Intelligent detection method for parts machined by numerical control machine tool

Abstract

The invention relates to the technical field of image processing, and particularly discloses an intelligent detection method for a part machined by a numerical control machine tool, which comprises the following steps of: acquiring an infrared image of a part image; dividing the part image into a plurality of local areas with the same temperature range according to the infrared image; if the part contains the coating and the temperature of the one or more local areas is greater than or less than the standard temperature, correcting the initial edge of the one or more local areas to obtain a corrected edge; calculating the roundness error of the part image according to the corrected edge of the part; and when the roundness error of the part image is greater than an error threshold value, judging that the corresponding part has defects. According to the intelligent detection method for the parts machined by the numerical control machine tool, the roundness error detection result of the parts is more accurate and reasonable, and misjudgment is prevented.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to an intelligent detection method for machining parts of a numerically controlled machine tool. Background Art

[0002] A numerically controlled machine tool is a core device in modern manufacturing. Through computer numerical control technology, precise control of the machine tool can be achieved, and various complex-shaped parts can be machined. The machined parts may have various defects, including roundness error, burrs, and surface unevenness. To prevent unqualified parts from flowing out, defect detection must be carried out before the parts leave the factory. For circular or annular parts, roundness detection is an important detection link for evaluating whether the circular contour of the part meets the design requirements. Roundness detection usually involves obtaining the actual contour of the part and comparing it with an ideal circle to obtain the roundness of the part.

[0003] Traditional methods for detecting part defects mainly rely on manual visual inspection, which has disadvantages such as low efficiency, strong subjectivity, and low accuracy of detection results. With the development of automatic defect detection technology based on machine vision, applying the automatic defect detection technology to the defect detection of parts can achieve high-efficiency and high-accuracy defect detection. For example, by using edge detection technology to obtain the edge of the part, and then automatically detecting the roundness of the edge of the part, and further determining whether the part to be detected has defects.

[0004] However, in the prior art, when performing roundness detection of parts, the influence of temperature and part coatings on the roundness detection of parts is not considered. Since the parts machined by numerically controlled machine tools are mostly made of metal materials such as steel, aluminum alloy, and copper alloy, these materials will expand and contract thermally under the influence of temperature. And some parts are coated with wear-resistant coatings, corrosion-resistant coatings, or oxidation-resistant coatings on their surfaces. Under the influence of temperature, the coatings of these parts are more likely to expand and contract thermally, causing the contour of the part to deform, and further resulting in an increase in the roundness error of circular or annular parts, which cannot reflect whether the roundness error of the part is caused by machining reasons, and thus misjudgment occurs. Summary of the Invention

[0005] The present invention provides an intelligent detection method for machining parts of a numerically controlled machine tool, aiming to solve the technical problem that in the prior art, due to the thermal expansion and contraction of parts, the roundness error of parts becomes larger, and thus misjudgment occurs during detection.

[0006] An intelligent detection method for machining parts of a numerically controlled machine tool according to the present invention includes the following steps: Obtain an infrared image of the part image; According to the infrared image, divide the part image into multiple local regions with the same temperature range; If the part has a coating and the temperature of one or more local regions is greater than or less than the standard temperature, the initial edges of the one or more local regions are corrected to obtain corrected edges; Calculate the roundness error of the part image based on the corrected edges of the part; when the roundness error of the part image is greater than the error threshold, it is determined that the corresponding part is defective; Among them, the obtaining of the corrected edges includes the following steps: Calculate the correction amount of each point on the initial edge; the magnitude of the correction amount is the product of the thermal expansion coefficient of the part and the absolute value of the temperature difference between the local region where the corresponding point on the initial edge is located; the temperature difference is the difference between the average temperature in the corresponding local region and the standard temperature; the direction of the correction amount is the perpendicular direction of the tangent line of the corresponding point on the initial edge; Connect the points obtained by moving each point on the initial edge in the direction of its correction amount by the corresponding correction amount in sequence to form the corrected edge.

[0007] In the above solution, the corrected edges are obtained through the original edges and the correction amounts of each point on them, correcting the displacement caused by thermal expansion and contraction, making the roundness error calculated based on the corrected edges more reasonable and accurate, and preventing misjudgment during detection.

[0008] Preferably, the local regions with the same temperature range are regions where the temperature difference between each position in the part image does not exceed the temperature threshold and the temperature gradient at each position does not exceed the temperature gradient threshold.

[0009] In the above solution, according to the temperature difference and temperature gradient, each region in the part image with close temperatures and small temperature changes is divided into the same local region, which is convenient for calculating the temperature change situation in the local region, and thus convenient for correcting the initial edges of the same local region in the subsequent steps.

[0010] Preferably, when the correction amount is positive, the corresponding point on the initial edge moves inward along the perpendicular direction of its tangent line towards the inside of the initial edge; when the correction amount is negative, the corresponding point on the initial edge moves outward along the perpendicular direction of its tangent line towards the outside of the initial edge.

[0011] In the above solution, by moving each point on the initial edge by the corresponding correction amount, the displacement of each point caused by thermal expansion and contraction is corrected, so that the corrected edges can exclude the interference of temperature and can truly reflect the roundness error of the part caused by processing reasons.

[0012] Preferably, the infrared image of the part image is obtained by an infrared thermal imager.

[0013] In the above solution, the infrared thermal imager can realize non-contact measurement, obtain the temperature at each position of the part, and can visually reflect the temperature distribution situation.

[0014] Preferably, the initial edge of the part image is obtained by the Sobel edge detection algorithm or the Canny edge detection algorithm.

[0015] In the above solution, the Sobel edge detection algorithm has the advantages of being simple and easy to implement and being robust to noise. The Canny edge detection algorithm has the advantages of high precision and being robust to noise.

[0016] Preferably, the standard temperature is the average temperature of each part under room temperature conditions.

[0017] Preferably, the roundness error of the part image is calculated by the least squares method.

[0018] In the above solution, calculating the roundness error by the least squares method has the advantages of high precision, strong robustness, and simple calculation.

[0019] Preferably, the roundness error of the part image is calculated by the least squares method, including the following steps: Construct an error function, which is the sum of the squares of the radial deviations of all points on the corrected edge from the ideal circle; the radial deviation is the difference between the distance from the corresponding point on the corrected edge to the assumed center of the ideal circle and the assumed radius of the ideal circle; Minimize the error function to obtain the true center and true radius of the ideal circle; According to the true center and true radius of the ideal circle, calculate the radial deviation of each point on the corrected edge; Take the difference between the maximum value and the minimum value of the radial deviations of each point on the corrected edge as the roundness error of the corresponding part image.

[0020] Preferably, the part image is an image after filtering and denoising, and the filtering method is one of Gaussian filtering, median filtering, and mean filtering.

[0021] In the above solution, through filtering and denoising, the interference of noise on the part image can be prevented, making the calculation result more accurate.

[0022] Preferably, the shape of the part is circular or annular.

[0023] The beneficial effects are: The solution of the present invention comprehensively considers the influence of the temperature distribution and coating condition of the part on the roundness error of the part. Through the original edge of the part image and the correction amount of each point thereon, a corrected edge is obtained, and the roundness error of the part image is calculated using the corrected edge, correcting the displacement of each point on the initial edge of the part caused by thermal expansion and contraction, making the calculation result of the roundness error of the part more reasonable and accurate, and preventing misjudgment during detection. Description of the Drawings

[0024] Figure 1 It is a flowchart of the steps of the intelligent detection method for machining parts by a numerically controlled machine tool according to an embodiment of the present invention; Figure 2 It is a flowchart of the steps for obtaining a corrected edge according to an embodiment of the present invention. Specific embodiments

[0025] The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0026] The present invention provides an intelligent detection method for machining parts by a numerically controlled machine tool. The detection object of the present invention is a circular part, which is hereinafter simply referred to as a part for simplicity. The machining defects of the part can be detected by roundness detection. Among them, roundness describes the geometric characteristics of a circular object and reflects the degree to which the cross-section of the object approaches an ideal circle. The parts in the present invention are circular, annular, and parts close to circular or annular. For example, if the roundness error meets the requirements, it means that the part has no machining defects; if the roundness error does not meet the requirements, it means that the part has defects. These defects include protrusions, depressions, or missing corners that appear at the edge of the part. However, in actual scenarios, during the transfer process of the part, due to reasons such as environmental temperature changes, touch, and friction, the surface temperature distribution of the part may be uneven.

[0027] When the part is heated, the molecules or atoms inside it will obtain energy and move faster, resulting in an increase in the average distance between molecules or atoms, thereby causing the volume of the part to expand. On the contrary, when the part cools, the movement speed of molecules or atoms slows down, and the average distance decreases, resulting in the volume of the part shrinking.

[0028] When the temperature distribution on the surface of the part is uneven, the areas with higher temperature on the part expand due to heat, and the areas with lower temperature contract due to cooling. That is to say, different regions of the part expand or contract, making the deformation sizes and directions of different regions of the part inconsistent, and further causing the roundness of the part to change, resulting in an increase in the roundness error.

[0029] Therefore, the increase in the roundness error of the part caused by thermal expansion and contraction will interfere with the roundness detection process of the part, resulting in errors in the detection results and misjudgment. That is to say, some parts judged to be defective may be due to thermal expansion and contraction, rather than due to machining reasons. And these parts return to their original state after the temperature distribution is uniform, and their roundness errors meet the requirements. Therefore, when detecting part defects, the interference of temperature factors should be considered, which can make the detection results more reasonable and accurate and avoid misjudgment.

[0030] As Figure 1 shown, the intelligent detection method for machining parts by a numerically controlled machine tool provided by the present invention includes the following steps: S1. Obtain the infrared image of the part image.

[0031] In this step, by obtaining the infrared image of the part image, the temperature at each position in the part image can be obtained. The infrared image can be obtained by an infrared thermal imager. An infrared thermal imager is an instrument that can detect and display the temperature distribution on the surface of an object and is suitable for non-contact measurement. It can not only obtain the temperature at each position in the part image, but also enable people to intuitively see the temperature differences at each position by capturing the infrared radiation emitted by the object and converting it into a visual image. By obtaining the infrared image, it is convenient for subsequent steps to process the part image.

[0032] In order to reduce the interference of noise on the part image, the part image is an image after filtering and denoising, where the filtering method is one of Gaussian filtering, median filtering, and mean filtering. Of course, other filtering and denoising methods can also be used and can be selected according to needs.

[0033] S2. According to the infrared image, divide the part image into multiple local regions with the same temperature range.

[0034] In this step, the local regions with the same temperature range are regions where the temperature difference between each position in the part image does not exceed the temperature threshold, and the temperature gradient at each position does not exceed the temperature gradient threshold. The temperature threshold and the temperature gradient threshold can be determined through experiments. Among them, the temperature gradient characterizes the temperature change situation of the corresponding part at each position. The temperature gradient refers to the rate of change of temperature in space and is expressed as the ratio of the difference in temperature between the corresponding position and its adjacent position in the part image to the Euclidean distance between the two positions. It describes how fast the temperature changes with position. The direction of the temperature gradient points to the direction where the temperature increases fastest, and its magnitude represents the temperature change per unit distance. According to the temperature at each position in the part image, the temperature gradient at each corresponding position can be obtained. According to the temperature difference between each position in the part image and the temperature gradient at each position, the part image is divided into multiple local regions.

[0035] In one embodiment, the region growing algorithm can also be used to divide the part image into multiple local regions. The region growing algorithm belongs to the prior art. Its basic idea is to select some pixel points in the image as seed points, and according to the similarity criterion, gradually merge the surrounding pixel points similar to the seed points into the same region until there are no pixel points that can be merged, thereby obtaining each local region. Among them, the similarity criterion is the similarity of the gray values of the pixel points in the part image. Since the temperatures at each position of the part are different, the gray values of the corresponding pixel points in the part image are also different. The higher the temperature, the larger the gray value of the corresponding pixel point. Therefore, the region growing algorithm can divide the regions with similar temperatures into the same local region by comparing the similarity of gray values.

[0036] In other embodiments, the watershed algorithm can also be used, which belongs to the prior art and will not be elaborated here.

[0037] In step S2, each region in the part image with similar temperatures and small temperature changes is divided into the same local region, which is convenient for calculating the temperature change in the local region, and further convenient for correcting the initial edge of the same local region in subsequent steps.

[0038] S3. If the part has a coating and the temperature of one or more local regions is greater than or less than the standard temperature, correct the initial edge of the one or more local regions to obtain a corrected edge.

[0039] This step comprehensively considers the roundness error of the part based on two factors: the difference between the temperature of the local region and the standard temperature, and the coating condition of the part. Among them, the standard temperature is the average temperature of each part under room temperature conditions. When the temperature of the local region is greater than or less than the standard temperature, it indicates that the temperature distribution of the corresponding part is uneven, and the part will expand and contract due to heat. Since most parts are made of metal and have a hard texture, the influence of a single temperature factor on the roundness error of the part is not obvious.

[0040] Therefore, the present invention also considers the influence factor of whether the part has a coating. Among them, the coating is a material layer applied on the surface of the part, used to protect the part, enhance its performance or change its appearance. For example, the coating includes wear-resistant coatings, corrosion-resistant coatings, and insulating coatings, etc. Since the coating of the part is usually thin, it is more likely to deform due to thermal expansion and contraction under the influence of temperature. Therefore, when calculating the roundness error of the part, it is necessary to consider not only the influence of temperature but also the presence or absence of the coating on the part.

[0041] The present invention comprehensively considers the influence of the temperature and coating of the part on the roundness error of the part, and calculates the roundness error of the corresponding part according to the corrected edge in the part image, making the calculation result of the roundness error of the part more accurate and reasonable, and further avoiding misjudgment during part detection.

[0042] The present invention first explains the situation of simultaneously satisfying two factors, that is, the part has a coating and the temperature of one or more local regions is greater than or less than the standard temperature. Specifically, when the temperature of the local region is greater than or less than the standard temperature, it indicates that there is an uneven temperature distribution region in the corresponding part. In this case, if the part has a coating, the part with the coating is more likely to deform due to thermal expansion and contraction under the influence of temperature, thus affecting the result of image recognition. That is to say, the roundness error of the part may become larger due to thermal expansion and contraction in the uneven temperature distribution region.

[0043] Whether the part has a coating is known before processing. Therefore, when determining whether the part has a coating, the presence or absence of the coating on the part can be directly input manually, which can save time and improve the detection efficiency.

[0044] In step S3, when both the temperature of the part image and the coating condition of the corresponding part meet the requirements, the roundness error of the part image is calculated based on the corrected edge of the part image. Among them, the corrected edge is the edge obtained by correcting the expansion or contraction caused by thermal expansion and contraction of the initial edge. The corrected edge can prevent the uneven temperature distribution of the part from causing uneven deformation of the part, and further causing the roundness error of the part to become larger.

[0045] Such as Figure 2 shown, the acquisition of the corrected edge includes the following steps: S31. Calculate the correction amount of each point on the initial edge.

[0046] In this step, the initial edge refers to the edge of the outer contour of the part, which can reflect the contour shape of the part. The initial edge can be obtained by the Sobel edge detection algorithm, which has the advantages of simple implementation and robustness to noise. Of course, the Canny edge detection algorithm can also be used, which has the advantages of high accuracy and robustness to noise. The Sobel edge detection algorithm and the Canny edge detection algorithm are both existing technologies, and will not be elaborated in this invention.

[0047] The magnitude of the correction amount is the product of the thermal expansion coefficient of the part and the absolute value of the temperature difference between the corresponding point on the initial edge and the local area. The temperature difference is the difference between the average temperature in the corresponding local area and the standard temperature. The direction of the correction amount is the perpendicular direction of the tangent line of the corresponding point on the initial edge. This is because the thermal expansion coefficient represents the change in the length of an object under a unit temperature change. Therefore, each point on the initial edge will expand outward or contract inward due to temperature changes. Specifically, when the temperature of the local area is greater than the standard temperature, the corresponding point will expand outward due to heat. When the temperature of the local area is less than the standard temperature, the corresponding point will contract inward due to cooling. The displacement amount of the corresponding point expanding outward or contracting inward is the correction amount corresponding to that point.

[0048] Specifically, the magnitude of the correction amount of the point on the initial edge of the th local area is: ; In the formula, is the thermal expansion coefficient of the material of the part, is the absolute value of the difference between the average value of each temperature in the th local area and the standard temperature.

[0049] In step S31, according to the thermal expansion coefficient of the part material and the temperature difference of the corresponding local area, the correction amount of each point on the initial edge is obtained, and then the initial edge can be corrected by the correction amount.

[0050] S32. Connect the points obtained by moving each point on the initial edge along the direction of its correction amount by the corresponding correction amount size in sequence to form the corrected edge.

[0051] In this step, when the correction amount is positive, the corresponding point on the initial edge moves inward along the vertical direction of its tangent towards the inside of the initial edge. When the correction amount is negative, the corresponding point on the initial edge moves outward along the vertical direction of its tangent towards the outside of the initial edge. This is because when the correction amount is positive, it indicates that the temperature difference of the local area is positive, that is, the temperature is increasing, and the points on the initial edge will expand outward due to heat, so the corresponding points need to be moved inward by the corresponding correction amount size for correction. When the correction amount is negative, it indicates that the temperature difference of the local area is negative, that is, the temperature is decreasing, and the points on the initial edge will contract inward due to cooling, so the corresponding points need to be moved outward by the corresponding correction amount size for correction.

[0052] Specifically, a rectangular coordinate system is established on the part image to obtain the coordinates of each point on the initial edge. According to the size and direction of the correction amount, the components of the correction amount on the horizontal and vertical axes of the coordinate system can be calculated. Therefore, the abscissa of each point on the corrected edge is the abscissa of the corresponding point on the initial edge plus the component of the corresponding correction amount on the horizontal axis, and the ordinate of each point on the corrected edge is the ordinate of the corresponding point on the initial edge plus the component of the corresponding correction amount on the vertical axis.

[0053] In steps S31 to S32, according to the thermal expansion coefficient and the temperature difference of the local area, the correction amount of each point on the corresponding initial edge is calculated, and then according to the size and direction of the correction amount, each point on the initial edge is corrected to obtain the corresponding corrected edge. Since the corrected edge corrects the displacement of each point on the initial edge caused by thermal expansion and contraction, it can avoid the increase of the roundness error of the part due to the uneven temperature distribution of the part, making the roundness error obtained according to the corrected edge more accurate and reasonable.

[0054] In step S3, after obtaining the corrected edge of the part image, it further includes step S33: Calculate the roundness error of the corresponding part image according to the corrected edge.

[0055] Among them, the calculation of the roundness error is a prior art, and the present invention lists a method for calculating the roundness error based on the least squares method. It evaluates the deviation between the corrected edge and the ideal circle by fitting an ideal circle. Step S33 includes the following steps: S331. Construct an error function, which is the sum of the squares of the radial deviations of all points on the corrected edge from the ideal circle; the radial deviation is the difference between the distance from the corresponding point on the corrected edge to the assumed center of the ideal circle and the assumed radius of the ideal circle.

[0056] Therefore, the radial deviation of the -th point on the corrected edge from the ideal circle is: ; In the formula, is the abscissa of the -th point on the corrected edge, is the ordinate of the -th point on the corrected edge, is the abscissa of the assumed center of the ideal circle, is the ordinate of the assumed center of the ideal circle, is the assumed radius of the ideal circle.

[0057] The error function is: ; In the formula, is the radial deviation of the -th point on the corrected edge from the ideal circle, is the total number of all points on the corrected edge.

[0058] S332. Minimize the error function to obtain the true center and true radius of the ideal circle.

[0059] For the convenience of solution, let , , then the error function is: .

[0060] Take the partial derivatives of the parameters , , in the above error function and set the derivatives to 0, three sets of equations can be obtained. Solve the equations to obtain the values of , , . Furthermore, the true center of the ideal circle is ( ), and the true radius of the ideal circle is .

[0061] S333. Calculate the radial deviation of each point on the corrected edge according to the true center and true radius of the ideal circle.

[0062] Substitute the true center and true radius of the ideal circle into the radial deviation formula in step S331 to obtain the radial deviations of each point on the corrected edge.

[0063] S334. Take the difference between the maximum and minimum values of the radial deviations of each point on the corrected edge as the roundness error of the corresponding part image .

[0064] Therefore, the roundness error of the part image is: ; wherein, is the maximum value of the radial deviations of each point on the corrected edge, is the minimum value of the radial deviations of each point on the corrected edge.

[0065] In step S33, calculating the roundness error using the least squares method has the advantages of high precision, strong robustness, and simple calculation.

[0066] In some other embodiments, the minimum circumscribed circle method can also be used to calculate the roundness error.

[0067] In the present invention, when the temperature and coating factors are not satisfied simultaneously, the roundness error of the part can be directly calculated using the initial edge in the part image, which can simplify the calculation steps and improve the detection efficiency. The calculation method of the roundness error is the same as that in step S33 and will not be elaborated here.

[0068] S4. When the roundness error of the part image is greater than the error threshold, it is determined that the corresponding part has a defect.

[0069] In this step, when the roundness error of the part is greater than the error threshold, it indicates that the roundness of the corresponding part is poor and the corresponding part has a defect. When it is determined that the corresponding part has a defect, measures such as alarm can be taken to timely remind the staff to check and prevent unqualified products from flowing out.

[0070] In the intelligent detection method for machining parts by the numerical control machine tool of the present invention, when the temperature and coating conditions of the part both meet the requirements, the corrected edge of the part image is used to calculate the roundness error of the corresponding part. Since the corrected edge is the corresponding initial edge plus the corresponding correction amount, which corrects the displacements of each point on the initial edge due to thermal expansion and contraction, the calculation result of the roundness error of the part is more reasonable and accurate, preventing misjudgment from occurring.

[0071] Although this specification has shown and described several embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many variations, modifications, and alternative approaches will occur to those skilled in the art without departing from the spirit and scope of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in practicing the present invention.

Claims

1. An intelligent detection method for machining parts by a numerical control machine tool, characterized in that, It includes the following steps: obtaining an infrared image of the part image; According to the infrared image, dividing the part image into multiple local areas with the same temperature range; If the part has a coating and the temperature of one or more local areas is greater than or less than the standard temperature, correcting the initial edge of one or more local areas to obtain a corrected edge; Calculating the roundness error of the part image based on the corrected edge of the part; when the roundness error of the part image is greater than the error threshold, it is determined that the corresponding part is defective; Among them, the obtaining of the corrected edge includes the following steps: Calculating the correction amount of each point on the initial edge; the magnitude of the correction amount is the product of the thermal expansion coefficient of the part and the absolute value of the temperature difference between the local area where the corresponding point on the initial edge is located; the temperature difference is the difference between the average temperature in the corresponding local area and the standard temperature; the direction of the correction amount is the vertical direction of the tangent line at the corresponding point on the initial edge; Connecting the points obtained by moving each point on the initial edge along the direction of its correction amount by the corresponding correction amount in sequence to form the corrected edge.

2. The intelligent detection method for machining parts by a numerically controlled machine tool according to claim 1, wherein, The local area with the same temperature range is an area where the temperature difference between each position in the part image does not exceed the temperature threshold and the temperature gradient at each position does not exceed the temperature gradient threshold.

3. The intelligent detection method for machining parts of a numerically controlled machine tool according to claim 1, wherein, When the correction amount is positive, the corresponding point on the initial edge moves inward along the vertical direction of its tangent line towards the inside of the initial edge; when the correction amount is negative, the corresponding point on the initial edge moves outward along the vertical direction of its tangent line towards the outside of the initial edge.

4. The intelligent detection method for machining parts by a numerically controlled machine tool according to claim 1, wherein, The infrared image of the part image is obtained by using an infrared thermal imager.

5. The intelligent detection method for machining parts of a numerical control machine tool according to claim 1, characterized in that, The initial edge of the part image is obtained by the Sobel edge detection algorithm or the Canny edge detection algorithm.

6. The intelligent detection method for machining parts by a numerically controlled machine tool according to claim 1, characterized in that, The standard temperature is the average temperature of each part under room temperature conditions.

7. The intelligent detection method for machining parts of a numerically controlled machine tool according to claim 1, wherein The roundness error of the part image is calculated by using the least squares method.

8. The intelligent detection method for machining parts by a numerical control machine tool according to claim 7, characterized in that, The roundness error of the part image is calculated by using the least squares method, including the following steps: Constructing an error function, which is the sum of the squares of the radial deviations of all points on the corrected edge from the ideal circle; the radial deviation is the difference between the distance from the corresponding point on the corrected edge to the assumed center of the ideal circle and the assumed radius of the ideal circle; Minimizing the error function to obtain the true center and true radius of the ideal circle; Calculating the radial deviation of each point on the corrected edge according to the true center and true radius of the ideal circle; Taking the difference between the maximum value and the minimum value of the radial deviations of each point on the corrected edge as the roundness error of the corresponding part image.

9. The intelligent detection method for machining parts by a numerically controlled machine tool according to claim 1, wherein, The part image is an image after filtering and denoising, and the filtering method is one of Gaussian filtering, median filtering, and mean filtering.

10. The intelligent detection method for machining parts by a numerical control machine tool according to claim 1, characterized in that, The shape of the part is circular or annular.

Images