CN118127683A - Spindle speed measuring method based on vision, computer and measuring robot - Google Patents
Spindle speed measuring method based on vision, computer and measuring robot Download PDFInfo
- Publication number
- CN118127683A CN118127683A CN202410253926.5A CN202410253926A CN118127683A CN 118127683 A CN118127683 A CN 118127683A CN 202410253926 A CN202410253926 A CN 202410253926A CN 118127683 A CN118127683 A CN 118127683A
- Authority
- CN
- China
- Prior art keywords
- spindle
- photo
- position information
- calculating
- included angle
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000001514 detection method Methods 0.000 claims description 80
- 238000003062 neural network model Methods 0.000 claims description 36
- 241001589086 Bellapiscis medius Species 0.000 claims description 23
- 238000009432 framing Methods 0.000 claims description 16
- 238000005259 measurement Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 10
- 238000000691 measurement method Methods 0.000 claims description 5
- 238000005498 polishing Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 description 11
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 9
- 229910052782 aluminium Inorganic materials 0.000 description 9
- 230000008859 change Effects 0.000 description 6
- 238000001228 spectrum Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000007547 defect Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000009941 weaving Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 241000549194 Euonymus europaeus Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 239000004411 aluminium Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000004753 textile Substances 0.000 description 1
Classifications
-
- D—TEXTILES; PAPER
- D01—NATURAL OR MAN-MADE THREADS OR FIBRES; SPINNING
- D01H—SPINNING OR TWISTING
- D01H13/00—Other common constructional features, details or accessories
- D01H13/32—Counting, measuring, recording or registering devices
-
- D—TEXTILES; PAPER
- D01—NATURAL OR MAN-MADE THREADS OR FIBRES; SPINNING
- D01H—SPINNING OR TWISTING
- D01H1/00—Spinning or twisting machines in which the product is wound-up continuously
- D01H1/14—Details
- D01H1/20—Driving or stopping arrangements
- D01H1/24—Driving or stopping arrangements for twisting or spinning arrangements, e.g. spindles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P3/00—Measuring linear or angular speed; Measuring differences of linear or angular speeds
- G01P3/64—Devices characterised by the determination of the time taken to traverse a fixed distance
- G01P3/68—Devices characterised by the determination of the time taken to traverse a fixed distance using optical means, i.e. using infrared, visible, or ultraviolet light
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Textile Engineering (AREA)
- Mechanical Engineering (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The application relates to a spindle speed measuring method based on vision, a computer and a measuring robot.
Description
Technical Field
The invention relates to the technical field of textile automation, in particular to a spindle speed measuring method based on vision, a computer and a measuring robot.
Background
The double twisting machine is twisting equipment, can realize one-to-two twisting, and improves twisting efficiency by times compared with the traditional twisting equipment; the two-for-one twister can bond two or more single yarns into a strand by twisting, and the performance of the raw yarn is enhanced. The two-for-one twisting spindle is the heart and key of the two-for-one twisting machine, and the two-for-one twisting machine is the spindle which is the biggest difference with the ring twisting machine. The common spindle can only increase one twist per rotation, and the two-for-one twisting spindle can generate two twists per rotation.
At present, a double-layer filament two-for-one twister is commonly adopted in the chemical fiber filament weaving industry, and the two-for-one twister is divided into an upper layer and a lower layer, and has a left surface and a right surface, each layer generally has 128 spindles, and each spindle is a production unit. The upper layer and the lower layer are respectively provided with a long belt, the spindles are driven to rotate by the friction force between the belt and the spindle foot position of each spindle, that is, 128 spindles on each layer are provided with rotating power by the same belt, and if the tension force of the belt is inconsistent with the pressure and friction force between each spindle due to temperature, aging and other reasons, the rotating speed deviation of the spindles can be caused. The rotation speed deviation of the spindle can lead to uneven twist of the product and finally cause cloth cover flaws in the weaving link. At present, the conventional rotating speed of the domestic two-for-one twister is set to 11000 revolutions per minute, namely 183.3 revolutions per second of the spindle. The two-for-one twister as a key process may cause quality problems such as heavy twisting, weak twisting, uneven twisting, etc. due to unavoidable slipping and uneven friction caused by belt transmission, so that the detection of the spindle speed is a key quality management action of a twisting weaving factory.
In the prior art, a speed measuring mode of spindles of a two-for-one twister is that a speed measuring sensor is arranged on each spindle of the two-for-one twister, and Chinese patent application number is CN201520258151.7, which proposes a three-in-one sensor for detecting spindle speed, twist and broken ends of the two-for-one twister on line. The disadvantage of this solution is the high cost of the sensors, for example 360 two-for-one twisters, each with 256 spindles, which requires 92160 sensors to be installed, if 40 yuan per sensor is calculated on average, 368.6 ten thousand yuan per sensor. In addition, the sensor is large in size, the daily operation of staff can be greatly disturbed after the sensor is installed, the sensor can be impacted when the pipe is plugged and unplugged, and the sensor is easy to damage.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention aims to provide a vision-based ingot speed measuring method, a computer and a measuring robot, so as to overcome the defects that the use of a sensor to measure the ingot speed in the prior art can increase the equipment cost and influence the equipment use.
The technical aim of the invention is realized by the following technical scheme: a vision-based ingot measurement method, comprising:
acquiring a set rotating speed of a spindle of the two-for-one twister, and calculating a first shooting frequency according to the set rotating speed; taking a first picture and a second picture of the same spindle according to the first shooting frequency;
inputting the first photo into a pre-trained target detection neural network model for detection, and obtaining first position information corresponding to a spindle in the first photo and second position information corresponding to a wire passing hole in the first photo;
Inputting the second photo into a pre-trained target detection neural network model for detection, and obtaining third position information corresponding to a spindle in the second photo and fourth position information corresponding to a wire passing hole in the second photo;
According to the first position information and the second position information, calculating a first included angle between a connecting line of the wire passing hole and the spindle axis in the first photo and a preset coordinate axis; calculating a second included angle between a connecting line of the wire passing hole and the spindle axis in the second photo and a preset coordinate axis according to the third position information and the fourth position information;
Calculating a first angle difference value according to the first included angle and the second included angle, and correspondingly calculating a first time difference value between the first photo and the second photo according to the first shooting frequency; and calculating a first actual rotating speed of the spindle according to the first angle difference value and the first time difference value.
Optionally, the obtaining the set rotation speed of the spindle of the two-for-one twister, calculating the first shooting frequency according to the set rotation speed includes:
Acquiring a set rotating speed omega 0 of a spindle of the two-for-one twister;
acquiring a preset first undersampling parameter P 1;
According to the set rotation speed omega 0 and the first undersampled parameter P 1, a first shooting frequency f 1：f1＝ω0/2πP1 is calculated.
Optionally, inputting the first photo into a pre-trained target detection neural network model for detection, to obtain first position information corresponding to the spindle in the first photo and second position information corresponding to the wire passing hole in the first photo, including:
Inputting the first photo into a pre-trained target detection neural network model for detection, and correspondingly obtaining a first boundary frame for framing a spindle in the first photo and a second boundary frame for framing a threading hole in the first photo;
Acquiring a first transverse coordinate x 1 corresponding to the top left corner vertex of the first boundary frame and a first transverse length l 1 of the first boundary frame; the first transverse coordinate x 1 and the first transverse length l 1 are recorded as first position information;
acquiring a second transverse coordinate x 2 corresponding to the top left corner vertex of the second boundary frame and a second transverse length l 2 of the second boundary frame; the second transverse coordinate x 2 and the second transverse length l 2 are recorded as second position information.
Optionally, calculating, according to the first position information and the second position information, a first included angle between a connecting line of the wire passing hole and the spindle axis in the first photo and a preset coordinate axis includes:
Acquiring the radius r of the spindle;
obtaining a fifth abscissa x 5 of the spindle in the first photo, where the axis of the spindle is located:
x5＝x1+l1/2；
a sixth abscissa x 6 where the center point of the threading hole in the first photo is located is obtained:
x6＝x2+l2/2；
calculating a first lateral distance Δx 1 between the fifth and sixth abscissas:
Δx1＝x5-x6；
Calculating a first included angle theta 1 according to the radius r and the first transverse distance delta x 1:
optionally, inputting the second photo into a pre-trained target detection neural network model for detection, to obtain third position information corresponding to the spindle in the second photo and fourth position information corresponding to the wire passing hole in the second photo, including:
Inputting the second photo into a pre-trained target detection neural network model for detection, and correspondingly obtaining a third boundary frame for framing a spindle in the second photo and a fourth boundary frame for framing a threading hole in the second photo;
Acquiring a third transverse coordinate x 3 corresponding to the left upper corner vertex of the third boundary frame and a third transverse length l 3 of the third boundary frame; recording the third transverse coordinate x 3 and the third transverse length l 3 as third position information;
Acquiring a fourth transverse coordinate x 4 corresponding to the top left corner vertex of the fourth bounding box and a fourth transverse length l 4 of the fourth bounding box; the fourth transverse coordinate x 4 and the fourth transverse length l 4 are noted as fourth position information.
Optionally, calculating a second included angle between a connecting line of the wire passing hole and the spindle axis in the second photo and a preset coordinate axis according to the third position information and the fourth position information includes:
Acquiring the radius r of the spindle;
obtaining a seventh abscissa x 7 of the second photo where the spindle axis is located:
x7＝x3+l3/2；
An eighth abscissa x 8 where the center point of the threading hole in the second photo is located is obtained:
x8＝x4+l4/2；
A second lateral distance Δx 2 between the seventh abscissa x 7 and the eighth abscissa x 8 is calculated:
Δx2＝x7-x8；
Calculating a second included angle theta 2 according to the radius r and the second transverse distance delta x 2:
optionally, the first angle difference is calculated according to the first included angle and the second included angle, and the first time difference between the first photo and the second photo is correspondingly calculated according to the first shooting frequency; according to the first angle difference value and the first time difference value, calculating a first actual rotating speed of the spindle, including:
Calculating a first angle difference dθ 1：dθ1＝θ2+θ1 according to the first included angle θ 1 and the second included angle θ 2;
Correspondingly calculating a first time difference dt 1：dt1＝1/f1 between the first picture and the second picture according to the first shooting frequency f 1;
Calculating a first actual rotation speed omega 1 of the spindle according to the first angle difference dθ 1 and the first time difference dt 1:
optionally, the method further comprises: acquiring a preset second undersampling parameter P 2;
According to the set rotation speed omega 0 and the second undersampled parameter P 2, calculating a second shooting frequency f 2:
f2＝ω0/2πP2；
Taking a third picture and a fourth picture of the same spindle according to the second shooting frequency f 2;
Inputting the third photo into a pre-trained target detection neural network model for detection, and obtaining fifth position information corresponding to a spindle in the third photo and sixth position information corresponding to a wire passing hole in the third photo;
inputting the fourth photo into a pre-trained target detection neural network model for detection, and obtaining seventh position information corresponding to a spindle in the fourth photo and eighth position information corresponding to a wire passing hole in the fourth photo;
According to the fifth position information and the sixth position information, a third included angle theta 3 between a connecting line of the wire passing hole and the spindle axis in the third photo and a preset coordinate axis is calculated; according to the seventh position information and the eighth position information, a fourth included angle theta 4 between a connecting line of the wire passing hole and the spindle axis in the fourth photo and a preset coordinate axis is calculated;
Calculating a second angle difference dθ 2：dθ2＝θ3+θ4 according to the third included angle θ 3 and the fourth included angle θ 4;
Correspondingly calculating a second time difference dt 2：dt2＝1/f2 between the first photo and the second photo according to the second shooting frequency f 2;
calculating a second actual rotating speed omega 2 of the spindle according to the second angle difference dθ 2 and the second time difference dt 2:
Judging whether the first actual rotation speed omega 1 is equal to the second actual rotation speed omega 2, if yes, recording the first actual rotation speed omega 1 or the second actual rotation speed omega 2 as the actual rotation speed omega.
A computer device comprising a memory and a processor; the memory is connected to the processor, and the memory is used for storing a computer program, and the processor is used for calling the computer program to enable the computer device to execute the method.
A vision-based ingot measurement robot, comprising: AGV base, stand, camera for shooting spindle, stroboscope for polishing, battery and above-mentioned computer equipment; the bottom of the upright post is fixedly connected with the AGV base; the battery is fixedly connected with the AGV base; the stroboscope and the camera are fixedly connected with the side wall of the upright post; the battery is electrically connected with the camera, the stroboscope, the AGV base and the computer equipment respectively.
In summary, the application has the following beneficial effects: according to the method for measuring the spindle speed based on vision, firstly, the shooting frequency of a photo is set, then the content on the photo is identified and detected by using a target detection model, and finally, the rotating speed of the spindle is calculated by using the position change quantity of the wire passing hole. Compared with the mode of manually detecting the spindle rotating speed, the spindle rotating speed detection device is higher in measuring accuracy and cannot be affected by errors caused by manual detection.
Drawings
FIG. 1 is a flow chart of a method for measuring ingot based on vision in the present invention;
FIG. 2 is a block diagram of a vision-based ingot measurement system of the present invention;
FIG. 3 is an internal block diagram of a computer device in accordance with an embodiment of the present invention;
FIG. 4 is a schematic diagram of a prior art stroboscope measuring spindle speed;
FIG. 5 is a schematic illustration of a marking spindle and a via using a target detection neural network model in accordance with the present invention;
FIG. 6 is a schematic illustration of the calculation of a first lateral distance according to the present invention;
FIG. 7 is a schematic illustration of the calculation of a second lateral distance according to the present invention;
FIG. 8 is a graph of a frequency spectrum of the present invention for measuring the position of a via;
FIG. 9 is a schematic diagram of a spectrum of the difference between the actual rotation speed and the set rotation speed according to the present invention;
FIG. 10 is a schematic view of a vision-based ingot measuring robot according to the present invention;
fig. 11 is a schematic view of the vision-based spindle measurement robot of the present invention measuring spindle rotation speed.
In the figure: 1. a photo shooting module; 2. a position information detection module; 3. an included angle calculation module; 4. and a spindle rotating speed calculating module.
Detailed Description
In order that the objects, features and advantages of the invention will be readily understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. Several embodiments of the invention are presented in the figures. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances. The terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature.
In the present invention, unless expressly stated or limited otherwise, a first feature "above" or "below" a second feature may include both the first and second features being in direct contact, as well as the first and second features not being in direct contact but being in contact with each other through additional features therebetween. Moreover, a first feature being "above," "over" and "on" a second feature includes the first feature being directly above and obliquely above the second feature, or simply indicating that the first feature is higher in level than the second feature. The first feature being "under", "below" and "beneath" the second feature includes the first feature being directly under and obliquely below the second feature, or simply means that the first feature is less level than the second feature. The terms "vertical," "horizontal," "left," "right," "up," "down," and the like are used for descriptive purposes only and are not to indicate or imply that the devices or elements being referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore should not be construed as limiting the invention.
The present invention will be described in detail below with reference to the accompanying drawings and examples.
Example 1
The invention provides a method for measuring ingot based on vision, as shown in figure 1, comprising the following steps:
s1, acquiring a set rotating speed of a spindle of a two-for-one twister, and calculating a first shooting frequency according to the set rotating speed; taking a first picture and a second picture of the same spindle according to the first shooting frequency;
S2, inputting the first photo into a pre-trained target detection neural network model for detection, and obtaining first position information corresponding to a spindle in the first photo and second position information corresponding to a wire passing hole in the first photo;
s3, inputting the second photo into a pre-trained target detection neural network model for detection, and obtaining third position information corresponding to the spindle in the second photo and fourth position information corresponding to the wire passing hole in the second photo;
S4, calculating a first included angle between a connecting line of the wire passing hole in the first photo and the spindle axis and a preset coordinate axis according to the first position information and the second position information; calculating a second included angle between a connecting line of the wire passing hole and the spindle axis in the second photo and a preset coordinate axis according to the third position information and the fourth position information;
S5, calculating a first angle difference value according to the first included angle and the second included angle, and correspondingly calculating a first time difference value between the first photo and the second photo according to the first shooting frequency; and calculating a first actual rotating speed of the spindle according to the first angle difference value and the first time difference value.
In particular, the applicant found that in actual production work, the aluminum cup of the spindle is of a regular structure around the shaft, and rotates around the axis when rotating, and does not perform translational movement, so that the contour shape of the aluminum cup is the same under the conditions of rotation and rest. Therefore, when the spindle rotates at a high speed in the production process, people can not easily distinguish the rotation speed or the rotation condition of the spindle by naked eyes. In order to solve the problems, the applicant found that the side wall of the aluminum cup of the spindle is provided with a wire passing hole, and when the aluminum cup rotates for one circle, the wire passing hole also rotates for one circle along with the aluminum cup, and the same rotating speed as the aluminum cup is maintained. The applicant has therefore conceived that the aluminium cup can be measured in terms of a stroboscopic velocimeter, the specific scheme being as follows:
Firstly, the preset rotating speed of the spindle of the two-for-one twister is obtained, for example, the existing spindle rotating speed is 11160rpm (revolutions per minute), namely 186 revolutions per second, the stroboscopic velocimeter is adjusted to be the same frequency as the rotating speed, namely 186Hz, if the actual speed of the spindle is matched with the preset speed, namely the frequency of the stroboscopic velocimeter is matched, after each time the velocimeter is lightened, the observed position of the wire passing hole relative to the aluminum cup is kept consistent by utilizing the vision residue effect, and if the rotating speed of the spindle is different from the preset rotating speed, the wire passing hole is gradually displaced under the flashing frequency. In general, the speed of displacement of the via is affected by the frequency difference. Since the spindle is driven by the belt drive, the speed of the spindle does not normally exceed the preset speed, so that the speed of the spindle is different from the preset speed as long as the movement of the wire passing hole is observed within the preset time. However, by using the method, too relying on subjective judgment of people, different people have different sensitivity degrees to the positions of the wire passing holes, so that whether the wire passing holes are offset or whether the offset of the wire passing holes exceeds the standard is judged, a quantization standard cannot be formed, and whether the rotating speed of the stator is smaller than a threshold value is difficult to accurately judge.
Aiming at the defects of the scheme, the application further provides a spindle speed measuring method based on vision, as shown in figures 5, 6 and 7, in the existing spindle rotation process, the wire passing hole on the spindle can be used as a reference object to show the rotation speed of the spindle, and when the frequency of the stroboscope is adjusted to be consistent with the rotation speed of the spindle, people can see that the wire passing hole is always in a position under the influence of vision residues. Likewise, the spindle photographs are taken by using the camera, and in the case that the frequency of the camera is consistent with the rotation speed of the spindle, the positions of the wire holes taken on the two photographs should be the same. Therefore, in the actual speed measurement process, the shooting frequency of the camera needs to be consistent with the preset rotation frequency of the spindle. Then, two pictures are taken of the spindle, and when the actual rotating speed of the spindle is inconsistent with the preset rotating speed, the positions of the wire passing holes on the two pictures are different. Calculating the angle change quantity of the wire passing hole according to the position difference of the wire passing hole on the photo, calculating the change total quantity of the wire passing hole in unit time according to the angle change quantity of the wire passing hole, and adding the change total quantity with a preset set rotating speed omega 0 to obtain the actual rotating speed omega of the spindle.
Illustrating: the common rotating speed of the two-for-one twisting spindle is 11000rpm, the spindle rotates for 18 circles within 0.1 second, if the ultra-high speed camera is used for shooting the spindle, the shooting time is taken as an x axis, the shot distance L of the wire passing hole of the aluminum cup from the zero point is taken as a y axis, and the obtained curve is shown in figure 8.
If the spindle speed deviates from the flash velocimeter, the naked eye can observe the rotation of the wire passing hole, and the rotation speed is the difference between the actual speed and the setting speed of the stroboscope. Assuming that the standard spindle speed is 11160rpm, the actual spindle speed is 10980rpm, the deviation is 180rpm, the flash velocimeter frequency is 11160rpm, namely the flash frequency is 11160/60=186 Hz, and the effect observed by naked eyes is as shown in fig. 9 (the time length of the horizontal axis in fig. 9 is 0.1 seconds), namely the position of the wire passing hole gradually deviates. Therefore, the actual rotating speed of the spindle can be obtained by measuring the offset of the wire passing hole, calculating the speed difference between the wire passing hole and the standard speed and finally adding the speed difference and the set speed. It can be understood by those skilled in the art that the sign of the speed difference may be positive or negative, that is, the actual rotation speed of the spindle may be greater than the set speed or may be less than the set speed, and only the corresponding sign needs to be set and added to the standard speed, which is not described in detail in the present application.
In summary, the method for measuring spindle speed based on vision is provided, firstly, the shooting frequency of a photo is set, then, the content on the photo is identified and detected by using a target detection model, and finally, the rotating speed of the spindle is calculated by using the position change amount of the wire passing hole.
Further, the obtaining the set rotation speed of the spindle of the two-for-one twister, and calculating the first shooting frequency according to the set rotation speed includes: acquiring a set rotating speed omega 0 of a spindle of the two-for-one twister; acquiring a preset first undersampling parameter P 1; according to the set rotation speed omega 0 and the first undersampled parameter P 1, a first shooting frequency f 1：f1＝ω0/2πP1 is calculated.
In practical application, if the standard spindle speed is 11160rpm (i.e. 186 Hz), the actual spindle speed is 10980rpm (i.e. 183 Hz), and the camera photographs at 186fps, which is equivalent to the preset rotation speed of the spindle, too many photos need to be identified by AI because of too high sampling rate, the requirements on the camera and the AI calculation force are still high, and the cost is very high. According to the nyquist sampling theorem, it is known that the original signal is recovered from the sampled signal without distortion, and the sampling frequency should be greater than 2 times the highest frequency of the signal. When the sampling frequency is less than 2 times of the highest frequency of the frequency spectrum, the frequency spectrum of the signal is aliased. When the sampling frequency is greater than the highest frequency of the frequency multiplication spectrum of 2, the spectrum of the signal is not aliased. Therefore, according to the actual situation, the frequency of shooting by the camera can be reduced, that is, the photo is downsampled, the sampling frequency of the camera is reduced to one fifth of the original frequency (the first undersampling parameter P 1), that is, 186/5=37.2 Hz, and then the actual measured value of the spindle speed is 183/5=36.6 Hz, that is, the two differ by 0.6Hz; after the rotational speed difference of the corresponding spindle is calculated, the rotational speed difference is multiplied by the sampling rate to obtain the final spindle rotational speed, namely
Further, the inputting the first photo into a pre-trained target detection neural network model for detection to obtain first position information corresponding to the spindle in the first photo and second position information corresponding to the wire passing hole in the first photo includes:
Inputting the first photo into a pre-trained target detection neural network model for detection, and correspondingly obtaining a first boundary frame for framing a spindle in the first photo and a second boundary frame for framing a threading hole in the first photo;
Acquiring a first transverse coordinate x 1 corresponding to the top left corner vertex of the first boundary frame and a first transverse length l 1 of the first boundary frame; the first transverse coordinate x 1 and the first transverse length l 1 are recorded as first position information;
acquiring a second transverse coordinate x 2 corresponding to the top left corner vertex of the second boundary frame and a second transverse length l 2 of the second boundary frame; the second transverse coordinate x 2 and the second transverse length l 2 are recorded as second position information.
Further, according to the first position information and the second position information, a first included angle between a connecting line of the wire passing hole and the spindle axis in the first photo and a preset coordinate axis is calculated, including:
Acquiring the radius r of the spindle;
obtaining a fifth abscissa x 5 of the spindle in the first photo, where the axis of the spindle is located:
x5＝x1+l1/2；
a sixth abscissa x 6 where the center point of the threading hole in the first photo is located is obtained:
x6＝x2+l2/2；
calculating a first lateral distance Δx 1 between the fifth and sixth abscissas:
Δx1＝x5-x6；
Calculating a first included angle theta 1 according to the radius r and the first transverse distance delta x 1:
further, the inputting the second photo into the pre-trained target detection neural network model for detection, to obtain third position information corresponding to the spindle in the second photo and fourth position information corresponding to the wire passing hole in the second photo, includes:
Inputting the second photo into a pre-trained target detection neural network model for detection, and correspondingly obtaining a third boundary frame for framing a spindle in the second photo and a fourth boundary frame for framing a threading hole in the second photo;
Acquiring a third transverse coordinate x 3 corresponding to the left upper corner vertex of the third boundary frame and a third transverse length l 3 of the third boundary frame; recording the third transverse coordinate x 3 and the third transverse length l 3 as third position information;
Acquiring a fourth transverse coordinate x 4 corresponding to the top left corner vertex of the fourth bounding box and a fourth transverse length l 4 of the fourth bounding box; the fourth transverse coordinate x 4 and the fourth transverse length l 4 are noted as fourth position information.
Further, according to the third position information and the fourth position information, calculating a second included angle between a connecting line of the wire passing hole and the spindle axis in the second photo and a preset coordinate axis includes:
Acquiring the radius r of the spindle;
obtaining a seventh abscissa x 7 of the second photo where the spindle axis is located:
x7＝x3+l3/2；
An eighth abscissa x 8 where the center point of the threading hole in the second photo is located is obtained:
x8＝x4+l4/2；
A second lateral distance Δx 2 between the seventh abscissa x 7 and the eighth abscissa x 8 is calculated:
Δx2＝x7-x8；
Calculating a second included angle theta 2 according to the radius r and the second transverse distance delta x 2:
in practical application, as shown in fig. 4, 5, 6 and 7, the wire passing holes on the spindle can be identified by a pre-trained target detection neural network model, and then the positions of the wire passing holes are correspondingly calculated through the coordinates and the sizes of the bounding boxes on the photo.
Further, a first angle difference is calculated according to the first included angle and the second included angle, and a first time difference between the first photo and the second photo is correspondingly calculated according to the first shooting frequency; according to the first angle difference value and the first time difference value, calculating a first actual rotating speed of the spindle, including:
Calculating a first angle difference dθ 1：dθ1＝θ2+θ1 according to the first included angle θ 1 and the second included angle θ 2;
Correspondingly calculating a first time difference dt 1：dt1＝1/f1 between the first picture and the second picture according to the first shooting frequency f 1;
Calculating a first actual rotation speed omega 1 of the spindle according to the first angle difference dθ 1 and the first time difference dt 1:
Further, the method further comprises the following steps: acquiring a preset second undersampling parameter P 2;
According to the set rotation speed omega 0 and the second undersampled parameter P 2, calculating a second shooting frequency f 2:
f2＝ω0/2πP2；
Taking a third picture and a fourth picture of the same spindle according to the second shooting frequency f 2;
Inputting the third photo into a pre-trained target detection neural network model for detection, and obtaining fifth position information corresponding to a spindle in the third photo and sixth position information corresponding to a wire passing hole in the third photo;
inputting the fourth photo into a pre-trained target detection neural network model for detection, and obtaining seventh position information corresponding to a spindle in the fourth photo and eighth position information corresponding to a wire passing hole in the fourth photo;
According to the fifth position information and the sixth position information, a third included angle theta 3 between a connecting line of the wire passing hole and the spindle axis in the third photo and a preset coordinate axis is calculated; according to the seventh position information and the eighth position information, a fourth included angle theta 4 between a connecting line of the wire passing hole and the spindle axis in the fourth photo and a preset coordinate axis is calculated;
Calculating a second angle difference dθ 2：dθ2＝θ3+θ4 according to the third included angle θ 3 and the fourth included angle θ 4;
Correspondingly calculating a second time difference dt 2：dt2＝1/f2 between the first photo and the second photo according to the second shooting frequency f 2;
calculating a second actual rotating speed omega 2 of the spindle according to the second angle difference dθ 2 and the second time difference dt 2:
Judging whether the first actual rotation speed omega 1 is equal to the second actual rotation speed omega 2, if yes, recording the first actual rotation speed omega 1 or the second actual rotation speed omega 2 as the actual rotation speed omega.
In practical applications, in order to avoid missed detection that generates an integer multiple of "frequency deviation", i.e. when the frequency deviation is an integer multiple of the sampling frequency, the frequency deviation is not observed after sampling. After the first actual rotation speed ω 1 is calculated, another sampling rate needs to be set, the sampling rate of one fifth is reduced to one fourth (namely, the second undersampling parameter P 2), the spindle rotation speed is measured once again and is recorded as the second actual rotation speed ω 2, and compared with the first actual rotation speed ω 1, if the two measurement results are the same, the rotation speed measurement result is accurate, if the two measurement results are not the same, the measurement result is not accurate enough, and the measurement needs to be re-performed.
As shown in fig. 2, the present invention also provides a vision-based ingot measurement system, comprising:
And a photo shooting module: the method comprises the steps of obtaining a set rotating speed of a spindle of a two-for-one twister, and calculating a first shooting frequency according to the set rotating speed; taking a first picture and a second picture of the same spindle according to the first shooting frequency;
The position information detection module: the method comprises the steps of inputting a first photo into a pre-trained target detection neural network model for detection, and obtaining first position information corresponding to a spindle in the first photo and second position information corresponding to a wire passing hole in the first photo; inputting the second photo into a pre-trained target detection neural network model for detection, and obtaining third position information corresponding to a spindle in the second photo and fourth position information corresponding to a wire passing hole in the second photo;
And an included angle calculating module: the first included angle between the connecting line of the wire passing hole and the spindle axis in the first photo and a preset coordinate axis is calculated according to the first position information and the second position information; calculating a second included angle between a connecting line of the wire passing hole and the spindle axis in the second photo and a preset coordinate axis according to the third position information and the fourth position information;
Spindle rotation speed calculation module: calculating a first angle difference value according to the first included angle and the second included angle, and correspondingly calculating a first time difference value between the first photo and the second photo according to the first shooting frequency; and calculating a first actual rotating speed of the spindle according to the first angle difference value and the first time difference value.
For a specific definition of a vision-based ingot-speed measurement system, reference is made to the definition of a vision-based ingot-speed measurement method hereinabove, and the description thereof will not be repeated. The various modules in a vision-based ingot measurement system described above may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The computer program is executed by a processor to implement a vision-based spindle speed measurement method.
It will be appreciated by those skilled in the art that the structure shown in FIG. 3 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of: comprising the following steps:
acquiring a set rotating speed of a spindle of the two-for-one twister, and calculating a first shooting frequency according to the set rotating speed; taking a first picture and a second picture of the same spindle according to the first shooting frequency;
inputting the first photo into a pre-trained target detection neural network model for detection, and obtaining first position information corresponding to a spindle in the first photo and second position information corresponding to a wire passing hole in the first photo;
Inputting the second photo into a pre-trained target detection neural network model for detection, and obtaining third position information corresponding to a spindle in the second photo and fourth position information corresponding to a wire passing hole in the second photo;
According to the first position information and the second position information, calculating a first included angle between a connecting line of the wire passing hole and the spindle axis in the first photo and a preset coordinate axis; calculating a second included angle between a connecting line of the wire passing hole and the spindle axis in the second photo and a preset coordinate axis according to the third position information and the fourth position information;
Calculating a first angle difference value according to the first included angle and the second included angle, and correspondingly calculating a first time difference value between the first photo and the second photo according to the first shooting frequency; and calculating a first actual rotating speed of the spindle according to the first angle difference value and the first time difference value.
In one embodiment, the obtaining the set rotational speed of the spindle of the two-for-one twister, calculating the first shooting frequency according to the set rotational speed includes:
Acquiring a set rotating speed omega 0 of a spindle of the two-for-one twister;
acquiring a preset first undersampling parameter P 1;
According to the set rotation speed omega 0 and the first undersampled parameter P 1, a first shooting frequency f 1：f1＝ω0/2πP1 is calculated.
In one embodiment, the inputting the first photo into the pre-trained target detection neural network model for detection, to obtain first position information corresponding to the spindle in the first photo and second position information corresponding to the via hole in the first photo includes:
Inputting the first photo into a pre-trained target detection neural network model for detection, and correspondingly obtaining a first boundary frame for framing a spindle in the first photo and a second boundary frame for framing a threading hole in the first photo;
Acquiring a first transverse coordinate x 1 corresponding to the top left corner vertex of the first boundary frame and a first transverse length l 1 of the first boundary frame; the first transverse coordinate x 1 and the first transverse length l 1 are recorded as first position information;
acquiring a second transverse coordinate x 2 corresponding to the top left corner vertex of the second boundary frame and a second transverse length l 2 of the second boundary frame; the second transverse coordinate x 2 and the second transverse length l 2 are recorded as second position information.
In one embodiment, the calculating, according to the first position information and the second position information, a first included angle between a connecting line of the wire hole and the spindle axis in the first photo and a preset coordinate axis includes:
Acquiring the radius r of the spindle;
obtaining a fifth abscissa x 5 of the spindle in the first photo, where the axis of the spindle is located:
x5＝x1+l1/2；
a sixth abscissa x 6 where the center point of the threading hole in the first photo is located is obtained:
x6＝x2+l2/2；
calculating a first lateral distance Δx 1 between the fifth and sixth abscissas:
Δx1＝x5-x6；
Calculating a first included angle theta 1 according to the radius r and the first transverse distance delta x 1:
In one embodiment, the inputting the second photo into the pre-trained target detection neural network model for detection, to obtain third position information corresponding to the spindle in the second photo and fourth position information corresponding to the via hole in the second photo includes:
Inputting the second photo into a pre-trained target detection neural network model for detection, and correspondingly obtaining a third boundary frame for framing a spindle in the second photo and a fourth boundary frame for framing a threading hole in the second photo;
Acquiring a third transverse coordinate x 3 corresponding to the left upper corner vertex of the third boundary frame and a third transverse length l 3 of the third boundary frame; recording the third transverse coordinate x 3 and the third transverse length l 3 as third position information;
Acquiring a fourth transverse coordinate x 4 corresponding to the top left corner vertex of the fourth bounding box and a fourth transverse length l 4 of the fourth bounding box; the fourth transverse coordinate x 4 and the fourth transverse length l 4 are noted as fourth position information.
In one embodiment, the calculating, according to the third position information and the fourth position information, a second included angle between a connecting line of the wire hole and the spindle axis in the second photo and a preset coordinate axis includes:
Acquiring the radius r of the spindle;
obtaining a seventh abscissa x 7 of the second photo where the spindle axis is located:
x7＝x3+l3/2；
An eighth abscissa x 8 where the center point of the threading hole in the second photo is located is obtained:
x8＝x4+l4/2；
A second lateral distance Δx 2 between the seventh abscissa x 7 and the eighth abscissa x 8 is calculated:
Δx2＝x7-x8；
Calculating a second included angle theta 2 according to the radius r and the second transverse distance delta x 2:
in one embodiment, the calculating a first angle difference according to the first included angle and the second included angle correspondingly calculates a first time difference between the first photo and the second photo according to the first shooting frequency; according to the first angle difference value and the first time difference value, calculating a first actual rotating speed of the spindle, including:
Calculating a first angle difference dθ 1：dθ1＝θ2+θ1 according to the first included angle θ 1 and the second included angle θ 2;
Correspondingly calculating a first time difference dt 1：dt1＝1/f1 between the first picture and the second picture according to the first shooting frequency f 1;
Calculating a first actual rotation speed omega 1 of the spindle according to the first angle difference dθ 1 and the first time difference dt 1:
In one embodiment, further comprising: acquiring a preset second undersampling parameter P 2;
According to the set rotation speed omega 0 and the second undersampled parameter P 2, calculating a second shooting frequency f 2:
f2＝ω0/2πP2；
Taking a third picture and a fourth picture of the same spindle according to the second shooting frequency f 2;
Inputting the third photo into a pre-trained target detection neural network model for detection, and obtaining fifth position information corresponding to a spindle in the third photo and sixth position information corresponding to a wire passing hole in the third photo;
inputting the fourth photo into a pre-trained target detection neural network model for detection, and obtaining seventh position information corresponding to a spindle in the fourth photo and eighth position information corresponding to a wire passing hole in the fourth photo;
According to the fifth position information and the sixth position information, a third included angle theta 3 between a connecting line of the wire passing hole and the spindle axis in the third photo and a preset coordinate axis is calculated; according to the seventh position information and the eighth position information, a fourth included angle theta 4 between a connecting line of the wire passing hole and the spindle axis in the fourth photo and a preset coordinate axis is calculated;
Calculating a second angle difference dθ 2：dθ2＝θ3+θ4 according to the third included angle θ 3 and the fourth included angle θ 4;
Correspondingly calculating a second time difference dt 2：dt2＝1/f2 between the first photo and the second photo according to the second shooting frequency f 2;
calculating a second actual rotating speed omega 2 of the spindle according to the second angle difference dθ 2 and the second time difference dt 2:
Judging whether the first actual rotation speed omega 1 is equal to the second actual rotation speed omega 2, if yes, recording the first actual rotation speed omega 1 or the second actual rotation speed omega 2 as the actual rotation speed omega.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
Example 2
Further, as shown in fig. 10 and 11, the device includes: AGV base, stand, camera for shooting spindle, stroboscope for polishing, battery and above-mentioned computer equipment; the bottom of the upright post is fixedly connected with the AGV base; the battery is fixedly connected with the AGV base; the stroboscope and the camera are fixedly connected with the side wall of the upright post; the battery is electrically connected with the camera, the stroboscope, the AGV base and the computer equipment respectively.
The AI camera and the flash lamp are arranged on a walking AGV chassis, and the AGV carries the machine stations with the ingot speed detection equipment to continuously carry out the inspection of the specified range in a workshop, so that one robot can be used for automatic ingot speed detection of a large number of machine stations.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above description is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above examples, and all technical solutions belonging to the concept of the present invention belong to the protection scope of the present invention. It should be noted that modifications and adaptations to the present invention may occur to one skilled in the art without departing from the principles of the present invention and are intended to be within the scope of the present invention.
Claims (10)
1. A vision-based ingot speed measurement method, comprising:
acquiring a set rotating speed of a spindle of the two-for-one twister, and calculating a first shooting frequency according to the set rotating speed; taking a first picture and a second picture of the same spindle according to the first shooting frequency;
inputting the first photo into a pre-trained target detection neural network model for detection, and obtaining first position information corresponding to a spindle in the first photo and second position information corresponding to a wire passing hole in the first photo;
Inputting the second photo into a pre-trained target detection neural network model for detection, and obtaining third position information corresponding to a spindle in the second photo and fourth position information corresponding to a wire passing hole in the second photo;
According to the first position information and the second position information, calculating a first included angle between a connecting line of the wire passing hole and the spindle axis in the first photo and a preset coordinate axis; calculating a second included angle between a connecting line of the wire passing hole and the spindle axis in the second photo and a preset coordinate axis according to the third position information and the fourth position information;
Calculating a first angle difference value according to the first included angle and the second included angle, and correspondingly calculating a first time difference value between the first photo and the second photo according to the first shooting frequency; and calculating a first actual rotating speed of the spindle according to the first angle difference value and the first time difference value.
2. The method for measuring spindle speed based on vision according to claim 1, wherein the step of obtaining the set rotational speed of the spindle of the two-for-one twister, and calculating the first photographing frequency according to the set rotational speed, comprises:
Acquiring a set rotating speed omega 0 of a spindle of the two-for-one twister;
acquiring a preset first undersampling parameter P 1;
According to the set rotation speed omega 0 and the first undersampled parameter P 1, a first shooting frequency f 1：f1＝ω0/2πP1 is calculated.
3. The method for measuring spindle speed based on vision according to claim 2, wherein the step of inputting the first photograph into a pre-trained target detection neural network model for detection to obtain first position information corresponding to the spindle in the first photograph and second position information corresponding to the via hole in the first photograph comprises the steps of:
Inputting the first photo into a pre-trained target detection neural network model for detection, and correspondingly obtaining a first boundary frame for framing a spindle in the first photo and a second boundary frame for framing a threading hole in the first photo;
Acquiring a first transverse coordinate x 1 corresponding to the top left corner vertex of the first boundary frame and a first transverse length l 1 of the first boundary frame; the first transverse coordinate x 1 and the first transverse length l 1 are recorded as first position information;
acquiring a second transverse coordinate x 2 corresponding to the top left corner vertex of the second boundary frame and a second transverse length l 2 of the second boundary frame; the second transverse coordinate x 2 and the second transverse length l 2 are recorded as second position information.
4. The method for measuring spindle speed based on vision according to claim 3, wherein calculating a first included angle between a connecting line of the wire hole and the spindle axis in the first photo and a preset coordinate axis according to the first position information and the second position information comprises:
Acquiring the radius r of the spindle;
obtaining a fifth abscissa x 5 of the spindle in the first photo, where the axis of the spindle is located:
x5＝x1+l1/2；
a sixth abscissa x 6 where the center point of the threading hole in the first photo is located is obtained:
x6＝x2+l2/2；
calculating a first lateral distance Δx 1 between the fifth and sixth abscissas:
Δx1＝x5-x6；
Calculating a first included angle theta 1 according to the radius r and the first transverse distance delta x 1:
5. the method for measuring spindle speed based on vision according to claim 4, wherein the step of inputting the second photograph into the pre-trained target detection neural network model for detection to obtain the third position information corresponding to the spindle in the second photograph and the fourth position information corresponding to the wire passing hole in the second photograph comprises the steps of:
Inputting the second photo into a pre-trained target detection neural network model for detection, and correspondingly obtaining a third boundary frame for framing a spindle in the second photo and a fourth boundary frame for framing a threading hole in the second photo;
Acquiring a third transverse coordinate x 3 corresponding to the left upper corner vertex of the third boundary frame and a third transverse length l 3 of the third boundary frame; recording the third transverse coordinate x 3 and the third transverse length l 3 as third position information;
Acquiring a fourth transverse coordinate x 4 corresponding to the top left corner vertex of the fourth bounding box and a fourth transverse length l 4 of the fourth bounding box; the fourth transverse coordinate x 4 and the fourth transverse length l 4 are noted as fourth position information.
6. The method for measuring spindle speed based on vision according to claim 5, wherein calculating a second included angle between a connecting line of the wire hole and the spindle axis in the second photo and a preset coordinate axis according to the third position information and the fourth position information comprises:
Acquiring the radius r of the spindle;
obtaining a seventh abscissa x 7 of the second photo where the spindle axis is located:
x7＝x3+l3/2；
An eighth abscissa x 8 where the center point of the threading hole in the second photo is located is obtained:
x8＝x4+l4/2；
A second lateral distance Δx 2 between the seventh abscissa x 7 and the eighth abscissa x 8 is calculated:
Δx2＝x7-x8；
Calculating a second included angle theta 2 according to the radius r and the second transverse distance delta x 2:
7. The method of claim 6, wherein the calculating a first angle difference based on the first angle and the second angle correspondingly calculates a first time difference between the first photograph and the second photograph based on the first photographing frequency; according to the first angle difference value and the first time difference value, calculating a first actual rotating speed of the spindle, including:
Calculating a first angle difference dθ 1：dθ1＝θ2+θ1 according to the first included angle θ 1 and the second included angle θ 2;
Correspondingly calculating a first time difference dt 1：dt1＝1/f1 between the first picture and the second picture according to the first shooting frequency f 1;
Calculating a first actual rotation speed omega 1 of the spindle according to the first angle difference dθ 1 and the first time difference dt 1:
8. The vision-based ingot-speed measurement method of claim 7, further comprising: acquiring a preset second undersampling parameter P 2;
According to the set rotation speed omega 0 and the second undersampled parameter P 2, calculating a second shooting frequency f 2:
f2＝ω0/2πP2；
Taking a third picture and a fourth picture of the same spindle according to the second shooting frequency f 2;
Inputting the third photo into a pre-trained target detection neural network model for detection, and obtaining fifth position information corresponding to a spindle in the third photo and sixth position information corresponding to a wire passing hole in the third photo;
inputting the fourth photo into a pre-trained target detection neural network model for detection, and obtaining seventh position information corresponding to a spindle in the fourth photo and eighth position information corresponding to a wire passing hole in the fourth photo;
According to the fifth position information and the sixth position information, a third included angle theta 3 between a connecting line of the wire passing hole and the spindle axis in the third photo and a preset coordinate axis is calculated; according to the seventh position information and the eighth position information, a fourth included angle theta 4 between a connecting line of the wire passing hole and the spindle axis in the fourth photo and a preset coordinate axis is calculated;
Calculating a second angle difference dθ 2：dθ2＝θ3+θ4 according to the third included angle θ 3 and the fourth included angle θ 4;
Correspondingly calculating a second time difference dt 2：dt2＝1/f2 between the first photo and the second photo according to the second shooting frequency f 2;
calculating a second actual rotating speed omega 2 of the spindle according to the second angle difference dθ 2 and the second time difference dt 2:
Judging whether the first actual rotation speed omega 1 is equal to the second actual rotation speed omega 2, if yes, recording the first actual rotation speed omega 1 or the second actual rotation speed omega 2 as the actual rotation speed omega.
9. A computer device comprising a memory and a processor; the memory is connected to the processor, the memory is used for storing a computer program, and the processor is used for calling the computer program to enable the computer device to execute the method of any one of claims 1 to 8.
10. A vision-based ingot measurement robot, comprising: an AGV bed, a post, a camera for shooting spindles, a stroboscope for polishing, a battery, and a computer device according to claim 9;
the bottom of the upright post is fixedly connected with the AGV base; the battery is fixedly connected with the AGV base;
The stroboscope and the camera are fixedly connected with the side wall of the upright post;
The battery is electrically connected with the camera, the stroboscope, the AGV base and the computer equipment respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410253926.5A CN118127683A (en) | 2024-03-06 | 2024-03-06 | Spindle speed measuring method based on vision, computer and measuring robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410253926.5A CN118127683A (en) | 2024-03-06 | 2024-03-06 | Spindle speed measuring method based on vision, computer and measuring robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118127683A true CN118127683A (en) | 2024-06-04 |
Family
ID=91245528
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410253926.5A Pending CN118127683A (en) | 2024-03-06 | 2024-03-06 | Spindle speed measuring method based on vision, computer and measuring robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118127683A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119313660A (en) * | 2024-12-16 | 2025-01-14 | 江苏格罗瑞节能科技有限公司 | Dynamic detection and feature extraction method of textile spindle speed |
-
2024
- 2024-03-06 CN CN202410253926.5A patent/CN118127683A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119313660A (en) * | 2024-12-16 | 2025-01-14 | 江苏格罗瑞节能科技有限公司 | Dynamic detection and feature extraction method of textile spindle speed |
| CN119313660B (en) * | 2024-12-16 | 2025-05-16 | 江苏格罗瑞节能科技有限公司 | Dynamic detection and feature extraction method of textile spindle speed |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118127683A (en) | Spindle speed measuring method based on vision, computer and measuring robot | |
| CN105841629A (en) | Photogrammetry monitoring system for monitoring inclination and sedimentation of cultural building relics | |
| CN102680478A (en) | Detection method and device of surface defect of mechanical part based on machine vision | |
| CN111962145A (en) | Method, device and equipment for detecting liquid level position of melt and computer storage medium | |
| CN108188835B (en) | Test device and test method for thermal elongation of CNC machine tool spindle based on machine vision | |
| CN110455378B (en) | Water meter small flow verification method based on machine vision | |
| CN108319979A (en) | A kind of framing recognition detection method based on scaling and rotation matching | |
| CN114066890A (en) | Gear defect detection method and device, computer equipment and storage medium | |
| CN118758945A (en) | Industrial product quality inspection system and method based on machine vision | |
| CN114972350B (en) | Method, device and equipment for detecting abnormality of mold and storage medium | |
| CN111578850B (en) | A measuring method for visually measuring the thickness of pile fabrics | |
| CN106767566B (en) | A kind of workpiece quality online monitoring and evaluation method and monitoring system | |
| CN107421956A (en) | A kind of raw silk or immersion silk appearance quality detecting device and detection method based on binocular vision | |
| CN112508995B (en) | A real-time dynamic measurement method of coal flow based on TOF camera | |
| CN115371543A (en) | Surface mounting precision calibration method | |
| CN117589063B (en) | Size detection method and size detection system | |
| US20060203254A1 (en) | Measurements of an axisymmetric part including helical coil springs | |
| CN105136617B (en) | A kind of interfacial tension measuring system | |
| CN117152703A (en) | Track tension control method and system for crawler lifting chassis | |
| CN113008267B (en) | Level ruler limit tilt qualified detection system and method based on image processing technology | |
| CN115541109A (en) | Method for monitoring unbalance of impeller based on machine vision | |
| CN114882036A (en) | Winding abnormity detection method for fiber fabric winding device | |
| CN111797695A (en) | Method and system for automatic identification of strand twist | |
| CN119756230B (en) | An automatic recognition and positioning method based on machine vision binocular measurement system | |
| CN119352201A (en) | A method, system, medium and computer for detecting abnormal state of a two-for-one twister |
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 |