Automatic spring size calibration system and method based on machine vision and medium

Abstract

The invention relates to the technical field of spring production, in particular to a spring size automatic calibration system and method based on machine vision and a medium, the common technical key points of the three schemes are as follows: a winding machine and a wire feeding mechanism construct a production line to produce a spring, and a data acquisition module acquires an image to be detected; the image to be detected is processed through an image processing module to obtain experimental image data of the spring, actual physical parameters, corresponding to the experimental image data, of the spring are obtained, a spring parameter deviation source is diagnosed through a parameter coupling model established in advance, and the spring parameter deviation source is still the spring parameter deviation source. Adjustment of machining parameters of equipment mechanisms in the production line is controlled through the control module, so that dynamic adjustment of the production line is achieved, an intelligent production workshop is constructed, and accurate control over the size and performance of the spring is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of spring production, and more particularly to a system, method and medium for automatically calibrating spring dimensions based on machine vision. Background Art

[0002] The definition of spring dimensions involves several key parameters that together determine the spring's physical characteristics and performance.

[0003] The spring dimensions mainly include spring wire diameter, spring outer diameter, spring inner diameter, spring middle diameter, pitch, number of effective coils, number of support coils, total number of coils, free height and spring expanded length.

[0004] For the production of springs, CNC spring winding machines are currently mostly used. Since CNC spring winding machines have higher production efficiency and automation, and can easily roll out complex shaped special-shaped springs, they have gradually been widely used in major domestic spring manufacturing companies.

[0005] For example, the invention patent with patent number 201711039917.2, the patent name is a manufacturing process of a spiral compression eccentric spring and its spring product, which discloses the following processes: spring winding, by calculating the difference in the outer diameter size of the spring adjacent coils, compiling a spring winding program, and forming it through computer control to produce a spring with staggered adjacent coil sizes; spring tempering, according to the required spring compression height, after calculation, the spring forming controls the deformation amount of the spring outer diameter size, controls the dimensional deformation law of the spring material after heat treatment, sets the corresponding tempering temperature and tempering time for the wound spring, and makes the spring naturally tempered to form an eccentric spring with orderly staggered outer diameter sizes.

[0006] It can be seen that it has become common to control the changing production through computer control according to the production needs of the spring itself.

[0007] However, due to the interplay of various factors during the CNC spring winding process, such as process parameters, mold parameters, and material properties, the actual spring processing requires extensive testing and continuous mold trials and modifications for different spring models and specifications to determine the processing technology. This significantly increases spring production costs, reduces spring production efficiency, and cannot guarantee the final geometric accuracy of the formed parts. Furthermore, excessive or insufficient roller pressure often results in wire flattening, insufficient extension length, and excessive fluctuations in forming speed, severely impacting the production efficiency and quality of the springs. This can cause the springs to jam during testing after production, necessitating constant debugging of the CNC spring winding machine to meet spring production requirements, making the production process particularly cumbersome. Summary of the Invention

[0008] In view of the above-mentioned deficiencies in the prior art, the first object of the present invention is to provide a spring size automatic calibration system based on machine vision to realize dynamic adjustment of the production line, build an intelligent production workshop, and achieve precise control of spring size and performance.

[0009] The first object of the present invention is achieved through the following technical solution: a spring size automatic calibration system based on machine vision, comprising: A data acquisition module is used to obtain images to be tested for the formed spring; An image processing module obtains experimental image data of the spring based on the image to be detected, performs spatial transformation processing on the experimental image data to obtain enhanced image data, and obtains actual physical parameters of the spring corresponding to the experimental image data; The analysis module obtains the actual physical parameters of the spring and diagnoses the root cause of the spring parameter deviation based on the pre-established parameter coupling model; The control module constructs a production line through a winding machine and a wire feeding mechanism, identifies the root cause of parameter deviation based on the parameter coupling model, and then controls the adjustment of processing parameters of equipment mechanisms in the production line.

[0010] Preferably, the parameter coupling model uses a neural network to train historical production data through the rotation speed of the winding machine and the wire feeding speed of the wire feeding mechanism to construct a mathematical model that can accurately reflect the coupling relationship between actual physical parameters.

[0011] Preferably, the actual physical parameters include the outer diameter, pitch, wire diameter and free length of the spring.

[0012] Preferably, the data acquisition module includes at least three groups of camera modules, and the shooting angles of the three groups of camera modules include top view, 45° side view and 90° side view, which are used to cover the full dimensions of the spring outer diameter, pitch, wire diameter and end face parallelism.

[0013] Preferably, the image processing module processes the experimental image data in the following manner: The method of processing the verification image data includes the following steps: In the S1 preprocessing stage, the RGB image is converted to the HSV space, the brightness channel is extracted for subsequent processing, and the experimental image data is divided into blocks to enhance the local contrast; S2 image segmentation uses the watershed algorithm to achieve regional segmentation, accurately extract the spring target, and generate a binary image; S3 feature extraction, based on the binary image, compares the image scale with the actual scale to find the actual physical parameters of the spring.

[0014] Preferably, based on the source of parameter deviation identified by the parameter coupling model, the adjustment direction of the processing parameters of the equipment mechanism in the possible production line is found by detecting the actual physical parameters of the spring, and a priority sorting experiment is performed based on the acquisition of the adjustment direction. The control module is used to control the execution of the adjustment of the processing parameters of the equipment mechanism in the production line, and further verification is performed based on the subsequent detection of the actual physical parameters of the spring until the actual physical parameters of the detected spring are qualified.

[0015] The second object is to provide an automatic calibration method.

[0016] An automatic calibration method comprises the following steps: S101, using a camera module matrix to take photos of the produced spring from multiple angles; S102, processing the acquired experimental image data through an image processing module, and obtaining actual physical parameters of the spring corresponding to the experimental image data, the actual physical parameters of the spring including the outer diameter, pitch, wire diameter, and free length of the spring; S103, based on the actual physical parameters of the spring obtained, substitute them into a pre-established parameter coupling model to diagnose the root cause of the spring parameter deviation and determine the root cause of the spring parameter deviation in the production line link; S104, based on the root cause of the spring parameter deviation, the control module dynamically adjusts the production parameters of the winding machine and the wire feeding mechanism to construct the production line until the actual physical parameters of the spring are qualified.

[0017] A third object is to provide a computer readable medium.

[0018] Preferably, a computer readable medium stores a computer program thereon, wherein the computer program performs the calibration method described above when executed by a processor.

[0019] In summary, the present invention has the beneficial effects: the springs produced by the production line constructed by the winding machine and the wire feeding mechanism are first obtained by the data acquisition module. The image to be detected is then processed by the image processing module to obtain the experimental image data of the spring, and the actual physical parameters of the spring corresponding to the experimental image data are obtained. Finally, the root cause of the spring parameter deviation is diagnosed through the pre-established parameter coupling model. According to the root cause of the spring parameter deviation, the control module is used to control the adjustment of the processing parameters of the equipment mechanism in the production line, thereby realizing dynamic adjustment of the production line, building an intelligent production workshop, and realizing precise control of the spring size and performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a schematic structural diagram of a system according to embodiment 1 of the present invention; Figure 2is a schematic diagram of the image processing flow in the first embodiment of the present invention; Figure 3 It is a flowchart of the calibration method of the second embodiment of the present invention.

[0021] Reference numerals: 1. Data acquisition module; 2. Image processing module; 3. Analysis module; 4. Control module. DETAILED DESCRIPTION

[0022] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0023] It should be noted that when a component is referred to as being “fixed to” or “disposed on” another component, it can be directly on the other component or indirectly on the other component. When a component is referred to as being “connected to” another component, it can be directly or indirectly connected to the other component.

[0024] It should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention.

[0025] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature identified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0026] Example 1: A spring size automatic calibration system based on machine vision, see Figure 1-Figure 2 ,include: An image processing module 21 is used to obtain an image to be inspected for the formed spring; An image processing module obtains experimental image data of the spring based on the image to be detected, performs spatial transformation processing on the experimental image data to obtain enhanced image data, and obtains actual physical parameters of the spring corresponding to the experimental image data; The analysis module 33 obtains the actual physical parameters of the spring and diagnoses the root cause of the spring parameter deviation based on a pre-established parameter coupling model; The control module 4 constructs a production line through a winding machine and a wire feeding mechanism, identifies the root cause of parameter deviation based on the parameter coupling model, and then controls the adjustment of processing parameters of equipment mechanisms in the production line.

[0027] In this embodiment, the springs produced by the production line constructed by the winding machine and the wire feeding mechanism are first obtained by the image processing module 21 to obtain the image to be detected, and then the image processing module processes the image to be detected to obtain experimental image data of the spring, and obtains the actual physical parameters of the spring corresponding to the experimental image data. Finally, the root cause of the spring parameter deviation is diagnosed through the pre-established parameter coupling model. According to the root cause of the spring parameter deviation, the control module 4 controls the adjustment of the processing parameters of the equipment mechanism in the production line, thereby realizing dynamic adjustment of the production line, building an intelligent production workshop, and realizing precise control of the spring size and performance.

[0028] The actual physical parameters include the outer diameter, pitch, wire diameter and free length of the spring.

[0029] Specifically, the parameter coupling model uses a neural network to train historical production data through the rotation speed of the winding machine and the wire feeding speed of the wire feeding mechanism to construct a mathematical model that can accurately reflect the coupling relationship between actual physical parameters.

[0030] This application builds a "perception-analysis-control" closed-loop system by real-time monitoring of core parameters such as the spring's free length L, wire diameter d, and pitch p, dynamically adjusting production equipment parameters to achieve precise control of spring size and performance.

[0031] When the free length L of the spring is too long, the pitch p of the spring size also increases. To compensate for this, the speed of the winding machine mandrel can be reduced or the wire feeding speed can be increased, thereby reducing the pitch and increasing the number of winding turns. When the pitch p of the spring size decreases and the number of spring coils increases, the pitch can be increased and the number of coils can be reduced to compensate by increasing the speed of the winding machine mandrel or reducing the wire feeding speed.

[0032] When the spring wire diameter d is out of tolerance, that is, the outer diameter W of the spring is too long and the free length L of the spring is too long, the wire feeding tension of the wire feeding mechanism can be adjusted to bring the spring production line back on track and perform adaptive debugging.

[0033] Settings for mathematical models: Assuming that the outer diameter, inner diameter, free length, and pitch of the spring are linearly related to the winding machine speed and wire feeding speed, the following multiple linear regression model can be constructed: Model of outer diameter W: D=β0W+β1W*V1+β2W*V2+ϵW; Model with free length L: H = β0L + β1L*V1 + β2L*V2 + ϵL; Where V1 is the winding machine speed, V2 is the wire feed speed, β0W and β0L are constants, β1L and β1W are the regression coefficients for the winding machine speed and β2L and β2W for the wire feed speed, and ϵW and ϵL are random error terms. Multiple linear regression models for parameters such as inner diameter and pitch can also be constructed using the same model as for outer diameter W.

[0034] To build a mathematical model, we first need to collect a large amount of actual production data. During the spring production process, sensors are used to record the winding machine speed and wire feed speed in real time. At the same time, a camera module is used to measure the outer diameter, inner diameter, free height, and pitch of the produced spring. Multiple sets of such data are recorded to form a data set. For example: Based on the identification parameter deviation root cause of the parameter coupling model, by detecting the actual physical parameters of the spring, the possible adjustment direction of the processing parameters of the equipment mechanism in the production line is found, and a priority sorting experiment is performed based on the acquisition of the adjustment direction. The control module 4 controls the execution of the adjustment to control the processing parameters of the equipment mechanism in the production line, and further verification is performed based on the subsequent detection of the actual physical parameters of the spring until the actual physical parameters of the detected spring are qualified.

[0035] To ensure the clarity of the image processing module 21, the image processing module 21 of this embodiment includes at least three groups of camera modules. The shooting angles of the three groups of camera modules include top view, side view 45° and side view 90°, which are used to cover the full dimensions of the spring outer diameter, pitch, wire diameter and end face parallelism, and the three groups of camera modules are synchronously exposed through the FPGA trigger board.

[0036] The deflection of the shooting angle of the three groups of camera modules is adjusted and set according to the position of the spring, so the shooting angle of the camera module can be adjusted according to actual conditions.

[0037] In order to ensure that the image processing module processes the experimental image data accurately, the method for processing the experimental image data in this embodiment includes the following steps: In the S1 preprocessing stage, the RGB image is converted to the HSV space, the brightness channel is extracted for subsequent processing, and the experimental image data is divided into blocks to enhance the local contrast; S2 image segmentation uses the watershed algorithm to achieve regional segmentation, accurately extract the spring target, and generate a binary image; S3 feature extraction, based on the binary image, compares the image scale with the actual scale to find the actual physical parameters of the spring.

[0038] Example 2: An automatic calibration method, see Figure 3 , including the following steps: S101, using a camera module matrix to take photos of the produced spring from multiple angles; S102, processing the acquired experimental image data through an image processing module, and obtaining actual physical parameters of the spring corresponding to the experimental image data, the actual physical parameters of the spring including the outer diameter, pitch, wire diameter, and free length of the spring; S103, based on the actual physical parameters of the spring obtained, substitute them into a pre-established parameter coupling model to diagnose the root cause of the spring parameter deviation and determine the root cause of the spring parameter deviation in the production line link; S104, based on the root cause of the spring parameter deviation, dynamically adjusts the production parameters of the winding machine and wire feeding mechanism to construct the production line through the control module 4 until the actual physical parameters of the spring meet the requirements. This has the beneficial effects of the corresponding system embodiment and is not further described here.

[0039] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the calibration method described in any of the above embodiments.

[0040] The computer-readable media of the embodiments of the present application include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information, and the information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RA), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, cassette tape, magnetic tape storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0041] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the calibration method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0042] The above embodiments are merely explanations of the present invention and are not limitations of the present invention. After reading this specification, those skilled in the art may make non-creative modifications to the embodiments as needed. However, as long as they are within the scope of the claims of the present invention, they are protected by patent law.

Claims

1. A spring size automatic calibration system based on machine vision, characterized by: include: A data acquisition module is used to obtain images to be tested for the formed spring; An image processing module obtains experimental image data of the spring based on the image to be detected, performs spatial transformation processing on the experimental image data to obtain enhanced image data, and obtains actual physical parameters of the spring corresponding to the experimental image data; The analysis module obtains the actual physical parameters of the spring and diagnoses the root cause of the spring parameter deviation based on the pre-established parameter coupling model; The control module constructs a production line through a winding machine and a wire feeding mechanism, identifies the root cause of parameter deviation based on the parameter coupling model, and then controls the adjustment of processing parameters of equipment mechanisms in the production line.

2. The automatic spring size calibration system based on machine vision according to claim 1 is characterized by: The parameter coupling model uses a neural network to train historical production data through the rotation speed of the winding machine and the wire feeding speed of the wire feeding mechanism to construct a mathematical model that can accurately reflect the coupling relationship between actual physical parameters.

3. The automatic spring size calibration system based on machine vision according to claim 1 is characterized by: The actual physical parameters include the outer diameter, pitch, wire diameter and free length of the spring.

4. The automatic spring size calibration system based on machine vision according to claim 1 is characterized by: The data acquisition module includes at least three groups of camera modules, and the shooting angles of the three groups of camera modules include top view, 45° side view and 90° side view, which are used to cover the full dimensions of the spring outer diameter, pitch, wire diameter and end face parallelism.

5. The automatic spring size calibration system based on machine vision according to claim 1 is characterized by: The image processing module processes the experimental image data in the following manner: The method of processing the verification image data includes the following steps: In the S1 preprocessing stage, the RGB image is converted to the HSV space, the brightness channel is extracted for subsequent processing, and the experimental image data is divided into blocks to enhance the local contrast; S2 image segmentation uses the watershed algorithm to achieve regional segmentation, accurately extract the spring target, and generate a binary image; S3 feature extraction, based on the binary image, compares the image scale with the actual scale to find the actual physical parameters of the spring.

6. The automatic spring size calibration system based on machine vision according to claim 2, characterized in that: Based on the identification parameter deviation root cause of the parameter coupling model, by detecting the actual physical parameters of the spring, the possible adjustment direction of the processing parameters of the equipment mechanism in the production line is found, and a priority sorting experiment is performed based on the acquisition of the adjustment direction. The control module is used to control the execution of the adjustment of the processing parameters of the equipment mechanism in the production line, and further verification is performed based on the subsequent detection of the actual physical parameters of the spring until the actual physical parameters of the detected spring are qualified.

7. An automatic calibration method, characterized by: The following steps are involved: S101, using a camera module matrix to take photos of the produced spring from multiple angles; S102, processing the acquired experimental image data through an image processing module, and obtaining actual physical parameters of the spring corresponding to the experimental image data, the actual physical parameters of the spring including the outer diameter, pitch, wire diameter, and free length of the spring; S103, based on the actual physical parameters of the spring obtained, substitute them into a pre-established parameter coupling model to diagnose the root cause of the spring parameter deviation and determine the root cause of the spring parameter deviation in the production line link; S104, based on the root cause of the spring parameter deviation, the control module dynamically adjusts the production parameters of the winding machine and the wire feeding mechanism to construct the production line until the actual physical parameters of the spring are qualified.

8. A computer-readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the calibration method according to claim 7 is implemented.

Images