Aluminum model deformation monitoring method, device, equipment and medium

Abstract

The invention relates to the technical field of data processing, in particular to an aluminum model deformation monitoring method and device, equipment and a medium. The method comprises the following steps: obtaining the model information, including internal and external patterns, of the to-be-detected model, so that the complex structure and design details of the model can be more accurately identified, a basis is provided for subsequently dividing the surface of the model into a plurality of non-overlapped sub-regions, fine division of each part of the model is realized, and the accuracy of the model is improved. At least one of image data, reflection data and ultrasonic data is collected in each sub-area, physical characteristics and structural states of the model are comprehensively covered, the surface condition can be visually displayed, the reflection data may reveal tiny changes of the surface or the interior, and the ultrasonic data can deeply detect defects or deformation in the material, so that the detection accuracy is improved. And the detection accuracy is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, equipment and medium for monitoring deformation of an aluminum model. Background Art

[0002] Architectural cement models, core tools in the production of cement and concrete products, are meticulously designed and meticulously manufactured to ensure that, after pouring, concrete (a composite material composed of cement, water, aggregate, and carefully selected additives) accurately replicates the model's form, solidifying into a diverse array of architectural components and products. These components are widely used in a variety of fields, including construction, transportation infrastructure, and water conservancy projects. From delicate water channels to sturdy railway covers, from highway molds to manhole covers and drainage systems, their importance is evident in every aspect.

[0003] Aluminum alloy stands out for its exceptional lightweight and excellent processing properties, and is a popular choice for modern architectural cement model production. This choice not only significantly reduces the model's weight, facilitating flexible transport, installation, and disassembly, but also facilitates the realization of complex structures and sophisticated designs, meeting the growing demand for personalization and customization.

[0004] However, due to the test of multiple concrete pours or improper operation, architectural cement models may occasionally deform. Once deformed, the quality of the resulting components cannot be guaranteed, resulting in defective products. Currently, the industry relies heavily on manual visual inspection to determine whether the model is deformed before pouring. However, this method is limited by human factors, making accuracy difficult to guarantee and still carries a certain risk of defective products. Therefore, improving the accuracy of architectural cement model deformation monitoring has become an urgent issue. Summary of the Invention

[0005] In order to improve the accuracy of deformation monitoring of building cement models, the present application provides an aluminum model deformation monitoring method, device, equipment and medium.

[0006] In a first aspect, the present application provides a method for monitoring deformation of an aluminum model, which adopts the following technical solution: A method for monitoring deformation of an aluminum model, comprising: Obtaining pattern information of the model to be tested, wherein the pattern information includes an internal pattern of the model and an external pattern of the model; Based on the pattern information, each surface of the model to be inspected is divided into a plurality of non-overlapping sub-areas; Determining detection information corresponding to each sub-region, where the detection information includes at least one of image data, reflection data, and ultrasonic data; Determine, based on the detection information corresponding to each sub-area, a monitoring result corresponding to each sub-area, wherein the monitoring result is normal or abnormal; If there is a sub-area with abnormal monitoring results, monitoring abnormality information is generated.

[0007] By adopting the above technical solution, by obtaining the pattern information of the model to be inspected, including internal and external patterns, the complex structure and design details of the model can be identified more accurately, providing a basis for subsequently dividing the model surface into multiple non-overlapping sub-areas, realizing a refined division of each part of the model, and collecting at least one of image data, reflection data and ultrasonic data in each sub-area, to achieve comprehensive coverage of the physical properties and structural state of the model, and intuitively display the surface condition. Reflection data may reveal subtle changes on the surface or inside, while ultrasonic data can deeply detect defects or deformations inside the material, thereby improving the accuracy of detection.

[0008] In a possible implementation, each surface of the model to be inspected is divided into a plurality of non-overlapping sub-areas based on the pattern information, including: Determining, based on the pattern information, a smooth area and a concave-convex area on each surface of the model to be inspected; The smooth area on each surface is divided into a plurality of non-overlapping first sub-areas, and the concave-convex area on each surface is divided into a plurality of non-overlapping second sub-areas, so as to obtain a plurality of non-overlapping sub-areas on each surface.

[0009] By employing this technical solution, by distinguishing between smooth and concave / convex areas, different detection strategies or parameter settings can be adopted based on the characteristics of different areas. Each surface can be subdivided into multiple sub-areas, and independent testing of each sub-area can more accurately capture the deformation of that area. Traditional overall testing methods may have difficulty accurately determining the deformation of concave / convex areas due to their complex shapes and uneven surfaces. However, by dividing the area into multiple small areas for testing, the deformation characteristics of each area can be more carefully observed and analyzed.

[0010] In one possible implementation, determining the detection information corresponding to each sub-region includes: Obtain image data corresponding to each sub-region; Based on the image data, determining whether there is an image abnormality in the sub-region; If there is an image abnormality in a sub-region, the sub-region corresponding to the image abnormality is determined as the target sub-region; If the target sub-region belongs to a smooth area, obtaining reflection data of the target sub-region to obtain detection information of each sub-region; If the target sub-region belongs to a concave-convex region, ultrasonic data of the target sub-region is acquired to obtain detection information of each sub-region.

[0011] By employing this technical solution, image data from each sub-region is acquired and, based on image analysis, a preliminary determination of image anomalies is made. This allows for the rapid elimination of most areas without obvious problems, allowing subsequent inspection resources to be more focused on areas with potential issues. Upon detecting an image anomaly, the sub-region corresponding to the anomaly is identified as the target sub-region, enabling precise location of potential problem areas. Based on the properties of the target sub-region (smooth or uneven), reflection data or ultrasonic data is captured in a targeted manner, making the inspection data more tailored to actual needs and improving both accuracy and effectiveness.

[0012] In one possible implementation, determining whether there is an image abnormality in a sub-region based on the image data includes: Extracting the current contour of the model to be detected and the current texture features and current shape features corresponding to each sub-region in the image data; Obtaining a standard contour corresponding to the model to be detected and standard texture features and standard shape features corresponding to each surface of the model to be detected; Comparing the current profile with the standard profile to determine whether the current profile is consistent with the standard profile; If the current contour is consistent with the standard contour, determining the standard texture features and standard shape features corresponding to each sub-region; The current texture features and current shape features corresponding to each sub-region are compared with the corresponding standard texture features and standard shape features to determine whether there is a sub-region where the current texture features are inconsistent with the standard texture features or the current shape features are inconsistent with the standard shape features, so as to determine whether there is an image abnormality in the sub-region.

[0013] By adopting the above technical solution, by extracting the current contour, texture features and shape features and comparing them with the standard values ​​item by item, it is possible to more accurately identify slight changes in the shape, texture, etc. of the sub-area, thereby improving the accuracy of detection and helping to discover potential deformation or damage problems. At the same time, it realizes a comprehensive assessment of the sub-area from multiple dimensions, thereby reducing the risk of missed detection due to single-dimensional detection and ensuring the reliability of the detection results.

[0014] In a possible implementation, if the target sub-region is a smooth region, determining the monitoring result corresponding to each sub-region based on the detection information corresponding to each sub-region includes: Based on the image data of each sub-region, determining that the monitoring results of the sub-regions other than the target sub-region are normal; determining whether the target sub-region is flat and smooth based on the reflection data corresponding to the target sub-region; If the target sub-region is flat and smooth, determining that the monitoring result corresponding to the target sub-region is normal; If the target sub-region is not flat or smooth, it is determined that the monitoring result corresponding to the target sub-region is abnormal.

[0015] By employing this technical solution, image data is used to initially determine that the monitoring results of non-target sub-areas are normal, allowing the majority of normal areas to be quickly eliminated, allowing inspection resources to be more concentrated on target sub-areas that may have problems. Furthermore, reflection data is used to further verify the flatness and smoothness of target sub-areas, making the inspection process more organized and efficient. This process design optimizes resource allocation and improves inspection efficiency by quickly identifying and eliminating normal areas in the initial screening phase and focusing on target sub-areas that may have problems during the in-depth inspection phase.

[0016] In a possible implementation, if the target sub-region is a concave-convex region, determining the monitoring result corresponding to each sub-region based on the detection information corresponding to each sub-region includes: Determining key points corresponding to the target sub-region; Calculating the horizontal value and the vertical value corresponding to each key point based on the ultrasonic data corresponding to the target sub-area; Based on the horizontal and vertical values ​​corresponding to each key point, the monitoring results corresponding to each sub-area are determined.

[0017] By adopting the above technical solution, due to the uneven surface and complex shape of the concave-convex area, traditional detection methods may find it difficult to accurately capture its deformation. By using ultrasonic data to calculate key points and calculate their horizontal and vertical values, the shape characteristics and deformation of the concave-convex area can be more accurately reflected, achieving precise detection of the concave-convex area, and can more objectively reflect the deformation of the concave-convex area, avoiding errors caused by subjective judgment.

[0018] In one possible implementation, determining the key point corresponding to the target sub-region includes: identifying a target pattern corresponding to the target sub-region; determining whether the target pattern is a regular pattern; If the target pattern is a regular pattern, determining the key point corresponding to the target pattern as the key point corresponding to the target sub-region; If the target pattern is an irregular image, a preset position point on the target sub-region is determined as a key point.

[0019] By adopting the above technical solution, by identifying the target pattern and taking into account both the regularity and irregularity of the target pattern, for regular patterns, it can be ensured that the selected key points are representative and can accurately reflect the shape characteristics and deformation of the target sub-area. For irregular images, position points can be preset on the target sub-area as key points, further enabling the solution to adapt to target sub-areas of different shapes and characteristics.

[0020] In a second aspect, the present application provides an aluminum model deformation monitoring device, which adopts the following technical solution: An aluminum model deformation monitoring device, comprising: An acquisition module is used to acquire the pattern information of the model to be detected, wherein the pattern information includes the internal pattern of the model and the external pattern of the model; A division module, configured to divide each surface of the model to be inspected into a plurality of non-overlapping sub-areas based on the pattern information; a first determining module, configured to determine detection information corresponding to each sub-region, wherein the detection information includes at least one of image data, reflection data, and ultrasonic data; A second determining module is configured to determine a monitoring result corresponding to each sub-area based on the detection information corresponding to each sub-area, wherein the monitoring result is normal or abnormal; The generation module is used to generate monitoring abnormality information if there is a sub-area with an abnormal monitoring result.

[0021] In a third aspect, the present application provides an electronic device, which adopts the following technical solution: An electronic device, comprising: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the aluminum model deformation monitoring method described in the first aspect above.

[0022] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium includes: a computer program stored therein that can be loaded by a processor and execute the aluminum model deformation monitoring method described in the first aspect.

[0023] In summary, the present application includes the following beneficial technical effects: by obtaining the pattern information of the model to be inspected, including internal and external patterns, the complex structure and design details of the model can be identified more accurately, which provides a basis for subsequently dividing the model surface into multiple non-overlapping sub-areas, realizing a refined division of each part of the model, and collecting at least one of image data, reflection data and ultrasonic data in each sub-area, so as to achieve comprehensive coverage of the physical properties and structural state of the model, and can intuitively display the surface condition. The reflection data may reveal subtle changes on the surface or inside, while the ultrasonic data can deeply detect defects or deformations inside the material, thereby improving the accuracy of detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a flow chart of a method for monitoring deformation of an aluminum model provided in an embodiment of the present application; Figure 2 Schematic diagram of a block diagram of an aluminum model deformation monitoring method provided in an embodiment of the present application; Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The following is combined with Figure 1 -Attached Figure 3 This application is described in further detail.

[0026] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0027] In order to facilitate understanding of the technical solutions proposed in this application, several elements that will be introduced in the description of this application are first introduced here. It should be understood that the following introduction is only for the convenience of understanding these elements, so as to understand the content of the embodiments of this application, and does not necessarily cover all possible situations.

[0028] Architectural cement models are molds specifically used for producing cement products (or concrete products). These models are precisely designed and manufactured. Concrete (primarily composed of cement, water, aggregate, and possibly other additives) is poured into the mold. Once the concrete solidifies, it forms a building component or product that exactly matches the mold's shape. Architectural cement models are widely used in construction, transportation, water conservancy, and other fields, such as making water chutes, railway covers, highway molds, manhole covers, and drainage ditches. Due to the lower density and excellent workability of aluminum alloys, aluminum models are lighter than traditional steel models and easier to process into various complex shapes and structures. This facilitates transport, installation, and disassembly, improving construction efficiency and allowing for the production of more complex and precise architectural cement models. This helps meet various special needs and customization requirements. Therefore, aluminum alloy is now commonly used in the production of architectural cement models. However, due to the stress of multiple concrete pours or improper handling, architectural cement models can sometimes deform. Once deformed, the quality of the resulting components cannot be guaranteed, resulting in defective products. Currently, the industry relies heavily on manual visual inspection to determine whether a model has deformed before pouring. However, this method is limited by human factors, making accuracy difficult to guarantee and still carries a certain risk of defective products. Therefore, improving the accuracy of deformation monitoring for architectural cement models has become a pressing issue.

[0029] In view of this, the first embodiment of the present application provides a method for monitoring the deformation of an aluminum model. By obtaining the pattern information of the model to be detected, including internal and external patterns, the complex structure and design details of the model can be identified more accurately, providing a basis for subsequently dividing the model surface into multiple non-overlapping sub-areas, realizing a refined division of each part of the model, and collecting at least one of image data, reflection data, and ultrasonic data in each sub-area, thereby achieving comprehensive coverage of the physical properties and structural state of the model, and intuitively displaying the surface condition. The reflection data may reveal subtle changes on the surface or inside, while the ultrasonic data can deeply detect defects or deformations inside the material, thereby improving the accuracy of detection.

[0030] join Figure 1 The first embodiment of the present application provides a method for monitoring deformation of an aluminum model, which is performed by an electronic device. The method includes: Step S101: Obtain the pattern information of the model to be detected.

[0031] The pattern information includes the model's internal pattern and external pattern. Architectural cement models are generally hollow, three-dimensional models. These models may differ from one another and have a certain thickness. Therefore, the dimensions of the inner and outer surfaces of these models may differ. Furthermore, concrete is poured into the interior of the cement model to create building components. Therefore, most cement models have uneven inner surfaces, while their outer surfaces are generally smooth. Specifically, the pattern information of the model to be tested may include the model's internal dimensions, its internal pattern, its external dimensions, and its external pattern.

[0032] Specifically, before each concrete pouring and after the building model pouring is completed, the number of the model to be inspected and the template information corresponding to the number can be obtained.

[0033] Step S102: Based on the pattern information, each surface of the model to be inspected is divided into a plurality of non-overlapping sub-areas.

[0034] To facilitate monitoring of every surface on the model to be inspected, the model to be inspected can be inspected in separate regions before each concrete pour and after the building model pouring is completed. Specifically, after obtaining the model's layout information, a determination is made as to whether the internal and external surfaces of the model to be inspected have uneven patterns or styles. If uneven patterns or styles are present, the internal and external surfaces of the model to be inspected are divided into non-overlapping uneven sub-regions and smooth sub-regions according to the uneven patterns.

[0035] When both the internal and external surfaces of the model to be inspected are smooth surfaces, the internal surface is divided into multiple sub-areas of uniform size and non-overlapping based on the size of the internal surface. Similarly, the external surface is divided into multiple sub-areas of uniform size and non-overlapping based on the size of the external surface.

[0036] When the internal surface of the model to be detected has an uneven pattern or style, and the external surface is a smooth surface, the internal surface of the model to be detected is divided into non-overlapping uneven sub-regions and smooth sub-regions according to the uneven pattern, and based on the size of the external surface, the external surface is divided into multiple sub-regions of uniform size and non-overlapping. Similarly, when the external surface of the model to be detected has an uneven pattern or style, and the internal surface is a smooth surface, the external surface of the model to be detected is divided into non-overlapping uneven sub-regions and smooth sub-regions according to the uneven pattern, and based on the size of the internal surface, the internal surface is divided into multiple sub-regions of uniform size and non-overlapping.

[0037] Step S103: Determine the detection information corresponding to each sub-region.

[0038] The detection information includes at least one of image data, reflection data, and ultrasonic data. Specifically, each subregion corresponds to at least one image data item, one ultrasonic data item, or one reflection data item. Specifically, image data refers to data acquired by an image acquisition device. Ultrasonic data refers to raw data acquired by ultrasonic detection equipment, including waveform, amplitude, frequency, and other data. Reflection data refers to reflection data generated by a light-emitting detection device emitting light onto a plane and receiving the reflected light.

[0039] Aluminum, as a metallic material, has excellent reflective properties, a property derived from its smooth and clean surface, which efficiently reflects light. When light strikes the surface of an aluminum plate, photons interact with the aluminum atoms on the surface, with some photons bouncing back into the air as reflected light. This allows for the acquisition of reflection data corresponding to smooth surfaces and ultrasonic data corresponding to rough surfaces. Specifically, the system receives image data corresponding to each sub-region captured by an imaging device, ultrasonic data for each uneven sub-region captured by an ultrasonic detection device, and reflection data for each smooth sub-region captured by an optical detection device, to obtain detection information corresponding to each sub-region.

[0040] Step S104: Determine the monitoring result corresponding to each sub-area based on the detection information corresponding to each sub-area.

[0041] Among them, the monitoring results are normal or abnormal.

[0042] Specifically, for the detection results corresponding to each sub-region: when the detection information corresponding to the sub-region is image data, the contour detection algorithm is used to extract the current contour of the sub-region, and the standard image corresponding to the model to be detected is obtained, and the position corresponding to the sub-region in the standard image is used as the standard contour to compare the standard contour corresponding to the sub-region with the current contour corresponding to the sub-region to analyze whether there is a difference. If there is a difference, it indicates that there may be deformation, that is, the monitoring result is abnormal.

[0043] When the detection information of the uneven sub-area is image data and ultrasonic data, refer to the above embodiment to determine whether the image data corresponding to the sub-area is abnormal. If the image data corresponding to the sub-area is abnormal, the ultrasonic data corresponding to the sub-area is obtained. Since the propagation speed of ultrasonic waves in aluminum materials is different from that of other media such as space, when a cavity or depression appears, the duration, phase and amplitude in the ultrasonic data may all change. Therefore, the collected ultrasonic data is pre-processed by filtering, amplification, etc. to improve the quality of the ultrasonic data, and the waveform, frequency and sound speed corresponding to the ultrasonic data are analyzed to judge the internal structure of the medium, so as to determine whether the sub-area is deformed and whether the monitoring result of the sub-area is abnormal; if the image data corresponding to the sub-area is normal, the monitoring result corresponding to the sub-area is determined to be normal.

[0044] When the detection information corresponding to the smooth sub-area is image data and reflection data, referring to the above embodiment, determine whether the image data corresponding to the sub-area is abnormal. If the image data corresponding to the sub-area is abnormal, obtain the reflection data corresponding to the sub-area, and determine whether the sub-area is deformed based on whether the reflected light in the reflection data is parallel, so as to determine whether the monitoring result of the sub-area is abnormal; if the image data corresponding to the sub-area is normal, determine that the monitoring result corresponding to the sub-area is normal.

[0045] Step S105: If there is a sub-region with an abnormal monitoring result, monitoring abnormality information is generated.

[0046] When there is a sub-region with an abnormal detection result, monitoring abnormality information including the location of the sub-region is generated, and an alarm message is generated to prompt the monitoring personnel to repair or discard the model to be detected.

[0047] In a possible implementation of the embodiment of the present application, in the above step S102, each surface of the model to be inspected is divided into multiple non-overlapping sub-areas based on the pattern information, which may specifically include: Based on the pattern information, determine the smooth area and the concave-convex area on each surface of the model to be inspected; The smooth area on each surface is divided into a plurality of non-overlapping first sub-areas, and the concave-convex area on each surface is divided into a plurality of non-overlapping second sub-areas, so as to obtain a plurality of non-overlapping sub-areas on each surface.

[0048] To facilitate monitoring of every surface on the model under inspection, the model can be inspected on a regional basis before each concrete pour and after the building model is completed. Specifically, the smoothness of the model surface can be tested by calculating the normal change, Gaussian curvature, or mean curvature of each vertex. Based on a preset smoothness threshold (such as the curvature change), areas above the threshold are considered concave and convex, while areas below the threshold are considered smooth.

[0049] Furthermore, these regions can be further subdivided using a region growing algorithm or a boundary-based method to ensure that they do not overlap and cover the entire surface as evenly as possible. Specifically, within each smooth region, the smooth region is further divided into multiple non-overlapping first sub-regions using a mesh simplification algorithm, and edge points and corner points in the concave-convex region are identified to obtain segmentation features in the concave-convex region. These features are used as segmentation boundaries, thereby achieving the division of the concave-convex region to obtain multiple non-overlapping sub-regions.

[0050] Furthermore, when both the internal surface and the external surface of the model to be inspected are smooth surfaces, that is, when there are no concave and convex areas, the internal surface is divided into multiple sub-areas of uniform size and non-overlapping based on the size of the internal surface, and the external surface is divided into multiple sub-areas of uniform size and non-overlapping based on the size of the external surface.

[0051] In a possible implementation of the embodiment of the present application, in the above embodiment, determining the detection information corresponding to each sub-region may specifically include: Obtain image data corresponding to each sub-region; Determining whether there is an image abnormality in the sub-region based on the image data; If there is an image abnormality in a sub-region, the sub-region corresponding to the image abnormality is determined as the target sub-region; If the target sub-region belongs to a smooth area, the reflection data of the target sub-region is obtained to obtain the detection information of each sub-region; If the target sub-region is a concave-convex region, ultrasonic data of the target sub-region is acquired to obtain detection information of each sub-region.

[0052] Obtain the image data corresponding to each sub-region, and use the contour detection algorithm to extract the current contour of the sub-region, and obtain the standard image corresponding to the model to be detected, and use the position corresponding to the sub-region in the standard image as the standard contour of the sub-region to compare the standard contour corresponding to the sub-region with the current contour corresponding to the sub-region to analyze whether there is a difference. If there is a difference, it indicates that there may be deformation, that is, the monitoring result is abnormal.

[0053] Furthermore, when a subregion corresponding to an abnormal monitoring result exists, the subregion corresponding to the abnormal monitoring result is determined as a target subregion. Furthermore, when the target subregion is a concave-convex area, ultrasonic data corresponding to the target subregion is acquired, and the ultrasonic data and image data are used as detection information corresponding to the target subregion. Image data corresponding to subregions outside the target subregion is used as detection information for the corresponding subregion.

[0054] When the target sub-region belongs to a smooth area, the reflection data corresponding to the target sub-region is obtained, and the reflection data and image data are used as the detection information corresponding to the target sub-region. At the same time, the image data corresponding to the sub-region outside the target sub-region is used as the detection information of the corresponding sub-region.

[0055] Furthermore, when the target sub-region belongs to both the concave-convex region and the smooth region, ultrasonic data corresponding to the target sub-region belonging to the concave-convex region is obtained, and reflection data corresponding to the target sub-region belonging to the smooth region is obtained to obtain detection information of each sub-region.

[0056] In one possible implementation of the embodiment of the present application, in the above embodiment, determining whether there is an image abnormality in a sub-region based on the image data may specifically include: Extracting the current contour of the model to be detected in the image data and the current texture features and current shape features corresponding to each sub-region; Obtaining the standard contour corresponding to the model to be detected and the standard texture features and standard shape features corresponding to each surface on the model to be detected; Compare the current profile with the standard profile to determine whether the current profile is consistent with the standard profile; If the current contour is consistent with the standard contour, the standard texture features and standard shape features corresponding to each sub-region are determined; The current texture features and current shape features corresponding to each sub-region are compared with the corresponding standard texture features and standard shape features to determine whether there is a sub-region where the current texture features are inconsistent with the standard texture features or the current shape features are inconsistent with the standard shape features, so as to determine whether there is an image abnormality in the sub-region.

[0057] When the model to be detected is deformed, there is a certain difference between the image of the deformed model to be detected and the image of the standard model to be detected. Therefore, the image of the deformed model to be detected can be compared with the image of the standard model to be detected to determine whether the model to be detected is deformed. Specifically, the current contour of the model to be detected can be extracted using a contour detection algorithm. For each sub-region, the current texture features can be extracted using a gray-level co-occurrence matrix, and the current shape features can be extracted using shape analysis technology to obtain the standard contour corresponding to the model to be detected and the standard texture features and standard shape features corresponding to each surface of the model to be detected. Then, the standard contour corresponding to the model to be detected and the standard texture features and standard shape features corresponding to each surface are obtained for subsequent comparison.

[0058] Furthermore, shape context matching can be used to compare the current contour of the model to be detected with the standard contour of the model to be detected to determine whether the current contour of the model to be detected is consistent with the standard contour of the model to be detected. If the current contour of the model to be detected is consistent with the standard contour of the model to be detected, the current texture features and current shape features of each sub-region are further compared with the corresponding standard features. Specifically, for texture features, a similarity metric can be used to compare the current texture with the standard texture; for shape features, the values ​​of the descriptors corresponding to each shape can be compared item by item to determine whether they are consistent. If the current contour of the model to be detected is inconsistent with the standard contour of the model to be detected, it is determined that the images corresponding to each sub-region are abnormal.

[0059] Furthermore, if there are any sub-regions where the current texture features are inconsistent with the standard texture features or the current shape features are inconsistent with the standard shape features, these sub-regions are marked as having image anomalies.

[0060] In one possible implementation of the embodiment of the present application, in the above embodiment, if the target sub-region is a smooth area, determining the monitoring result corresponding to each sub-region based on the detection information corresponding to each sub-region may specifically include: Based on the image data of each sub-region, determining that the monitoring results of the sub-regions other than the target sub-region are normal; Determining whether the target sub-region is flat and smooth based on the reflection data corresponding to the target sub-region; If the target sub-region is flat and smooth, the monitoring result corresponding to the target sub-region is determined to be normal; If the target sub-region is not flat or smooth, the monitoring result corresponding to the target sub-region is determined to be abnormal.

[0061] When all target sub-areas belong to smooth areas, the reflection data corresponding to the target sub-areas can be used to determine the monitoring results corresponding to the target sub-areas. Specifically, when the target sub-areas belong to smooth areas, the monitoring results corresponding to the target sub-areas are determined by obtaining the reflection data of the target sub-areas. The reflection data includes the reflection intensity and angular distribution of the light. Further, the reflection data is processed to evaluate whether the target sub-areas are flat and smooth based on the analysis results of the reflection data. Specifically, a preset intensity threshold range and a preset angle threshold range are obtained, and it is determined whether the reflection intensity and angular distribution in the reflection data meet the preset intensity threshold range and the preset angle threshold range, so as to determine whether the surface roughness and the reflected light uniformity index meet the requirements of flatness and smoothness.

[0062] Furthermore, if the target sub-region is determined to be flat and smooth after evaluation, the monitoring result corresponding to the target sub-region is determined to be normal; if the target sub-region is not flat or smooth (that is, it does not meet the set standard or threshold), the monitoring result corresponding to the target sub-region is determined to be abnormal.

[0063] In one possible implementation of the embodiment of the present application, in the above embodiment, if the target sub-region is a concave-convex region, determining the monitoring result corresponding to each sub-region based on the detection information corresponding to each sub-region may specifically include: Determine the key points corresponding to the target sub-region; Based on the ultrasonic data corresponding to the target sub-area, the horizontal and vertical values ​​corresponding to each key point are calculated; Based on the horizontal and vertical values ​​corresponding to each key point, the monitoring results corresponding to each sub-area are determined.

[0064] The horizontal value represents the uniformity or integrity of the material at that point along the direction of ultrasonic propagation (usually the depth direction), while the vertical value represents the structural characteristics or defect size perpendicular to the direction of ultrasonic propagation (such as transverse or radial direction).

[0065] When the target sub-region belongs to a concave-convex area, since the concave-convex area is difficult to detect, some key points in the target sub-region can be detected to improve the detection efficiency. Specifically, when the target sub-region belongs to a concave-convex area, the method for determining the monitoring result corresponding to the target sub-region can be: according to the geometric shape of the target sub-region, the key points corresponding to the geometric shape are selected as the key points corresponding to the target sub-region. For example, the geometric shape corresponding to the target sub-region is a square, and the key points of the square are the center point and four vertices. Therefore, the key points corresponding to the target sub-region are the center point and four vertices. Among them, when the target sub-region is an irregular shape, the shape corresponding to the target sub-region is compared with the preset regular shape, and the preset regular shape with the highest similarity is used as the shape corresponding to the target sub-region.

[0066] Furthermore, ultrasonic data corresponding to the target sub-area is obtained. The ultrasonic data includes the reflection intensity, propagation time, and path of the ultrasonic wave. Furthermore, the ultrasonic data is processed, and for each key point, the corresponding ultrasonic features, such as the intensity, waveform, and phase of the reflected wave, are extracted from the processed ultrasonic data. Based on the ultrasonic features at the key points and the feature extraction of the waveform, the corresponding horizontal and vertical values ​​are calculated. The preset horizontal value threshold and the preset vertical value threshold are obtained, and the horizontal and vertical values ​​of each key point are compared with the corresponding thresholds. If the horizontal and vertical values ​​of all key points are within the set threshold range, the monitoring result of the target sub-area is determined to be normal; if there is at least one key point whose horizontal value or vertical value exceeds the threshold range, the monitoring result of the target sub-area is determined to be abnormal.

[0067] More specifically, the peaks in the waveform are identified and their corresponding time or depth positions are recorded to obtain the horizontal value of the key point, the average depth corresponding to all sampling points in the waveform is calculated, the maximum amplitude value in the waveform is recorded, and the energy of the waveform in the entire time or depth range is calculated by integrating the square of the amplitude, and the average amplitude of all sampling points in the waveform is calculated to obtain the vertical value of the key point.

[0068] Furthermore, when there are multiple target sub-areas and some target sub-areas belong to the concave-convex area and some target sub-areas belong to the smooth area, for the target sub-area belonging to the concave-convex area, the above-mentioned method of determining the monitoring result corresponding to the target sub-area when the target sub-area belongs to the concave-convex area is adopted; for the target sub-area belonging to the smooth area, the above-mentioned method of determining the monitoring result corresponding to the target sub-area when the target sub-area belongs to the smooth area is adopted.

[0069] In a possible implementation of the embodiment of the present application, in the above embodiment, determining the key points corresponding to the target sub-region may specifically include: identifying a target pattern corresponding to the target sub-region; determining whether the target pattern is a regular pattern; If the target pattern is a regular pattern, determining the key points corresponding to the target pattern as the key points corresponding to the target sub-region; If the target pattern is an irregular image, a preset position point on the target sub-region is determined as a key point.

[0070] The regular pattern is a pattern in a preset pattern library.

[0071] Specifically, the target pattern in the target sub-region can be identified by comparing it with a preset pattern library and using an image recognition algorithm. The identified target pattern is then analyzed to check whether it meets the predefined regular pattern standards. More specifically, the shape corresponding to the target sub-region is compared with the preset regular shape to determine whether there is a preset regular pattern in the preset pattern library with a similarity greater than a preset similarity threshold. If there is a preset regular pattern in the preset pattern library with a similarity greater than the preset similarity threshold, the target pattern is determined to be a regular pattern; if there is no preset regular pattern in the preset pattern library with a similarity greater than the preset similarity threshold, the target pattern is determined to be an irregular pattern.

[0072] Furthermore, if the target pattern is determined to be regular, key points are determined based on the pattern's characteristics. For example, in a circular pattern, key points might be the center and specific edge points (such as quartering or eighth dividing points); in a rectangular pattern, key points might be the four corners and the center. Key points in a regular pattern should represent the pattern's primary features and structure.

[0073] If the target pattern is determined to be irregular, key points are selected according to a preset rule. For example, several points near the geometric center of the pattern and significant change points on the edge of the pattern can be selected as key points.

[0074] The above embodiment introduces a method for monitoring the deformation of an aluminum model from the perspective of a method flow, and the following embodiment introduces a device for monitoring the deformation of an aluminum model from the perspective of a virtual module or a virtual unit. Please refer to the following embodiment for details.

[0075] See also Figure 2 The aluminum model deformation monitoring device 200 may specifically include: an acquisition module 201, a division module 202, a first determination module 203, a second determination module 204, and a generation module 205, wherein: An aluminum model deformation monitoring device 200 includes: An acquisition module 201 is used to acquire pattern information of a model to be detected, where the pattern information includes an internal pattern of the model and an external pattern of the model; A division module 202 is configured to divide each surface of the model to be inspected into a plurality of non-overlapping sub-areas based on the pattern information; A first determining module 203 is configured to determine detection information corresponding to each sub-region, where the detection information includes at least one of image data, reflection data, and ultrasonic data; A second determination module 204 is configured to determine a monitoring result corresponding to each sub-region based on the detection information corresponding to each sub-region, and whether the monitoring result is normal or abnormal; The generating module 205 is configured to generate monitoring abnormality information if there is a sub-region with an abnormal monitoring result.

[0076] In one possible implementation of the embodiment of the present application, when the division module 202 divides each surface of the to-be-detected model into a plurality of non-overlapping sub-regions based on the pattern information, it can be specifically used to: Based on the pattern information, determine the smooth area and the concave-convex area on each surface of the model to be inspected; The smooth area on each surface is divided into a plurality of non-overlapping first sub-areas, and the concave-convex area on each surface is divided into a plurality of non-overlapping second sub-areas, so as to obtain a plurality of non-overlapping sub-areas on each surface.

[0077] In one possible implementation of the embodiment of the present application, when determining the detection information corresponding to each sub-region, the first determining module 203 is specifically configured to: Obtain image data corresponding to each sub-region; Determining whether there is an image abnormality in the sub-region based on the image data; If there is an image abnormality in a sub-region, the sub-region corresponding to the image abnormality is determined as the target sub-region; If the target sub-region belongs to a smooth area, the reflection data of the target sub-region is obtained to obtain the detection information of each sub-region; If the target sub-region is a concave-convex region, ultrasonic data of the target sub-region is acquired to obtain detection information of each sub-region.

[0078] In one possible implementation of the embodiment of the present application, when the first determination module 203 determines whether there is an image abnormality in a sub-region based on the image data, it is specifically configured to: Extracting the current contour of the model to be detected in the image data and the current texture features and current shape features corresponding to each sub-region; Obtaining the standard contour corresponding to the model to be detected and the standard texture features and standard shape features corresponding to each surface on the model to be detected; Compare the current profile with the standard profile to determine whether the current profile is consistent with the standard profile; If the current contour is consistent with the standard contour, the standard texture features and standard shape features corresponding to each sub-region are determined; The current texture features and current shape features corresponding to each sub-region are compared with the corresponding standard texture features and standard shape features to determine whether there is a sub-region where the current texture features are inconsistent with the standard texture features or the current shape features are inconsistent with the standard shape features, so as to determine whether there is an image abnormality in the sub-region.

[0079] In one possible implementation of the embodiment of the present application, if the target sub-region is a smooth region, the first determination module 203 is specifically configured to: Based on the image data of each sub-region, determining that the monitoring results of the sub-regions other than the target sub-region are normal; Determining whether the target sub-region is flat and smooth based on the reflection data corresponding to the target sub-region; If the target sub-region is flat and smooth, the monitoring result corresponding to the target sub-region is determined to be normal; If the target sub-region is not flat or smooth, the monitoring result corresponding to the target sub-region is determined to be abnormal.

[0080] In one possible implementation of the embodiment of the present application, if the target sub-region is a concave-convex region, the first determination module 203 is specifically configured to: Determine the key points corresponding to the target sub-region; Based on the ultrasonic data corresponding to the target sub-area, the horizontal and vertical values ​​corresponding to each key point are calculated; Based on the horizontal and vertical values ​​corresponding to each key point, the monitoring results corresponding to each sub-area are determined.

[0081] In a possible implementation of the embodiment of the present application, the first determining module 203 is specifically configured to: identifying a target pattern corresponding to the target sub-region; determining whether the target pattern is a regular pattern; If the target pattern is a regular pattern, determining the key points corresponding to the target pattern as the key points corresponding to the target sub-region; If the target pattern is an irregular image, a preset position point on the target sub-region is determined as a key point.

[0082] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0083] See also Figure 3 , the embodiment of the present application also introduces an electronic device from the perspective of a physical device, such as Figure 3 As shown, Figure 3 The electronic device 300 shown includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 300 may further include a transceiver 304. It should be noted that in actual applications, the number of transceivers 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0084] Processor 301 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0085] Bus 302 may include a path for transmitting information between the above components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. Bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0086] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0087] The memory 303 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the above method embodiment.

[0088] Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc., and can also be servers, etc. Figure 3 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0089] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding contents of the aforementioned method embodiment.

[0090] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0091] The above are only some of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for monitoring deformation of an aluminum model, characterized in that: include: Obtaining the pattern information of the model to be detected, wherein the pattern information includes the internal pattern of the model and the external pattern of the model; Based on the template information, each surface of the model to be detected is divided into a plurality of non-overlapping sub-areas; Determine detection information corresponding to each sub-region, where the detection information includes at least one of image data, reflection data, and ultrasonic data; Based on the detection information corresponding to each of the sub-areas, determining a monitoring result corresponding to each of the sub-areas, wherein the monitoring result is normal or abnormal; If there is a sub-area with abnormal monitoring results, monitoring abnormality information is generated.

2. The aluminum model deformation monitoring method according to claim 1, characterized in that: The method of dividing each surface of the model to be detected into a plurality of non-overlapping sub-areas based on the template information includes: Based on the pattern information, determining a smooth area and a concave-convex area on each surface of the model to be detected; The smooth area on each surface is divided into a plurality of non-overlapping first sub-areas, and the concave-convex area on each surface is divided into a plurality of non-overlapping second sub-areas, so as to obtain a plurality of non-overlapping sub-areas on each surface.

3. The aluminum model deformation monitoring method according to claim 2, characterized in that: The determining the detection information corresponding to each sub-region includes: Obtain image data corresponding to each sub-region; Based on the image data, determining whether there is an image abnormality in the sub-region; If there is an image abnormality in the sub-region, determining the sub-region corresponding to the image abnormality as the target sub-region; If the target sub-region belongs to a smooth region, obtaining reflection data of the target sub-region to obtain detection information of each sub-region; If the target sub-region belongs to a concave-convex region, ultrasonic data of the target sub-region is acquired to obtain detection information of each sub-region.

4. The aluminum model deformation monitoring method according to claim 3, characterized in that: The determining, based on the image data, whether there is an image abnormality in a sub-region includes: Extracting the current contour of the model to be detected in the image data and the current texture features and current shape features corresponding to each sub-region; Acquire the standard contour corresponding to the model to be detected and the standard texture features and standard shape features corresponding to each face on the model to be detected; Comparing the current profile with the standard profile to determine whether the current profile is consistent with the standard profile; If the current contour is consistent with the standard contour, determining the standard texture features and standard shape features corresponding to each sub-region; The current texture features and current shape features corresponding to each sub-region are compared with the corresponding standard texture features and standard shape features to determine whether there is a sub-region where the current texture features are inconsistent with the standard texture features or the current shape features are inconsistent with the standard shape features, so as to determine whether there is an image anomaly in the sub-region.

5. The aluminum model deformation monitoring method according to claim 3 or 4, characterized in that: If the target sub-region belongs to a smooth region, determining the monitoring result corresponding to each sub-region based on the detection information corresponding to each sub-region includes: Based on the image data of each sub-region, determining that the monitoring results of the sub-regions other than the target sub-region are normal; Determining whether the target sub-region is flat and smooth based on the reflection data corresponding to the target sub-region; If the target sub-region is flat and smooth, determining that the monitoring result corresponding to the target sub-region is normal; If the target sub-region is not flat or smooth, it is determined that the monitoring result corresponding to the target sub-region is abnormal.

6. The method for monitoring deformation of an aluminum model according to claim 3 or 4, characterized in that: If the target sub-region belongs to a concave-convex region, determining the monitoring result corresponding to each sub-region based on the detection information corresponding to each sub-region includes: Determine the key points corresponding to the target sub-region; Based on the ultrasonic data corresponding to the target sub-area, calculating the horizontal value and the vertical value corresponding to each key point; Based on the horizontal value and vertical value corresponding to each key point, the monitoring result corresponding to each sub-area is determined.

7. The aluminum model deformation monitoring method according to claim 6, characterized in that: The determining the key point corresponding to the target sub-region includes: identifying a target pattern corresponding to the target sub-region; Determining whether the target pattern is a regular pattern; If the target pattern is a regular pattern, determining the key point corresponding to the target pattern as the key point corresponding to the target sub-region; If the target pattern is an irregular image, a preset position point on the target sub-region is determined as a key point.

8. An aluminum model deformation monitoring device, characterized in that: include: An acquisition module, used for acquiring pattern information of a model to be detected, wherein the pattern information includes an internal pattern of the model and an external pattern of the model; A division module, used for dividing each surface of the to-be-detected model into a plurality of non-overlapping sub-areas based on the template information; A first determination module, configured to determine detection information corresponding to each sub-region, wherein the detection information includes at least one of image data, reflection data, and ultrasonic data; A second determination module is used to determine the monitoring result corresponding to each sub-area based on the detection information corresponding to each sub-area, and the monitoring result is normal or abnormal; The generation module is used to generate monitoring abnormality information if there is a sub-area with abnormal monitoring results.

9. An electronic device, characterized in that: The electronic device includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the aluminum model deformation monitoring method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed in a computer, the computer is caused to execute the aluminum model deformation monitoring method according to any one of claims 1 to 7.

Images