A valve body tapping calibration method and system based on machine vision

Abstract

The present invention relates to the technical field of valve body processing, and specifically discloses a tapping calibration method and system for a valve body based on machine vision, including: before tapping the valve body, obtaining the defect degree and defect distribution on the surface of the hole to be tapped on the valve body, and then performing gray-scale statistical analysis to obtain a gray-scale offset coefficient and a gray-scale uniformity coefficient; then, based on the gray-scale offset coefficient and the gray-scale uniformity coefficient, output a minor defect coefficient for tapping defects, evaluate the quality of the hole to be tapped, and generate a minor defect signal based on the quality evaluation result; then, obtain the defect type on the surface of the hole to be tapped on the valve body, and at the same time perform fusion analysis with the minor defect signal and the defect type to obtain a regulation coefficient, and dynamically calibrate the tapping parameters; through a comprehensive and multi-dimensional evaluation method, the present invention accurately grasps the defect degree and distribution on the surface of the hole to be tapped, and dynamically adjusts the processing parameters according to different defect types, effectively reducing the influence of defects and improving the tapping success rate.

Description

Technical Field

[0001] The present invention relates to the technical field of valve body processing, and particularly relates to a valve body tapping calibration method and system based on machine vision. Background Art

[0002] During the processing of valve bodies, tapping is a key process, and the tapping quality directly affects the overall performance and service life of the valve body. However, various defects such as scratches and rust may exist in the tapping holes to be processed on the valve body before processing, and these defects will lead to tapping failure or unqualified products.

[0003] Currently, traditional valve body tapping methods often lack an effective evaluation of the quality of the tapping holes to be processed, and it is impossible to accurately grasp the defect degree and distribution of the hole surface. It is also difficult to dynamically adjust the processing parameters according to the actual defects of the holes during the tapping process, so it is impossible to effectively reduce the impact of defects on the tapping quality, resulting in a low tapping success rate and unstable product quality.

[0004] Therefore, a valve body tapping calibration method that can accurately evaluate the quality of the tapping holes to be processed and dynamically adjust the processing parameters according to the hole defects is needed to improve the tapping success rate and product quality. Summary of the Invention

[0005] The purpose of the present invention is to provide a valve body tapping calibration method and system based on machine vision to solve at least one of the above-mentioned prior art problems.

[0006] In the first aspect, the present invention provides a valve body tapping calibration method based on machine vision, including the following steps:

[0007] Before valve body tapping, obtain the defect degree and defect distribution on the surface of the tapping hole to be processed on the valve body, and then perform gray-scale statistical analysis to obtain the gray-scale offset coefficient and gray-scale uniformity coefficient;

[0008] Then, based on the gray-scale offset coefficient and gray-scale uniformity coefficient, output the tapping defect mildness coefficient, evaluate the quality of the tapping hole to be processed, and generate a minor defect signal based on the quality evaluation result;

[0009] Then, obtain the defect type on the surface of the tapping hole to be processed on the valve body, and at the same time, perform fusion analysis with the minor defect signal and the defect type to obtain a regulation coefficient, and dynamically calibrate the tapping parameters.

[0010] In the second aspect, the present invention provides a valve body tapping calibration system based on machine vision, and the system includes:

[0011] Quality analysis module: Before valve body tapping, obtain the defect degree and defect distribution on the surface of the tapping hole to be processed on the valve body, and then perform gray-scale statistical analysis to obtain the gray-scale offset coefficient and gray-scale uniformity coefficient;

[0012] Based on the gray-scale offset coefficient and the gray-scale uniformity coefficient, the tapping defect mild coefficient is output, the quality of the hole position to be tapped is evaluated, and based on the quality evaluation result, a minor defect signal is generated;

[0013] Parameter regulation module: Obtain the defect type on the surface of the hole position to be tapped on the valve body, and at the same time perform fusion analysis with the minor defect signal and the defect type to obtain a regulation coefficient, and dynamically calibrate the tapping parameters.

[0014] Advantages of the present invention:

[0015] (1) By combining technologies such as gray-scale histogram analysis, surface sub-region division, and annular sub-region division, the present invention quantitatively evaluates the hole position to be tapped from multiple dimensions. It not only considers the overall gray-scale offset of the inner surface of the hole position, but also delves into different levels of annular sub-regions, comprehensively and meticulously grasping the degree and distribution of defects. Compared with traditional single-dimensional detection methods, the evaluation results are more accurate and reliable, providing a more targeted basis for subsequent tapping operations;

[0016] (2) The present invention can accurately distinguish qualified and defective sub-regions, and through calculating various coefficients, such as gray-scale offset coefficient, gray-scale uniformity coefficient, and tapping defect mild coefficient, etc., quantitatively grade the defects, enabling the staff to clearly understand the specific quality status of each hole position to be tapped, and take corresponding treatment measures for defects of different degrees, avoiding blind processing, and improving the production efficiency and the stability of product quality;

[0017] (3) According to the minor defect signal generated by the quality evaluation, the present invention identifies the defect type, and combines with the regional offset coefficient to calculate the regulation coefficient to realize the dynamic regulation of the processing parameters; the method of flexibly adjusting the processing parameters according to the actual defect situation effectively reduces the influence of defects on the tapping quality and greatly improves the tapping success rate; for example, for scratch defects, by increasing the cutting speed or reducing the feed rate, the scratches can be covered or reduced to a certain extent to ensure the smooth progress of the tapping process. Description of the drawings

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0019] Figure 1 It is a flowchart of a valve body tapping calibration method based on machine vision provided in Embodiment 1 of the present invention;

[0020] Figure 2 It is a schematic structural diagram of a valve body tapping calibration system based on machine vision provided in the second embodiment of the present invention;

[0021] Figure 3 It is a schematic structural diagram of a valve body tapping calibration device based on machine vision provided in the third embodiment of the present invention. Detailed implementation manners

[0022] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0023] Embodiment 1

[0024] Figure 1 It is a flowchart of a valve body tapping calibration method based on machine vision provided in the first embodiment of the present invention. The embodiments of the present invention are applicable to a situation of a valve body tapping calibration method based on machine vision. This valve body tapping calibration method based on machine vision can be executed by a valve body tapping calibration system based on machine vision. This valve body tapping calibration system based on machine vision can be implemented by software and / or hardware, and this valve body tapping calibration system based on machine vision can be configured in a valve body tapping calibration device based on machine vision. Optionally, a valve body tapping calibration device based on machine vision can be an electronic device, and this electronic device can be a notebook, a desktop computer, a smart tablet, etc. The embodiments of the present invention do not limit this.

[0025] A valve body tapping calibration method provided by the embodiments of the present invention specifically includes the following steps:

[0026] Step 1: Before the valve body tapping process, analyze the defect degree and defect distribution on the surface of the hole position to be tapped on the valve body, so as to evaluate the quality of the hole position to be tapped, and generate a minor defect signal based on the quality evaluation result;

[0027] In some implementation schemes, before the valve body tapping process, obtain an image of the hole position to be tapped on the valve body through image recognition technology and convert it into a grayscale histogram;

[0028] Based on the grayscale values of the grayscale histogram, divide the inner surface of the hole position to be tapped into regions, and divide those with the same grayscale value into the same region to obtain surface sub-regions;

[0029] It should be noted that the inner surface of the tapping hole position can be divided into regions by using methods such as threshold segmentation or region growing in image processing technology. Combining with the gray values in the gray histogram, the inner surface of the tapping hole position is divided into multiple surface sub-regions, so that the gray values in each surface sub-region are consistent. Here, the image processing technology is all existing technology and will not be elaborated here;

[0030] Based on any one surface sub-region, extract the gray value of the surface sub-region, calculate the difference between the gray value and the standard gray value, and take the absolute value to obtain the gray offset value. Then calculate the ratio of the gray offset value to the standard gray value to obtain the gray offset ratio;

[0031] It should be noted that the standard gray value represents the gray characteristics of the inner surface of the tapping hole position under ideal conditions, that is, the standard gray value is the gray value preset by the process before the tapping process of the tapping hole position;

[0032] Preset a gray offset ratio threshold, and compare and analyze the gray offset ratios of each surface sub-region with the gray offset ratio threshold respectively;

[0033] If the gray offset ratio ≤ the gray offset ratio threshold, it means that the gray value of the surface sub-region corresponding to the gray offset ratio has a small deviation from the standard gray value, and the surface sub-region corresponding to the gray offset ratio is marked as a surface qualified sub-region;

[0034] If the gray offset ratio > the gray offset ratio threshold, it means that the gray value of the surface sub-region corresponding to the gray offset ratio has a large deviation from the standard gray value, and the surface sub-region corresponding to the gray offset ratio is marked as a surface defect sub-region;

[0035] Extract the gray offset ratios of all surface qualified sub-regions and calculate their mean value to obtain the qualified offset mean value;

[0036] At the same time, extract the gray offset ratios of all surface defect sub-regions and mark them as defect offset ratios;

[0037] Extract the area of the surface defect sub-region and calculate the ratio with the total area of the inner surface of the tapping hole position to obtain the defect influence coefficient;

[0038] Through the formula: , calculate to obtain the defect offset weighted ratio QB, where B is the defect offset ratio and Y is the defect influence coefficient;

[0039] Calculate the mean value of the defect offset weighted ratios of all surface defect sub-regions to obtain the defect offset mean value;

[0040] Then perform weighted summation of the qualified offset mean value and the defect offset mean value to obtain the gray offset coefficient;

[0041] It should be noted that the weighting basis for the weighted summation of the qualified offset mean and the defect offset mean is as follows: based on the proportions of all surface qualified sub-regions and all surface defect sub-regions in the total inner surface area of the tapping hole position respectively, and then the weighted summation calculation is carried out;

[0042] Based on the thread helix direction and thread tooth width during the tapping process, the inner surface of the tapping hole position is divided into regions to obtain multiple annular sub-regions;

[0043] It should be noted that the annular sub-regions represent different levels along the hole depth direction, and each level corresponds to specific thread features;

[0044] Based on any one of the annular sub-regions, the gray-scale offset ratio of all surface qualified sub-regions within the annular sub-region and the defect offset weighted ratio of all surface defect sub-regions within the annular sub-region are extracted, and they are weighted and summed according to the area proportions of the surface qualified sub-regions and surface defect sub-regions within the annular sub-region to obtain the regional offset coefficient;

[0045] Extract the regional offset coefficients of all annular sub-regions to obtain a regional offset coefficient sequence: , where N represents the total number of all annular sub-regions, and the value of N is 1, 2,..., N;

[0046] Use the wavelet basis function to perform wavelet decomposition on the regional offset coefficient sequence to obtain the detail coefficients;

[0047] It should be noted that the wavelet basis function includes but is not limited to: Haar wavelet, Daubechies wavelet (db series), Symlets wavelet;

[0048] It should be noted that wavelet decomposition decomposes the signal at different scales. Each layer of decomposition will obtain a set of detail coefficients (representing the high-frequency part of the signal and reflecting the local changes of the signal). Wavelet decomposition is based on the discrete wavelet transform (DWT), and its core is to perform convolution and downsampling operations on the signal through the high-pass filter g;

[0049] Exemplarily, the calculation process of the detail coefficients is as follows:

[0050] Through the formula: , the detail coefficients are calculated ;

[0051] where L is the length of the high-pass filter, k is the summation index, and the value range is from 0 to L - 1, is the coefficient of the high-pass filter during the wavelet decomposition process;

[0052] Based on the detail coefficients, the gray-scale uniformity coefficient is calculated;

[0053] Exemplarily, the calculation process of the gray-scale uniformity coefficient is as follows:

[0054] Through the formula: , the gray-scale uniformity coefficient E is calculated and obtained;

[0055] Then, the gray-scale offset coefficient and the gray-scale uniformity coefficient are summed up to obtain the minor tapping defect coefficient;

[0056] A preset minor tapping defect coefficient threshold is set, and the minor tapping defect coefficient is compared and analyzed with the minor tapping defect coefficient threshold, so as to evaluate the quality of the to-be-tapped hole position;

[0057] If the minor tapping defect coefficient ≤ the minor tapping defect coefficient threshold, it indicates that the quality of the to-be-tapped hole position is good and its defect is relatively minor, that is, a minor defect signal is generated;

[0058] If the minor tapping defect coefficient ≤ the minor tapping defect coefficient threshold, it indicates that the quality of the to-be-tapped hole position is poor and its defect is relatively serious, that is, a serious defect signal is generated, thereby prompting the staff to reprocess the to-be-tapped hole position to avoid tapping failure or unqualified products;

[0059] Step 2: Based on the minor defect signal, calculate the regulation coefficient according to the defect type and degree, so as to dynamically regulate the processing parameters;

[0060] Among them, the processing parameters include but are not limited to: cutting speed, feed rate;

[0061] In some embodiments, based on the minor defect signal, through image recognition technology, the defect type of any annular sub-region is recognized, and at the same time, the regional offset coefficient of the annular sub-region is obtained, so as to calculate and obtain the regulation coefficient;

[0062] Among them, the defect types include but are not limited to: scratches, rust;

[0063] Based on the defect type and regulation coefficient of the annular sub-region, when tapping is performed on the annular sub-region, the processing parameters are regulated;

[0064] Exemplarily, based on the defect type and regulation coefficient of the annular sub-region, the process of regulating the processing parameters when tapping is performed on the annular sub-region is as follows:

[0065] Taking the defect type of minor scratches as an example, based on the regulation coefficient, the cutting speed is increased, so as to accelerate the material removal rate, thereby masking or reducing the influence of scratches to a certain extent; it is also possible to reduce the feed rate based on the regulation coefficient, so as to reduce the contact pressure between the tool and the workpiece during each cutting, which helps to reduce the expansion and depth of scratches;

[0066] Among them, the process of obtaining the regulation coefficient is as follows:

[0067] Through the formula: , the regulation coefficient K is calculated, where is the regional offset coefficient, E is the gray level uniformity coefficient, Q is the minor tapping defect coefficient, is the coefficient weight factor, and its value range is [0, 1], is the overall influence factor, and its value range is [0, 1], and ;

[0068] It should be noted that represents the contribution of the regional offset situation of each circular sub-region itself to the regulation coefficient. The larger the regional offset coefficient S, the more serious the gray level offset within the circular sub-region, and the greater the positive influence on the regulation coefficient; represents the influence of the overall gray level uniformity and overall quality on the current circular sub-region, is a proportionality coefficient that links the overall gray level uniformity degree with the overall quality assessment. When E is large and Q is small, it indicates that the overall gray level is uneven and the quality is poor, which will amplify the influence of the regional offset coefficient S of the current circular sub-region on the regulation coefficient; otherwise, it will reduce the influence;

[0069] The technical solution of the embodiment of the present invention is mainly as follows: Before tapping the valve body, using image recognition technology combined with gray level histogram analysis, the inner surface of the hole to be tapped is carefully divided into multiple surface sub-regions; by calculating the gray level offset ratio and comparing it with the preset threshold, the qualified and defective sub-regions are accurately distinguished; moreover, the qualified offset mean value and defective offset mean value are further calculated, and the gray level offset coefficient is obtained by weighted summation according to the sub-region area ratio; at the same time, the circular sub-regions are divided in combination with the thread characteristics, the regional offset coefficient sequence is calculated and wavelet decomposition is performed to obtain the detail coefficients and then the gray level uniformity coefficient is calculated, and finally the minor tapping defect coefficient is comprehensively obtained; the present invention accurately grasps the defect degree and distribution of the surface of the hole to be tapped through a comprehensive and multi-dimensional evaluation method, providing a reliable basis for the subsequent tapping operation; then, according to the minor defect signal generated by the quality assessment, the defect type is identified and the regulation coefficient is calculated in combination with the regional offset coefficient, and the processing parameters are dynamically regulated according to different defect types, effectively reducing the influence of defects and improving the tapping success rate, and the regulation coefficient takes into account multiple factors and can be flexibly adapted according to the actual situation of the hole position.

[0070] Embodiment 2

[0071] On the basis of Embodiment 1, please refer to Figure 2 shown, a valve body tapping calibration system based on machine vision described in the embodiment of the present invention includes:

[0072] Quality analysis module: Before the tapping process of the valve body, analyze the defect degree and defect distribution on the surface of the tapping hole position on the valve body, respectively obtain the gray scale offset coefficient and the gray scale uniformity coefficient, calculate the minor defect coefficient of tapping based on the gray scale offset coefficient and the gray scale uniformity coefficient, evaluate the quality of the tapping hole position to be processed, and generate a minor defect signal based on the quality evaluation result;

[0073] Parameter regulation module: Based on the minor defect signal, calculate the regulation coefficient according to the defect type and degree, so as to dynamically regulate the processing parameters.

[0074] Embodiment III

[0075] Refer to Figure 3 Moreover, the embodiment of the present invention further provides a computer device 3, including: a memory 302, a processor 301, and a computer program 303 stored on the memory 302. When the computer program 303 is executed on the processor 301, it implements a valve body tapping calibration method based on machine vision as described in any one of the above methods.

[0076] The computer device 3 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art can understand that Figure 3 merely examples of the computer device 3, which do not constitute a limitation to the computer device 3, may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0077] The so-called processor 301 may be a central processing unit (CPU), and the processor 301 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0078] The memory 302 may be an internal storage unit of the computer device 3 in some embodiments, such as a hard disk or memory of the computer device 3. The memory 302 may also be an external storage device of the computer device 3 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the computer device 3. Further, the memory 302 may also include both the internal storage unit and the external storage device of the computer device 3. The memory 302 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0079] Embodiment 4

[0080] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it implements a valve body tapping calibration method based on machine vision as described in any one of the above methods.

[0081] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above embodiment methods of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable medium may at least include: any entity or device capable of carrying the computer program code to the photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium may not be an electrical carrier signal and a telecommunication signal.

[0082] In the above embodiments, the descriptions of the various embodiments have their own focuses. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0083] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0084] In the embodiments disclosed in this application, it should be understood that the disclosed devices / terminal devices and methods can be implemented in other ways. For example, the device / terminal device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be electrical, mechanical or other forms.

[0085] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0086] The above formulas are all dimensionless and take their numerical calculations. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the actual situation. The preset parameters in the formulas are set by technicians in this field according to the actual situation.

[0087] The above has described in detail an embodiment of the present invention, but the content described is only a preferred embodiment of the present invention and cannot be considered to be used to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A valve body tapping calibration method based on machine vision, characterized in that: The following steps are involved: Before tapping the valve body, obtain the defect degree and defect distribution of the surface of the hole to be tapped on the valve body, and then perform grayscale statistical analysis to obtain the grayscale deviation coefficient and grayscale uniformity coefficient; Then, based on the grayscale deviation coefficient and grayscale uniformity coefficient, the tapping defect lightness coefficient is output, the quality of the hole to be tapped is evaluated, and based on the quality evaluation result, a slight defect signal is generated; Then, the defect type of the surface of the hole to be tapped on the valve body is obtained, and the control coefficient is obtained by fusion analysis with the slight defect signal and the defect type to dynamically calibrate the tapping parameters; Extract the gray value of the surface sub-area, calculate the difference between the gray value and the standard gray value, take the absolute value, obtain the gray offset value, and then calculate the ratio of the gray offset value to the standard gray value to obtain the gray offset ratio; Compare and analyze the grayscale offset ratio of each surface sub-region with the grayscale offset ratio threshold respectively; Extract the grayscale deviation ratios of all qualified sub-regions on the surface, calculate the mean, and obtain the qualified deviation mean; Extract the grayscale offset ratio of all surface defect sub-regions and mark it as defect offset ratio, denoted as B; The area of ​​the surface defect sub-region is extracted and the ratio is calculated with the total area of ​​the inner surface of the hole to be tapped to obtain the defect influence coefficient, which is recorded as Y. By formula: , calculate and obtain the defect offset weighted ratio QB; The defect offset weighted ratios of all surface defect sub-areas are averaged to obtain the defect offset mean; Then, the qualified offset mean and the defective offset mean are weightedly summed to obtain the grayscale offset coefficient; Based on the thread rotation direction and thread width during the tapping process, the inner surface of the hole to be tapped is divided into regions to obtain multiple annular sub-regions; The grayscale offset ratio of all qualified sub-regions on the surface of the annular sub-region is weighted and the defect offset weighted ratio of all defective sub-regions on the surface of the annular sub-region is weighted to obtain the region offset coefficient; Extracting the regional shift coefficients of all annular sub-regions to obtain a regional shift coefficient sequence; The wavelet basis function is used to perform wavelet decomposition on the regional migration coefficient sequence to obtain the detail coefficient ; Then, based on the detail coefficient, the output grayscale uniformity coefficient E is calculated using the wavelet coefficient energy formula; The grayscale deviation coefficient and the grayscale uniformity coefficient are summed and calculated to obtain the tapping defect lightness coefficient; By formula: , calculate and obtain the control coefficient K, where: is the regional deviation coefficient, E is the gray uniformity coefficient, Q is the tapping defect lightness coefficient, is the coefficient weight factor, is the overall impact factor.

2. A valve body tapping calibration method based on machine vision according to claim 1, characterized in that: The process of obtaining the grayscale deviation coefficient is: Before tapping the valve body, the image of the hole to be tapped on the valve body is obtained through image recognition technology and converted into a grayscale histogram; Based on the gray value of the gray histogram, the inner surface of the tapped hole is divided into regions, and the regions with the same gray value are divided into the same region to obtain surface sub-regions; Extract the deviation ratio between the gray value of each surface sub-region and the standard gray value, which is recorded as gray deviation ratio; If the grayscale offset ratio is less than or equal to the grayscale offset ratio threshold, the corresponding surface sub-region is marked as a qualified surface sub-region; If the grayscale offset ratio is greater than the grayscale offset ratio threshold, the corresponding surface sub-region is marked as a surface defect sub-region.

3. The valve body tapping calibration method based on machine vision according to claim 1, characterized in that: The process of evaluating the quality of the hole to be tapped and generating a minor defect signal based on the quality evaluation results is as follows: If the tapping defect light symptomatic coefficient is ≤ the tapping defect light symptomatic coefficient threshold, a light defect signal is generated.

4. The valve body tapping calibration method based on machine vision according to claim 1, characterized in that: The process of dynamically calibrating tapping parameters is: Identify the defect type of any annular sub-region, calculate it with the regional offset coefficient of the annular sub-region, and obtain the control coefficient; Based on the defect type and the control coefficient of the annular sub-region, the processing parameters are controlled when the annular sub-region is undergoing a tapping process.

5. A valve body tapping calibration system based on machine vision, characterized in that: The system is used to execute the method described in any one of claims 1 to 4 above, and the system comprises: Quality analysis module: Before tapping the valve body, obtain the defect degree and defect distribution of the surface of the hole to be tapped on the valve body, and then perform grayscale statistical analysis to obtain the grayscale deviation coefficient and grayscale uniformity coefficient; Then, based on the grayscale deviation coefficient and grayscale uniformity coefficient, the tapping defect lightness coefficient is output, the quality of the hole to be tapped is evaluated, and based on the quality evaluation result, a slight defect signal is generated; Parameter control module: obtains the defect type on the surface of the hole to be tapped on the valve body, and simultaneously integrates and analyzes it with the slight defect signal and the defect type to obtain the control coefficient, and dynamically calibrates the tapping parameters.

Images