CN118447019B

CN118447019B - Die casting defect detection method, device and equipment

Info

Publication number: CN118447019B
Application number: CN202410903032.6A
Authority: CN
Inventors: 郝跃洪; 宋先招; 王光军
Original assignee: Nanchang Zhongli Precision Casting Co ltd
Current assignee: Nanchang Zhongli Precision Casting Co ltd
Priority date: 2024-07-08
Filing date: 2024-07-08
Publication date: 2024-10-01
Anticipated expiration: 2044-07-08
Also published as: CN118447019A

Abstract

The application is suitable for the technical field of die casting detection, and particularly relates to a die casting defect detection method, a device and equipment, wherein the method comprises the following steps: dividing the visual image information of the die casting into a first characteristic area and a second characteristic area by acquiring the visual image information of the die casting to be detected; determining first defect characteristic information reflecting defects of the first characteristic region according to the first characteristic region of the visual image information of the die casting; determining characteristic recognition parameters of a second characteristic region recognition algorithm according to the first defect characteristic information of the first characteristic region; determining second defect characteristic information reflecting characteristic details of defects of the second characteristic region according to the characteristic identification parameters of the second characteristic region; and determining a defect detection result of the die casting according to the first defect characteristic information of the first characteristic region and the second defect characteristic information of the second characteristic region, improving the consistency and the detection efficiency of the detection result, and meeting the high-speed production requirement of the modern manufacturing industry.

Description

Die casting defect detection method, device and equipment

Technical Field

The application belongs to the technical field of die casting detection, and particularly relates to a die casting defect detection method, device and equipment.

Background

Die casting is a manufacturing process in which molten metal is injected into a mold at high pressure to be rapidly cooled and formed, which is efficient but is prone to some typical drawbacks. Die casting defect inspection refers to a series of inspection measures performed on die casting products to find and evaluate various defects that may exist during the die casting production process in order to ensure die casting quality.

Traditional die casting detection methods such as manual visual inspection rely on experience of operators, particularly when fatigue or attention is dispersed, the inspection is long in time consumption, and for mass-produced die castings, the traditional detection methods are long in time consumption and different in judgment result, so that the consistency of detection results is low, the detection efficiency is low, and the high-speed production requirements of modern manufacturing industry are difficult to meet.

Disclosure of Invention

The embodiment of the application provides a method, a device and equipment for detecting die-casting defects, which can solve the problems that the consistency of detection results is low, the detection efficiency is low and the high-speed production requirements of modern manufacturing industry are difficult to meet due to the fact that the traditional detection method consumes long time and the judgment results are different in the die-casting defect detection process.

In a first aspect, an embodiment of the present application provides a method for detecting a die-casting defect, including:

Visual image information of a die casting to be detected is obtained, and the visual image information of the die casting is divided into a first characteristic area and a second characteristic area; wherein the first feature region and the second feature region are different;

Determining first defect characteristic information of the first characteristic region according to the first characteristic region of the visual image information of the die casting; the first defect characteristic information is used for reflecting the characteristic detailed condition of defects of the first characteristic area;

Determining a feature identification parameter of the second feature region according to the first defect feature information of the first feature region; wherein the characteristic recognition parameters are used for controlling and optimizing a recognition algorithm;

Determining second defect characteristic information of the second characteristic region according to the characteristic identification parameters of the second characteristic region; wherein the second defect characteristic information is used for reflecting the characteristic details of defects of the second characteristic area;

And determining a defect detection result of the die casting according to the first defect characteristic information of the first characteristic region and the second defect characteristic information of the second characteristic region.

The technical scheme provided by the embodiment of the application at least has the following technical effects:

According to the die casting defect detection method provided by the embodiment of the application, the visual image information of the die casting to be detected is divided into the first characteristic area and the second characteristic area by acquiring the visual image information of the die casting; determining first defect characteristic information reflecting characteristic details of defects of the first characteristic region according to the first characteristic region of the visual image information of the die casting; determining feature recognition parameters for controlling and optimizing a second feature region recognition algorithm according to the first defect feature information of the first feature region; determining second defect characteristic information reflecting characteristic details of defects of the second characteristic region according to the characteristic identification parameters of the second characteristic region; and determining a defect detection result of the die casting according to the first defect characteristic information of the first characteristic region and the second defect characteristic information of the second characteristic region, improving the consistency and the detection efficiency of the detection result, and meeting the high-speed production requirement of the modern manufacturing industry.

In a second aspect, an embodiment of the present application provides a die casting defect detecting device, including:

the device comprises an acquisition unit, a detection unit and a control unit, wherein the acquisition unit is used for acquiring visual image information of a die casting to be detected and dividing the visual image information of the die casting into a first characteristic area and a second characteristic area; wherein the first feature region and the second feature region are different;

A determining unit configured to determine first defect feature information of the first feature area according to the first feature area of the visual image information of the die casting; the first defect characteristic information is used for reflecting the characteristic detailed condition of defects of the first characteristic area;

A parameter unit, configured to determine a feature identification parameter of the second feature area according to the first defect feature information of the first feature area; wherein the characteristic recognition parameters are used for controlling and optimizing a recognition algorithm;

The identification unit is used for determining second defect characteristic information of the second characteristic region according to the characteristic identification parameters of the second characteristic region; wherein the second defect characteristic information is used for reflecting the characteristic details of defects of the second characteristic area;

And the evaluation unit is used for determining a defect detection result of the die casting according to the first defect characteristic information of the first characteristic region and the second defect characteristic information of the second characteristic region.

In a third aspect, an embodiment of the present application provides a die casting defect detection apparatus, including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the method according to any one of the first aspects when executing the computer program.

In a fourth aspect, embodiments of the present application provide a computer program product for, when run on a terminal device, causing the terminal device to perform the method of any of the above aspects.

It will be appreciated that the advantages of the second to fourth aspects may be seen from the relevant description of the above aspects, and will not be repeated here.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic flow chart of a method for detecting a die-casting defect according to an embodiment of the present application;

FIG. 2 is a flowchart of step S100 in a die-casting defect detection method according to an embodiment of the present application;

Fig. 3 is a flowchart of step S120 of a die-casting defect detection method according to an embodiment of the present application;

fig. 4 is a flowchart illustrating a step S130 of a die-casting defect detecting method according to an embodiment of the present application;

Fig. 5 is a flowchart illustrating a step S140 of a die casting defect detecting method according to an embodiment of the present application;

fig. 6 is a flowchart illustrating a step S200 of a die-casting defect detecting method according to an embodiment of the present application;

fig. 7 is a flowchart of step S300 of a die casting defect detecting method according to an embodiment of the present application;

Fig. 8 is a flowchart illustrating a step S500 of a die-casting defect detecting method according to an embodiment of the present application;

fig. 9 is a flowchart of step S520 of the die casting defect detecting device according to an embodiment of the present application;

FIG. 10 is a schematic diagram of a die-casting defect detecting device according to an embodiment of the present application;

Fig. 11 is a schematic structural view of a die casting defect detecting apparatus according to an embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It should also be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.

As used in the present description and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a condition or event is determined" or "if a condition or event is detected" may be interpreted in the context to mean "upon determination" or "in response to determination" or "upon detection of a condition or event, or" in response to detection of a condition or event.

Furthermore, the terms "first," "second," "third," and the like in the description of the present specification and in the appended claims, are used for distinguishing between descriptions and not necessarily for indicating or implying a relative importance.

Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.

In order to solve the problems, the embodiment of the application provides a die casting defect detection method, a device and equipment. In the method, visual image information of a die casting to be detected is divided into a first characteristic area and a second characteristic area by acquiring the visual image information of the die casting; determining first defect characteristic information reflecting characteristic details of defects of the first characteristic region according to the first characteristic region of the visual image information of the die casting; determining feature recognition parameters for controlling and optimizing a second feature region recognition algorithm according to the first defect feature information of the first feature region; determining second defect characteristic information reflecting characteristic details of defects of the second characteristic region according to the characteristic identification parameters of the second characteristic region; and determining a defect detection result of the die casting according to the first defect characteristic information of the first characteristic region and the second defect characteristic information of the second characteristic region, improving the consistency and the detection efficiency of the detection result, and meeting the high-speed production requirement of the modern manufacturing industry.

The die-casting defect detection method provided by the embodiment of the application can be applied to terminal equipment, and the terminal equipment is the execution main body of the die-casting defect detection method provided by the embodiment of the application, and the embodiment of the application does not limit the specific type of the terminal equipment.

For example, the terminal device may be an industrial controller, a smart detection robot, an embedded system, an internet of things (IoT) sensor node, a mobile detection unit, a remote monitoring station, an automated test stand of a smart factory, a cloud-connected analysis device, a highly integrated portable detection kit, a desktop computer, a smart large screen, a smart television, a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, an in-vehicle device, an internet of vehicle terminal, a computer, a laptop computer, or the like.

In order to better understand the die-casting defect detection method provided by the embodiment of the present application, a specific implementation procedure of the die-casting defect detection method provided by the embodiment of the present application is described in the following by way of example.

Fig. 1 shows a schematic flow chart of a method for detecting a die-casting defect according to an embodiment of the present application, where the method for detecting a die-casting defect includes:

S100, obtaining visual image information of a die casting to be detected, and dividing the visual image information of the die casting into a first characteristic area and a second characteristic area; wherein the first and second characteristic regions are different.

Illustratively, a high resolution industrial camera may be used to take pictures of the die casting from multiple angles, resulting in a high definition visual image of the die casting, with the entire image being divided into two main areas of interest using preset image processing techniques such as edge detection, thresholding, etc.: a first feature region and a second feature region. These two regions correspond to portions of the die cast part that are expected to have different characteristics or defect tendencies, respectively. Firstly, edge detection is carried out on visual image information of the die casting, and the contour of the die casting is found out. Based on the edge detection results, the curvature changes of each section of the die casting edge are analyzed, and characteristic points with significantly changed curvature directions are identified, which are usually caused by structural changes, edges and corners or defects. Based on the feature points of the curvature direction change, particularly those end points on the two sides of the curvature direction difference, minimum detection areas are constructed, which become target detection areas because they are likely to contain or be adjacent to the die casting defect. All the determined target detection areas are divided into first feature areas, while all the image areas outside the target detection areas are divided into indirect detection areas, i.e. second feature areas.

In one possible implementation, referring to fig. 2, in step S100, visual image information of a die casting to be detected is acquired, and the visual image information of the die casting is divided into a first feature area and a second feature area, including:

S110, acquiring visual image information of the die casting to be detected, and performing edge detection on the visual image information of the die casting.

It will be appreciated that the original visual image may be processed using a predetermined edge detection algorithm (e.g., canny edge detection, sobel operator, laplacian operator, etc.) in order to highlight the die cast contours and internal structural edges.

S120, determining characteristic points in which the curvature direction changes on the edge of the die casting in the visual image information based on the result of edge detection on the visual image information of the die casting.

It is understood that the feature points where the curvature direction changes significantly can be identified by analyzing the curvature change on the edge based on the result of the edge detection. These feature points are typically located at corners of the edge or where the shape changes significantly, which is critical to distinguishing between different feature regions. For example, at the portion where the edge of the die cast changes from smooth to curved, these feature points mark the start or end of the structural change.

Optionally, referring to fig. 3, S120, determining, based on a result of edge detection on visual image information of the die casting, a feature point in the visual image information where a curvature direction on an edge of the die casting changes includes:

S121, determining curvature change values of all sections of the die casting edge in the visual image information based on the result of edge detection on the visual image information of the die casting.

For example, each successive edge segment may be analyzed after edge detection is completed to calculate a curvature change value for each segment. Curvature is a measure of the degree of curvature of a curve at a point, and the average or local curvature of each segment of the edge can be obtained mathematically (e.g., by the derivative of the curve or a curvature formula) to quantify the bending characteristics of the edge. Curvature is a mathematical quantity describing the degree of curve bending at a certain point, and its calculation formula can be expressed as k= |dα/ds|. This formula defines curvature from a geometric perspective, where K denotes curvature, dα is the angle through which the curve turns over a small arc length ds (i.e., the change in tangential direction to the point on the curve), and |dα/ds| is the absolute value of this rate of change of angle, i.e., the change in angle per arc length. This definition intuitively embodies the concept of "degree of bending" and is independent of the specific parametric form of the curve.

S122, positioning a characteristic position corresponding to curvature direction change according to curvature change values of all sections of the die casting edge in the visual image information; wherein the curvature directions of the two sides of the characteristic position are different.

It will be appreciated that based on the calculated values of the edge curvature variations of the segments, the locations where those curvature directions are significantly changed are identified. This means that at these locations the edge transitions from one bending tendency to another, such as from convex to concave or a sharp change in direction. The different directions of curvature on both sides of these locations become important markers for distinguishing between different feature areas. For example, if an edge is nearly straight, its curvature is near zero; if the arc is formed, the curvature is a constant; where the edges are bent or pointed, the curvature may vary significantly.

And S123, determining the characteristic position as a characteristic point with the curvature direction changed on the edge of the die casting according to the characteristic position corresponding to the curvature direction change.

It will be appreciated that the sharp curvature change point is just the feature location to be found. The location where these curvatures suddenly increase (form a flange) or decrease (form a groove) represents an irregular change in the structure of the component, and can be considered as an abnormal site or a site of connection. For example, a component transitions from a smooth top edge to an acute angle at the interface where the curvature suddenly increases from a low value, indicating that the edge direction changes from nearly horizontal to vertical. At a recognized feature location, such as the acute angle turn described above, the edge profiles on both sides of the feature location are significantly different. One side may be a smooth curve along the top of the cylinder and the other side may be a straight or curved edge vertically downward, which radically changes the curvature direction, clearly distinguishing between different functional areas, and possibly also high-incidence areas of potential defects, such as burrs, cracks or irregular shapes, that may occur during casting, and accurately identifying these positions helps to quickly focus on possible problem areas, improving the pertinence and accuracy of defect detection.

S130, determining a target detection area in the visual image information according to the feature points of the change of the curvature direction on the edge of the die casting in the visual image information.

It will be appreciated that by identifying the feature points, a target detection area can be defined that requires particular attention. These areas surround the edge variation feature points, including the locations where defects are likely to occur in the expectation or the critical structural features of the die casting, ensuring that subsequent analysis focuses on the most critical or most likely problematic areas on the die casting.

Optionally, referring to fig. 4, S130, determining the target detection area in the visual image information according to the feature point of the change of the curvature direction on the edge of the die casting in the visual image information includes:

s131, determining an endpoint of change of the curvature direction on the edge of the die casting according to the characteristic points of change of the curvature direction on the edge of the die casting in the visual image information.

It will be appreciated that the characteristic points of change in curvature direction refer to points on the die casting contour where there is a significant change in curvature (i.e., degree of curve bending), such as from straight to curved or where there is a sharp change in degree of bending, are critical locations for identifying shape changes on the die casting edge. These feature points are critical to determining the geometric characteristics of the die cast parts because they often mark the beginning and end of the turning or complex shape of the edge. By detecting the characteristic points through an algorithm, the accurate position of the shape change of the edge of the die casting can be effectively positioned, namely, the endpoint of the change of the curvature direction is determined. For example, if the curvature value of a region suddenly increases from near zero (indicating a straight line portion) to a high value (indicating entry into a curved portion), then the feature point is marked as an endpoint.

And S132, constructing a minimum detection area of the change of the curvature direction on the edge of the die casting in the visual image information based on the end point of the change of the curvature direction on the edge of the die casting, and taking the minimum detection area as a target detection area in the visual image information.

It will be appreciated that the end points of the die casting edge where the direction of curvature changes mark the locations of the die casting edge where the curvature changes significantly, can connect adjacent end points at a distance within a predetermined range to form a series of line segments. These line segments enclose a polygonal area which encloses all feature points and which theoretically covers only the part where the edge curvature change is most pronounced, i.e. the smallest detection area. By doing so, the detection range can be effectively reduced, and unnecessary image analysis burden is reduced. The minimum detection area is a polygonal area that is as compact as possible, while ensuring that all critical features are contained. By constructing such regions, geometric algorithms, such as convex hull algorithms (Convex Hull), can be applied to ensure that the polygon boundaries can closely surround all endpoints, or by more complex algorithms to find the smallest area surrounding the polygon, ensuring that the detection region is both accurate and efficient.

Illustratively, there are three endpoints, for example:

the end point A is the left upper corner of the part and the straight line turns.

Endpoint B, point above the middle, where the degree of bending is exacerbated.

Endpoint C, the point in the middle of the right side at which the curve turns straight.

Constructing a minimum polygon, namely drawing a polygon by taking the three endpoints as vertexes. Starting from the end point A, connecting A-B-C in a clockwise or anticlockwise sequence, and finally returning to the point A. The polygonal boundary is closely attached to the curvature change area of the edge of the die casting, and a 'minimum detection area' is formed, so that a possible problem area can be accurately identified, and the pertinence and the accuracy of defect detection are improved.

And S140, dividing the visual image information of the die casting into a first characteristic area and a second characteristic area according to the target detection area in the visual image information.

It is understood that the visual image information is precisely divided into the first feature region and the second feature region based on the determined target detection region. Based on the edge detection results, the curvature changes of each section of the die casting edge are analyzed, and characteristic points with significantly changed curvature directions are identified, which are usually caused by structural changes, edges and corners or defects. Based on the feature points of the curvature direction change, particularly those end points on the two sides of the curvature direction difference, minimum detection areas are constructed, which become target detection areas because they are likely to contain or be adjacent to the die casting defect. All the determined target detection areas are divided into first feature areas, while all the image areas outside the target detection areas are divided into indirect detection areas, i.e. second feature areas.

Alternatively, referring to fig. 5, S140, dividing the visual image information of the die casting into a first feature area and a second feature area according to the target detection area in the visual image information includes:

s141, determining an indirect detection area in the visual image information according to the target detection area in the visual image information; wherein the indirect detection area includes an image area outside of all the target detection areas in the image.

It is understood that the target detection area refers to the minimum detection area established based on the end points of the die casting edge where the curvature direction changes, which have been identified during the image analysis. These regions are determined by analyzing the image pixel data by algorithms that mark their locations based on the shape, color, texture, etc. characteristics of the object. The indirect detection area refers to an image area outside of all target detection areas in the image. The indirect detection region is not detected by defect recognition by the curvature change feature, but by the detection result of the target detection region and a preset detection pattern.

S142, dividing all target detection areas in the visual image information into first characteristic areas and dividing all indirect detection areas in the visual image information into second characteristic areas.

It will be appreciated that the first characteristic region is the smallest detection region constructed based on the end points where the direction of curvature changes on the die casting edge, and is also the direct detection region.

S200, determining first defect characteristic information of a first characteristic area according to the first characteristic area of visual image information of the die casting; wherein the first defect characteristic information is used for reflecting the characteristic details of defects of the first characteristic region.

It will be appreciated that the first feature region is subjected to further analysis aimed at identifying and extracting feature information associated with the defect. This may include calculating pixel intensities, texture features, shape parameters, etc. to determine if the region is defective and its characteristics. For example, if the first feature area is a surface portion of a die cast part, signs of defects such as cracks, holes, or irregularities are sought. The first defect characteristic information is a detailed description of the characteristic details of the single defect which is identified and recorded, namely, each defect identified by the first characteristic area has corresponding defect characteristic information, namely, each single defect corresponds to the first defect characteristic information.

In one possible implementation, referring to fig. 6, S200, determining first defect feature information of a first feature area according to the first feature area of visual image information of the die casting includes:

S210, determining the change characteristics of curvature change values of all sections of the edge of the die casting in the first characteristic area according to the first characteristic area of the visual image information of the die casting.

It will be appreciated that detailed analysis of die cast edges can be used to identify possible signs of defects by calculating changes in edge curvature. The change in edge curvature can sensitively reflect surface discontinuities such as crack initiation or termination points, as well as unintended deformation of the shape, which is particularly effective for identifying small or hidden defects. The curve of the curvature change value can be obtained through a preset statistical algorithm of the curvature change value of each section of the die casting edge of the first characteristic region, and the curve of the curvature change value can reflect the change characteristic of the curvature change value.

S220, identifying preliminary defect characteristic information of the first characteristic region according to the change characteristics of curvature change values of all sections of the die casting edge of the first characteristic region.

It will be appreciated that the pattern recognition algorithm may be used to classify the curvature change characteristics to identify possible defect regions by analyzing the change characteristics of the edges from the curve of curvature change values. And according to the change characteristics of the curvature change value, primarily determining defect types such as cracks, holes or unevenness, wherein the primarily determined defect types are primarily defect characteristic information. The identified preliminary defect signature information is recorded for further analysis and processing. Through deep analysis of the change characteristics of the curvature change value, defects existing on the surface of the die casting can be effectively identified. And the contours of the defects may be extracted from the image using connected component analysis or contour tracking algorithms to size the defects. This process can sensitively detect surface discontinuities and provide a reliable data basis for subsequent defect feature extraction and optimization design. For example, a curvature change curve may be analyzed using a preset algorithm to identify significant curvature change points (e.g., peaks, valleys, etc.). These significant points of change may correspond to discontinuities or defect locations of the surface. And primarily judging the defect type according to the form and the position of the obvious change point. For linear defects such as cracks, the length of the longest continuous contour can be calculated as the length of the defect by calculating the linear distance or curve length between the contour endpoints. For width measurement, several key points (e.g., widest points) on the profile can be selected, and the lateral distance between these points can be calculated. Or if the defect has a more regular shape, the average width can be estimated by analyzing the thickness distribution of the profile. For example:

cracking: a sharp peak or valley in the curvature change curve indicates the initiation or termination of a crack.

Holes: a broad and gentle valley appears in the curvature change curve, indicating a depression or hole in the surface.

Unevenness: a plurality of small-amplitude fluctuations occur in the curvature change curve, which represent surface irregularities.

And recording the identified defect type, the position, the size and the like of the defect type to form preliminary defect characteristic information. For example:

Defect type: and (5) cracking.

Position: edge positions [ x1, x2].

Size: 1.8 long and 1.5 wide.

Characterization: a significant spike in curvature change value occurs between locations x1, x 2.

S230, based on the preliminary defect characteristic information of the first characteristic region, matching the relation between each preliminary defect characteristic information of the first characteristic region and the corresponding standard size.

For example, a standard size information base storing die casting design specifications and quality standards may be established in advance. These standard size information bases define the allowable tolerance ranges for die castings and the maximum allowable size of defects. Each of the identified preliminary defect feature information is matched and checked for whether it is within the allowable range of the standard size. Specifically, the dimensions (e.g., length, width, depth) of the inspected defects are compared to standard dimensions. If the defect size is within the allowable range of the standard size, then the defect is deemed not to require repair. If the defect size is outside the allowable range of the standard size, the defect is marked as a defect requiring repair.

S240, determining the first defect characteristic information of the first characteristic region according to the relation between each piece of preliminary defect characteristic information of the first characteristic region and the corresponding standard size.

It can be appreciated that the first defect characteristic information of the first characteristic region is finally determined based on the matching result of the preliminary defect characteristic information and the standard size. Specifically, the type, severity and repair requirements of the defect are determined by evaluating the relationship of the preliminary defect characterization information to the standard size. The first defect characteristic information is a detailed description of the identified and recorded defect characteristics. And evaluating whether each piece of preliminary defect characteristic information meets the standard size requirement. Based on the matching result, defect feature information is classified, for example:

Defect type: and (5) cracking.

Position: edge positions [ x1, x2].

Qualified defects: the defect size is within the standard allowable range and no repair is required.

Determining defect characteristic information based on standard size matching not only improves the scientificity and accuracy of defect detection, but also promotes the improvement of production efficiency and cost control.

S300, determining characteristic identification parameters of a second characteristic region according to first defect characteristic information of the first characteristic region; the feature recognition parameter is used for recognizing defect feature information of the second feature area.

It will be appreciated that the parameters for analyzing the second feature region may be adjusted or set based on the defect characteristics found in the first feature region. The feature recognition parameter refers to a series of parameter variables used for controlling and optimizing recognition in the process of feature recognition, and is a specific parameter for recognizing defect feature information of the second feature region. For example, these parameters may be specific thresholds, input weights of template matching rules to optimize the ability to identify potential defects in the second feature region, embodying strategies adapted from known information to improve accuracy of subsequent analysis.

In one possible implementation, referring to fig. 7, S300, determining, according to first defect feature information of the first feature area, feature identification parameters of the second feature area includes:

s310, determining a first defect characteristic information map of the die casting according to the first defect characteristic information of the first characteristic region; the first defect characteristic information map is used for reflecting details of all known defect characteristic information of the first characteristic region.

It will be appreciated that a defect signature, i.e. a first defect signature, is generated based on the defect signature found in the first feature region. The map includes information on defect type, location, size, and severity. For example, if a crack and hole are found in the first feature region, the map will record specific details of the defects, such as the location, length, location, diameter, etc. of the crack. The first defect characteristic information map is a chart or database formed by integrating detailed description and statistical data of all known defect characteristic information of the first characteristic region, and defect characteristic distribution of the first characteristic region is displayed in a graphical mode, so that quick understanding and analysis are facilitated. Illustratively, the first defect characterization information map may be implemented using the matplotlib library of Python for visualizing defect characterization information.

S320, determining a characteristic recognition mode of a second characteristic region according to the first defect characteristic information map of the die casting; wherein the feature recognition pattern includes parameters and methods for recognizing a specific type of defect.

It will be appreciated that determining the identification pattern for analyzing the second feature region based on the first defect feature information map creates a set of identification patterns based on the type and distribution characteristics of defects in the defect feature information map. And classifying and marking the defects in the first defect characteristic information map. May include identifying different types of defects such as cracks, pinholes, cold shut, shrinkage cavity, etc. The distribution and characteristics of defects in the first feature region are analyzed. Such as analyzing defect density, defect type distribution, geometry of defects, defect location, etc. And determining parameters of an image processing algorithm according to the defect type and the distribution characteristics, and establishing a characteristic recognition mode for the second characteristic region. This mode affects how the parameters of the image processing algorithm are set and how the sensitivity of the detection is adjusted. Feature recognition mode is a method or strategy for automatically detecting, extracting and distinguishing different features from data. The feature recognition pattern includes parameters and methods for recognizing a specific type of defect. For example, if a crack is found to be multiple in the first feature region, parameters for crack detection, such as a threshold for enhanced crack detection and a template matching rule, are emphasized in the second feature region.

S330, determining the characteristic recognition parameters of the second characteristic region according to the characteristic recognition mode of the second characteristic region and the first defect characteristic information map.

It can be understood that the identification parameters of the second feature region are set according to the identification mode and the defect feature information map. Specific parameters are set according to the recognition mode. These parameters may be thresholds including image processing, edge detection parameters, template matching weights, etc. to optimize the accuracy and efficiency of defect identification. For example, the defect characteristic information map of the first characteristic region shows that the crack is a main defect type, the proportion of the crack to the number of all defects is higher than a certain threshold value, so that the detection of the crack is enhanced by adjusting the characteristic identification parameters through a preset mapping relation, and the threshold value of the edge detection algorithm is adjusted to be a lower value so as to increase the detection sensitivity of the fine edge of the crack. In classifying the defect types, the weight of the crack is adjusted to be higher so as to identify the crack preferentially, and an additional crack characteristic extraction step can be introduced when the crack proportion exceeds a preset threshold value, such as morphological operation or a thin line detection algorithm, so as to improve the detection rate of the crack. For example, the defect information map shows that the proportion of the defect types of the holes in the first feature area to the number of all defects is higher than a certain threshold, so that the parameters of the edge detection algorithm can be adjusted by presetting the mapping relation adjustment parameters to better identify the holes, so that the edge detection algorithm can better capture the details of the edges of the holes, and a shape matching algorithm is introduced to perform shape constraint on the detected holes, for example, only the holes which are approximately circular are accepted, and the minimum and maximum diameter ranges of the holes are set to exclude the holes which are too small or too large, so that false detection is reduced. Through these steps, the accuracy and efficiency of subsequent analysis can be effectively improved through known information.

Illustratively, the crack defects account for 70%, followed by holes, 25%, and other types of defects account for 5% in total. For the second feature region, a detection algorithm needs to be optimized to ensure high-precision crack and hole identification while maintaining efficient detection speed. By the mapping relation, since the crack usually presents as a fine line, the high-low threshold ratio of the edge detection algorithm (such as Canny edge detection) in the image processing is adjusted to be in a wider range (such as 1:3 to 1:5), so that the sensitivity to the fine edge is improved. And introducing a common crack form template library, increasing the weight of template matching to 1.5 times that of the original template, preferentially matching crack characteristics, removing noise around the crack by applying open operation, and connecting the crack edges of the crack by closed operation so as to completely identify a crack path.

S400, determining second defect characteristic information of the second characteristic region according to the characteristic identification parameters of the second characteristic region; wherein the second defect characteristic information is used to reflect the characteristic details of defects of the second characteristic region.

It will be appreciated that the second feature region may be carefully analyzed using the set feature recognition parameters to recognize defect feature information in the second feature region. This step is based on knowledge learned from the first region to purposefully detect defect types that may be more hidden or different. The second defect characteristic information is a corresponding detail and description of the defect identified and recorded at the time of detection of the second characteristic region.

In one possible implementation manner, S400, determining second defect feature information of the second feature area according to the feature identification parameter of the second feature area includes:

S410, determining second defect characteristic information of the second characteristic region according to the characteristic identification parameters of the second characteristic region through the characteristic identification mode of the second characteristic region.

It will be appreciated that knowledge previously learned from the first feature region and preset feature recognition parameters (e.g., adjusted thresholds, pattern matching for a particular modality, edge detection sensitivity, etc.) may be applied to image processing and analysis of the second feature region. But may also include, but are not limited to, adjusting the brightness contrast of the image, performing a particular type of filtering to enhance the target feature, and using preset edge detection algorithm parameters to highlight potential defect boundaries. Scanning and analyzing the second characteristic region by utilizing the characteristic recognition mode after adjustment, such as texture analysis and shape recognition. These patterns may be specifically designed to identify specific types of defects, such as fine scratches, irregular pits, or foreign object embedding of specific size and morphology. And extracting identification defect information from the second characteristic region through the identification mode. And recording the identified defect type and the position thereof to form second defect characteristic information. May be examples that include identifying a new defect type that is different from the first feature region, or that exhibit finer different features (e.g., finer, shape changes, etc.) in the same type of defect. Further data analysis, such as statistical analysis, feature vector calculation, etc., is performed on the extracted second defect feature information to ensure accuracy of the identification. Through fine parameter adjustment and advanced feature recognition technology, the defect condition in the second feature area is deeply explored and accurately judged, and effective recognition can be ensured even if the defect is more complicated or hidden.

S500, determining a defect detection result of the die casting according to the first defect characteristic information of the first characteristic region and the second defect characteristic information of the second characteristic region.

It can be appreciated that the defect characteristic information of the first characteristic region and the second characteristic region can be integrated to determine a comprehensive detection result so as to determine the overall defect condition of the die casting. The method can be simple logic judgment (if the number of defects exceeds a threshold value, the defects are judged to be unqualified), or a more complex algorithm model, and various factors such as the types, the positions, the sizes and the like of the defects are comprehensively considered, so that a defect detection result is finally output.

In one possible implementation, referring to fig. 8, S500, determining a defect detection result of the die casting according to the first defect feature information of the first feature area and the second defect feature information of the second feature area includes:

s510, determining a second defect characteristic information map of the die casting according to second defect characteristic information of the second characteristic region; wherein the second defect characteristic information map is used for reflecting details of all known defect characteristic information of the second characteristic region.

It will be appreciated that all of the second defect signature information obtained from the second signature region analysis is integrated to form an exhaustive map. And recording and classifying the key attributes of the defect types, positions, sizes, shapes and the like of all the identified second characteristic areas. The frequency of occurrence of each defect type and their distribution in the second characteristic region are counted. And evaluating the potential influence of the defects on the functions and the strength of the die castings according to the properties and the sizes of the defects and the preset mapping relation. And generating a second defect characteristic information map of the second characteristic region by combining the information. The second defect characteristic information map is a visual representation of the details of all known defect characteristic information of the second characteristic region, so that the defect mode and the characteristic distribution of the second characteristic region can be understood visually. For example, the second defect characteristic information of the second characteristic region indicates that three main defects of air holes, cracks and surface irregularities exist, the air holes are found at 15 positions, the diameter range is 5-15mm, the air holes are uniformly distributed, the number of the cracks is 4, the length of the cracks is 10-30mm, the cracks are concentrated at the edge of the second characteristic region, and the surface irregularities account for 5% of the total area of the second characteristic region. According to preset standards, pores and cracks have a direct effect on structural strength, while surface irregularities may affect appearance and assembly. And (3) integrating the information, creating a second defect characteristic information map of the second characteristic region, and displaying the positions and densities of various defects by using different colors and marks based on a preset visual tool library, so that visual understanding is facilitated.

S520, determining the defect complexity of the die casting according to the first defect characteristic information map and the second defect characteristic information map of the die casting.

It can be appreciated that the overall defect condition of the die casting can be comprehensively estimated by combining the defect characteristic information map of the first characteristic region and the map of the second characteristic region just constructed. Comparing the defect types, distribution, frequencies and severity of the two feature areas, common points and differences are identified. A set of evaluation criteria may be pre-established to take into account the number, type, uniformity of distribution, and potential impact on product performance of the defects. According to the mapping relation between the actual detection data and the evaluation standard, the defect complexity of the die casting is divided into a plurality of grades such as simple, medium and complex, and the like, so that a basis is provided for subsequent decision. A score and weight may be set for each dimension according to the actual situation.

Optionally, referring to fig. 9, S520, determining the defect complexity of the die casting according to the first defect feature information map and the second defect feature information map of the die casting includes:

S521, determining defect distribution data of the die casting according to the first defect characteristic information map and the second defect characteristic information map of the die casting.

It can be appreciated that the defect distribution data of the die casting is updated by analyzing the first defect characteristic information map and the second defect characteristic information map of the die casting. These maps may include multidimensional information about the location, size, frequency, and morphology of various types of defects (e.g., cracks, shrinkage cavities, cold shut, etc.) on the die cast. By combining the two maps, the concentrated area, the distribution rule and the potential relevance of the defects are identified. The defect distribution data not only records the case of a single defect, but also reveals the spatial relationship and overall layout between defects.

S522, determining defect complexity of the die casting according to the defect distribution data of the die casting and a preset defect sequence; the defect sequences are used for reflecting the influence degree of different defects on the die casting.

It is understood that the defect complexity of the die casting can be evaluated based on the obtained defect distribution data in combination with a preset defect sequence. The preset defect sequence is a sorting mechanism, and the defects are classified according to different defect types, positions, sizes and other factors, so that the potential influence degree of each defect on the functions, strength, appearance and service life of the die casting is reflected. In short, certain defects (such as large cracks in critical load bearing parts) may be arranged at the front end of the sequence, which poses a significant threat to die casting performance; some minor surface imperfections may be located later, with relatively little impact. By comparing the defect distribution data with the defect sequence, the overall defect condition of the die casting can be quantified, which defects are primary concerns and which may be secondary considerations. The defect complexity can be determined based on the defect distribution data and a preset defect sequence (assuming that cracks > shrinkage holes in the sequence and the larger the size is, the more serious the effect is). All defect types and the occurrence frequency thereof are counted. Assuming that there are n different defect types in total, the distribution probability of each type occurrence can be calculated by calculating the number of defects of each type, and the entropy of each defect type is calculated to represent the degree of disorder of the defect distribution, i.e., the defect complexity. The influence of different defect types on the die casting can be reflected through a preset defect sequence, for example, the defect complexity can be reflected by summarizing entropy and weight of the defect types to obtain disorder degree of the defect types.

And S530, determining a defect detection result of the die casting according to the defect complexity of the die casting.

It can be appreciated that a determination is made as to the overall quality condition of the die casting based on the result of the evaluation of the defect complexity. The defect detection result of the die casting may be mapped to the section according to the value of the defect complexity by setting a threshold section for the defect complexity. For example, [0, a ] is a simple interval, (a, b ] is a medium interval, (b, infinity) is a complex interval, a simple interval may mean that a product meets a standard, defects in the complex interval may require reworking, scrapping or special quality control inspection, a detailed detection report is compiled, the detection process, the type of defects found, the complexity rating and final processing advice are summarized, the detection result can also be fed back to a production flow for guiding process adjustment, mold maintenance or quality standard revision to form closed-loop quality control.

Corresponding to the method for detecting a die-casting defect in the above embodiment, the embodiment of the present application further provides a device for detecting a die-casting defect, where each unit of the device can implement each step of the method for detecting a die-casting defect. Fig. 10 is a block diagram showing a die-casting defect detecting apparatus according to an embodiment of the present application, and only a portion related to the embodiment of the present application is shown for convenience of explanation.

Referring to fig. 10, the die casting defect detecting apparatus includes:

It should be noted that, because the content of information interaction and execution process between the above devices/units is based on the same concept as the method embodiment of the present application, specific functions and technical effects thereof may be referred to in the method embodiment section, and will not be described herein.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit module may exist alone physically, or two or more unit modules may be integrated in one unit, where the integrated unit may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above device may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.

The embodiment of the application also provides a die-casting defect detection device, and fig. 11 is a schematic structural diagram of the die-casting defect detection device according to an embodiment of the application. As shown in fig. 11, the die casting defect detecting apparatus 6 of this embodiment includes: at least one processor 60 (only one is shown in fig. 11), at least one memory 61 (only one is shown in fig. 11), and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60, which processor 60, when executing the computer program 62, causes the die casting defect detection apparatus 6 to implement the steps of any of the respective die casting defect detection method embodiments described above, or causes the die casting defect detection apparatus 6 to implement the functions of the respective units of the respective apparatus embodiments described above.

Illustratively, the computer program 62 may be partitioned into one or more units that are stored in the memory 61 and executed by the processor 60 to complete the present application. The one or more units may be a series of computer program instruction segments capable of performing a specific function for describing the execution of the computer program 62 in the die casting defect detection apparatus 6.

The die casting defect detection device 6 may be an industrial controller, an intelligent detection robot, an embedded system, an internet of things (IoT) sensor node, a mobile detection unit, a remote monitoring station, an automated test stand of an intelligent factory, a cloud-connected analysis device. The die casting defect detection apparatus may include, but is not limited to, a processor 60, a memory 61. It will be appreciated by those skilled in the art that fig. 11 is merely an example of the die casting defect detection apparatus 6 and is not meant to be limiting of the die casting defect detection apparatus 6, and may include more or fewer components than shown, or may combine certain components, or different components, such as may also include input-output devices, network access devices, buses, etc.

The Processor 60 may be a central processing unit (Central Processing Unit, CPU), the Processor 60 may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), off-the-shelf Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 61 may in some embodiments be an internal storage unit of the die casting defect detection apparatus 6, such as a hard disk or a memory of the die casting defect detection apparatus 6. The memory 61 may in other embodiments also be an external storage device of the die casting defect detecting device 6, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the die casting defect detecting device 6. Further, the memory 61 may also include both an internal memory unit and an external memory device of the die casting defect detecting device 6. The memory 61 is used for storing an operating system, application programs, boot loader (BootLoader), data, other programs, etc., such as program codes of the computer program. The memory 61 may also be used for temporarily storing data that has been output or is to be output.

Embodiments of the present application also provide a computer readable storage medium storing a computer program which, when executed by a processor, performs the steps of any of the various method embodiments described above.

The embodiments of the present application provide a computer program product for causing a terminal device to carry out the steps of any of the respective method embodiments described above when the computer program product is run on the terminal device.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiments, and may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a terminal device, a recording medium, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, and a software distribution medium. Such as a U-disk, removable hard disk, magnetic or optical disk, etc.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus/method for detecting a die casting defect may be implemented in other manners. For example, the die casting defect detection apparatus/die casting defect detection device embodiments described above are merely illustrative, e.g., the division of the units is merely a logical functional division, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.

Claims

1. A die casting defect detection method, characterized by comprising:

Determining a feature identification parameter of the second feature region according to the first defect feature information of the first feature region; the feature recognition parameters are used for recognizing defect feature information of the second feature area;

Determining a defect detection result of the die casting according to the first defect characteristic information of the first characteristic region and the second defect characteristic information of the second characteristic region;

The method for obtaining the visual image information of the die casting to be detected includes the steps of:

acquiring visual image information of a die casting to be detected, and performing edge detection on the visual image information of the die casting;

Determining feature points in the visual image information, wherein the feature points change in the curvature direction on the edge of the die casting, based on the result of edge detection on the visual image information of the die casting;

determining a target detection area in the visual image information according to the characteristic points with the curvature direction changed on the edge of the die casting in the visual image information;

Dividing the visual image information of the die casting into a first characteristic area and a second characteristic area according to the target detection area in the visual image information;

The dividing the visual image information of the die casting into a first characteristic region and a second characteristic region according to the target detection region in the visual image information includes:

Determining an indirect detection area in the visual image information according to the target detection area in the visual image information; wherein the indirect detection area comprises an image area outside all target detection areas in the image;

And dividing all the target detection areas in the visual image information into first characteristic areas, and dividing all the indirect detection areas in the visual image information into second characteristic areas.

2. The die casting defect detection method according to claim 1, wherein the determining a feature point in the visual image information at which a curvature direction on an edge of the die casting changes based on a result of edge detection of the visual image information of the die casting includes:

Determining curvature change values of all sections of the die casting edge in the visual image information based on the result of edge detection on the visual image information of the die casting;

positioning a characteristic position corresponding to curvature direction change according to the curvature change value of each section of the die casting edge in the visual image information; wherein the curvature directions of the two sides of the characteristic position are different;

And determining the characteristic position as a characteristic point with the curvature direction changed on the edge of the die casting according to the characteristic position corresponding to the curvature direction change.

3. The die casting defect detection method according to claim 1, wherein the determining the target detection area in the visual image information based on the feature points in the visual image information where the curvature direction on the die casting edge changes includes:

determining an endpoint of change of the curvature direction on the edge of the die casting according to the characteristic points of change of the curvature direction on the edge of the die casting in the visual image information;

And constructing a minimum detection area of the change of the curvature direction on the edge of the die casting in the visual image information based on the end point of the change of the curvature direction on the edge of the die casting, and taking the minimum detection area as a target detection area in the visual image information.

4. The die casting defect detection method according to claim 2, wherein the determining first defect feature information of the first feature area from the first feature area of the visual image information of the die casting includes:

Determining the change characteristics of the curvature change values of the sections of the die casting edge of the first characteristic area according to the first characteristic area of the visual image information of the die casting;

Identifying preliminary defect characteristic information of the first characteristic region according to the change characteristics of the curvature change values of the sections of the die casting edge of the first characteristic region;

Matching the relation between each piece of preliminary defect characteristic information of the first characteristic region and the corresponding standard size based on the preliminary defect characteristic information of the first characteristic region;

and determining first defect characteristic information of the first characteristic region according to the relation between each piece of preliminary defect characteristic information of the first characteristic region and the corresponding standard size.

5. The die casting defect detection method according to claim 1, wherein the determining the feature identification parameter of the second feature region based on the first defect feature information of the first feature region includes:

Determining a first defect characteristic information map of the die casting according to the first defect characteristic information of the first characteristic region; the first defect characteristic information map is used for reflecting details of all known defect characteristic information of the first characteristic region;

Determining a characteristic recognition mode of the second characteristic region according to the first defect characteristic information map of the die casting; wherein the feature recognition pattern includes parameters and methods for recognizing a specific type of defect;

And determining the characteristic identification parameters of the second characteristic region according to the characteristic identification mode of the second characteristic region and the first defect characteristic information map.

6. The die casting defect detection method according to claim 5, wherein the determining second defect feature information of the second feature region according to the feature identification parameter of the second feature region includes:

And determining second defect characteristic information of the second characteristic region according to the characteristic identification parameters of the second characteristic region through the characteristic identification mode of the second characteristic region.

7. The die casting defect detection method according to claim 5, wherein the determining the defect detection result of the die casting based on the first defect feature information of the first feature region and the second defect feature information of the second feature region includes:

determining a second defect characteristic information map of the die casting according to the second defect characteristic information of the second characteristic region; the second defect characteristic information map is used for reflecting details of all known defect characteristic information of the second characteristic region;

determining defect complexity of the die casting according to the first defect characteristic information map and the second defect characteristic information map of the die casting;

and determining a defect detection result of the die casting according to the defect complexity of the die casting.

8. The method of claim 7, wherein determining the defect complexity of the die cast part based on the first defect signature and the second defect signature of the die cast part comprises:

Determining defect distribution data of the die casting according to the first defect characteristic information map and the second defect characteristic information map of the die casting;

determining defect complexity of the die casting according to the defect distribution data of the die casting and a preset defect sequence; the defect sequences are used for reflecting the influence degree of different defects on the die castings.

9. A die casting defect detecting device, characterized by comprising:

an evaluation unit configured to determine a defect detection result of the die casting based on the first defect feature information of the first feature region and the second defect feature information of the second feature region;

wherein the acquisition unit is further configured to:

10. A die casting defect detection apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the method of any of claims 1 to 8 when executing the computer program.