CN116846162B - Method and device for controlling stator lamination of submersible motor, electronic equipment and storage medium - Google Patents
Method and device for controlling stator lamination of submersible motor, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116846162B CN116846162B CN202310866921.5A CN202310866921A CN116846162B CN 116846162 B CN116846162 B CN 116846162B CN 202310866921 A CN202310866921 A CN 202310866921A CN 116846162 B CN116846162 B CN 116846162B
- Authority
- CN
- China
- Prior art keywords
- image information
- determining
- unqualified
- punched
- proportion
- 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.)
- Active
Links
- 238000003475 lamination Methods 0.000 title claims abstract description 68
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000003860 storage Methods 0.000 title claims abstract description 27
- 238000004080 punching Methods 0.000 claims abstract description 121
- 238000003062 neural network model Methods 0.000 claims abstract description 33
- 238000013135 deep learning Methods 0.000 claims abstract description 17
- 238000004590 computer program Methods 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 13
- 238000010030 laminating Methods 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 9
- 230000000694 effects Effects 0.000 abstract description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 9
- 230000007547 defect Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241001310793 Podium Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02K—DYNAMO-ELECTRIC MACHINES
- H02K15/00—Methods or apparatus specially adapted for manufacturing, assembling, maintaining or repairing of dynamo-electric machines
- H02K15/02—Methods or apparatus specially adapted for manufacturing, assembling, maintaining or repairing of dynamo-electric machines of stator or rotor bodies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V10/225—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on a marking or identifier characterising the area
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Manufacturing & Machinery (AREA)
- Power Engineering (AREA)
- Manufacture Of Motors, Generators (AREA)
Abstract
The application relates to a method, a device, electronic equipment and a storage medium for controlling lamination of a stator of an oil-submerged motor, which belong to the technical field of manufacturing of stators of motors, and acquire first image information with a punching sheet before lamination; identifying the punching sheet in the first image information according to the deep-learning neural network model, and determining unqualified punching sheets; acquiring position information of unqualified punched pieces, and generating unqualified punched piece removal information based on the position information; judging whether the number of the unqualified punched pieces detected in a preset time period reaches a preset value; if yes, generating prompt information for suspending lamination of the punching sheet. The application has the effect of improving the quality of the stator.
Description
Technical Field
The application relates to the technical field of motor manufacturing control, in particular to a method and a device for controlling stator lamination of a submersible motor, electronic equipment and a storage medium.
Background
The submersible motor is lifting equipment used in the later period of petroleum exploitation and mainly comprises a motor head, a stator, a rotor, a shaft, a spline, a connecting seat and other parts. The stator lamination processing is an important step in the manufacturing process of the submersible motor.
And during stator lamination, stacking a stack of stator punching sheets, compacting, and detecting after each section of prepressing is finished, and then stacking the next stack.
The quality of the stator punching sheet directly influences the performance of the motor, and if the punching sheet has the defects of folding sheets, tooth breakage, cracks and the like, the stator can be deformed or the lamination is not in place after lamination, so that the electromagnetic performance of the motor can not meet the design requirement.
Disclosure of Invention
In order to improve stator quality, the application provides a method and a device for controlling stator lamination of an oil-immersed motor, electronic equipment and a storage medium.
In a first aspect, the application provides a method for controlling stator lamination of a submersible motor, which adopts the following technical scheme:
before lamination, acquiring first image information with a punching sheet;
identifying the punching sheet in the first image information according to the deep-learning neural network model, and determining unqualified punching sheets;
acquiring position information of unqualified punched pieces, and generating unqualified punched piece removal information based on the position information;
judging whether the number of the unqualified punched pieces detected in a preset time period reaches a preset value;
if yes, generating prompt information for suspending lamination of the punching sheet.
Through adopting above-mentioned technical scheme, electronic equipment acquires the first image information that has the punching before the lamination, discerns image information according to neural network model, detects unqualified punching, and then generates unqualified punching according to the position information of unqualified punching and get rid of information, in time clears away unqualified punching to if detect a plurality of unqualified punching in the preset time quantum, then generate the suggestion information that pauses the punching and fold, remind the workman to overhaul, avoid causing bigger loss, guarantee the stator quality of folding.
Further, the acquiring the first image information with the punching sheet includes:
acquiring original image information at intervals of preset time;
identifying the original image information according to the film stamping identification neural network model, and determining the position information of the film stamping in the original image information;
Dividing the original image information according to the position information of the punching sheet, and determining a plurality of first image information, wherein each first image information comprises one punching sheet.
By adopting the technical scheme, the electronic equipment acquires the original image information at intervals of preset time, the position information of the punching sheet is determined by using the punching sheet identification neural network model, and then the original image information is segmented to obtain the first image information of the small blocks, so that the punching sheet can be identified according to the first image information conveniently.
Further, after determining the failed punched pieces, the method further comprises:
determining unqualified punched sheets as punched sheets to be rechecked;
acquiring a plurality of second image information with the punched pieces to be rechecked;
Judging whether each piece of second image information is consistent with the first image information or not; if the two types of the stamping sheets are consistent, determining that the stamping sheets to be rechecked are unqualified;
if the second image information is inconsistent, inputting any one of the second image information into a deep learning neural network model, and determining whether the punched sheet in the second image information is qualified or not;
If the punching sheet is not qualified, determining that the punching sheet to be rechecked is not qualified;
if so, determining whether the punched sheets in the second image information are qualified, respectively calculating the proportion of the qualified number and the unqualified number to the total number of the second image information, and determining the rechecking result of the punched sheets to be rechecked according to the proportion.
By adopting the technical scheme, after the electronic equipment determines the unqualified punched pieces, the electronic equipment enters a rechecking process to acquire a plurality of pieces of second image information with the punched pieces to be rechecked, and if the second image information is consistent with the first image information, the first analysis can be deduced to be correct; if the images are inconsistent, identifying the punched sheets in the second image information according to the neural network model of deep learning, detecting again, if the detection results are also unqualified, deducing that the primary analysis is correct, and if the detection results are inconsistent, further analysis is needed, so that more accurate punched sheet detection results are obtained.
Further, the obtaining the plurality of second image information with the to-be-rechecked punching sheet includes:
acquiring initial time of determining to-be-rechecked punching sheets as unqualified;
Acquiring the position and the transmission speed of a punching sheet to be rechecked in the first image information;
acquiring third image information at intervals of preset time from the initial time;
Determining a search area corresponding to the position in the third image information;
determining an intercepting area with the same size as the first image information in the searching area according to the transmission speed of the punching sheet to be checked and the moment of acquiring the third image information;
And determining a truncated area in the third image information as the second image information.
By adopting the technical scheme, the electronic equipment firstly determines the searching area in the third image information according to the position of the punching sheet to be checked in the image information, determines the intercepting area in the searching area according to the conveying speed of the punching sheet and the moment of acquiring the third image information, and the intercepting area is the unqualified punching sheet, so that the second image information with the punching sheet to be checked is quickly obtained.
Further, the determining the rechecking result of the to-be-rechecked punching sheet according to the proportion includes:
Determining the proportion of the qualified quantity to the total number of the third image information as a first proportion;
determining the proportion of the unqualified quantity to the total number of the third image information as a second proportion;
judging whether the difference value between the first proportion and the second proportion is smaller than a first preset value or not; if yes, generating error information; otherwise, determining the result corresponding to the highest proportion as a rechecking result of the punching sheet to be rechecked.
By adopting the technical scheme, when the detection results are different, the electronic equipment determines a unique rechecking result according to the qualified and unqualified proportions, and analyzes according to the actual situation to obtain a more accurate analysis result.
Further, the method further comprises:
acquiring the heights of a preset number of punched sheets after lamination under a first pressure;
Judging whether the height is smaller than or equal to a preset height; if yes, finishing the laminating step;
otherwise, judging whether the difference between the height and the preset height reaches a second preset value;
If the preset value is reached, determining a proportion in a preset table according to the difference value, multiplying the first pressure by the proportion, and determining the updated first pressure;
If the preset value is not reached, the first pressure is not changed;
Repeatedly obtaining the heights of a preset number of punched sheets after lamination under the first pressure;
And judging whether the height is smaller than a preset height or not until the laminating step is completed.
Through adopting above-mentioned technical scheme, electronic equipment acquires the height of punching after the first time fold and press, when the height does not reach the requirement, carries out fold again, in order to prevent that the power is too big, electronic equipment reduces first pressure according to corresponding proportion according to the difference of height and preset height, makes pressure and punching fold and press the process together carry out adaptive adjustment, improves stator processingquality to when the height is close to preset height, no longer reduces first pressure, reduces the calculated amount.
Further, if the ratio corresponding to the difference value does not exist in the preset table, determining the ratio in the preset table according to the difference value includes:
Generating a graph based on the proportion corresponding to each difference value in a preset table;
And determining a proportion corresponding to the difference value in the graph.
By adopting the technical scheme, the electronic equipment adopts a plurality of data to generate a graph as a reference, so that the corresponding proportion of various differences is conveniently determined, and the data storage quantity is reduced.
In a second aspect, the application provides a submersible motor stator lamination control device, which adopts the following technical scheme:
The first image information acquisition module is used for acquiring first image information with a punching sheet before lamination;
The detection module is used for identifying the punching sheet in the first image information according to the deep-learning neural network model and determining unqualified punching sheets;
the unqualified punching sheet removing module is used for acquiring position information of unqualified punching sheets and generating unqualified punching sheet removing information based on the position information;
the judging module is used for judging whether the number of the unqualified punched pieces detected in the preset time period reaches a preset value;
And the prompt information generation module is used for generating prompt information for suspending lamination of the punching sheet when the judgment module judges that the punching sheet is positive.
Through adopting above-mentioned technical scheme, first image information acquisition module acquires the first image information that has the towards the piece before folding, detection module discernment image information according to neural network model, detect unqualified towards the piece, and then unqualified towards the piece and get rid of the module and get rid of the unqualified towards piece removal information according to the position information of unqualified towards ticket generation, in time clear up unqualified towards the piece, guarantee the folding quality, and judge that the module if detect a plurality of unqualified towards the piece in preset time quantum, prompt message generation module generates the prompt message that pauses towards the piece folding, remind the workman to overhaul, avoid causing bigger loss.
In a third aspect, the present application provides an electronic device, which adopts the following technical scheme:
An electronic device, comprising:
at least one processor;
A memory;
At least one computer program, wherein the at least one computer program is stored in the memory and configured to be executed by the at least one processor, the at least one computer program configured to: performing the method of any of the first aspects.
Through adopting above-mentioned technical scheme, the computer program in the treater execution memory, acquire the first image information that has the punching before folding presses, discernment image information according to neural network model, detect unqualified punching, and then according to the position information generation unqualified punching removal information of unqualified punching, in time clear unqualified punching, guarantee the laminating quality, and if detect a plurality of unqualified punching in the preset time quantum, then generate the suggestion information that pauses punching and fold and press, remind the workman to overhaul, avoid causing bigger loss.
In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical scheme:
A computer readable storage medium storing a computer program capable of being loaded by a processor and executing the method according to any one of the first aspects.
By adopting the technical scheme, the processor executes the computer program in the computer readable storage medium, acquires the first image information with the punching sheet before lamination, identifies the image information according to the neural network model, detects the unqualified punching sheet, further generates unqualified punching sheet removal information according to the position information of the unqualified punching sheet, eliminates the unqualified punching sheet in time, ensures lamination quality, and generates prompt information for suspending lamination of the punching sheet if a plurality of unqualified punching sheets are detected in a preset time period, reminds workers to overhaul, and avoids causing larger loss.
In summary, the present application includes at least one of the following beneficial technical effects:
1. Acquiring first image information with punched sheets before lamination, identifying the image information according to a neural network model, detecting unqualified punched sheets, further generating unqualified punched sheet removal information according to unqualified punched sheet position information, timely removing the unqualified punched sheets, ensuring lamination quality, and generating prompt information for suspending lamination of the punched sheets if a plurality of unqualified punched sheets are detected within a preset time period, reminding workers of overhauling, and avoiding larger loss;
2. The electronic equipment determines unqualified punched sheets or acquires a plurality of pieces of first image information with unqualified punched sheets, and if the first image information is consistent with the image information, the first analysis can be deduced to be correct; if the images are inconsistent, identifying the punched sheets in the first image information according to the neural network model of deep learning, detecting again, if the detection results are also unqualified, deducing that the primary analysis is correct, and if the detection results are inconsistent, further analysis is needed, so that more accurate punched sheet detection results are obtained;
3. The electronic equipment acquires the height of the punching sheet after primary lamination, and performs lamination again when the height does not meet the requirement, so as to prevent excessive force, and the electronic equipment reduces the first pressure according to the corresponding proportion according to the difference between the height and the preset height, so that the pressure and the lamination process are adaptively adjusted together, and the stator processing quality is improved.
Drawings
Fig. 1 is a schematic flow chart of a method for controlling stator lamination of a submersible motor according to an embodiment of the application.
Fig. 2 is a schematic flow chart of determining second image information in third image information in an embodiment of the application.
Fig. 3 is a block diagram of a stator lamination control device of an oil submersible motor according to an embodiment of the application.
Fig. 4 is a block diagram of an electronic device in an embodiment of the application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present 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.
In addition, the term "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In this context, unless otherwise specified, the term "/" generally indicates that the associated object is an "or" relationship.
The embodiment of the application discloses a stator lamination control method of an oil-immersed motor. The cloud computing system is executed by the electronic equipment, and the electronic equipment can be a server or a terminal device, wherein the server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server for providing cloud computing services. The terminal device may be, but is not limited to, a smart phone, a tablet computer, a desktop computer, etc. Referring to fig. 1, the flow (step S101 to step S105) is as follows:
Step S101: before lamination, first image information with a punched sheet is acquired.
Specifically, a conveyor belt is arranged in front of a lamination device used for laminating the stator, a camera is arranged above the conveyor belt, and the camera shoots a punched piece every preset time to obtain an image with the punched piece. The punched sheets are regularly arranged on the conveyor belt according to the requirement of the laminating device, so that more than one punched sheet may exist in the shot image, and in order to facilitate rapid detection of the punched sheets, the step S101 includes (steps S11 to S13):
step S11: and acquiring original image information at preset time intervals.
Specifically, under the condition that the punching sheet is conveyed at a constant speed, the electronic equipment acquires the original image information shot by the camera.
Step S12: and identifying the original image information according to the film identification neural network model, and determining the position information of the film in the original image information.
Specifically, the electronic equipment establishes a sample database and a neural network model, performs deep learning training on the neural network model according to the sample database, obtains a deep learning film stamping identification neural network model, and can identify film stamping in image information.
The electronic equipment inputs the original image information into the punching identification neural network model, outputs the image information with the mark, marks the outer edge of the punching, and the marked position represents the position information of the punching.
Step S13: dividing the original image information according to the position information of the punching sheet, and determining a plurality of first image information, wherein each first image information comprises one punching sheet.
Specifically, the electronic device generates a rectangular frame outside each mark, so that the punching sheet is positioned in the rectangular frame, and then the electronic device divides the original image information according to the range of the rectangular frame to obtain a plurality of first image information.
Step S102: and identifying the punching sheet in the first image information according to the deep-learning neural network model, and determining the unqualified punching sheet.
Specifically, the failure of the punched sheet may occur after the punching process, and causes of the failure of the punched sheet include a folded sheet, broken teeth, cracks, and the like. The electronic equipment establishes a sample library, wherein the sample library comprises sample images of a plurality of qualified punched sheets and unqualified punched sheets. The electronic equipment inputs the sample image into the neural network model, and trains by using a deep learning method to obtain the neural network model capable of identifying whether the punching sheet is qualified or not.
Step S103: and acquiring position information of the unqualified punched piece, and generating unqualified punched piece removal information based on the position information.
Specifically, a manipulator for picking up unqualified punched sheets is arranged at the downstream of the camera and in front of the laminating device along the conveying direction of the punched sheets, and the electronic equipment determines the position information when the unqualified punched sheets move to the lower part of the manipulator according to the position of the unqualified punched sheets in the image information, so that the manipulator can select the unqualified punched sheets.
Step S104: judging whether the number of the unqualified punched pieces detected in a preset time period reaches a preset value; if yes, step S105 is executed: and generating prompt information for suspending lamination of the punching sheet.
Specifically, the preset time and the preset value may be set according to the processing speed. For example, the press produces 4 punches simultaneously per second, then the preset time is 2 seconds and the preset value may be 4.
Therefore, when the number of unqualified punched sheets reaches a preset value in a preset time period, the abnormal punching process or the abnormal existence of the current sheet is indicated, and the prompting information for suspending lamination of the punched sheets is generated to prompt a user to carry out shutdown inspection.
In another possible implementation, the film in the image information is affected by the current illumination or environment, and may cause erroneous judgment. In order to reduce the possibility of erroneous judgment, referring to fig. 2, the above method further includes (steps S21 to S22):
step S21: and acquiring a plurality of second image information with the punched pieces to be checked. Specifically, the method comprises the following steps (step Sa to step Sf):
Step Sa: and acquiring the initial time of the to-be-rechecked punching sheet determined to be unqualified.
Step Sb: and acquiring the position and the conveying speed of the punching sheet to be checked in the first image information.
Specifically, the electronic device establishes a coordinate system in the first image information, takes the transmission direction as the x axis, and further determines the area where the unqualified punched sheet is located in the coordinate system.
Step Sc: and acquiring third image information at intervals of preset time from the initial time.
Step Sd: a search area corresponding to the position is determined in the third image information.
Specifically, at least one auxiliary camera is arranged downstream of the conveyor belt conveying the punched sheet and in front of the laminating device, and the auxiliary camera shoots the punched sheet again, namely third image information. The pictures shot by the auxiliary cameras are connected. The punching sheet is transmitted for a distance every preset time, so that the electronic equipment acquires the third image information from the auxiliary camera every preset time, and when the preset time is set, the current unqualified punching sheet can be shot in each third image information according to the transmission speed.
Further, the search area is the area where the unqualified punched sheet is located in the same longitudinal section, for example, if the coordinate section of the second image information is (0, 0) - (50, 50), and the position of the unqualified punched sheet is located in the rectangular area where (10, 0) - (20, 10), the search area is the rectangular area where (0, 0) - (50, 10).
Step Se: and determining an intercepting area with the same size as the first image information in the searching area according to the transmission speed of the punching sheet to be checked and the moment of acquiring the third image information.
Specifically, the electronic device determines a difference between the time when the third image information is acquired and the initial time, calculates a time difference, calculates a distance of movement of the punching sheet according to a product of the time difference and the conveying speed, further determines a position of the punching sheet in the third image after the corresponding distance of movement of the punching sheet according to the scale of the third image information, and further determines a intercepting area in the searching area.
Step Sf: and determining a truncated area in the third image information as the second image information.
Specifically, the size of the interception area is the same as that of the first image information, and the moved punched sheet to be rechecked is located in the interception area. Thus determining the second image information.
Step S22: judging whether each piece of second image information is consistent with the first image information or not; if they are consistent, step S23 is executed: determining that the punched sheet to be rechecked is unqualified; if there is an inconsistency, step S24 is performed.
Specifically, if the second image information is consistent with the first image information, it can be inferred that the primary detection result is correct and basically correct, and the failure of the punched sheet to be rechecked can be determined; if there is an inconsistency, it is necessary to further check whether the punched sheet is truly unacceptable.
Step S24: inputting any second image information into a deep learning neural network model, and determining whether the punching sheet in the second image information is qualified; if not, executing step S23; if yes, step S25 is executed: determining whether the punched sheets in each piece of second image information are qualified, respectively calculating the proportion of the qualified number and the unqualified number to the total number of the pieces of second image information, and determining the rechecking result of the punched sheets to be rechecked according to the proportion.
Specifically, when the punched piece in the second image is inconsistent with the punched piece in the first image information, the electronic equipment judges whether the punched piece in the second image information is qualified according to the neural network model, and if the judgment result is still unqualified, the fact that the punched piece has defects can be determined; if the judgment result is qualified, further analysis is needed to determine whether the judgment result is qualified.
Step S25 includes the following procedures (step S251 to step S255) when determining the review result of the punched sheet to be reviewed according to the ratio:
Step S251: and determining the proportion of the qualified quantity to the total number of the third image information as a first proportion.
Step S252: and determining the proportion of the unqualified quantity to the total number of the third image information as a second proportion.
Step S253: judging whether the difference value between the first proportion and the second proportion is smaller than a first preset value; if yes, step S254 is executed: generating error information; otherwise, step S255 is executed: and determining the result corresponding to the highest proportion as a rechecking result of the punched sheet to be rechecked.
Specifically, if the punched sheet has a defect, the second proportion is far greater than the first proportion in the result of the neural network model analysis; if the punched sheet does not have defects, the first proportion is far greater than the second proportion; if the difference between the first ratio and the second ratio is smaller than the first preset value, that is, the first ratio and the second ratio are similar, it is difficult to analyze whether the punched sheet has a defect, and the reason of the result is not known, so that an error message is generated to prompt the user.
Further, in the process of producing the submersible motor stator, the punching sheets are required to be stacked together and then laminated, in the lamination process, if the applied pressure is too large, the stator and rotor pressing rings deform, the tooth parts are too large to open, and if the applied pressure is too small, the punching sheets cannot be pressed in place, so that the electromagnetic performance of the motor cannot meet the design requirement. In order to adjust the applied pressure in time and improve the lamination effect of the stator, the method further comprises the following steps of (S31-S37):
Step S31: and acquiring the heights of the laminated punching sheets with the preset number under the first pressure.
Specifically, the first pressure is set according to actual needs, a ranging sensor is arranged above the stacking position of the punching sheet on the stacking device, the ranging sensor measures the distance from the top surface of the punching sheet, and then the distance from the stacking bottom surface of the punching sheet is set through a preset ranging sensor, and the difference between the two distances is the height after stacking.
Step S32: judging whether the height is smaller than or equal to a preset height; if yes, step S33 is executed: finishing the laminating step; otherwise, step S34 is performed.
Specifically, the preset height is the standard height of the stator of the submersible motor, the electronic equipment compares the height after lamination with the preset height, when the height is smaller than or equal to the preset height, lamination reaches the standard, and in order to reach the standard, lamination is generally needed for many times.
Step S34: judging whether the difference between the height and the preset height reaches a second preset value or not; if the second preset value is reached, step S35 is executed: determining a proportion in a preset table according to the difference value, multiplying the first pressure by the proportion, and determining updated first pressure; if the preset value is not reached, step S36 is executed: the first pressure is not altered.
Specifically, the preset value is set according to actual needs, when the difference between the height and the preset height reaches the second preset value, the difference between the height of the laminated front punching sheet and the preset height is larger, so that the first pressure can be reduced according to the proportion, and the proportion is determined according to the difference. In general, the smaller the difference, the smaller the corresponding ratio, i.e., the smaller the difference, the less pressure is used for lamination.
However, if the difference value does not reach the second preset value, the height is closer to the preset height, the electronic device does not need to change the first pressure, and the lamination is repeated.
Step S37: step S31 and step S32 are repeatedly performed until the lamination step is completed.
In order to better perform the above method, the embodiment of the present application further provides a submersible motor stator lamination control device, referring to fig. 3, the submersible motor stator lamination control device 200 includes:
A first image information obtaining module 201, configured to obtain first image information with a punched sheet before lamination;
the detection module 202 is configured to identify a punched piece in the first image information according to the neural network model of deep learning, and determine an unqualified punched piece;
The unqualified punching sheet removing module 203 is configured to obtain position information of an unqualified punching sheet, and generate unqualified punching sheet removing information based on the position information;
a judging module 204, configured to judge whether the number of unqualified punched pieces detected in the preset time period reaches a preset value;
the prompt information generating module 205 is configured to generate a prompt message for suspending lamination of the punched sheet when the judgment module 204 judges that the lamination is yes.
Further, the first image information acquisition module 201 is specifically configured to:
acquiring original image information at intervals of preset time;
identifying original image information according to the film stamping identification neural network model, and determining the position information of the film stamping in the original image information;
Dividing the original image information according to the position information of the punching sheet, and determining a plurality of first image information, wherein each first image information comprises one punching sheet.
Further, the submersible motor stator lamination control device 200 further includes:
The first image information acquisition module is used for acquiring a plurality of second image information with the punching sheet to be checked;
the second judging module is used for judging whether each piece of second image information is consistent with the first image information or not;
the first rechecking module is used for determining that the punched sheet to be rechecked is unqualified when the second judging module judges that the punched sheets are consistent;
The analysis module is used for inputting any one piece of second image information into the deep learning neural network model when the second judgment module judges that the second image information is inconsistent, and determining whether the punched piece in the second image information is qualified or not;
the second rechecking module is used for determining that the punched sheet to be rechecked is unqualified when the analysis module determines that the punched sheet is unqualified;
And the third rechecking module is used for determining whether the punched sheets in each piece of the second image information are qualified or not when the analysis module determines that the punched sheets are qualified, respectively calculating the proportion of the qualified number and the unqualified number to the total number of the second image information, and determining rechecking results of the punched sheets to be rechecked according to the proportion.
Further, the first image information acquisition module is specifically configured to:
acquiring initial time of determining to-be-rechecked punching sheets as unqualified;
Acquiring the position and the transmission speed of a punching sheet to be rechecked in the first image information;
acquiring third image information at intervals of preset time from the initial time;
determining a search area corresponding to the position in the third image information;
determining an intercepting area with the same size as the first image information in the searching area according to the transmission speed of the punching sheet to be checked and the moment of acquiring the third image information;
And determining a truncated area in the third image information as the second image information.
Further, when determining the rechecking result of the to-be-rechecked punching sheet according to the proportion, the third rechecking module is specifically configured to:
Determining the proportion of the qualified quantity to the total number of the third image information as a first proportion;
determining the proportion of the unqualified quantity to the total number of the third image information as a second proportion;
Judging whether the difference value between the first proportion and the second proportion is smaller than a first preset value; if yes, generating error information; otherwise, determining the result corresponding to the highest proportion as a rechecking result of the punching sheet to be rechecked.
Further, the submersible motor stator lamination control device 200 further includes:
The height acquisition module is used for acquiring the heights of the laminated punching sheets with the preset number under the first pressure;
the first height judging module is used for judging whether the height is smaller than or equal to a preset height;
ending the lamination module, wherein the lamination module is used for completing the lamination step when the height judgment module judges that the height judgment module is positive;
the second height judging module is used for judging whether the difference value between the height and the preset height reaches a second preset value or not when the height judging module judges that the difference value is not;
The first pressure updating module is used for determining a proportion in a preset table according to the difference value when the second height judging module judges that the preset value is reached, multiplying the first pressure by the proportion, and determining the updated first pressure; if the preset value is not reached, the first pressure is not changed;
the circulation module is used for repeatedly obtaining the heights of the punched sheets with preset numbers after being overlapped under the first pressure; judging whether the height is smaller than the preset height or not until the laminating step is completed.
Further, when the first pressure updating module determines the ratio in the preset table according to the difference value, the first pressure updating module is specifically configured to:
Generating a graph based on the proportion corresponding to each difference value in a preset table;
The scale corresponding to the difference is determined in the graph.
The various modifications and specific examples of the method in the foregoing embodiment are equally applicable to the submersible motor stator lamination control device in this embodiment, and those skilled in the art will clearly know the implementation method of the submersible motor stator lamination control device in this embodiment through the foregoing detailed description of the submersible motor stator lamination control method, so the description will not be repeated here for brevity.
To better implement the above method, an embodiment of the present application provides an electronic device, referring to fig. 4, an electronic device 300 includes: a processor 301, a memory 303, and a display screen 305. Wherein the memory 303 and the display 305 are both coupled to the processor 301, such as via a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that, in practical applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 is not limited to the embodiment of the present application.
The Processor 301 may be a CPU (Central Processing Unit ), general purpose Processor, DSP (DIGITAL SIGNAL Processor, data signal Processor), ASIC (Application SPECIFIC INTEGRATED Circuit), FPGA (Field Programmable GATE ARRAY ) or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. Processor 301 may also be a combination that implements computing functionality, e.g., comprising one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
Bus 302 may include a path to transfer information between the components. Bus 302 may be a PCI (PERIPHERAL COMPONENT INTERCONNECT, peripheral component interconnect standard) bus or an EISA (Extended Industry Standard Architecture ) bus, or the like. Bus 302 may be divided into an address bus, a data bus, a control bus, and the like.
The Memory 303 may be, but is not limited to, a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory ) or other type of dynamic storage device that can store information and instructions, an EEPROM (ELECTRICALLY ERASABLE PROGRAMMABLE READ ONLY MEMORY ), a CD-ROM (Compact Disc Read Only Memory, compact disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The memory 303 is used for storing application program codes for executing the inventive arrangements and is controlled to be executed by the processor 301. The processor 301 is configured to execute the application code stored in the memory 303 to implement what is shown in the foregoing method embodiments.
The electronic device 300 shown in fig. 4 is only an example and should not be construed as limiting the functionality and scope of use of embodiments of the application.
The embodiment of the application also provides a computer readable storage medium, which stores a computer program, when the program is executed by a processor, the method for controlling the lamination of the stator of the submersible motor provided by the embodiment is realized, the processor executes the computer program in the computer readable storage medium, the processor acquires first image information with the punched sheet before lamination, identifies the image information according to a neural network model, detects the unqualified punched sheet, further generates unqualified punched sheet removing information according to the position information of the unqualified punched sheet, timely clears the unqualified punched sheet, ensures lamination quality, and generates prompt information for suspending lamination of the punched sheet to remind workers of maintenance and avoid causing larger loss if a plurality of unqualified punched sheets are detected within a preset time period.
In this embodiment, the computer-readable storage medium may be a tangible device that holds and stores instructions for use by the instruction execution device. The computer readable storage medium may be, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination of the preceding. In particular, the computer readable storage medium may be a portable computer disk, hard disk, USB flash disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), podium random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital Versatile Disk (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical coding device, and any combination of the foregoing.
The computer program in this embodiment contains program code for executing all the methods described above, and the program code may include instructions corresponding to the execution of the steps of the methods provided in the embodiments described above. The computer program may be downloaded from a computer readable storage medium to the respective computing/processing device or to an external computer or external storage device via a network (e.g., the internet, a local area network, a wide area network, and/or a wireless network). The computer program may execute entirely on the user's computer and as a stand-alone software package.
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.
In addition, it is to be understood that relational terms such as first and second are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Claims (8)
1. The method for controlling the lamination of the stator of the submersible motor is characterized by comprising the following steps of:
before lamination, acquiring first image information with a punching sheet;
identifying the punching sheet in the first image information according to the deep-learning neural network model, and determining unqualified punching sheets;
acquiring position information of unqualified punched pieces, and generating unqualified punched piece removal information based on the position information;
judging whether the number of the unqualified punched pieces detected in a preset time period reaches a preset value;
if yes, generating prompt information for suspending lamination of the punching sheet;
after determining the failed punched pieces, the method further comprises:
determining unqualified punched sheets as punched sheets to be rechecked;
acquiring a plurality of second image information with the punched pieces to be rechecked;
Judging whether each piece of second image information is consistent with the first image information or not; if the two types of the stamping sheets are consistent, determining that the stamping sheets to be rechecked are unqualified;
if the second image information is inconsistent, inputting any one of the second image information into a deep learning neural network model, and determining whether the punched sheet in the second image information is qualified or not;
If the punching sheet is not qualified, determining that the punching sheet to be rechecked is not qualified;
If yes, determining whether the punched sheets in each piece of second image information are qualified, respectively calculating the proportion of the qualified number and the unqualified number to the total number of the pieces of second image information, and determining the rechecking result of the punched sheets to be rechecked according to the proportion;
The obtaining the plurality of second image information with the to-be-rechecked punching sheet comprises the following steps:
acquiring initial time of determining to-be-rechecked punching sheets as unqualified;
Acquiring the position and the transmission speed of a punching sheet to be rechecked in the first image information;
acquiring third image information at intervals of preset time from the initial time;
Determining a search area corresponding to the position in the third image information;
determining an intercepting area with the same size as the first image information in the searching area according to the transmission speed of the punching sheet to be checked and the moment of acquiring the third image information;
And determining a truncated area in the third image information as the second image information.
2. The method of claim 1, wherein the acquiring the first image information with the punched sheet comprises:
acquiring original image information at intervals of preset time;
identifying the original image information according to the film stamping identification neural network model, and determining the position information of the film stamping in the original image information;
Dividing the original image information according to the position information of the punching sheet, and determining a plurality of first image information, wherein each first image information comprises one punching sheet.
3. The method according to claim 1, wherein the determining the rechecking result of the sheet to be rechecked according to the ratio includes:
Determining the proportion of the qualified quantity to the total number of the third image information as a first proportion;
determining the proportion of the unqualified quantity to the total number of the third image information as a second proportion;
judging whether the difference value between the first proportion and the second proportion is smaller than a first preset value or not; if yes, generating error information; otherwise, determining the result corresponding to the highest proportion as a rechecking result of the punching sheet to be rechecked.
4. The method according to claim 1, wherein the method further comprises:
acquiring the heights of a preset number of punched sheets after lamination under a first pressure;
Judging whether the height is smaller than or equal to a preset height; if yes, finishing the laminating step;
otherwise, judging whether the difference between the height and the preset height reaches a second preset value;
If the preset value is reached, determining a proportion in a preset table according to the difference value, multiplying the first pressure by the proportion, and determining the updated first pressure;
If the preset value is not reached, the first pressure is not changed;
Repeatedly obtaining the heights of a preset number of punched sheets after lamination under the first pressure;
And judging whether the height is smaller than a preset height or not until the laminating step is completed.
5. The method of claim 4, wherein if there is no proportion corresponding to the difference in the preset table, determining the proportion in the preset table according to the difference includes:
Generating a graph based on the proportion corresponding to each difference value in a preset table;
And determining a proportion corresponding to the difference value in the graph.
6. The utility model provides a submersible motor stator pressure-superposed control device which characterized in that includes:
The first image information acquisition module is used for acquiring first image information with a punching sheet before lamination;
The detection module is used for identifying the punching sheet in the first image information according to the deep-learning neural network model and determining unqualified punching sheets;
the unqualified punching sheet removing module is used for acquiring position information of unqualified punching sheets and generating unqualified punching sheet removing information based on the position information;
the judging module is used for judging whether the number of the unqualified punched pieces detected in the preset time period reaches a preset value;
The prompt information generation module is used for generating prompt information for suspending lamination of the punching sheet when the judgment module judges that the punching sheet is positive;
further comprises:
determining unqualified punched sheets as punched sheets to be rechecked;
The first image information acquisition module is used for acquiring a plurality of second image information with the punching sheet to be checked;
the second judging module is used for judging whether each piece of second image information is consistent with the first image information or not;
the first rechecking module is used for determining that the punched sheet to be rechecked is unqualified when the second judging module judges that the punched sheets are consistent;
The analysis module is used for inputting any one piece of second image information into the deep learning neural network model when the second judgment module judges that the second image information is inconsistent, and determining whether the punched piece in the second image information is qualified or not;
the second rechecking module is used for determining that the punched sheet to be rechecked is unqualified when the analysis module determines that the punched sheet is unqualified;
the third rechecking module is used for determining whether the punched sheets in each piece of second image information are qualified or not when the analysis module determines that the punched sheets are qualified, respectively calculating the proportion of the qualified number and the unqualified number to the total number of the pieces of second image information, and determining rechecking results of the punched sheets to be rechecked according to the proportion;
The first image information acquisition module is specifically configured to:
acquiring initial time of determining to-be-rechecked punching sheets as unqualified;
Acquiring the position and the transmission speed of a punching sheet to be rechecked in the first image information;
acquiring third image information at intervals of preset time from the initial time;
determining a search area corresponding to the position in the third image information;
determining an intercepting area with the same size as the first image information in the searching area according to the transmission speed of the punching sheet to be checked and the moment of acquiring the third image information;
And determining a truncated area in the third image information as the second image information.
7. An electronic device, characterized in that,
At least one processor;
A memory;
At least one computer program, wherein the at least one computer program is stored in the memory and configured to be executed by the at least one processor, the at least one computer program configured to: performing the method of any one of claims 1 to 5.
8. A computer readable storage medium, characterized in that a computer program is stored which can be loaded by a processor and which performs the method according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310866921.5A CN116846162B (en) | 2023-07-14 | 2023-07-14 | Method and device for controlling stator lamination of submersible motor, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310866921.5A CN116846162B (en) | 2023-07-14 | 2023-07-14 | Method and device for controlling stator lamination of submersible motor, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116846162A CN116846162A (en) | 2023-10-03 |
| CN116846162B true CN116846162B (en) | 2024-06-14 |
Family
ID=88163247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310866921.5A Active CN116846162B (en) | 2023-07-14 | 2023-07-14 | Method and device for controlling stator lamination of submersible motor, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116846162B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117066337B (en) * | 2023-10-18 | 2023-12-29 | 南通双耀冲压有限公司 | Stamping control method and system for motor stator and rotor machining |
| CN118151687B (en) * | 2024-05-09 | 2024-07-09 | 深圳市欣茂鑫实业有限公司 | Pressure control method and system for copper column crimping |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112801976A (en) * | 2021-01-28 | 2021-05-14 | 河南省四合印务有限公司 | Detection system and method for correcting binding mispasting of books and periodicals and computer device |
| CN115482234A (en) * | 2022-10-08 | 2022-12-16 | 浙江花园药业有限公司 | High-precision defect detection method and system for aluminum-plastic blister medicines |
| CN115833501A (en) * | 2022-11-28 | 2023-03-21 | 贵州航天林泉电机有限公司 | Core lamination system of micro-special motor |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110006912A (en) * | 2019-04-26 | 2019-07-12 | 上海电气集团股份有限公司 | A kind of silicon steel sheet Surface Quality Inspection System and operation method for generator |
| JP2022059876A (en) * | 2020-10-02 | 2022-04-14 | 東芝産業機器システム株式会社 | Manufacturing system and manufacturing method of laminated iron core |
| CN114120221A (en) * | 2021-11-06 | 2022-03-01 | 北京奇天大胜网络科技有限公司 | Environment checking method based on deep learning, electronic equipment and storage medium |
| CN114552903A (en) * | 2021-12-28 | 2022-05-27 | 株洲南方机电制造有限公司 | Lamination forming method and device for stator core of high-power motor or generator |
-
2023
- 2023-07-14 CN CN202310866921.5A patent/CN116846162B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112801976A (en) * | 2021-01-28 | 2021-05-14 | 河南省四合印务有限公司 | Detection system and method for correcting binding mispasting of books and periodicals and computer device |
| CN115482234A (en) * | 2022-10-08 | 2022-12-16 | 浙江花园药业有限公司 | High-precision defect detection method and system for aluminum-plastic blister medicines |
| CN115833501A (en) * | 2022-11-28 | 2023-03-21 | 贵州航天林泉电机有限公司 | Core lamination system of micro-special motor |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116846162A (en) | 2023-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116846162B (en) | Method and device for controlling stator lamination of submersible motor, electronic equipment and storage medium | |
| CN103917987B (en) | Pass through the measurement of the belt wear of the rim detection of raster image | |
| CN109727229B (en) | Method and device for detecting false solder | |
| CN111758117B (en) | Inspection system, recognition system, and learning data generation device | |
| CN113607742A (en) | Battery cell tab detection method and device, electronic equipment and storage medium | |
| JP2020134187A (en) | Flaw inspection device and method | |
| CN105303573A (en) | Pin detection method and system for gold needle type element | |
| WO2021017797A1 (en) | Counting check device,counting system and method | |
| JP6731320B2 (en) | Mold design support method and mold design support system | |
| CN117367516B (en) | Aluminum-plastic composite board performance detection system based on multidimensional test | |
| CN114494105A (en) | System and method for monitoring press line defects | |
| CN109685791A (en) | A kind of corrugated board robust detection algorithm based on more window auto-correlation skin texture detections | |
| CN101696876B (en) | Visual detection method for VCM magnetic steel | |
| JP4305645B2 (en) | Simulation method for sheet forming | |
| CN114240928B (en) | Partition detection method, device and equipment for board quality and readable storage medium | |
| JP2005138120A (en) | Method for simulating deflection distribution of die in press forming | |
| KR20230065558A (en) | Deep learning-based MLCC stacked alignment inspection system and method | |
| WO2020189347A1 (en) | Individual identification information generation method, individual identification information generation device and program | |
| Suppitaksakul et al. | Machine vision system for counting the number of corrugated cardboard | |
| CN107931397B (en) | Online monitoring device and method for punching machine | |
| CN117876359B (en) | Rubber product defect detection method, device, equipment and medium | |
| CN109559294B (en) | Method and device for detecting quality of circular hole of drop | |
| JP5790063B2 (en) | Design support apparatus, design support method, and program | |
| CN118081171B (en) | Abnormal intelligent identification method and system applied to metal plate welding | |
| CN112730427B (en) | Product surface defect detection method and system based on machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |