CN117911501A - High-precision positioning method for metal processing drilling - Google Patents
High-precision positioning method for metal processing drilling Download PDFInfo
- Publication number
- CN117911501A CN117911501A CN202410319328.3A CN202410319328A CN117911501A CN 117911501 A CN117911501 A CN 117911501A CN 202410319328 A CN202410319328 A CN 202410319328A CN 117911501 A CN117911501 A CN 117911501A
- Authority
- CN
- China
- Prior art keywords
- time
- metal
- image
- pipeline
- offset
- 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
- 239000002184 metal Substances 0.000 title claims abstract description 97
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012545 processing Methods 0.000 title claims abstract description 37
- 238000005553 drilling Methods 0.000 title claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims abstract description 21
- 238000011156 evaluation Methods 0.000 claims abstract description 15
- 230000005856 abnormality Effects 0.000 claims abstract description 8
- 125000004122 cyclic group Chemical group 0.000 claims abstract description 6
- 238000003062 neural network model Methods 0.000 claims abstract description 6
- 230000004044 response Effects 0.000 claims abstract description 5
- 230000011218 segmentation Effects 0.000 claims description 25
- 238000003754 machining Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000005555 metalworking Methods 0.000 claims description 2
- 239000000463 material Substances 0.000 abstract description 4
- 239000002699 waste material Substances 0.000 abstract description 4
- 238000012797 qualification Methods 0.000 abstract 1
- 230000006870 function Effects 0.000 description 9
- 238000005520 cutting process Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The application relates to the field of image processing, in particular to a high-precision positioning method for metal processing drilling, which comprises the following steps: acquiring a shooting image of a metal pipeline, converting the shooting image into a gray level image, and performing image processing to obtain a pipeline area image; calculating the offset of the metal pipeline; collecting vibration amplitude of a metal pipeline, and calculating vibration abnormality evaluation; training a preset cyclic neural network model to obtain a time sequence prediction model; and obtaining a vibration amplitude sequence, inputting the vibration amplitude sequence into a time sequence prediction model, generating a predicted offset of the metal pipeline at the next moment, and controlling the machine to stop processing in response to the predicted offset being greater than a preset offset threshold. According to the application, the metal part deflection caused by vibration is accurately positioned in the processing process, the deflection of the next moment is predicted, and the processing is stopped when the deflection is greater than the preset deflection threshold value, so that the qualification rate of finished products is improved, and the waste of metal part materials is reduced.
Description
Technical Field
The application relates to the field of image processing, in particular to a high-precision positioning method for metal processing drilling.
Background
During the processing of metal parts, corresponding software and a control system can be used for controlling the drill bit to move at a certain speed and in a certain direction, and through drilling holes with different depths on the metal parts, the drill bit can move for slotting or engraving on a metal plate or a metal pipeline.
When the drill bit is used for processing the metal piece, vibration can be generated, the clamp for clamping the metal piece is unstable under the influence of the vibration, and the phenomenon of deviation of the notch can occur, so that the processed metal piece is unqualified. At present, the detection of the metal piece is only carried out after the cutting is finished, and the detection cannot be carried out in the processing process, so that the waste of the metal piece material is caused.
Disclosure of Invention
In order to accurately position the metal part deflection caused by vibration in the machining process, the deflection of the next moment is predicted, machining is stopped when the deflection is overlarge, the yield of finished products is improved, and the waste of metal part materials is reduced.
A metal processing drilling high-precision positioning method comprises the following steps: acquiring a shooting image of a metal pipeline, converting the shooting image into a gray level image, and performing image processing to obtain a pipeline area image; calculating the offset of the metal pipeline; collecting vibration amplitude of a metal pipeline, and calculating vibration abnormality evaluation, wherein a calculation formula is as follows:，/> Wherein/> Represents the/>Vibration abnormality evaluation at time,/>For/>Evaluation parameter of time/>Represents the/>The amplitude of the vibration at the moment in time,Representing the number of vibration amplitudes in the history process,/>Represents the/>Vibration amplitude at time,/>，/>Representing the time during the history of the process,/>The moment is the real-time moment of the current machining process, will/>Normalizing to obtain a weight;
Training a preset cyclic neural network model to obtain a time sequence prediction model, wherein the loss function expression in the training process is as follows:
，/> representing a loss function,/> Weight representing time 1-Weight representing time 2/(Represents the/>Weight of time,/>For the true offset of the metal pipeline at time 1,/>For the true offset of the metal pipeline at time 2,/>Is a metal pipeline of the first/>Real offset of time,/>For the predicted offset of the metal pipeline at time 1,/>For the predicted offset of the metal pipeline at time 2,/>For/>Predicting offset of the metal pipeline at the moment; and obtaining a vibration amplitude sequence, inputting the vibration amplitude sequence into a time sequence prediction model, generating a predicted offset of the metal pipeline at the next moment, and controlling the machine to stop processing in response to the predicted offset being greater than a preset offset threshold.
Optionally, calculating the offset of the metal pipe includes the steps of: constructing a reference vector and a real-time vector in the processing process, wherein the starting points of the reference vector and the real-time vector are the midpoints of the projection of the drill bit on the pipeline area image, and the end points are the central positions of the pipeline area; calculating the offset, wherein the calculation formula is as follows:
Wherein/> Represents the/>Offset of metal pipe at time,/>Represents the/>Real-time vector of time,/>Representing the reference vector.
Optionally, collecting a photographed image of the metal pipeline, converting the photographed image into a gray-scale image, and performing image processing to obtain a pipeline region image, including the steps of: training a preset semantic segmentation model to obtain a segmentation model; acquiring a shooting video of a metal pipeline overlooking angle, and acquiring a shooting image of each frame in the shooting video; and converting the shot image into a gray image, and obtaining a pipeline region image in the gray image through a segmentation model.
Optionally, training a preset semantic segmentation model to obtain a segmentation model, including: and respectively marking the pipeline region and the background region in the sample image, putting the sample image into a semantic segmentation network model for training, and completing training to obtain a segmentation model when the training times reach the preset times.
Optionally, the acquisition frequency of the vibration amplitude of the metal pipe is the same as the number of frames of the photographed image.
Optionally, collecting the vibration amplitude of the metal pipe includes: and installing a vibration accelerator on a clamp for clamping the metal pipeline to be processed so as to acquire the vibration amplitude.
The application has the following technical effects:
The reason why the image processing mode is not adopted in the prior art for positioning the metal cutting error is as follows: the metal scraps during cutting can interfere with the observation of the cutting position, so that the cutting precision of the cutting position cannot be directly observed. And combining a neural network, predicting the offset at the next moment, and stopping processing when the offset is larger than a preset offset threshold value, so that the yield of finished products is improved, and the waste of metal piece materials is reduced.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present application will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, several embodiments of the application are illustrated by way of example and not by way of limitation, and like or corresponding reference numerals refer to like or corresponding parts.
FIG. 1 is a flow chart of a method for locating a metal working borehole with high accuracy according to an embodiment of the present application.
Fig. 2 is a flowchart of a method of step S1 in a high precision positioning method for metal processing drilling according to an embodiment of the present application.
Fig. 3 is a flowchart of a method of step S2 in a high precision positioning method for metal processing drilling according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be understood that when the terms "first," "second," and the like are used in the claims, the specification and the drawings of the present application, they are used merely for distinguishing between different objects and not for describing a particular sequential order. The terms "comprises" and "comprising" when used in the specification and claims of the present application are taken to specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The application scene of the application is as follows: in the operation process of the drill bit on the metal pipeline, the metal pipeline can vibrate, the continuous vibration in long-term operation can lead to loosening of the clamp, the position of the metal pipeline changes, and the position of the metal pipeline can irregularly move in the actual production process because the change is caused by vibration.
Therefore, the vibration data in the drilling process need to be monitored in a variable amplitude, and when the variable amplitude of the vibration is large, the position of the metal pipeline is possibly deviated to a large extent, so that the drilling position is deviated, and the machining precision is reduced.
The embodiment of the application discloses a high-precision positioning method for metal processing drilling, which comprises the following steps of S1-S5 with reference to FIG. 1:
S1: and acquiring a shooting image of the metal pipeline, converting the shooting image into a gray level image, and performing image processing to obtain a pipeline region image.
Referring to fig. 2, step S1 includes steps S10 to S12, specifically as follows:
s10: training a preset semantic segmentation model to obtain a segmentation model.
And respectively marking the pipeline region and the background region in the sample image, putting the sample image into a semantic segmentation network model for training, and completing training to obtain a segmentation model when the training times reach the preset times.
The sample image is a historical metal pipeline shooting image, the pipeline area is marked as 1, the other areas are marked as 0, and the model is trained in the semantic segmentation network model. The semantic segmentation network model is a deep learning model for image semantic segmentation, and is generally constructed by a convolutional neural network. Exemplary are U-Net.
After the number of training times reaches the preset number of times, stopping training, and in one embodiment, stopping training when the preset number of times is 1000 or the loss function in the training process is equal to 0.01, so as to obtain a segmentation model, wherein in one embodiment, the loss function in the semantic segmentation network model training adopts a mean square error loss function.
S11: and acquiring a shooting video of the overlooking angle of the metal pipeline, and acquiring a shooting image of each frame in the shooting video.
And arranging a camera above the metal pipeline, acquiring a shot video of a overlooking angle in the processing process, extracting and storing a plurality of frames of shot images, wherein the extracted frame number is 60 frames by way of example.
S12: and converting the shot image into a gray image, and obtaining a pipeline region image in the gray image through a segmentation model.
In one embodiment, taking a machining process as an example, a gray level image of a previous frame when a drill bit contacts a metal pipeline is acquired, and a metal pipeline segmentation network is put into the metal pipeline to obtain a pipeline region image in a marked image as a standard region image of the machining process. And after the processing is started, acquiring a real-time gray level image in the processing process, and obtaining a pipeline region image in the real-time gray level image.
S2: and calculating the offset of the metal pipeline.
Referring to fig. 3, step S2 includes steps S20 to S21, specifically as follows:
S20: and constructing a reference vector and a real-time vector in the processing process, wherein the starting points of the reference vector and the real-time vector are the midpoints of the projection of the drill bit on the pipeline area image, and the ending points are the central positions of the pipeline area.
The midpoint position of the projection of the marking drill bit on the pipeline area image is used as a starting point, the pipeline area image is a rectangular image, the intersection point of the diagonal lines of the pipeline area is used as a central position, and the central position is used as an end point. In the standard region image, a vector formed by connecting the start point and the end point is a reference vector. In the pipeline region image of the real-time gray scale image, the vector connecting the start point and the end point is a real-time vector.
S21: an offset is calculated.
The calculation formula of the offset is: Wherein/> Represents the/>Offset of metal pipe at time,/>Represents the/>Real-time vector of time,/>Representing the reference vector.
S3: and (5) collecting the vibration amplitude of the metal pipeline, and calculating the vibration abnormality evaluation.
And installing a vibration accelerator on a clamp for clamping the metal pipeline to be processed so as to acquire the vibration amplitude. The acquisition frequency of the vibration amplitude of the metal pipeline is the same as the frame number of the shot image. Illustratively, the number of frames is 60 frames and the acquisition frequency is 60 times per second.
And acquiring real-time vibration data of the metal pipeline in the processing process, and recording the real-time vibration data as a vibration real-time data set. Calculating an abnormal vibration evaluation of the metal pipeline, wherein the higher the abnormal vibration evaluation is, the more serious the abnormal vibration appears at the moment, and the calculation formula of the abnormal vibration evaluation is as follows:
，/> Wherein/> Represents the/>Vibration abnormality evaluation at time,/>Is the firstEvaluation parameter of time/>Represents the/>Vibration amplitude at time,/>Representing the number of vibration amplitudes in the history process, i.e. the history process has/>Moment,/>Represents the/>Vibration amplitude at time,/>，/>Representing the time during the history of the process,/>The moment is the real-time moment of the current machining process, will/>And normalizing to obtain the weight.
Each moment corresponds to a vibration anomaly evaluation and a metal pipe offset. When the vibration amplitude at the current time suddenly increases, the vibration abnormality evaluation increases.
S4: training a preset cyclic neural network model to obtain a time sequence prediction model.
The recurrent neural network (Recurrent Neural Network, RNN) is a neural network suitable for handling problems involving time series data. By modeling the data in the time dimension, the long-term dependency relationship in the sequence data can be effectively captured. And training the cyclic neural network model to obtain a time sequence prediction model, and realizing the effect of predicting the change trend of future data by modeling the historical data.
And taking the vibration amplitude sequence as a training set, taking the offset of the corresponding metal pipeline as an output set, putting the output set into a cyclic neural network model, and completing training in response to the trend of a loss function to 0 or the training times reaching 100 times.
The loss function expression of the training process is:
，/> representing a loss function,/> Weight representing time 1-Weight representing time 2/(Represents the/>Weight of time,/>For the true offset of the metal pipeline at time 1,/>For the true offset of the metal pipeline at time 2,/>Is a metal pipeline of the first/>Real offset of time,/>For the predicted offset of the metal pipeline at time 1,/>For the predicted offset of the metal pipeline at time 2,/>For/>Predicted offset of the metal pipe at the moment. The loss function is used to measure the degree of deviation of the predicted value from the actual value.
S5: and obtaining a vibration amplitude sequence, inputting the vibration amplitude sequence into a time sequence prediction model, generating a predicted offset of the metal pipeline at the next moment, and controlling the machine to stop processing in response to the predicted offset being greater than a preset offset threshold.
Illustratively, the offset threshold is set to 10.
And obtaining the predicted offset of the metal pipeline at the next moment according to the acquired vibration amplitude sequence, and controlling the machine to stop processing when the predicted offset is larger than a preset offset threshold value, which indicates that the metal pipeline at the next moment has larger offset and has larger influence on the processing precision.
While various embodiments of the present application have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Many modifications, changes, and substitutions will now occur to those skilled in the art without departing from the spirit and scope of the application. It should be understood that various alternatives to the embodiments of the application described herein may be employed in practicing the application.
The above embodiments are not intended to limit the scope of the present application, so: all equivalent changes in structure, shape and principle of the application should be covered in the scope of protection of the application.
Claims (6)
1. The high-precision positioning method for the metal processing drilling hole is characterized by comprising the following steps of:
Acquiring a shooting image of a metal pipeline, converting the shooting image into a gray level image, and performing image processing to obtain a pipeline area image;
Calculating the offset of the metal pipeline;
collecting vibration amplitude of a metal pipeline, and calculating vibration abnormality evaluation, wherein a calculation formula is as follows:
，/> Wherein/> Represents the/>Vibration abnormality evaluation at time,/>For/>Evaluation parameter of time/>Represents the/>Vibration amplitude at time,/>Representing the number of vibration amplitudes in the history process,/>Represents the/>Vibration amplitude at time,/>，/>Representing the time during the history of the process,/>The moment is the real-time moment of the current machining process, pair/>Normalizing to obtain a weight;
Training a preset cyclic neural network model to obtain a time sequence prediction model, wherein the loss function expression in the training process is as follows:
，/> representing a loss function,/> Weight representing time 1-Weight representing time 2/(Represents the/>Weight of time,/>For the true offset of the metal pipeline at time 1,/>For the true offset of the metal pipeline at time 2,/>Is a metal pipeline of the first/>Real offset of time,/>For the predicted offset of the metal pipeline at time 1,/>For the predicted offset of the metal pipeline at time 2,/>For/>Predicting offset of the metal pipeline at the moment;
And obtaining a vibration amplitude sequence, inputting the vibration amplitude sequence into a time sequence prediction model, generating a predicted offset of the metal pipeline at the next moment, and controlling the machine to stop processing in response to the predicted offset being greater than a preset offset threshold.
2. The method of high precision positioning of a metal tooling borehole of claim 1, wherein calculating the offset of the metal pipe comprises the steps of:
Constructing a reference vector and a real-time vector in the processing process, wherein the starting points of the reference vector and the real-time vector are the midpoints of the projection of the drill bit on the pipeline area image, and the end points are the central positions of the pipeline area;
calculating the offset, wherein the calculation formula is as follows: Wherein/> Represents the/>Offset of metal pipe at time,/>Represents the/>Real-time vector of time,/>Representing the reference vector.
3. The method for locating a metal pipe in high precision according to claim 1 or 2, wherein capturing a photographed image of the metal pipe, converting the photographed image into a gray-scale image and performing image processing to obtain a pipe region image, comprises the steps of:
Training a preset semantic segmentation model to obtain a segmentation model;
Acquiring a shooting video of a metal pipeline overlooking angle, and acquiring a shooting image of each frame in the shooting video;
and converting the shot image into a gray image, and obtaining a pipeline region image in the gray image through a segmentation model.
4. A method of locating a metal working borehole with high accuracy as set forth in claim 3, wherein training a predetermined semantic segmentation model to obtain a segmentation model comprises:
And respectively marking the pipeline region and the background region in the sample image, putting the sample image into a semantic segmentation network model for training, and completing training to obtain a segmentation model when the training times reach the preset times.
5. A method of locating a metal tooling borehole with high accuracy according to claim 3, wherein the frequency of acquisition of the vibration amplitude of the metal pipe is the same as the number of frames of the captured image.
6. The method of high precision positioning of a metal tooling borehole of claim 1, wherein collecting vibration amplitude of a metal pipe comprises: and installing a vibration accelerator on a clamp for clamping the metal pipeline to be processed so as to acquire the vibration amplitude.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410319328.3A CN117911501B (en) | 2024-03-20 | High-precision positioning method for metal processing drilling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410319328.3A CN117911501B (en) | 2024-03-20 | High-precision positioning method for metal processing drilling |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117911501A true CN117911501A (en) | 2024-04-19 |
| CN117911501B CN117911501B (en) | 2024-06-04 |
Family
ID=
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180101943A1 (en) * | 2016-10-06 | 2018-04-12 | General Electric Technology Gmbh | System, method and apparatus for locating the position of a component for use in a manufacturing operation |
| US20180150058A1 (en) * | 2016-11-25 | 2018-05-31 | Glowforge Inc. | Fabrication with image tracing |
| CN108154187A (en) * | 2018-01-04 | 2018-06-12 | 湘潭大学 | A kind of deep hole based on vibration signal, which is pecked, bores processing quality detection method |
| CN109784424A (en) * | 2019-03-26 | 2019-05-21 | 腾讯科技（深圳）有限公司 | A kind of method of image classification model training, the method and device of image procossing |
| US20200065957A1 (en) * | 2018-05-31 | 2020-02-27 | Rdi Technologies, Inc. | Monitoring of objects based on frequency spectrum of motion and frequency filtering |
| CN111275667A (en) * | 2020-01-13 | 2020-06-12 | 武汉科技大学 | Machining error detection method and device and machining method |
| CN115082403A (en) * | 2022-06-22 | 2022-09-20 | 南京北新智能科技有限公司 | Belt deviation detection algorithm based on semantic segmentation |
| WO2022252558A1 (en) * | 2021-05-31 | 2022-12-08 | 上海商汤智能科技有限公司 | Methods for neural network training and image processing, apparatus, device and storage medium |
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180101943A1 (en) * | 2016-10-06 | 2018-04-12 | General Electric Technology Gmbh | System, method and apparatus for locating the position of a component for use in a manufacturing operation |
| CN109791399A (en) * | 2016-10-06 | 2019-05-21 | 通用电器技术有限公司 | Position for positioning component is to be used for the system used in manufacturing operation, method and apparatus |
| US20180150058A1 (en) * | 2016-11-25 | 2018-05-31 | Glowforge Inc. | Fabrication with image tracing |
| CN108154187A (en) * | 2018-01-04 | 2018-06-12 | 湘潭大学 | A kind of deep hole based on vibration signal, which is pecked, bores processing quality detection method |
| US20200065957A1 (en) * | 2018-05-31 | 2020-02-27 | Rdi Technologies, Inc. | Monitoring of objects based on frequency spectrum of motion and frequency filtering |
| CN109784424A (en) * | 2019-03-26 | 2019-05-21 | 腾讯科技（深圳）有限公司 | A kind of method of image classification model training, the method and device of image procossing |
| CN111275667A (en) * | 2020-01-13 | 2020-06-12 | 武汉科技大学 | Machining error detection method and device and machining method |
| WO2022252558A1 (en) * | 2021-05-31 | 2022-12-08 | 上海商汤智能科技有限公司 | Methods for neural network training and image processing, apparatus, device and storage medium |
| CN115082403A (en) * | 2022-06-22 | 2022-09-20 | 南京北新智能科技有限公司 | Belt deviation detection algorithm based on semantic segmentation |
Non-Patent Citations (2)
| Title |
|---|
| 王冠君;: "数控机床加工操作中的误差研究", 科学技术创新, no. 29, 25 September 2020 (2020-09-25) * |
| 赵凡;: "深孔加工过程中振刀现象对零件加工的影响与对策研究", 决策探索(中), no. 09, 18 September 2020 (2020-09-18) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105929799B (en) | Operator's quality control method and operator's qualitative control device | |
| CN110879583B (en) | Intelligent assembly workshop quality prediction and control system and method based on digital twins | |
| CN116009480B (en) | Fault monitoring method, device and equipment of numerical control machine tool and storage medium | |
| CN114355953B (en) | High-precision control method and system of multi-axis servo system based on machine vision | |
| CN106441851A (en) | Method for detecting fatigue life of mechanical part | |
| CN116840243B (en) | Correction method and system for machine vision object recognition | |
| CN113534741A (en) | Control method and system for milling thin-walled workpiece | |
| CN117911501B (en) | High-precision positioning method for metal processing drilling | |
| CN115880296A (en) | Machine vision-based prefabricated part quality detection method and device | |
| CN116618878A (en) | Pre-welding process parameter determination method, welding quality online prediction method, device and storage medium | |
| CN117911501A (en) | High-precision positioning method for metal processing drilling | |
| CN116703254B (en) | Production information management system for mechanical parts of die | |
| CN112734858B (en) | Binocular calibration precision online detection method and device | |
| CN112262027B (en) | Abnormality determination device and abnormality determination method | |
| CN117182928B (en) | Intelligent grabbing robot hand synchronous control system | |
| CN114326593A (en) | Tool life prediction system and method | |
| CN1782672A (en) | Method and apparatus for improved fault detection in power generation equipment | |
| CN116228766B (en) | Intelligent regulation and control method and system for plasma processing equipment | |
| CN114377874B (en) | Flow monitoring method and device for spraying equipment and readable storage medium | |
| CN114266286A (en) | Online detection method and device for welding process information | |
| JP2018140471A (en) | Control device and machine learning device | |
| CN117392771B (en) | Monitoring alarm system and method for sand core placement robot | |
| CN115409944B (en) | Three-dimensional scene rendering and data correction system based on low-code digital twin | |
| CN117291996B (en) | Motion control vision calibration system based on image data processing | |
| CN117124136B (en) | Machine tool correction method, system, device and medium |
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 |