Brake disc identification code recognition device based on machine vision and recognition method thereof

Abstract

The invention discloses a brake disc identification code recognition device based on machine vision and a recognition method thereof, relates to a passenger train part identification code recognition device, and solves the problems of low efficiency and easy misjudgment and missed judgment of manual recognition of brake disc manufacturing identification. A rotary motor is fixed on a piston rod of a lifting cylinder; the clamping air cylinder is fixed to a rotating shaft of the rotary motor, a piston rod of the clamping air cylinder can drive the clamp to clamp the brake disc, the lifting air cylinder can drive the brake disc to move in the axial direction of the lifting air cylinder, and the rotary motor can drive the brake disc to rotate in the circumferential direction of the lifting air cylinder. The image collecting assembly is used for collecting circumferential image information of the brake disc and uploading the circumferential image information to the upper computer, and the identification code of the identification area on the brake disc is recognized through the upper computer. The beneficial effects are that the identification speed is fast; the problems that in the prior art, time and labor are consumed in manual checking, and the identification accuracy is greatly influenced by human factors are solved, and repeated manual labor is reduced.

Description

Technical Field

[0001] The invention relates to a device for identifying identification codes of parts of a railway passenger car. Background Art

[0002] With the rapid development of railway transportation, the safe identification of railway passenger car brake discs has become crucial; the manufacturing identification code of railway passenger car brake discs contains important product information, such as manufacturer code, production date, product number or furnace number, etc.; the existing manual identification method is inefficient, prone to misjudgment and omission, and cannot meet the high quality and high efficiency requirements of railway production. Summary of the invention

[0003] The purpose of the present invention is to solve the problems of low efficiency and easy misjudgment and missed judgment in manual identification of brake disc manufacturing identification, and proposes a brake disc identification code recognition device and recognition method based on machine vision.

[0004] The brake disc identification code recognition device based on machine vision described in the present invention comprises a lifting cylinder, a rotary motor, a clamping cylinder, a fixture and an image acquisition component;

[0005] The rotary motor is fixed on the piston rod of the lifting cylinder;

[0006] The clamping cylinder is fixed on the rotating shaft of the rotary motor, and the piston rod of the clamping cylinder can drive the clamp to clamp the brake disc, so that the lifting cylinder can drive the brake disc to move along its axial direction, and the rotary motor can drive the brake disc to rotate along its circumferential direction;

[0007] The image acquisition component is used to acquire circumferential image information of the brake disc, and upload the circumferential image information to a host computer, and the host computer recognizes the identification code of the identification area on the brake disc.

[0008] Furthermore, the identification code recognition device also includes a frame, a slide plate, two slide rails and a crossbeam;

[0009] The frame is a "U"-shaped structure, and the open end of the "U"-shaped structure is fixed on the ground;

[0010] The crossbeam is fixed to the middle of the frame;

[0011] The top end of the lifting cylinder is fixed on the frame;

[0012] The image acquisition component is fixed on the side wall of the frame;

[0013] The upper ends of the two slide rails are respectively fixed to the top of the frame, the lower ends of the two slide rails are respectively fixed to the crossbeam, and the two slide rails are respectively located on both sides of the lifting cylinder; at the same time, the two slide rails are parallel to the piston rod of the lifting cylinder;

[0014] The slide plate is fixed to the bottom end of the piston rod of the lifting cylinder; and the slide plate slides along the length direction of the two slide rails;

[0015] The rotary motor is fixed on the slide plate.

[0016] Further, the identification code recognition device also includes a cylinder bottom plate;

[0017] The cylinder base plate is fixed on the rotating shaft of the rotary motor;

[0018] The clamping cylinder is fixed on the cylinder bottom plate.

[0019] Furthermore, the identification code recognition device also includes a light source component;

[0020] The light source assembly is fixed on the side wall of the frame, and the light source assembly is used to illuminate the brake disc.

[0021] Furthermore, the rotation angle of the rotating shaft of the rotary motor is 360 degrees to 400 degrees.

[0022] A method for identifying a manufacturing identification code of a railway passenger car brake disc based on machine vision, wherein the identification method is implemented based on a brake disc identification code identification device based on machine vision;

[0023] The identification method comprises the following steps:

[0024] Step 1: Use an image acquisition component to acquire circumferential images of the brake disc to obtain circumferential image information;

[0025] Step 2: The host computer first intercepts the circumferential image information obtained by the image acquisition component along the width direction to obtain a strip image with the entire identification area, and then divides the strip image into equal lengths, and selects the image with the identification area from the images after equal length division as the pre-marked image;

[0026] Step 3: Perform positioning and OCR character annotation on the pre-annotated image in step 2 to obtain an image to be recognized;

[0027] Step 4: Input the image to be recognized obtained in step 3 into the character recognition algorithm model and output the identification code.

[0028] Furthermore, the specific steps of obtaining circumferential image information in step 1 are:

[0029] Step 1: When the brake disc is directly below the fixture, the piston rod of the lifting cylinder is controlled to extend so that the fixture contacts the brake disc;

[0030] Step 1 and 2, drive the clamp to clamp the brake disc by controlling the clamping cylinder;

[0031] Step 13: Control the piston rod of the lifting cylinder to shorten so that the fixture and the brake disc move upward. When the brake disc and the image acquisition component are at the same level, the piston rod of the lifting cylinder stops moving;

[0032] Step 14: Turn on the image acquisition component, and at the same time, the rotating shaft of the rotary motor starts to rotate. When the rotating shaft of the rotary motor rotates through the rotation angle, the image acquisition component completes acquiring the circumferential image information.

[0033] Furthermore, the specific formula for dividing the strip image into equal lengths in step 2 is:

[0034]

[0035] Among them, s is the interception length; i is the number of interceptions.

[0036] Furthermore, after the pre-annotated image is formed in step 2, contrast adjustment, denoising and geometric transformation are sequentially performed on the pre-annotated image, and then step 3 is performed.

[0037] Furthermore, the character recognition algorithm model in step 4 is obtained through neural network model training. The specific training method is:

[0038] Step 41: Collect circumferential image information of multiple brake discs to obtain a data set;

[0039] Step 42: intercept the data set obtained in step 41 with equal width and step length, select images with brake disc manufacturing logo from the intercepted images, and obtain a preprocessed data set;

[0040] Step 43: preprocess the preprocessed data set obtained in step 42 to obtain a pre-labeled data set;

[0041] Step 44: perform positioning annotation and OCR character annotation on the pre-annotated data set obtained in step 43 to obtain a pre-training data set;

[0042] Step 45: Input the pre-trained data set obtained in step 44 into the neural network model for training, optimize the parameters of the neural network model, and form a character recognition algorithm model.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] The invention solves the problem in the prior art that the railway passenger car brake disc is manually viewed directly, which is time-consuming and labor-intensive, and the recognition efficiency and recognition accuracy are greatly affected by human factors.

[0045] The invention discloses a method for identifying the manufacturing mark of a railway passenger car brake disc based on machine vision. The method adopts width interception and performs equal-step segmentation on the image after width interception, accurately obtains the ROI area, removes the image without the mark area, and performs image enhancement and noise reduction processing on the image, thereby reducing the time of training and reasoning, speeding up the efficiency, reducing misjudgment, and improving the accuracy. The recognition accuracy is greater than 95%, which meets the production needs of industrial enterprises.

[0046] The character recognition algorithm model in the present invention can better process high-dimensional data, extract important features in images, and train the model by a large amount of annotated data, thereby ensuring the accuracy of recognition.

[0047] The brake disc identification code recognition device based on machine vision described in the present invention adopts an encoder to control the image acquisition component to scan, which takes a total of 10 seconds and has a fast recognition speed. It solves the problem in the prior art that manual viewing is time-consuming and labor-intensive and the recognition accuracy is greatly affected by human factors, thereby reducing repetitive manual labor.

[0048] The invention relates to the field of identification code recognition of railway passenger car parts. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a schematic diagram of the overall structure of a brake disc identification code recognition device based on machine vision according to a specific implementation mode 1;

[0050] Figure 2 This is a physical picture of the brake disc in the first specific implementation mode;

[0051] Figure 3 This is a flow chart of a method for identifying a manufacturing identification code of a railway passenger car brake disc based on machine vision in specific implementation method six.

[0052] Among them, 1 is a frame; 2 is a slide plate; 3 is a lifting cylinder; 4 is a rotary motor; 5 is a clamping cylinder; 6 is a cylinder bottom plate; 7 is a fixture; 8 is a light source component; 9 is an image acquisition component; 10 is a brake disc; 11 is a slide rail; 12 is a crossbeam; and 13 is a marking area. DETAILED DESCRIPTION

[0053] Specific implementation method 1. Combination Figure 1 to Figure 2 The present embodiment is described as a brake disc identification code recognition device based on machine vision, wherein the identification code recognition device comprises a lifting cylinder 3, a rotary motor 4, a clamping cylinder 5, a fixture 7 and an image acquisition component 9;

[0054] The rotary motor 4 is fixed on the piston rod of the lifting cylinder 3;

[0055] The clamping cylinder 5 is fixed on the rotating shaft of the rotary motor 4, and the piston rod of the clamping cylinder 5 can drive the clamp 7 to clamp the brake disc 10, so that the lifting cylinder 3 can drive the brake disc 10 to move along its axial direction, and the rotary motor 4 can drive the brake disc 10 to rotate along its circumferential direction;

[0056] The image acquisition component 9 is used to acquire circumferential image information of the brake disc 10 and upload the circumferential image information to a host computer, and the host computer recognizes the identification code of the identification area 13 on the brake disc 10 .

[0057] In this embodiment, the image acquisition component 9 adopts a linear array camera; the image acquisition component 9 is controlled by an encoder; the clamping cylinder 5 and the clamp 7 constitute a grasping component, and the grasping component is used to accurately grasp and lift the brake disc 10 to the image detection position after the brake disc 10 is directly below the clamp 7; the clamp 7 is composed of two grippers, and the distance between the two grippers is controlled by the clamping cylinder 5. When the two grippers of the clamp 7 are close, the two grippers extend into the center hole of the brake disc 10. In the process of extending the piston rod of the clamping cylinder 5, the distance between the two grippers of the clamp 7 gradually increases, so that the two grippers are in close contact with the inner wall of the center hole of the brake disc 10, thereby completing the radial grasping of the brake disc 10 by the grasping component; the rotating shaft of the rotary motor 4 drives the grasping component and the brake disc 10 to be selected, so that the image acquisition component 9 collects the complete circumferential image information of the brake disc 10;

[0058] The working principle of the identification code recognition device is:

[0059] When the piston rod of the clamping cylinder 5 moves in telescopic motion, it drives the clamp 7 to clamp or release the brake disc 10. After the clamp 7 clamps the brake disc, the lifting and lowering motion of the lifting cylinder 3 drives the rotary motor 4 to move up and down, thereby raising the brake disc 10 clamped by the clamp 7 to the image detection position; after the brake disc 10 is raised to the image detection position, the rotary reduction motor 4 works to drive the clamped and raised brake disc 10 to rotate according to the rotation angle, and the image acquisition component 9 captures a complete circumferential image of the brake disc 10 through the rotation of the brake disc 10.

[0060] Specific implementation method 2: This implementation method further defines the brake disc identification code recognition device based on machine vision described in specific implementation method 1. In this implementation method, the identification code recognition device further includes a frame 1, a slide plate 2, two slide rails 11 and a crossbeam 12;

[0061] The frame 1 is a "U"-shaped structure, and the open end of the "U"-shaped structure is fixed on the ground;

[0062] The crossbeam 12 is fixed to the middle of the frame 1;

[0063] The top end of the lifting cylinder 3 is fixed on the frame 1;

[0064] The image acquisition component 9 is fixed on the side wall of the frame 1;

[0065] The upper ends of the two slide rails 11 are respectively fixed to the top of the frame 1, and the lower ends of the two slide rails 11 are respectively fixed to the crossbeam 12, and the two slide rails 11 are respectively located on both sides of the lifting cylinder 3; at the same time, the two slide rails 11 are parallel to the piston rod of the lifting cylinder 3;

[0066] The slide plate 2 is fixed to the bottom end of the piston rod of the lifting cylinder 3; and the slide plate 2 slides along the length direction of the two slide rails 11;

[0067] The rotary motor 4 is fixed on the slide plate 2 .

[0068] In this embodiment, the frame 1 is installed on the automatic conveying line of the brake disc 10; the frame 1 is used to fix the lifting cylinder 3 and the image acquisition component 9; and through the setting of the slide plate 2 and the slide rail 11, the lifting cylinder 3 will not rotate autonomously during the extension and retraction process, avoiding the uncontrolled rotation angle of the rotary motor 4, so that the image acquisition component 9 can capture a complete circumferential image of the brake disc 10; and through the setting of the slide plate 2, the structural stability of the entire identification device can be strengthened, reducing the possibility of damage to the lifting cylinder 3 during the lifting process.

[0069] Specific implementation method 3: This implementation method further limits the brake disc identification code recognition device based on machine vision described in specific implementation method 1 or 2. In this implementation method, the identification code recognition device further includes a cylinder bottom plate 6;

[0070] The cylinder base plate 6 is fixed on the rotating shaft of the rotary motor 4;

[0071] The clamping cylinder 5 is fixed on a cylinder base plate 6 .

[0072] In this embodiment, by adding the cylinder bottom plate 6 , the fixation of the outer wall of the clamping cylinder 5 and the rotating shaft of the rotary motor 4 is facilitated, and the cylinder bottom plate 6 can increase the firmness of the outer wall of the clamping cylinder 5 .

[0073] Specific implementation method 4: This implementation method further limits the brake disc identification code recognition device based on machine vision described in specific implementation method 1. In this implementation method, the identification code recognition device further includes a light source assembly 8;

[0074] The light source assembly 8 is fixed on the side wall of the frame 1 , and the light source assembly 8 is used to illuminate the brake disk 10 .

[0075] In this embodiment, the light source assembly 8 is disposed close to the image acquisition assembly 9. By adding the light source assembly 8, sufficient lighting is provided to the image acquisition assembly 9, thereby ensuring that the manufacturing mark of the brake disc 10 is clearly visible.

[0076] Specific implementation method 5: This implementation method further limits the brake disc identification code recognition device based on machine vision described in specific implementation method 1. In this implementation method, the rotation angle of the rotating shaft of the rotary motor 4 is 360 degrees to 400 degrees.

[0077] In this embodiment, after multiple identification verifications, when the rotation angle of the rotating shaft of the rotary motor 4 is between 360 degrees and 400 degrees, the collection time is minimized while ensuring that the complete circumferential image information of the brake disc 10 is collected; if the rotation angle is too large, the collection time is wasted and the recognition efficiency is affected.

[0078] Specific implementation method VI. Combination Figure 3 This embodiment is described. This embodiment describes a method for identifying a manufacturing identification code of a railway passenger car brake disc based on machine vision. The identification method is implemented based on a brake disc identification code identification device based on machine vision described in Specific Embodiment 1.

[0079] The identification method comprises the following steps:

[0080] Step 1: Use the image acquisition component 9 to acquire circumferential images of the brake disc 10 to obtain circumferential image information;

[0081] Step 2: The host computer first intercepts the circumferential image information obtained by the image acquisition component 9 along the width direction to obtain a strip image with the entire identification area 13, and then divides the strip image into equal lengths, and selects the image with the identification area 13 from the images after the equal length division as the pre-marked image;

[0082] Step 3: Perform positioning and OCR character annotation on the pre-annotated image in step 2 to obtain an image to be recognized;

[0083] Step 4: Input the image to be recognized obtained in step 3 into the character recognition algorithm model and output the identification code.

[0084] In this embodiment, in step three, the host computer performs a width cut on the circumferential image information acquired by the image acquisition component 9 to obtain a strip image with the entire identification area 13, and divides the strip image into equal lengths, thereby removing the image portion that does not contain the identification code 13, reducing invalid recognition in subsequent steps, and achieving the purpose of improving the host computer's recognition speed of image information and improving recognition accuracy; the character recognition algorithm model in step four adopts the convolutional neural network CNN through the design of local connection, weight sharing, translation invariance and sparse connection, which can better process high-dimensional data and extract important features in the image, and train the model through a large amount of labeled data to ensure recognition accuracy.

[0085] The recognition method adopts width capture, and performs equal-step segmentation on the image after width capture, accurately obtains the ROI area, removes the image of the unmarked area 13, and enhances and reduces noise on the image, thereby reducing the time of training and reasoning, speeding up efficiency, reducing misjudgment, and improving accuracy. The recognition accuracy is greater than 95%, which meets the production needs of industrial enterprises. The purpose of positioning and marking the pre-marked image in step three is to prevent the order of the identification codes contained in the equal-step segmentation image from being confused, and then provide recognition accuracy through positioning and marking.

[0086] Specific implementation method 7: This implementation method further limits the brake disc identification code recognition method based on machine vision described in specific implementation method 6. In this implementation method, the specific steps of obtaining circumferential image information in step 1 are:

[0087] Step 11: When the brake disc 10 is located directly below the fixture 7, the piston rod of the lifting cylinder 3 is controlled to extend so that the fixture 7 is in contact with the brake disc 10;

[0088] Step 1 and 2, driving the clamp 7 to clamp the brake disc 10 by controlling the clamping cylinder 5;

[0089] Step 13: Control the piston rod of the lifting cylinder 3 to shorten so that the clamp 7 and the brake disc 10 move upward. When the brake disc 10 and the image acquisition component 9 are at the same level, the piston rod of the lifting cylinder 3 stops moving.

[0090] Step 14: Turn on the image acquisition component 9, and at the same time, the rotating shaft of the rotary motor 4 starts to rotate. When the rotating shaft of the rotary motor 4 rotates through the rotation angle, the image acquisition component 9 completes acquiring the circumferential image information.

[0091] In this embodiment, through the cooperation of the lifting cylinder 3, the clamping cylinder 5, the clamp 7 and the rotary motor 4, the image acquisition component 9 can acquire complete circumferential image information of the brake disc 10 in the shortest time.

[0092] Specific implementation eight: This implementation further defines the brake disc identification code recognition method based on machine vision described in specific implementation nine. In this implementation, the specific formula for dividing the strip image into equal lengths in step two is:

[0093]

[0094] Among them, s is the interception length; i is the number of interceptions.

[0095] In this embodiment, the width of the strip image is w, and the total width of the circumferential image information is n, then n>w; and the width w of the strip image is greater than the width of the identification area 13, and at the same time, the closer the width w of the strip image is to the width of the identification area 13, the faster the host computer processes the image to be identified in the subsequent process; the interception length s is less than the length of the identification area 13, but must be greater than the width of a single character; wherein, the 11 characters contained in the identification code are arranged side by side with equal spacing, and the length of the identification area 13 is equal to the sum of the width of the 11 characters and the spacing between 10 adjacent characters.

[0096] Specific implementation method nine: This implementation method further limits the brake disc identification code recognition method based on machine vision described in specific implementation method six. In this implementation method, after the pre-labeled image is formed in step two, the pre-labeled image is first subjected to contrast adjustment, denoising and geometric transformation in sequence, and then step three is executed.

[0097] In this embodiment, the quality of the pre-labeled image is improved and the diversity of the data is increased through contrast adjustment, denoising and geometric transformation.

[0098] Specific implementation method 10: This implementation method further defines the brake disc identification code recognition method based on machine vision described in specific implementation method 6. In this implementation method, the character recognition algorithm model in step 4 is obtained by training a neural network model. The specific training method is:

[0099] Step 41: Collect circumferential image information of multiple brake discs 10 to obtain a data set;

[0100] Step 42: intercept the data set obtained in step 41 with equal width and step length, select images with brake disc manufacturing logo from the intercepted images, and obtain a preprocessed data set;

[0101] Step 43: preprocess the preprocessed data set obtained in step 42 to obtain a pre-labeled data set;

[0102] Step 44: perform positioning annotation and OCR character annotation on the pre-annotated data set obtained in step 43 to obtain a pre-training data set;

[0103] Step 45: Input the pre-trained data set obtained in step 44 into the neural network model for training, optimize the parameters of the neural network model, and form a character recognition algorithm model.

[0104] In this embodiment, the accuracy of the character recognition algorithm model is guaranteed by training and optimizing the parameters of the neural network model using a large amount of labeled data in the pre-training data set.

[0105] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A brake disc identification code recognition device based on machine vision, characterized in that: The identification code recognition device comprises a lifting cylinder (3), a rotary motor (4), a clamping cylinder (5), a clamp (7) and an image acquisition component (9); The rotary motor (4) is fixed on the piston rod of the lifting cylinder (3); The clamping cylinder (5) is fixed on the rotating shaft of the rotary motor (4), and the piston rod of the clamping cylinder (5) can drive the clamp (7) to clamp the brake disc (10), so that the lifting cylinder (3) can drive the brake disc (10) to move along its axial direction, and the rotary motor (4) can drive the brake disc (10) to rotate along its circumferential direction; The image acquisition component (9) is used to acquire circumferential image information of the brake disc (10), and upload the circumferential image information to a host computer, and the host computer identifies the identification code of the identification area (13) on the brake disc (10).

2. The brake disc identification code recognition device based on machine vision according to claim 1, characterized in that: The identification code recognition device also includes a frame (1), a slide plate (2), two slide rails (11) and a crossbeam (12); The frame (1) is a "U"-shaped structure, and the open end of the "U"-shaped structure is fixed on the ground; The crossbeam (12) is fixed to the middle part of the frame (1); The top end of the lifting cylinder (3) is fixed on the frame (1); The image acquisition component (9) is fixed on the side wall of the frame (1); The upper ends of the two slide rails (11) are respectively fixed to the top of the frame (1), the lower ends of the two slide rails (11) are respectively fixed to the crossbeam (12), and the two slide rails (11) are respectively located on both sides of the lifting cylinder (3); at the same time, the two slide rails (11) are parallel to the piston rod of the lifting cylinder (3); The slide plate (2) is fixed to the bottom end of the piston rod of the lifting cylinder (3); and the slide plate (2) slides along the length direction of the two slide rails (11); The rotary motor (4) is fixed on the slide plate (2).

3. A brake disc identification code recognition device based on machine vision according to claim 1 or 2, characterized in that: The identification code recognition device also includes a cylinder bottom plate (6); The cylinder base plate (6) is fixed on the rotating shaft of the rotary motor (4); The clamping cylinder (5) is fixed on a cylinder bottom plate (6).

4. The brake disc identification code recognition device based on machine vision according to claim 1, characterized in that: The identification code recognition device also includes a light source component (8); The light source assembly (8) is fixed on the side wall of the frame (1), and the light source assembly (8) is used to illuminate the brake disc (10).

5. The brake disc identification code recognition device based on machine vision according to claim 1, characterized in that: The rotation angle of the rotating shaft of the rotary motor (4) is 360 degrees to 400 degrees.

6. A method for identifying the manufacturing identification code of a railway passenger car brake disc based on machine vision, wherein the identification method is implemented based on the brake disc identification code identification device based on machine vision as claimed in claim 1; It is characterized in that The identification method comprises the following steps: Step 1: using an image acquisition component (9) to acquire circumferential images of the brake disc (10) to obtain circumferential image information; Step 2: The host computer first intercepts the circumferential image information acquired by the image acquisition component (9) along the width direction to obtain a strip image with the entire identification area (13), and then divides the strip image into equal lengths, and selects the image with the identification area (13) from the images after the equal length division as the pre-marked image; Step 3: Perform positioning and OCR character annotation on the pre-annotated image in step 2 to obtain an image to be recognized; Step 4: Input the image to be recognized obtained in step 3 into the character recognition algorithm model and output the identification code.

7. The method for identifying the manufacturing mark of a railway passenger car brake disc based on machine vision according to claim 6, characterized in that: The specific steps for obtaining circumferential image information in step 1 are: Step 11: When the brake disc (10) is located directly below the clamp (7), the piston rod of the lifting cylinder (3) is controlled to extend so that the clamp (7) contacts the brake disc (10); Step 1 and 2, driving the clamp (7) to clamp the brake disc (10) by controlling the clamping cylinder (5); Step 13: Control the piston rod of the lifting cylinder (3) to shorten so that the clamp (7) and the brake disc (10) move upward. When the brake disc (10) and the image acquisition component (9) are at the same level, the piston rod of the lifting cylinder (3) stops moving. Step 14: Turn on the image acquisition component (9), and at the same time, the rotating shaft of the rotary motor (4) starts to rotate. When the rotating shaft of the rotary motor (4) rotates through the rotation angle, the image acquisition component (9) completes acquiring the circumferential image information.

8. The method for identifying the manufacturing mark of a railway passenger car brake disc based on machine vision according to claim 6, characterized in that: The specific formula for dividing the strip image into equal lengths in step 2 is: Among them, s is the interception length; i is the number of interceptions.

9. The method for identifying the manufacturing mark of a railway passenger car brake disc based on machine vision according to claim 6, characterized in that: After the pre-annotated image is formed in step 2, contrast adjustment, denoising and geometric transformation are performed on the pre-annotated image in sequence, and then step 3 is executed.

10. The method for identifying the manufacturing mark of a railway passenger car brake disc based on machine vision according to claim 6, characterized in that: The character recognition algorithm model in step 4 is obtained through neural network model training. The specific training method is: Step 41: Collect circumferential image information of a plurality of brake discs (10) to obtain a data set; Step 42: intercept the data set obtained in step 41 with equal width and step length, select images with brake disc manufacturing logo from the intercepted images, and obtain a preprocessed data set; Step 43: preprocess the preprocessed data set obtained in step 42 to obtain a pre-labeled data set; Step 44: perform positioning annotation and OCR character annotation on the pre-annotated data set obtained in step 43 to obtain a pre-training data set; Step 45: Input the pre-trained data set obtained in step 44 into the neural network model for training, optimize the parameters of the neural network model, and form a character recognition algorithm model.

Images