Shaft part forging forming monitoring method and system

Abstract

The invention relates to the technical field of image processing, in particular to a shaft part forging forming monitoring method and system. The method comprises the following steps: acquiring characteristic values of pixel points in a surface image of a formed shaft part in a plurality of channels in an HSV color space, and gradient direction angles of the pixel points; determining the local consistency of the pixel points; determining a weighted Euclidean distance between the pixel points; clustering all pixel points according to the weighted Euclidean distance to obtain a plurality of clusters; determining the gradient saliency and the number of candidate angular points of the image region where the clustering cluster is located; and on the basis of the number of the candidate corner points, the candidate corner points are obtained through a Harris corner point detection algorithm, and whether forging of the shaft part is qualified or not is measured according to the Euclidean distance between the candidate corner points. According to the method, the problem of inaccurate recognition caused by large feature difference of different geometric regions is solved through the number of the candidate angular points of the image region where the adaptive clustering cluster is located, and the accuracy of monitoring the forging quality of the shaft parts is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method and system for monitoring the forging of shaft parts. Background Art

[0002] In the manufacturing process of complex metal parts, shaft parts are usually produced using a forging process, which places strict requirements on dimensional accuracy. However, problems such as internal friction in machine tools and loose components, which are common during the forging process, often lead to insufficient pressure or uneven pressure distribution in the hydraulic system. This phenomenon directly affects the fluidity and filling effect of the metal material, and in turn causes uneven internal structure of the part. During the subsequent cooling process, this unevenness is further amplified, resulting in significant differences in strength and hardness in different areas of the part, and ultimately causes uneven deformation after cold forming, such as distortion or dimensional deviation, which seriously affects the quality and performance indicators of the part. Therefore, it is crucial to monitor the shape of cold-formed shaft parts in order to promptly detect and handle unqualified parts and ensure product quality.

[0003] Shaft parts themselves have many geometric regions, such as transition fillets and shoulders. The edges of these regions are often subjected to complex stress and strain states during the forging process. The fluidity and filling effect of metal materials are more easily hindered in these areas, resulting in uneven distribution of materials in the edge areas. After cooling and forming, these edge areas are more likely to deform, and these deformations will cause significant changes in the gradient of the local area. However, the traditional Harris corner detection algorithm relies on a global threshold to identify obvious gradient direction angle change points. However, due to the large differences in the gradients of different geometric regions of shaft parts, a fixed global threshold is difficult to accurately adapt to the characteristics of all geometric regions, resulting in a decrease in the accuracy of corner recognition, which in turn affects the monitoring of shaft part forging. Summary of the Invention

[0004] In order to solve the problem that the traditional Harris corner detection algorithm relies on a global threshold to identify obvious gradient direction angle change points, but since the gradients of different geometric areas of shaft parts have large differences, the fixed global threshold is difficult to accurately adapt to the characteristics of all geometric areas, resulting in reduced accuracy of corner point recognition, which in turn affects the monitoring of shaft part forging, the present invention provides a shaft part forging monitoring method and system.

[0005] In a first aspect, the present invention provides a method for monitoring the forging of shaft parts, which adopts the following technical solution: A method for monitoring the forging of shaft parts, comprising: obtaining characteristic values ​​of multiple channels of pixel points in the HSV color space and the gradient direction angles of the pixel points in a surface image of the shaft part after forming; recording any pixel point as a target pixel point, and determining the local consistency of the target pixel point based on the characteristic values ​​of the target pixel point and pixels in the neighborhood in each channel in the HSV color space; in response to the cosine similarity between the characteristic vectors corresponding to all channels of the target pixel point and any other pixel point being greater than 0, weighting the Euclidean distance between the two pixel points based on the local consistency of the two pixel points and the cosine similarity. , obtaining a weighted Euclidean distance between two pixel points; clustering all pixel points according to the weighted Euclidean distance to obtain a number of clusters; determining the gradient significance of the image region where the cluster is located according to the difference in gradient direction angles between pixel points in the cluster and the number of pixel points in the cluster; determining the number of candidate corner points in the image region where the cluster is located according to the gradient significance, the number of all pixel points, and a preset global threshold; based on the number of candidate corner points, obtaining candidate corner points using the Harris corner detection algorithm, and measuring whether the shaft part forging is qualified according to the Euclidean distance between the candidate corner points.

[0006] The present invention utilizes local consistency analysis to dynamically adjust detection standards according to the features of different geometric regions, adapting to various gradient differences, thereby improving the accuracy of corner point recognition; clustering pixels by weighted Euclidean distance can effectively distinguish different feature regions, reducing the problem of reduced clustering accuracy caused by traditional clustering methods, and increasing sensitivity to fine structures; combining the gradient direction angle and number of pixel points to determine the significance of clusters, improving the ability to recognize key features, and providing a more reliable basis for monitoring forging quality; by adaptively adjusting the number of candidate corner points in the image area where each cluster is located, the problem of inaccurate recognition caused by large differences in features in different geometric regions is effectively solved, thereby improving the accuracy of forging quality monitoring of shaft parts.

[0007] Furthermore, the method for obtaining the eigenvalues ​​is: converting the RGB color space of the surface image into the HSV color space, and obtaining the eigenvalues ​​of multiple channels of the pixel points in the surface image in the HSV color space.

[0008] Furthermore, the method for obtaining the gradient direction angle is: gray-scale processing is performed on the surface image, and the gradient direction angle of the pixel point is obtained on the gray-scale processed surface image using a Sobel operator.

[0009] Furthermore, the local consistency satisfies: Where, For the The local consistency of pixels, For the The pixel at the The eigenvalues ​​of the channels, For the The pixel in the neighborhood The pixel at the The eigenvalues ​​of the channels, For the The number of pixels in the neighborhood of a pixel, is the number of channels, is the natural exponential function.

[0010] The present invention determines local consistency by integrating HSV multi-channel features and neighborhood information, accurately depicts the local color characteristics of shaft parts, and provides rich and reliable information for corner point identification; calculates local consistency in exponential form, enhances sensitivity to feature differences, ensures numerical stability, and facilitates subsequent weighted Euclidean distance clustering and other operations.

[0011] Furthermore, the weighted Euclidean distance satisfies: Where, For the Pixels and The weighted Euclidean distance between pixels, For the Pixels and The Euclidean distance between pixels, For the The local consistency of pixels, No. The local consistency of pixels, For the The feature vector corresponding to each pixel in all channels is: For the The feature vector corresponding to each pixel in all channels is: For the Pixels and The cosine similarity between the feature vectors corresponding to all channels of the pixel points, is the absolute value symbol.

[0012] The present invention integrates the Euclidean distance, local consistency and cosine similarity of pixel points to comprehensively measure the relationship between pixels and provide a more accurate distance measurement for clustering. When the cosine similarity of the eigenvector is greater than 0, the weight is adaptively adjusted, and the distance is dynamically adjusted according to the difference in local consistency to adapt to the characteristics of different regions of shaft parts.

[0013] Furthermore, the clustering adopts an iterative self-organizing clustering algorithm.

[0014] Furthermore, the gradient significance satisfies: Where, For the The gradient significance of the image region where the clusters are located, For the The first The gradient direction angle of each pixel, For the The first The gradient direction angle of each pixel, For the The number of pixels in a cluster, is the standard normalization function.

[0015] The present invention calculates the gradient angular differences of all pixels within the same cluster. The gradient significance can fully reflect the visual feature complexity of the area, so that the algorithm not only focuses on the characteristics of a single pixel, but also on the feature changes of the entire area, thereby providing a more comprehensive feature description. The calculation of gradient significance emphasizes the gradient angular changes between pixels within the same cluster, which can effectively identify the complexity of the structure in the area. An increase in significance usually means that this area may contain more edge or detail information, thus providing a more important basis for subsequent corner point recognition.

[0016] Furthermore, the number of candidate corner points satisfies: Where, For the The number of candidate corner points in the image region where the cluster is located, For the The gradient significance of the image region where the clusters are located, is the number of clusters, is the preset global threshold, is the number of pixels in the surface image, Is the rounding function.

[0017] The present invention can dynamically adjust the number of candidate corner points according to the relative complexity of regional features. This adaptability ensures that more corner points are detected in feature-rich areas, thereby improving the sensitivity and accuracy of monitoring. Combined with a preset global threshold, the number of candidate corner points can be controlled while ensuring that the detection results meet certain quality standards. This ensures that the number of corner points not only depends on local features but also takes into account the global detection goals, thereby improving the stability and reliability of quality monitoring.

[0018] Furthermore, the method of measuring whether the forging of shaft parts is qualified based on the Euclidean distance between candidate corner points includes: in response to the difference between the maximum value of the Euclidean distance between all candidate corner points in the surface image of the shaft part after forming and the maximum value of the Euclidean distance between all candidate corner points in the surface image of the standard shaft part being greater than a preset abnormality threshold, determining that the forging of the shaft part after current forming is unqualified, issuing an early warning prompt, and completing the forging monitoring of the shaft parts.

[0019] In a second aspect, the present invention provides a shaft parts forging monitoring system, which adopts the following technical solution: A shaft part forging monitoring system includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned shaft part forging monitoring method is implemented.

[0020] By adopting the above technical solution, the above-mentioned method for monitoring the forging of shaft parts is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0021] The present invention has the following technical effects: Obtain the multi-channel eigenvalues ​​of the pixels in the HSV color space on the surface of the shaft parts, and combine it with the gradient direction angle analysis. When determining the local consistency, the color information is fully considered based on the eigenvalues ​​of the target pixel and the neighboring points in each HSV channel, reducing the interference of color differences and making the corner point recognition more accurate. When the cosine similarity of the eigenvectors of the target pixel and the remaining pixels is greater than 0, the Euclidean distance is weighted by combining the local consistency and cosine similarity to obtain the weighted Euclidean distance. This weighting method can comprehensively consider the color feature similarity and local consistency between the pixels, making the clustering results more reasonable. In the shaft parts image, the pixels with similar colors and local structures will be more accurately divided into the same cluster cluster, which is convenient for the subsequent corner point recognition. It provides a more reliable basis for differentiation; clustering the pixels to obtain cluster clusters, and when determining the gradient significance, the gradient direction angle difference and number of pixels in the cluster are taken into account. Different geometric regions are analyzed according to their own gradient and pixel distribution, without relying on a unified global threshold, which is in line with the characteristics of large regional gradient differences in shaft parts; the number of candidate corner points is determined by combining the gradient significance, the total number of pixels and the preset global threshold. This dynamic method integrates local and overall pixel information, accurately identifies potential corner points in different areas, and avoids missed detection and false detection caused by fixed thresholds; accurately identifying corner points can capture changes in the forming shape of parts, and by comparing distances with qualified standards, it can promptly detect abnormalities such as shape deviations, provide a reliable basis for quality control, and improve the monitoring efficiency of forging of shaft parts. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a flow chart of a method for monitoring the forging of shaft parts according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0024] The embodiment of the present invention discloses a method for monitoring the forging of shaft parts. Figure 1 , including steps S1 to S6: S1: Obtain the characteristic values ​​of multiple channels of the pixel points in the surface image of the formed shaft part in the HSV color space, as well as the gradient direction angle of the pixel points.

[0025] It should be noted that by using an industrial camera to capture images in a uniformly illuminated environment, and selecting an appropriate shooting angle and distance based on the size and shape of the shaft part's surface after molding, we ensured that comprehensive surface detail was captured. The surfaces of shaft parts have diverse geometric features (such as transition fillets and shoulders), which can be affected by various factors in the RGB color space. For example, under the same lighting conditions, different geometric features may produce different shadows or light reflections, resulting in inaccurate or difficult-to-distinguish color features in the RGB color space for different geometric regions. Considering that the three parameters of hue, saturation, and brightness in the HSV color space can more intuitively reflect the color information in the image and are relatively robust to changes in lighting, the surface image is converted from the RGB color space to the HSV color space to more accurately extract color features.

[0026] Specifically, the method for obtaining the characteristic value is: The RGB color space of the surface image is converted to the HSV color space, and the characteristic values ​​of multiple channels of the pixel points in the surface image in the HSV color space are obtained.

[0027] Specifically, the method for obtaining the gradient direction angle is: The surface image is gray-scaled, and the Sobel operator is used to obtain the gradient direction angle of the pixel point on the gray-scaled surface image.

[0028] S2: Determine the local consistency of pixels.

[0029] It should be noted that different geometric regions of shaft parts often exhibit significant variations in visual features such as color and brightness. These variations can be effectively reflected in the HSV color space. Pixels with similar local consistency often belong to the same geometric region because they have similar color characteristics and spatial distribution. Conversely, pixels with significant differences in local consistency may belong to different geometric regions. Therefore, by analyzing the local consistency of each pixel, we can obtain the spatial distribution consistency of these features for each pixel.

[0030] Any pixel is recorded as the target pixel, and the local consistency of the target pixel is determined based on the characteristic values ​​of each channel of the target pixel and the pixels in the neighborhood in the HSV color space.

[0031] Specifically, the local consistency satisfies: ; Where, For the The local consistency of pixels, For the The pixel at the The eigenvalues ​​of the channels, For the The pixel in the neighborhood The pixel at the The eigenvalues ​​of the channels, For the The number of pixels in the neighborhood of a pixel, is the number of channels, is the natural exponential function.

[0032] Among them, local consistency reflects the consistency of the HSV color space features of the current pixel and the pixels in its neighborhood. The larger the value, the closer the color features of the pixel and the surrounding pixels are in different channels. Indicates the The pixel point and the pixel point in the neighborhood are The sum of the absolute differences of the eigenvalues ​​of each channel. The smaller the value, the smaller the difference between the pixel and the pixels in the neighborhood on this channel, which means that the color feature changes of the pixel and the pixels in the neighborhood on this channel are more consistent; the local consistency of the color features on each channel is summed to reflect the overall consistency of the pixel relative to its neighborhood in the entire HSV color space, that is, The smaller the value, the higher the local consistency of the current pixel.

[0033] S3: Determine the weighted Euclidean distance between pixels.

[0034] It's important to note that traditional clustering methods often only consider pixel color and coordinate information for clustering. However, at the intersection of different regions, color differences are minimal and locations are close, ignoring the consistency of local pixel features. This can lead to misclassification of pixels in these regions, which are crucial for corner identification. Therefore, by introducing local consistency (the similarity of the local color features of two pixels) and cosine similarity (the similarity of the color features of two pixels) to measure the cluster distance between pixels, we can more accurately reflect the true relationship between pixels.

[0035] In response to the cosine similarity between the feature vectors corresponding to all channels of the target pixel and any other pixel points being greater than 0, the Euclidean distance between the two pixel points is weighted according to the local consistency of the two pixel points and the cosine similarity to obtain a weighted Euclidean distance between the two pixel points.

[0036] Specifically, the weighted Euclidean distance satisfies: ; Where, For the Pixels and The weighted Euclidean distance between pixels, For the Pixels and The Euclidean distance between pixels, For the The local consistency of pixels, No. The local consistency of pixels, For the The feature vector corresponding to each pixel in all channels is: For the The feature vector corresponding to each pixel in all channels is: For the Pixels and The cosine similarity between the feature vectors corresponding to all channels of the pixel points, is the absolute value symbol.

[0037] Among them, the weighted Euclidean distance reflects the spatial distance and color feature similarity between pixels. The smaller the value, the closer the spatial distribution between the two pixels and the similar color features, which means that the two pixels may be in the same geometric area (because different geometric areas are prone to produce different shadows or light reflection effects due to different lighting, which means that the color features of different geometric areas vary significantly); when the feature vectors of the two pixels are more similar, that is, , indicating that the color features of the two pixels are similar in each channel; in this case, if the local consistency difference of the two pixels after normalization is also smaller, it means that the local color features of the two pixels are also more similar, which means that the two pixels are more likely to be distributed in the same geometric area; therefore, it is necessary to reduce the current Euclidean distance so that the two pixels can be clustered. Conversely, if the local consistency difference of the two pixels is larger, it means that the two pixels may be located at the intersection of different areas. In this case, it is necessary to increase the current Euclidean distance to avoid clustering; The more dissimilar the two pixel feature vectors are, , which means that the two pixels do not belong to the same area. Their Euclidean distance is relatively large, so just keep the original distance.

[0038] S4: Clustering all pixel points according to the weighted Euclidean distance to obtain a number of clusters.

[0039] Specifically, the clustering adopts an iterative self-organizing clustering algorithm.

[0040] The weighted Euclidean distance between pixels is used to replace the distance in the traditional iterative self-organizing clustering algorithm for clustering. Clustering is stopped until the clusters no longer change, and the final clustering result, that is, several clusters, is obtained.

[0041] S5: Determine the gradient significance and the number of candidate corner points in the image region where the cluster is located.

[0042] It should be noted that clustering pixels with similar color characteristics and spatial distributions into one category distinguishes the different possible geometric regions of a part. However, different geometric regions often experience complex stress and strain states during the forging process, which can lead to differences in gradient significance across regions. Traditional Harris corner detection algorithms rely on a global threshold to identify points with significant gradient angular changes, but this ignores the large variability in gradients across regions of actual geometric mutations. A fixed global threshold cannot accurately adapt to the characteristics of all mutation regions, resulting in inaccurate corner identification. Therefore, it is necessary to analyze the degree of gradient angular change across the pixels in each region to assess the region's gradient significance and adaptively adjust the appropriate threshold for each region.

[0043] The gradient significance of the image region where the cluster is located is determined based on the difference in gradient direction angles between pixels in the cluster and the number of pixels in the cluster.

[0044] Specifically, the gradient significance satisfies: ; Where, For the The gradient significance of the image region where the clusters are located, For the The first The gradient direction angle of each pixel, For the The first The gradient direction angle of each pixel, For the The number of pixels in a cluster, is the standard normalization function.

[0045] The number of candidate corner points in the image region where the cluster is located is determined according to the gradient significance, the number of all pixel points, and a preset global threshold.

[0046] Specifically, the number of candidate corner points satisfies: ; Where, For the The number of candidate corner points in the image region where the cluster is located, For the The gradient significance of the image region where the clusters are located, is the number of clusters, is the preset global threshold, is the number of pixels in the surface image, Is the rounding function.

[0047] The implementer can set the global threshold according to the specific implementation situation, for example, 1%. The traditional Harris corner detection algorithm uses the formula of the corner response function to obtain the response value of each pixel according to the eigenvalue of the second-order matrix. The global threshold is generally set to the first as candidate corner points.

[0048] Among them, in the gradient significance calculation formula Indicates the The mean difference in gradient direction angle between two pixels in the image area where the clusters are located (the pixels in the clusters are exactly the same as those in the image area where the clusters are located). The larger the value, the more obvious the gradient change in the current image area, that is, the more details and edge information the image area contains, which may mean that there are more potential corner points in the image area. In the formula for calculating the number of candidate corner points, Indicates the The significance weight of the image region where the cluster is located is used. If the gradient significance of the image region where the cluster is located is greater, the threshold needs to be reduced to identify more potential corner points. Therefore, the Get the number of candidate corner points that should be assigned to each image region, because Indicates the The saliency weights of the image area where the clusters are located are calculated, so the sum of the saliency weights of all clusters is 1. Therefore, the rounding function is used to ensure that the total number of candidate corner points remains unchanged.

[0049] S6: Based on the number of candidate corner points, the Harris corner point detection algorithm is used to obtain candidate corner points, and the euclidean distance between the candidate corner points is used to measure whether the forging of the shaft part is qualified.

[0050] It should be noted that for each cluster in the image area, the response value of each pixel is sorted from large to small, and the pixel with the largest response value after sorting is selected. pixels as candidate corner points, where It is the number of candidate corner points in the image area where the cluster is located.

[0051] Specifically, the method of measuring whether the forging of shaft parts is qualified based on the Euclidean distance between candidate corner points includes: In response to the fact that the difference between the maximum value of the Euclidean distance between all candidate corner points in the surface image of the formed shaft part and the maximum value of the Euclidean distance between all candidate corner points in the surface image of the standard shaft part is greater than a preset abnormality threshold, the forging of the current formed shaft part is determined to be unqualified, and an early warning prompt is issued to complete the forging monitoring of the shaft part.

[0052] Implementers can set the abnormal threshold according to specific implementation circumstances, for example, 0.1 cm.

[0053] An embodiment of the present invention further discloses a system for monitoring the forging of shaft parts, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, a method for monitoring the forging of shaft parts according to the present invention is implemented.

[0054] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0055] The above are all preferred embodiments of the present invention, and are not intended to limit the scope of protection of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for monitoring the forging of shaft parts, characterized in that: include: Obtain the characteristic values ​​of multiple channels of the pixel points in the surface image of the formed shaft part in the HSV color space, as well as the gradient direction angle of the pixel points; Any pixel is marked as the target pixel, and the local consistency of the target pixel is determined based on the characteristic values ​​of each channel of the target pixel and the pixels in the neighborhood in the HSV color space; In response to the cosine similarity between the feature vectors corresponding to all channels of the target pixel and any other pixel being greater than 0, weighting the Euclidean distance between the two pixels according to the local consistency of the two pixels and the cosine similarity to obtain a weighted Euclidean distance between the two pixels; Clustering all pixels according to the weighted Euclidean distance to obtain a number of clusters; According to the difference in gradient direction angles between pixels in the cluster and the number of pixels in the cluster, the gradient significance of the image region where the cluster is located is determined; Determining the number of candidate corner points in the image region where the cluster is located based on the gradient significance, the number of all pixels, and a preset global threshold; Based on the number of candidate corner points, the Harris corner point detection algorithm is used to obtain candidate corner points, and the euclidean distance between the candidate corner points is used to measure whether the forging of the shaft parts is qualified.

2. A method for monitoring the forging of shaft parts according to claim 1, characterized in that: The method for obtaining the characteristic value is: The RGB color space of the surface image is converted to the HSV color space, and the characteristic values ​​of multiple channels of the pixel points in the surface image in the HSV color space are obtained.

3. The method for monitoring the forging of shaft parts according to claim 1, characterized in that: The method for obtaining the gradient direction angle is: The surface image is gray-scaled, and the Sobel operator is used to obtain the gradient direction angle of the pixel point on the gray-scaled surface image.

4. A method for monitoring the forging of shaft parts according to claim 1, characterized in that: The local consistency satisfies: ； Where, For the The local consistency of pixels, For the The pixel at the The eigenvalues ​​of the channels, For the The pixel in the neighborhood The pixel at the The eigenvalues ​​of the channels, For the The number of pixels in the neighborhood of a pixel, is the number of channels, is the natural exponential function.

5. The method for monitoring the forging of shaft parts according to claim 1, characterized in that: The weighted Euclidean distance satisfies: ； Where, For the Pixels and The weighted Euclidean distance between pixels, For the Pixels and The Euclidean distance between pixels, For the The local consistency of pixels, No. The local consistency of pixels, For the The feature vector corresponding to each pixel in all channels is: For the The feature vector corresponding to each pixel in all channels is: For the Pixels and The cosine similarity between the feature vectors corresponding to all channels of the pixel points, is the absolute value symbol.

6. A method for monitoring the forging of shaft parts according to claim 1, characterized in that: The clustering adopts an iterative self-organizing clustering algorithm.

7. A method for monitoring the forging of shaft parts according to claim 1, characterized in that: The gradient significance satisfies: ； Where, For the The gradient significance of the image region where the clusters are located, For the The first The gradient direction angle of each pixel, For the The first The gradient direction angle of each pixel, For the The number of pixels in a cluster, is the standard normalization function.

8. A method for monitoring the forging of shaft parts according to claim 1, characterized in that: The number of candidate corner points satisfies: ； Where, For the The number of candidate corner points in the image region where the cluster is located, For the The gradient significance of the image region where the clusters are located, is the number of clusters, is the preset global threshold, is the number of pixels in the surface image, Is the rounding function.

9. The method for monitoring the forging of shaft parts according to claim 1, characterized in that: The method of measuring whether the forging of shaft parts is qualified based on the Euclidean distance between the candidate corner points includes: In response to the fact that the difference between the maximum value of the Euclidean distance between all candidate corner points in the surface image of the formed shaft part and the maximum value of the Euclidean distance between all candidate corner points in the surface image of the standard shaft part is greater than a preset abnormality threshold, the forging of the current formed shaft part is determined to be unqualified, and an early warning prompt is issued to complete the forging monitoring of the shaft part.

10. A monitoring system for forging shaft parts, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for monitoring the forging of shaft parts according to any one of claims 1 to 9 is implemented.

Images