Method and system for automatically collecting abrasion loss of milling cutter, medium and computing equipment

Abstract

The invention relates to the field of milling cutter abrasion state detection, and discloses a milling cutter abrasion loss automatic collection method and system, a medium and computing equipment, and the method comprises the steps that a to-be-detected milling cutter is driven to rotate through an automatic rotating cutter holder device so as to obtain images of all cutting edges of the milling cutter, and the cutting edges in all the images are in a horizontal state; the images of all the cutting edges serve as input data, batch prediction is conducted on the input data through a prediction model trained by the yov9, and wear areas in the predicted images are obtained and marked; determining the highest abrasion point in the marked abrasion area, and measuring the distance from the highest point to the horizontal line where the cutting edge is located to obtain the abrasion width. According to the invention, the problems of low efficiency and inaccurate measurement of the wear value of the cutter measured by an off-line optical image method can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of milling cutter wear state detection, and in particular to a method, system, medium and computing device for automatically collecting milling cutter wear based on YOLOv9. Background Art

[0002] The tool is the core element of the processing system. It has a direct impact on product quality. Once the tool fails and is not discovered in time, it will directly affect the product processing quality and production efficiency. In serious cases, it may even cause machine damage and endanger personnel safety. Therefore, monitoring the status of the tool is of great significance to manufacturing companies.

[0003] Existing tool condition monitoring is mainly carried out through direct measurement and indirect measurement. The direct method obtains the wear of the tool's back face through a specific direct measurement method to determine the tool's condition, including optical imaging method, contact resistance measurement method and radioactive element method, etc. The disadvantage is that the usage scenarios are limited or can only be performed when the tool is not working and it is usually very time-consuming when the tool is not working; the indirect method is to measure signals related to the tool and indirectly obtain the tool's condition through mapping relationships, including mechanical signals, vibration signals, acoustic emission signals, etc. The disadvantage is that too many sensors directly lead to increased costs and there will be a lot of redundant information interference.

[0004] Many offline optical imaging methods use traditional image processing methods, such as the paper "CNC Disk Milling Cutter Wear Status Detection Method Based on Machine Vision", which uses edge detection to extract wear features after image preprocessing. However, the accuracy is not high and the adaptability to different wear areas is insufficient, making it easy to fail to detect. Deep learning methods, such as the paper "Research and Application of Milling Cutter Status Detection Method Based on Deep Learning", reduce the pixels of the wear area of ​​the blade due to taking wide-angle photos of the tool, and small targets are not easy to detect, resulting in reduced accuracy and failure to detect feature areas. Summary of the invention

[0005] In view of the above problems, the purpose of the present invention is to provide a method, system, medium and computing device for automatically collecting milling cutter wear, which can solve the problems of low efficiency and inaccurate measurement of tool wear values ​​using offline optical imaging methods.

[0006] To achieve the above-mentioned purpose, in the first aspect, the technical solution adopted by the present invention is: a method for automatically collecting the wear of a milling cutter, which specifically includes: driving the milling cutter to be tested to rotate by an automatic rotating tool holder device to obtain images of all the blades of the milling cutter, and the blades in all images are in a horizontal state; taking the images of all the blades as input data, batch predicting the input data through the prediction model trained by yolov9, obtaining the wear area in the predicted image and marking it; determining the highest point of wear in the marked wear area, measuring the distance from the highest point to the horizontal line where the blade is located, and obtaining the wear width.

[0007] Further, the automatic rotating tool holder device includes: a milling cutter fixing bracket, a synchronous belt, a synchronous belt pulley, a motor bracket, a motor, a base, a tapered roller bearing and a motor drive controller;

[0008] The milling cutter fixing bracket is arranged on the top of the base through a tapered roller bearing, and the milling cutter to be tested is installed on the milling cutter fixing bracket and rotates with the milling cutter fixing bracket;

[0009] The motor bracket is arranged on the side of the base, the motor is mounted on the motor bracket, and the output shaft of the motor is coaxially connected with the synchronous belt pulley;

[0010] The synchronous belt pulley is connected to the milling cutter fixing bracket through a synchronous belt, so that the synchronous belt pulley is driven by the motor to rotate, thereby driving the milling cutter fixing bracket to rotate;

[0011] The motor drive controller drives the motor to work according to the set rotation angle, so that the motor drives the milling cutter fixing bracket to rotate according to the fixed rotation angle.

[0012] Furthermore, the milling cutter fixing bracket is a hollow pulley, the upper part of which has a slot for fixing the milling cutter to be tested, and the hollow pulley and the tapered roller bearing adopt an interference fit;

[0013] The diameter of the hollow pulley is much larger than the diameter of the synchronous belt pulley.

[0014] Furthermore, an oblong hole for installing a motor bracket is provided on the side of the base, and the motor bracket is installed in the oblong hole by means of screws and nuts, so that the position of the motor bracket can be adjusted through the oblong hole and thus the preload force of the synchronous belt can be adjusted.

[0015] Furthermore, the milling cutter to be measured is driven to rotate by the automatic rotating tool holder device to obtain images of all cutting edges of the milling cutter, and the cutting edges in all images are in a horizontal state, including:

[0016] Set the target angle of the encoder on the motor, and use the motor drive controller with a built-in PID control algorithm to rotate the milling cutter to the target angle and collect the blade image;

[0017] Opencv is used to detect the edge of the blade image and Hough transform is used to detect the tool angle. The milling cutter angle is manually adjusted according to the detected angle so that the initial state of the milling cutter is horizontal.

[0018] Furthermore, the prediction model trained by yolov9 includes: labeling all blade images with Labelme, selecting the worn area and making it into a data set, and using the data set as a training set to train the prediction model of yolov9.

[0019] Furthermore, the prediction model trained by yolov9 is used to perform batch prediction on the input data, and the wear areas in the predicted images are obtained and marked, including:

[0020] The predicted image is obtained through the prediction model trained by yolov9, and instance segmentation is performed, and the segmented wear area is marked in red;

[0021] The segmented image is extracted with opencv and binarized to obtain a binary image containing only pixels in the worn area, and the wear width of the worn area is measured by pixel scanning.

[0022] In the second aspect, the technical solution adopted by the present invention is: a system for automatically collecting milling cutter wear, which includes: an image acquisition module, which drives the milling cutter to be tested to rotate through an automatic rotating tool holder device to obtain images of all cutting edges of the milling cutter, and the cutting edges in all images are in a horizontal state; a wear area acquisition module, which takes the images of all cutting edges as input data, performs batch prediction on the input data through a prediction model trained by yolov9, obtains and marks the wear area in the predicted image; a wear width determination module, which determines the highest point of wear in the marked wear area, measures the distance from the highest point to the horizontal line where the cutting edge is located, and obtains the wear width.

[0023] In a third aspect, the technical solution adopted by the present invention is: a computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions, and when the instructions are executed by a computing device, the computing device executes any one of the above methods.

[0024] In a fourth aspect, the technical solution adopted by the present invention is: a computing device, comprising: one or more processors, a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the above methods.

[0025] The present invention adopts the above technical solution, which has the following advantages:

[0026] 1. The present invention uses yolov9 to perform target detection and instance segmentation in the wear area. Yolov9 has significantly improved the detection accuracy while maintaining high speed. Yolov9 introduces a new loss function or training strategy to improve the accuracy of the model and has stronger small target detection capabilities. Yolov9 improves the feature fusion strategy and has strong detection capabilities for targets of different scales.

[0027] 2. The present invention designs an automatic rotating tool holder, and the tool is rotated in situ by means of a designed hollow pulley milling cutter fixing bracket, so as to achieve the purpose of photographing different blades.

[0028] 3. The present invention uses an integral separation position PID to control the motor drive belt, which reduces the influence of the integral term in the front end of the control and increases the influence in the back end of the control, thereby reducing the vibration of the tool after rotation and increasing the control accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is an overall flow chart of the method for automatically collecting the wear amount of a milling cutter in an embodiment of the present invention;

[0030] Figure 2 Schematic diagram of the wear area of ​​the milling cutter in an embodiment of the present invention;

[0031] Figure 3 This is a schematic structural diagram of an automatic rotating tool holder device in an embodiment of the present invention;

[0032] Figure 4 Schematic diagram of the control flow of the automatic rotating tool holder device in an embodiment of the present invention;

[0033] Figure 5 It is a schematic diagram of the automatic milling cutter wear collection and measurement process based on yolov9 in an embodiment of the present invention;

[0034] Figure 6 This is a schematic diagram of the installation position of the microscope camera in an embodiment of the present invention;

[0035] Reference numerals:

[0036] 1-hollow pulley milling cutter fixing bracket; 2-synchronous belt; 3-synchronous belt pulley; 4-motor bracket; 5-DC reduction motor; 6-base; 7-tapered roller bearing; 8-microscope camera; 9-camera bracket. DETAILED DESCRIPTION

[0037] In order to use the optical imaging method to measure the wear value of the tool, it is necessary to use a microscope and an industrial camera to take the image of the milling cutter and measure the wear value. In order to increase the pixels of the wear area to improve the accuracy of feature recognition, the microscope needs to be adjusted to the maximum magnification, resulting in only one blade being visible in the photo, but the milling cutter has four blades, so when measuring the wear value, it is necessary to manually rotate the tool to take a picture of the next blade, and use the measurement system of the microscope camera to manually measure the width of the wear value. Manually rotating the tool leads to low efficiency, and manually measuring the wear value leads to inaccurate measurement results. If different people manually measure the wear value, the different habits of different people lead to greater deviations in the measured wear value. Therefore, in order to solve the problem of low efficiency and inaccuracy in measuring the wear value of the tool by the offline optical imaging method, the present invention provides a method, system, medium and computing device for automatically collecting the wear value of the milling cutter.

[0038] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present invention.

[0039] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0040] In one embodiment of the present invention, a method for automatically collecting the wear of a milling cutter is provided. In this embodiment, Figure 1 As shown, the method comprises the following steps:

[0041] 1) The milling cutter to be measured is driven to rotate by an automatic rotating tool holder device to obtain images of all cutting edges of the milling cutter, and the cutting edges in all images are in a horizontal state;

[0042] In this embodiment, the Hough line is used to detect and calculate the angle of the straight line, and the initial angle of the milling cutter is manually adjusted to 0° according to the angle data. The rotation angle of the motor is accurately controlled by the PID controller so that the blade of the milling cutter is in a horizontal state each time it rotates.

[0043] 2) Taking all blade images as input data, batch prediction is performed on the input data through the prediction model trained by yolov9, and the wear area in the predicted image is obtained and marked;

[0044] 3) Determine the highest point of wear in the marked wear area, measure the distance from the highest point to the horizontal line where the blade is located, and obtain the wear width.

[0045] In the above step 1), after the features of the milling cutter are extracted using yolov9, the feature area (such as Figure 2 The wear width is measured by finding the highest point of wear and measuring the distance from the highest point to the blade straight line (as shown in the red area in the figure). Figure 1 If the blade is not horizontal, you need to detect the highest point and the blade straight line (as shown in the yellow line in Figure 1 The blue line in the figure shows the coordinate system (shown in the figure) and a coordinate system is established to measure the position and angle of the blade straight line, and the function of the blade straight line is obtained. At the same time, the coordinates of the highest point of wear in the coordinate system are measured, and finally the distance from the highest point to the blade straight line is calculated. However, the shapes of the highest points are different, and it is difficult to detect them using conventional corner point detection methods. At the same time, since the blade is no longer flat when it is worn, it is also difficult to use Hough transform for straight line detection. If the blade straight line cannot be detected, the function of the blade straight line cannot be calculated. Therefore, it is necessary to ensure that the blade is horizontal in the captured image, and the present invention achieves this by automatically rotating the blade holder device.

[0046] like Figure 3 As shown, the automatic rotating tool holder device includes: a milling cutter fixing bracket 1, a synchronous belt 2, a synchronous belt pulley 3, a motor bracket 4, a motor 5, a base 6, a tapered roller bearing 7 and a motor drive controller. Among them:

[0047] The milling cutter fixing bracket 1 is arranged on the top of the base 6 through a tapered roller bearing 7, and the milling cutter to be tested is installed on the milling cutter fixing bracket 1 and rotates with the milling cutter fixing bracket 1;

[0048] The motor bracket 4 is arranged on the side of the base 6, the motor 5 is mounted on the motor bracket 4, and the output shaft of the motor 5 is coaxially connected with the synchronous belt pulley 3;

[0049] The synchronous belt pulley 3 is connected to the milling cutter fixing bracket 1 through the synchronous belt 2, so that the synchronous belt pulley 3 is driven by the motor 5 to rotate, thereby driving the milling cutter fixing bracket 1 to rotate;

[0050] The motor driving controller drives the motor 5 to work according to the set rotation angle, so that the motor 5 drives the milling cutter fixing bracket 1 to rotate at a fixed rotation angle.

[0051] In this embodiment, the motor 5 is a deceleration DC motor with an encoder, and the deceleration DC motor is mounted on the motor bracket 4 by screws. Among them, the motor bracket 4 and the DC deceleration motor are connected by six screws, and the synchronous belt pulley 3 and the DC deceleration motor are connected by one screw.

[0052] In this embodiment, in order to realize the rotation of the tool, the milling cutter fixing bracket 1 is a hollow pulley, and the upper part of the hollow pulley has a slot for fixing the milling cutter to be tested. The hollow pulley is installed on the tapered roller bearing 7 to facilitate disassembly and maintenance, and the hollow pulley and the tapered roller bearing 7 adopt an interference fit, and the tapered roller bearing 7 and the base 6 adopt an interference fit.

[0053] Among them, the diameter of the hollow pulley is much larger than the diameter of the synchronous belt pulley 3. Since the present invention uses a small pulley (i.e., the synchronous belt pulley 3) to drive a large pulley (i.e., the hollow pulley) for belt transmission, a higher reduction ratio is generated. Due to the high transmission ratio, the accuracy of the rotation angle measured by the encoder on the motor can be improved, so that the angle of each rotation is fixed, and the use of a reduction DC motor plus an encoder reduces the cost.

[0054] In this embodiment, the side of the base 6 is provided with an oblong hole for installing the motor bracket 4, and the motor bracket 4 is installed in the oblong hole by screws and nuts, so that the position of the motor bracket 4 can be adjusted through the oblong hole to adjust the preload force of the synchronous belt 2. Among them, four pairs of screws and nuts are used for installation between the motor bracket 4 and the base 6.

[0055] In this embodiment, the motor drive controller uses stm32f103zet6 as the main control chip and L298N as the motor driver. The integral separation position PID is used to control the motor drive synchronous belt 2. The formula of the integral separation position PID is:

[0056]

[0057] Where e(k) is the deviation signal, K p is the proportionality coefficient, K i is the integration coefficient, K d is the differential coefficient, T is the sampling time, β is the switching coefficient of the integral term, and ε is the set threshold.

[0058] Since the control accuracy is increased and the vibration of the motor is reduced, the position of the blade for taking the photo is fixed after rotation, which is convenient for image processing.

[0059] In the above embodiment, Figure 6 As shown, the microscope camera 8 for taking pictures of the blade is arranged on the tool holder for mounting the milling cutter to be tested, directly above the milling cutter fixing bracket 1. In this embodiment, the microscope camera 8 can be mounted on the camera bracket 9 and is located directly above the milling cutter fixing bracket 1.

[0060] Among them, STM32 uses USB protocol to communicate with the microscope camera, and controls the microscope camera to take pictures of the blade after each rotation of the knife holder.

[0061] In this embodiment, the milling cutter to be measured is driven to rotate by the automatic rotating tool holder device to obtain images of all the cutting edges of the milling cutter, and the cutting edges in all images are in a horizontal state, such as Figure 4 As shown, the following steps are included:

[0062] 1.1) Set the target angle of the encoder on the motor 5, and the motor drive controller has a built-in PID control calculation method to rotate the milling cutter to the target angle and collect the blade image;

[0063] Specifically, the current angle and the target angle read by the motor encoder are used as inputs of the PID controller to output a PWM control signal of the motor 5 so that the milling cutter rotates to the target angle;

[0064] For example, when photographing a four-blade milling cutter, the target angle is initially 0°, after the first photo is taken, the target angle is changed to 90°, after the second photo is taken, the target angle is changed to 180°, after the third photo is taken, the target angle is changed to 270°, and after the fourth photo is taken, the target angle is changed back to 0°.

[0065] 1.2) Use OpenCV to detect the edge of the blade image and use Hough transform to detect the tool angle. According to the detected angle, the milling cutter angle is manually adjusted so that the initial state of the milling cutter is horizontal.

[0066] Specifically, opencv is used to perform edge detection on the blade image and Hough transform is used to detect the straight line. The detected straight line is the straight line where the blade is located. The angle of the straight line is calculated according to the two endpoints (x1, y1) and (x2, y2) of the detected straight line:

[0067]

[0068] Manually adjust the milling cutter angle according to the detected angle so that the initial state of the milling cutter is horizontal.

[0069] like Figure 4As shown, after the Stm32 is turned on, it first initializes the timer, gpio, serial port and USB. In the timer interrupt part, the TIM timer in the encoder mode obtains the data of the motor encoder, and performs PID control calculation according to the data of the encoder to obtain the direction and speed of the motor. Another TIM timer continuously outputs PWM signals to control the motor speed. In addition, there are two GPIOs to control the forward and reverse rotation of the motor. In the main program part, after the stm32 is initialized, the button status is continuously detected. When the button is detected to be pressed, the USB channel controls the camera to complete the action of clicking the camera button on the camera's operating system, and then changes the target angle of PID control. The timer interrupt function automatically controls the motor to rotate to the new target angle, and then repeats the operation and performs it a total of four times to take photos of the four blades of a knife. Then the buzzer alarms to notify the operator that the photo is completed. The photographer can take the knife away at this time, and the main program continues to detect the button status.

[0070] In the above step 2), the prediction model trained by yolov9 is specifically: Labelme is used to annotate the images of all blades, the worn area is framed out and made into a data set, and the data set is used as a training set to train the prediction model of yolov9.

[0071] In the above step 2), the input data is batch predicted by the prediction model trained by yolov9, and the wear area in the predicted image is obtained and marked, such as Figure 5 As shown, the following steps are included:

[0072] 2.1) Obtain the predicted image through the prediction model trained by yolov9, perform instance segmentation, and mark the segmented wear area in red;

[0073] 2.2) The segmented image is extracted with opencv and binarized to obtain a binary image containing only pixels in the worn area, and the wear width of the worn area is measured by pixel scanning.

[0074] In this embodiment, specifically, a model trained with yolov9 is used to perform batch prediction on the taken pictures, the predicted pictures mark the worn areas in red, and then the predicted folder is read, processing starts from the first picture, the red channel is extracted, and then the picture is binarized to obtain a picture containing only pixels in the worn area, and then the picture is scanned from top to bottom, the number of pixels in each column is calculated, the maximum value is selected as the wear width, the pixel value N is converted according to the scale to obtain the actual wear width, and then the next picture is selected to repeat the above operations until the last picture is processed.

[0075] Specifically, the calculation is performed based on the distance automatically marked on the photo taken by the microscope camera. The distance x is marked on the photo, the number of pixels n for measuring this distance, the scale of the image is x / n, and the final wear width is N*(x / n).

[0076] In summary, when the present invention is used, the wear amount of the tool can be automatically and quickly accurately obtained when the milling cutter is not in working state. The present invention drives the milling cutter to rotate through the automatic rotating tool holder device to automatically take wear photos, and collects and measures the wear amount based on yolov9. A DC motor with an encoder is used to drive the milling cutter fixing bracket 1 to rotate through the synchronous belt 2. The milling cutter is installed on the milling cutter fixing bracket 1. The motor is controlled by the integral separation position PID to keep the blade in a horizontal state and in the same position on the photo after each rotation. At the same time, the image is instance segmented and feature extracted through yolov9 and opencv, and the width of the blade wear is measured.

[0077] In one embodiment of the present invention, a system for automatically collecting milling cutter wear is provided, comprising:

[0078] The image acquisition module drives the milling cutter to be measured to rotate through the automatic rotating tool holder device to obtain images of all the cutting edges of the milling cutter, and the cutting edges in all images are in a horizontal state;

[0079] The wear area acquisition module takes the images of all blades as input data, performs batch prediction on the input data through the prediction model trained by yolov9, obtains the wear area in the predicted image and marks it;

[0080] The wear width determination module determines the highest wear point in the marked wear area, measures the distance from the highest point to the horizontal line where the blade is located, and obtains the wear width.

[0081] In the above embodiment, the automatic rotating tool holder device includes: a milling cutter fixing bracket 1, a synchronous belt 2, a synchronous belt pulley 3, a motor bracket 4, a motor 5, a base 6, a tapered roller bearing 7 and a motor drive controller.

[0082] The milling cutter fixing bracket 1 is arranged on the top of the base 6 through a tapered roller bearing 7, and the milling cutter to be tested is installed on the milling cutter fixing bracket 1 and rotates with the milling cutter fixing bracket 1;

[0083] The motor bracket 4 is arranged on the side of the base 6, the motor 5 is mounted on the motor bracket 4, and the output shaft of the motor 5 is coaxially connected with the synchronous belt pulley 3;

[0084] The synchronous belt pulley 3 is connected to the milling cutter fixing bracket 1 through the synchronous belt 2, so that the synchronous belt pulley 3 is driven by the motor 5 to rotate, thereby driving the milling cutter fixing bracket 1 to rotate;

[0085] The motor driving controller drives the motor 5 to work according to the set rotation angle, so that the motor 5 drives the milling cutter fixing bracket 1 to rotate at a fixed rotation angle.

[0086] In this embodiment, the milling cutter fixing bracket 1 is a hollow pulley, the upper part of which has a slot for fixing the milling cutter to be tested, and the hollow pulley and the tapered roller bearing 7 adopt an interference fit; the diameter of the hollow pulley is much larger than the diameter of the synchronous belt pulley 3.

[0087] In this embodiment, an oblong hole for installing the motor bracket 4 is provided on the side of the base 6. The motor bracket 4 is installed in the oblong hole by screws and nuts, so that the position of the motor bracket 4 can be adjusted through the oblong hole to adjust the preload force of the synchronous belt 2.

[0088] In this embodiment, the milling cutter to be measured is driven to rotate by the automatic rotating tool holder device to obtain images of all cutting edges of the milling cutter, and the cutting edges in all images are in a horizontal state, including:

[0089] The target angle of the encoder on the motor 5 is set, and the motor drive controller has a built-in PID control calculation method to rotate the milling cutter to the target angle and collect the blade image;

[0090] Opencv is used to detect the edge of the blade image and Hough transform is used to detect the tool angle. The milling cutter angle is manually adjusted according to the detected angle so that the initial state of the milling cutter is horizontal.

[0091] In the above embodiments, the prediction model trained by yolov9 includes: using Labelme to annotate all blade images, selecting the wear area and making it into a data set, and using the data set as a training set to train the prediction model of yolov9.

[0092] In the above embodiments, the prediction model trained by yolov9 is used to perform batch prediction on the input data, and the wear area in the predicted image is obtained and marked, including:

[0093] The predicted image is obtained through the prediction model trained by yolov9, and instance segmentation is performed, and the segmented wear area is marked in red;

[0094] The segmented image is extracted with opencv and binarized to obtain a binary image containing only pixels in the worn area, and the wear width of the worn area is measured by pixel scanning.

[0095] The system provided in this embodiment is used to execute the above-mentioned method embodiments. Please refer to the above-mentioned embodiments for specific processes and detailed contents, which will not be repeated here.

[0096] A computing device provided in one embodiment of the present invention may be a terminal, which may include: a processor, a communications interface, a memory, a display screen, and an input device. The processor, the communications interface, and the memory communicate with each other through a communication bus. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium and an internal memory, wherein the non-volatile storage medium stores an operating system and a computer program, and the computer program is executed by the processor to implement the methods in the above embodiments; the internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a management network, NFC (near field communication) or other technologies. The display screen may be a liquid crystal display screen or an electronic ink display screen, and the input device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computing device, or an external keyboard, touchpad or mouse, etc. The processor may call the logic instructions in the memory.

[0097] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0098] In one embodiment of the present invention, a computer program product is provided, wherein the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the methods provided by the above-mentioned method embodiments.

[0099] In one embodiment of the present invention, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores server instructions, and the computer instructions enable a computer to execute the methods provided in the above embodiments.

[0100] The above embodiment provides a computer-readable storage medium, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.

[0101] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0102] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0103] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for automatically collecting milling cutter wear, characterized in that: include: The milling cutter to be measured is driven to rotate by an automatic rotating cutter holder device to obtain images of all cutting edges of the milling cutter, and the cutting edges in all images are in a horizontal state; Taking all blade images as input data, the prediction model trained by yolov9 is used to perform batch prediction on the input data, and the wear area in the predicted image is obtained and marked; Determine the highest point of wear in the marked wear area, measure the distance from the highest point to the horizontal line where the blade is located, and obtain the wear width.

2. The method for automatically collecting the wear of a milling cutter according to claim 1, characterized in that: The automatic rotating tool holder device comprises: a milling cutter fixing bracket (1), a synchronous belt (2), a synchronous belt pulley (3), a motor bracket (4), a motor (5), a base (6), a tapered roller bearing (7) and a motor drive controller; The milling cutter fixing bracket (1) is arranged on the top of the base (6) via a tapered roller bearing (7); the milling cutter to be tested is mounted on the milling cutter fixing bracket (1) and rotates with the milling cutter fixing bracket (1); The motor bracket (4) is arranged on the side of the base (6), the motor (5) is mounted on the motor bracket (4), and the output shaft of the motor (5) is coaxially connected to the synchronous belt pulley (3); The synchronous belt pulley (3) is connected to the milling cutter fixing bracket (1) through the synchronous belt (2), so that the synchronous belt pulley (3) is driven by the motor (5) to rotate, thereby driving the milling cutter fixing bracket (1) to rotate; The motor drive controller drives the motor (5) to work according to a set rotation angle, so that the motor (5) drives the milling cutter fixing bracket (1) to rotate at a fixed rotation angle.

3. The method for automatically collecting the wear of a milling cutter as claimed in claim 2, characterized in that: The milling cutter fixing bracket (1) is a hollow pulley, the upper part of which is provided with a slot for fixing the milling cutter to be tested, and the hollow pulley and the tapered roller bearing (7) are in interference fit; The diameter of the hollow pulley is much larger than the diameter of the synchronous belt pulley (3).

4. The method for automatically collecting the wear of a milling cutter as claimed in claim 2, characterized in that: The side of the base (6) is provided with an oblong hole for mounting the motor bracket (4), and the motor bracket (4) is mounted in the oblong hole by means of screws and nuts, so that the position of the motor bracket (4) can be adjusted through the oblong hole, thereby adjusting the preload force of the synchronous belt (2).

5. The method for automatically collecting the wear of a milling cutter as claimed in claim 2, characterized in that: The milling cutter to be tested is rotated by the automatic rotating tool holder device to obtain images of all the cutting edges of the milling cutter, and the cutting edges in all images are in a horizontal state, including: The target angle of the encoder on the motor (5) is set, and the motor drive controller has a built-in PID control calculation method to rotate the milling cutter to the target angle and collect the blade image; Opencv is used to detect the edge of the blade image and Hough transform is used to detect the tool angle. The milling cutter angle is manually adjusted according to the detected angle so that the initial state of the milling cutter is horizontal.

6. The method for automatically collecting the wear of a milling cutter according to claim 1, characterized in that: The prediction model trained by yolov9 includes: using Labelme to annotate all blade images, selecting the wear area and making it into a data set, and using the data set as a training set to train the prediction model of yolov9.

7. The method for automatically collecting the wear of a milling cutter according to claim 1, characterized in that: The prediction model trained by yolov9 is used to perform batch prediction on the input data, and the wear areas in the predicted images are obtained and marked, including: The predicted image is obtained through the prediction model trained by yolov9, and instance segmentation is performed, and the segmented wear area is marked in red; The segmented image is extracted with opencv and binarized to obtain a binary image containing only pixels in the worn area, and the wear width of the worn area is measured by pixel scanning.

8. A milling cutter wear automatic collection system, characterized in that: include: The image acquisition module drives the milling cutter to be measured to rotate through the automatic rotating tool holder device to obtain images of all the cutting edges of the milling cutter, and the cutting edges in all images are in a horizontal state; The wear area acquisition module takes the images of all blades as input data, performs batch prediction on the input data through the prediction model trained by yolov9, obtains the wear area in the predicted image and marks it; The wear width determination module determines the highest wear point in the marked wear area, measures the distance from the highest point to the horizontal line where the blade is located, and obtains the wear width.

9. A computer-readable storage medium storing one or more programs, characterized in that: The one or more programs include instructions, which, when executed by a computing device, cause the computing device to perform any one of the methods of claims 1 to 7.

10. A computing device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any one of the methods described in claims 1 to 7.

Images