and precisely measuring the depth of each drilling hole and the corresponding drilling hole position through an image processing technology. For example, the entry coordinates and borehole depth of each borehole can be accurately captured by image recognition and edge detection algorithms, resulting in real-time borehole depth data and borehole position data. Meanwhile, a drill bit parameter set of the lathe is acquired in real time, wherein the drill bit parameter set comprises a drill bit rotating speed and a feed speed. This involves real-time communication with the lathe control to obtain the operating parameters of the lathe device at the current time. For example, the actual rotational speed and feed rate of the drill bit may be monitored, with these parameters directly affecting the cutting effectiveness and speed during actual drilling. Through the real-time acquisition, drilling parameters can be dynamically adjusted and optimized to adapt to different plate characteristics and changed production environments. By integrating the steps, by accurately analyzing the real-time image data in the drilling operation, not only the real-time drilling depth data and the real-time position data are obtained, but also the drill bit parameter set of the lathe can be timely acquired. The method can realize real-time monitoring and adjustment of drilling parameters in the drilling process, thereby improving the accuracy and efficiency of drilling.
S106, carrying out drilling deviation analysis on the plate to be processed according to the drilling depth data and the drilling position data to obtain drilling deviation data, carrying out control parameter analysis on the lathe according to the drilling deviation data to obtain target control parameters, and controlling the lathe to carry out drilling control on the plate to be processed according to the target control parameters.
It should be noted that, based on the drilling depth data and the drilling position data obtained in real time, drilling deviation analysis is performed to identify any deviation from the expected drilling path. By comparing the actual borehole data with the expected path, the actual deviation of the borehole can be calculated. For example, if the image analysis shows that the borehole depth at a particular location deviates from the expected value, the deviation will be recorded and borehole deviation data formed.
And carrying out control parameter analysis of the lathe based on the drilling deviation data. This step involves in-depth knowledge of the cause of the deviation and determining the lathe control parameters that need to be adjusted. For example, if the deviation is mainly due to non-uniformity of cutting effect caused by variation of hardness of the material, the feed rate of the drill may be adjusted to accommodate plates of different hardness.
By performing analysis of the target control parameters, the optimal lathe control parameter setting under the current condition is obtained. This may include adjusting the rotational speed, feed rate, etc. of the drill bit. For example, the most efficient bit rotational speed at a particular hardness may be determined based on sheet property information and previous drilling experience to minimize deviation.
Finally, according to the obtained target control parameters, the lathe is controlled in real time so as to correct deviation and maintain high-precision drilling in subsequent drilling operation. Through the closed loop feedback control, the operation parameters of the lathe can be continuously optimized in the actual machining process, each drilling hole is ensured to meet the expected requirement, and efficient and accurate plate machining is realized.
In a specific embodiment, the process of executing step S101 may specifically include the following steps:
(1) Performing plate corner positioning on a plate to be processed to obtain corner position data of the plate to be processed;
(2) Extracting plate attribute of the plate to be processed to obtain plate attribute data of the plate to be processed;
(3) Performing image acquisition parameter calibration on the plate to be processed based on the plate attribute data, wherein the image acquisition parameters comprise: image exposure time, light source intensity, and sampling frequency;
(4) Carrying out image acquisition area analysis on the plate to be processed according to the angular point position data to obtain an image acquisition area of the plate to be processed;
(5) And carrying out image scanning on the plate to be processed based on the image acquisition area and the image acquisition parameters to obtain image scanning data of the plate to be processed.
Specifically, firstly, plate corner positioning is performed on a plate to be processed, and corner position data of the plate to be processed are accurately obtained through a high-precision image processing technology. For example, using a corner detection algorithm, specific points on the edges of the sheet material may be detected, resulting in accurate corner coordinates. Subsequently, the sheet material to be processed is subjected to sheet material attribute extraction, and various item of attribute data of the sheet material can be extracted through an image analysis technology, including physical properties, texture features and any possible defects. This step ensures that the actual properties of the sheet are taken into account during subsequent image acquisition and processing. And (3) calibrating image acquisition parameters based on the plate attribute data, wherein the parameters comprise image exposure time, light source intensity, sampling frequency and the like. The calibration process is to optimize the quality of image acquisition to accommodate variations in different sheet properties. For example, for darker panels, the exposure time may be adjusted to ensure that a clear image is obtained. And (3) carrying out image acquisition area analysis through angular point position data to determine an image acquisition area of the plate to be processed. This analysis is to ensure that the entire panel surface is covered during the image scanning process while minimizing the waste of resources to collect unnecessary areas. Finally, based on the determined image acquisition area and the determined image acquisition parameters, image scanning is carried out, and high-quality image scanning data of the plate to be processed are obtained. In the process, the comprehensive influence of the angular point position, the attribute characteristic and the image acquisition parameter of the plate is comprehensively considered, so that accurate and comprehensive image data are ensured to be obtained, and a solid foundation is provided for the follow-up intelligent drilling process.
In a specific embodiment, as shown in fig. 2, the process of executing step S102 may specifically include the following steps:
s201, performing image enhancement processing on the image scanning data to obtain enhanced image data corresponding to the image scanning data;
s202, extracting plate texture features from the enhanced image data to obtain plate texture feature data;
s203, performing defect detection on the enhanced image data to obtain a plate defect position corresponding to the enhanced image data;
s204, combining the plate defect positions and the plate texture feature data into plate attribute information of the plate to be processed.
It should be noted that, by using the acquired image scanning data, image enhancement processing is performed first, and by applying an image processing technique, image quality and sharpness are improved, and corresponding enhanced image data is obtained. For example, the texture and characteristics of the surface of the plate can be more clearly seen by adopting algorithms such as contrast enhancement, histogram equalization and the like. Subsequently, the enhanced image data are subjected to panel texture feature extraction. By using advanced image processing algorithms, such as Convolutional Neural Networks (CNNs), the texture information in the image can be mined deep to extract the microstructure and texture features of the sheet surface. For example, CNNs may learn and identify grain patterns for different woods to obtain more representative board grain characterization data. Meanwhile, defect detection is carried out on the enhanced image data, and possible defects such as cracks, flaws and the like on the surface of the plate can be detected through an image analysis and machine learning method, and the positions of the defects can be accurately calibrated. This step provides the ability to monitor and evaluate the surface quality of the sheet in real time. And finally, combining the plate defect position information and the plate texture feature data to form complete plate attribute information. This comprehensive information includes the surface characteristics of the sheet, texture information, and any possible imperfections, which provides a comprehensive basis for subsequent borehole path planning. Through the process, the whole quality of the plate is comprehensively analyzed while the high-quality image is acquired, and more accurate and reliable plate attribute information is provided for intelligent drilling.
In a specific embodiment, the process of executing step S103 may specifically include the following steps:
(1) Obtaining physical property data of a plate to be processed, wherein the physical property data comprises: plate thickness data, plate hardness data and plate density data;
(2) Constructing a digital twin body of a plate to be processed according to the physical property data, and constructing drilling paths of the digital twin body to obtain a plurality of candidate drilling paths;
(3) Inputting the texture feature data of the plate and the defect positions of the plate into a plurality of initial layers of a drilling path planning model to sequentially perform forward propagation processing to obtain a plurality of feature vectors;
(4) Inputting a plurality of feature vectors into a target layer of a drilling path planning model to carry out track coordinate mapping to obtain a plurality of path track coordinate sets;
(5) Generating a plurality of drilling paths to be processed according to the path track coordinate sets;
(6) And carrying out path data combination on the plurality of candidate drilling paths and the plurality of drilling paths to be processed to obtain a plurality of target drilling paths.
Specifically, first, physical property data of a plate to be processed is obtained, including information such as thickness, hardness, density and the like of the plate. These data are used to construct a digital twin of the sheet to be processed, i.e. by mathematical modeling and simulation techniques, a digital model corresponding to the actual sheet is generated in a computer. For example, the thickness, hardness and density of the sheet are measured and these data are then used to construct a digital twin. Based on the digital twins, borehole path construction is performed, and a plurality of candidate borehole paths are generated by simulating a borehole process on a digital model. These candidate paths take into account the physical properties of the sheet material to ensure feasibility and effectiveness in the actual machining process. Inputting the plate texture feature data and the plate defect position into a drilling path planning model, and performing forward propagation processing to obtain a plurality of feature vectors. These feature vectors capture the texture features of the sheet surface and any possible defect information, providing detailed input features for subsequent path planning. And inputting the plurality of feature vectors into a target layer of the drilling path planning model, and performing track coordinate mapping to obtain a plurality of path track coordinate sets. This step maps the feature vectors to actual path coordinates through model learning, forming potential borehole paths. And finally, carrying out path data combination according to the plurality of candidate drilling paths and the plurality of drilling paths to be processed to obtain a plurality of target drilling paths. The process comprehensively considers physical properties, texture characteristics and defect information to generate a plurality of optimized and highly-adaptive target drilling paths, and provides a comprehensive path selection scheme for intelligent drilling.
In a specific embodiment, the process of executing the step S104 may specifically include the following steps:
(1) Inputting a plurality of target drilling paths into a numerical control module of a lathe device, and planning drilling time of the plurality of target drilling paths through the numerical control module based on preset target operation duration to obtain target drilling time;
(2) And controlling the lathe device to perform drilling operation on the plate to be processed based on the target drilling time, and collecting real-time image data of the plate to be processed in the drilling operation process in real time.
Specifically, after a plurality of target drilling paths are acquired, the system inputs the paths into a numerical control module of the lathe device. Based on the preset target operation duration, the numerical control module utilizes an advanced algorithm to plan drilling time for a plurality of target drilling paths so as to ensure that all drilling tasks are completed within a specified time. This process takes into account factors such as the length of each path, the difficulty, and the performance of the lathe apparatus. And (3) obtaining the target drilling time of each target drilling path by the system through the drilling time planning of the numerical control module. For example, for a simpler path, the system may allocate a shorter time, while for a complex path, more time may be allocated to ensure high quality processing. Based on the obtained target drilling time, the system controls the lathe device to drill the plate to be processed. The system collects real-time image data of the sheet material to be processed in real time throughout the drilling process, which helps to monitor any anomalies in the process, such as material damage, misalignment, etc. The closed-loop control mechanism of the intelligent drilling system enables the system to flexibly adjust parameters such as drilling paths, processing speeds and the like in actual operation so as to adapt to different plate characteristics and process requirements, and therefore efficient and accurate plate processing is achieved.
In a specific embodiment, the process of executing the step S105 may specifically include the following steps:
(1) Calibrating the drilling position of the real-time image data to obtain drilling position data, wherein the drilling position data comprises a plurality of drilling position coordinates;
(2) Based on a plurality of drilling position coordinates, performing image segmentation on the real-time image data to obtain segmented image data corresponding to each drilling position coordinate;
(3) Respectively extracting drilling depths of the segmented image data corresponding to each drilling position coordinate to obtain drilling depths corresponding to each drilling position coordinate, and merging the drilling depths corresponding to each drilling position coordinate into drilling depth data;
(4) Collecting a drill bit parameter set of a lathe in real time, wherein the drill bit parameter set comprises: drill speed and feed rate.
Specifically, the real-time image data is calibrated in drilling position, and a plurality of drilling position coordinates are identified and obtained through an image processing technology. This can be achieved by calculating the position of a specific mark point or edge in the image, ensuring that each borehole position is accurately located. For example, computer vision algorithms may be used to detect holes or other specific marks in the image. Based on the obtained drilling position coordinates, image segmentation is performed, real-time image data are divided into a plurality of areas, and each area corresponds to one drilling position coordinate. This may be achieved by segmentation algorithms such as watershed algorithms or convolutional neural networks, ensuring that each borehole location has corresponding segmented image data. And then, carrying out drilling depth extraction on the segmented image data corresponding to each drilling position coordinate. Through image processing and analysis, the borehole depth of each segmented image can be calculated. For example, by measuring the distance from the drill bit to the surface of the sheet in the image, borehole depth information for each borehole location may be obtained. Meanwhile, a drill bit parameter set of the lathe is acquired in real time, wherein the drill bit parameter set comprises parameters such as a drill bit rotating speed, a feed speed and the like. These parameters are critical to subsequent borehole control as they affect the speed and accuracy of the borehole. And finally, merging the drilling depth data corresponding to each drilling position coordinate into a drilling depth data set. This step ensures that the depth information for each borehole position is combined with the actual image data and lathe parameters to provide an accurate reference for subsequent borehole control. This integrated process ensures accurate real-time monitoring and control of each drilling location for efficient sheet processing.
In a specific embodiment, the process of executing step S106 may specifically include the following steps:
(1) Respectively carrying out drilling time mapping on the drilling depth corresponding to each drilling position coordinate to obtain the drilling time corresponding to each drilling position coordinate;
(2) Respectively carrying out standard drilling depth matching on the drilling time corresponding to each drilling position coordinate to obtain standard drilling depth data corresponding to each drilling position coordinate;
(3) Carrying out drilling deviation analysis on the drilling depth corresponding to each drilling position coordinate and the standard drilling depth data corresponding to each drilling position coordinate to obtain drilling deviation data;
(4) And carrying out control parameter analysis on the lathe according to the drilling deviation data to obtain target control parameters, and controlling the lathe to carry out drilling control on the plate to be processed according to the target control parameters.
It should be noted that, the drilling time mapping is performed on the real-time drilling depth corresponding to each drilling position coordinate, and the expected drilling time corresponding to each drilling position coordinate is obtained by using the previously planned target drilling time. This mapping takes into account the depth of each borehole and the performance of the lathe apparatus to ensure that each borehole task is completed within a specified time. And then, respectively carrying out standard drilling depth matching on the expected drilling time corresponding to each drilling position coordinate, and obtaining standard drilling depth data corresponding to each drilling position coordinate. This step is achieved by mapping the expected drilling time back to the standard depth, thereby matching the actual drilling depth, and thus obtaining standard depth data. Next, a borehole deviation analysis is performed on the actual borehole depth corresponding to each borehole position coordinate and the standard borehole depth data. And comparing the difference between the actual depth and the standard depth, and calculating the drilling deviation data of each drilling position. For example, if the actual depth is shallow, a positive deviation is detected and vice versa. And finally, carrying out control parameter analysis on the lathe according to the obtained drilling deviation data to obtain target control parameters. By analysing the deviation data, it is possible to determine control parameters that need to be adjusted, such as adjusting the bit speed or feed speed, to improve the accuracy of the machining. And the obtained target control parameters are synthesized to control the lathe in real time, so that the expected depth of each drilling position can be ensured in the whole plate processing process, and the drilling control with high quality and high efficiency is realized.
The embodiment of the invention also provides a plate drilling device based on artificial intelligence, as shown in fig. 3, which specifically comprises:
a frame 301, which is provided with a processing table for placing a plate to be processed;
the scanning mechanism 302 is arranged on the frame, and the acquisition end of the scanning mechanism is arranged opposite to the processing table and is used for scanning images of the plate to be processed to obtain image scanning data of the plate to be processed;
the scanning mechanism can adopt an industrial camera or a binocular camera;
the analysis mechanism 303 is arranged on the rack, is electrically connected with the scanning mechanism, and is used for analyzing the plate attribute information of the plate to be processed according to the image scanning data to obtain the plate attribute information of the plate to be processed;
the planning mechanism 304 is arranged on the frame, is electrically connected with the analysis mechanism, and is used for inputting the plate attribute information into a preset drilling path planning model to carry out drilling path planning, so as to obtain a plurality of target drilling paths;
the operation mechanism 305 is arranged on the frame, is electrically connected with the planning mechanism, and is used for carrying out drilling operation on the plate to be processed through a plurality of target drilling paths and collecting real-time image data of the plate to be processed in the drilling operation process in real time;
The collection mechanism 306 is disposed on the frame and electrically connected with the operation mechanism, and is configured to perform drilling parameter analysis on the real-time image data, obtain drilling depth data and drilling position data corresponding to the real-time image data, and collect a drill bit parameter set of the lathe in real time, where the drill bit parameter set includes: drill rotational speed and feed rate;
the acquisition mechanism can also adopt an industrial camera or a binocular camera;
the control mechanism 307 is arranged on the frame, is electrically connected with the acquisition mechanism and the operation mechanism respectively, and is used for carrying out drilling deviation analysis on the plate to be processed according to the drilling depth data and the drilling position data to obtain drilling deviation data, carrying out control parameter analysis on the operation mechanism according to the drilling deviation data to obtain target control parameters, and controlling the operation mechanism to carry out drilling control on the plate to be processed according to the target control parameters.
The analysis mechanism, the planning mechanism and the control mechanism are integrated on the PLC;
the working mechanism 305 comprises a transverse moving component 3051, a longitudinal moving component 3052 and a drilling component 3053, wherein the transverse moving component is connected with the longitudinal moving component and used for driving the longitudinal moving component and the drilling component to move transversely synchronously, the longitudinal moving component is used for driving the drilling component to move longitudinally, the drilling component comprises a rotating motor and a drill bit, the rotating motor is connected with the longitudinal moving component, and the drill bit is arranged at the driving end of the rotating motor.
The transverse moving assembly comprises a screw rod and a nut and is used for controlling the drill bit assembly to transversely move, the longitudinal moving assembly comprises a gear and a rack and is used for controlling the drill bit assembly to longitudinally move, and the drill bit comprises a rotary motor and a drill bit.
Through the cooperative work of the modules, various attribute information of the plate to be processed, including physical properties, texture features and possible defect positions, can be accurately obtained through image scanning and analysis. This helps to build a comprehensive board property model. And generating a plurality of target drilling paths according to the plate attribute information by using a preset drilling path planning model. Such a plan takes into account the multifaceted nature of the sheet material, making the drilling path more adaptable to different sheet material types and process requirements. By acquiring real-time image data in the drilling operation process in real time, drilling depth data, drilling position data and a drill bit parameter set can be timely obtained. This provides the necessary information for real-time monitoring and control, ensuring accuracy and consistency in the drilling process. Drilling parameter analysis obtains drilling depth data and drilling position data through processing the real-time image data. By combining the drill bit parameter set, the influence of drilling parameters can be analyzed, a foundation is provided for subsequent drilling deviation analysis, and parameter optimization is performed when needed. The analysis of the drilling deviation data provides feedback of actual machining conditions, and the control parameter analysis of the lathe can be performed according to the data. By adjusting the control parameters in real time, the deviation in the drilling process can be automatically corrected, and the accuracy and quality of drilling are improved. The whole scheme combines the technologies of image processing, deep learning, real-time control and the like, so that the drilling process is more intelligent. This helps to improve production efficiency, reduce material waste, and ensure consistency and quality stability of production. The above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the scope of the claims.
Claims (9)
1. An artificial intelligence based plate drilling method, which is characterized by comprising the following steps:
carrying out image scanning on a plate to be processed to obtain image scanning data of the plate to be processed;
performing plate attribute information analysis on the plate to be processed according to the image scanning data to obtain plate attribute information of the plate to be processed;
inputting the plate attribute information into a preset drilling path planning model to carry out drilling path planning to obtain a plurality of target drilling paths;
controlling a preset lathe device to drill the plate to be processed through a plurality of target drilling paths, and collecting real-time image data of the plate to be processed in the drilling process in real time;
and carrying out drilling parameter analysis on the real-time image data to obtain drilling depth data and drilling position data corresponding to the real-time image data, and collecting a drill bit parameter set of the lathe in real time, wherein the drill bit parameter set comprises: drill rotational speed and feed rate;
and carrying out drilling deviation analysis on the plate to be processed according to the drilling depth data and the drilling position data to obtain drilling deviation data, carrying out control parameter analysis on the lathe according to the drilling deviation data to obtain target control parameters, and controlling the lathe to carry out drilling control on the plate to be processed according to the target control parameters.
2. The artificial intelligence based panel drilling method according to claim 1, wherein the step of performing image scanning on the panel to be processed to obtain image scanning data of the panel to be processed comprises the steps of:
performing plate corner positioning on the plate to be processed to obtain corner position data of the plate to be processed;
extracting plate attribute of the plate to be processed to obtain plate attribute data of the plate to be processed;
and calibrating image acquisition parameters of the plate to be processed based on the plate attribute data, wherein the image acquisition parameters comprise: image exposure time, light source intensity, and sampling frequency;
carrying out image acquisition area analysis on the plate to be processed through the angular point position data to obtain an image acquisition area of the plate to be processed;
and carrying out image scanning on the plate to be processed based on the image acquisition area and the image acquisition parameters to obtain image scanning data of the plate to be processed.
3. The artificial intelligence based board drilling method according to claim 1, wherein the board attribute information analysis is performed on the board to be processed according to the image scanning data to obtain board attribute information of the board to be processed, and the board attribute information step includes:
Performing image enhancement processing on the image scanning data to obtain enhanced image data corresponding to the image scanning data;
extracting the texture features of the plate from the enhanced image data to obtain plate texture feature data;
performing defect detection on the enhanced image data to obtain a plate defect position corresponding to the enhanced image data;
and merging the plate defect positions and the plate texture feature data into the plate attribute information of the plate to be processed.
4. The artificial intelligence based board drilling method according to claim 3, wherein the step of inputting the board attribute information into a preset drilling path planning model to perform drilling path planning to obtain a plurality of target drilling paths comprises the steps of:
obtaining physical property data of the plate to be processed, wherein the physical property data comprises: plate thickness data, plate hardness data and plate density data;
constructing a digital twin body of the plate to be processed according to the physical property data, and constructing drilling paths of the digital twin body to obtain a plurality of candidate drilling paths;
inputting the plate texture feature data and the plate defect positions into a plurality of initial layers of the drilling path planning model to sequentially perform forward propagation processing to obtain a plurality of feature vectors;
Inputting a plurality of feature vectors into a target layer of the drilling path planning model to carry out track coordinate mapping to obtain a plurality of path track coordinate sets;
generating a plurality of drilling paths to be processed according to a plurality of path track coordinate sets;
and carrying out path data combination on the candidate drilling paths and the drilling paths to be processed to obtain a plurality of target drilling paths.
5. The artificial intelligence based board drilling method according to claim 1, wherein the step of controlling a preset lathe means to perform a drilling operation on the board to be processed through a plurality of the target drilling paths and collecting real-time image data of the board to be processed during the drilling operation in real time comprises:
inputting a plurality of target drilling paths into a numerical control module of the lathe device, and planning drilling time of the plurality of target drilling paths through the numerical control module based on preset target operation duration to obtain target drilling time;
and controlling the lathe device to drill the plate to be processed based on the target drilling time, and collecting real-time image data of the plate to be processed in the drilling process in real time.
6. The artificial intelligence based panel drilling method according to claim 1, wherein the drilling parameter analysis is performed on the real-time image data to obtain drilling depth data and drilling position data corresponding to the real-time image data, and a drill parameter set of the lathe is collected in real time, wherein the drill parameter set includes: drill bit rotational speed and feed rate steps, including:
calibrating the drilling position of the real-time image data to obtain drilling position data, wherein the drilling position data comprises a plurality of drilling position coordinates;
based on a plurality of drilling position coordinates, performing image segmentation on the real-time image data to obtain segmented image data corresponding to each drilling position coordinate;
respectively extracting drilling depths from the segmented image data corresponding to each drilling position coordinate to obtain drilling depths corresponding to each drilling position coordinate, and merging the drilling depths corresponding to each drilling position coordinate into drilling depth data;
collecting a drill bit parameter set of the lathe in real time, wherein the drill bit parameter set comprises: drill speed and feed rate.
7. The artificial intelligence based panel drilling method according to claim 6, wherein the drilling deviation analysis is performed on the panel to be processed according to the drilling depth data and the drilling position data to obtain drilling deviation data, the control parameter analysis is performed on the lathe according to the drilling deviation data to obtain a target control parameter, and the lathe is controlled to perform the drilling control step on the panel to be processed according to the target control parameter, and the method comprises the following steps:
respectively carrying out drilling time mapping on the drilling depth corresponding to each drilling position coordinate to obtain the drilling time corresponding to each drilling position coordinate;
respectively carrying out standard drilling depth matching on the drilling time corresponding to each drilling position coordinate to obtain standard drilling depth data corresponding to each drilling position coordinate;
carrying out drilling deviation analysis on the drilling depth corresponding to each drilling position coordinate and the standard drilling depth data corresponding to each drilling position coordinate to obtain drilling deviation data;
and carrying out control parameter analysis on the lathe according to the drilling deviation data to obtain target control parameters, and controlling the lathe to carry out drilling control on the plate to be processed according to the target control parameters.
8. An artificial intelligence based panel drilling apparatus for performing the artificial intelligence based panel drilling method according to any one of claims 1 to 7, comprising:
the machine frame is provided with a processing table which is used for placing a plate to be processed;
the scanning mechanism is arranged on the frame, and the acquisition end of the scanning mechanism is arranged opposite to the processing table and is used for scanning images of the plate to be processed to obtain image scanning data of the plate to be processed;
the analysis mechanism is arranged on the frame, is electrically connected with the scanning mechanism and is used for analyzing the plate attribute information of the plate to be processed according to the image scanning data to obtain the plate attribute information of the plate to be processed;
the planning mechanism is arranged on the frame and is electrically connected with the analysis mechanism, and is used for inputting the plate attribute information into a preset drilling path planning model to carry out drilling path planning so as to obtain a plurality of target drilling paths;
the operation mechanism is arranged on the frame, is electrically connected with the planning mechanism, and is used for carrying out drilling operation on the plate to be processed through a plurality of target drilling paths and collecting real-time image data of the plate to be processed in the drilling operation process in real time;
The acquisition mechanism is arranged on the frame and is electrically connected with the operation mechanism, and is used for carrying out drilling parameter analysis on the real-time image data to obtain drilling depth data and drilling position data corresponding to the real-time image data, and acquiring a drill bit parameter set of the lathe in real time, wherein the drill bit parameter set comprises: drill rotational speed and feed rate;
the control mechanism is arranged on the frame, is electrically connected with the acquisition mechanism and the operation mechanism respectively, and is used for carrying out drilling deviation analysis on the plate to be processed according to the drilling depth data and the drilling position data to obtain drilling deviation data, carrying out control parameter analysis on the operation mechanism according to the drilling deviation data to obtain target control parameters, and controlling the operation mechanism to carry out drilling control on the plate to be processed according to the target control parameters.
9. The artificial intelligence based panel drilling device of claim 8, wherein the working mechanism comprises a transverse moving assembly, a longitudinal moving assembly and a drilling assembly, the transverse moving assembly is connected with the longitudinal moving assembly and used for driving the longitudinal moving assembly and the drilling assembly to move transversely synchronously, the longitudinal moving assembly is used for driving the drilling assembly to move longitudinally, the drilling assembly comprises a rotary motor and a drill bit, the rotary motor is connected with the longitudinal moving assembly, and the drill bit is arranged at the driving end of the rotary motor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311843587.8A CN117483838B (en) | 2023-12-29 | 2023-12-29 | Board drilling method and device based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311843587.8A CN117483838B (en) | 2023-12-29 | 2023-12-29 | Board drilling method and device based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117483838A true CN117483838A (en) | 2024-02-02 |
| CN117483838B CN117483838B (en) | 2024-03-12 |
Family
ID=89681477
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311843587.8A Active CN117483838B (en) | 2023-12-29 | 2023-12-29 | Board drilling method and device based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117483838B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102756429A (en) * | 2012-07-31 | 2012-10-31 | 成都川美新技术开发有限公司 | Ceramic-substrate-based high-precision automatic drilling machine |
| CN108972573A (en) * | 2018-06-12 | 2018-12-11 | 浙江大学 | A kind of industrial robot automation wheel hub polishing system and method based on characteristics of image identification |
| CN110125455A (en) * | 2019-05-27 | 2019-08-16 | 清华大学 | A method of for optimizing drill bit pose in robotic drill |
| CN111299815A (en) * | 2020-02-13 | 2020-06-19 | 西安交通大学 | Visual detection and laser cutting trajectory planning method for low-gray rubber pad |
| CN112025099A (en) * | 2020-08-10 | 2020-12-04 | 武汉智能装备工业技术研究院有限公司 | Intelligent laser deburring system and laser deburring method |
| CN114630202A (en) * | 2022-02-28 | 2022-06-14 | 中国土木工程集团有限公司 | Drilling real-time monitoring system and monitoring method based on 5G communication technology |
| CN114851209A (en) * | 2022-06-21 | 2022-08-05 | 上海大学 | Industrial robot working path planning optimization method and system based on vision |
| CN114918455A (en) * | 2022-06-21 | 2022-08-19 | 国营芜湖机械厂 | Automatic hole making equipment and method for surface of large aviation component |
| US20220412205A1 (en) * | 2021-06-29 | 2022-12-29 | Landmark Graphics Corporation | Casing wear and pipe defect determination using digital images |
| CN115582644A (en) * | 2022-10-19 | 2023-01-10 | 中国铁建重工集团股份有限公司 | Welding method and welding system |
-
2023
- 2023-12-29 CN CN202311843587.8A patent/CN117483838B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102756429A (en) * | 2012-07-31 | 2012-10-31 | 成都川美新技术开发有限公司 | Ceramic-substrate-based high-precision automatic drilling machine |
| CN108972573A (en) * | 2018-06-12 | 2018-12-11 | 浙江大学 | A kind of industrial robot automation wheel hub polishing system and method based on characteristics of image identification |
| CN110125455A (en) * | 2019-05-27 | 2019-08-16 | 清华大学 | A method of for optimizing drill bit pose in robotic drill |
| CN111299815A (en) * | 2020-02-13 | 2020-06-19 | 西安交通大学 | Visual detection and laser cutting trajectory planning method for low-gray rubber pad |
| CN112025099A (en) * | 2020-08-10 | 2020-12-04 | 武汉智能装备工业技术研究院有限公司 | Intelligent laser deburring system and laser deburring method |
| US20220412205A1 (en) * | 2021-06-29 | 2022-12-29 | Landmark Graphics Corporation | Casing wear and pipe defect determination using digital images |
| CN114630202A (en) * | 2022-02-28 | 2022-06-14 | 中国土木工程集团有限公司 | Drilling real-time monitoring system and monitoring method based on 5G communication technology |
| CN114851209A (en) * | 2022-06-21 | 2022-08-05 | 上海大学 | Industrial robot working path planning optimization method and system based on vision |
| CN114918455A (en) * | 2022-06-21 | 2022-08-19 | 国营芜湖机械厂 | Automatic hole making equipment and method for surface of large aviation component |
| CN115582644A (en) * | 2022-10-19 | 2023-01-10 | 中国铁建重工集团股份有限公司 | Welding method and welding system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117483838B (en) | 2024-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106881462B (en) | A kind of on-line checking and optimization system for selective laser fusing forming defects | |
| CN110253019A (en) | A kind of quality monitoring and control method of selective laser fusing | |
| CN110728667A (en) | Automatic and accurate cutter wear loss measuring method based on gray level image probability | |
| CN206415478U (en) | A kind of Sepecial holes type spinneret plate perforating press | |
| CN110443791B (en) | Workpiece detection method and device based on deep learning network | |
| CN107900190B (en) | A kind of Sepecial holes type spinneret plate perforating press and the positioning and processing method based on the perforating press | |
| CN109693140B (en) | Intelligent flexible production line and working method thereof | |
| CN108489394A (en) | A kind of large-scale sheet metal works almost T-stable automatic detection device and method | |
| CN115993804B (en) | Cutter parameter adjustment method based on numerical control machine tool and related equipment | |
| CN108389184A (en) | A kind of workpiece drilling number detection method based on machine vision | |
| CN117483838B (en) | Board drilling method and device based on artificial intelligence | |
| CN111524154A (en) | Image-based tunnel segment automatic segmentation method | |
| CN115546125A (en) | Method for error detection and track deviation correction of additive manufacturing cladding layer based on point cloud information | |
| CN115265371A (en) | Steel plate online real-time measurement method based on line structured light | |
| CN208042989U (en) | A kind of large-scale sheet metal works almost T-stable automatic detection device | |
| CN116321757B (en) | Precise control method and system for printed circuit board processing | |
| CN117506931A (en) | Groove cutting path planning and correcting equipment and method based on machine vision | |
| CN106780655B (en) | Manual decision method and system for automatic welding path | |
| CN116109633B (en) | Window detection method and device for bearing retainer | |
| US11422542B2 (en) | Workpiece surface quality issues detection | |
| CN115625317B (en) | Surface water wave optimization processing method and system for die casting regulation and control | |
| CN113790675A (en) | Method for detecting furnace building result based on itinerant scanning of single laser line profiler | |
| CN113469988A (en) | Defect identification method | |
| CN118134062B (en) | Numerical control machine tool casting quality tracking system | |
| CN115582840B (en) | Method and system for calculating sorting and grabbing pose of borderless steel plate workpiece and sorting method |
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 |