Part quality detection method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of automation, in particular to a part quality detection method and device, electronic equipment and a storage medium. According to the part quality detection method provided by the embodiment of the invention, the computer aided design model corresponding to the target part needs to be acquired firstly; performing geometric feature analysis on the target part based on a computer aided design model to obtain part geometric feature information; generating a plurality of pieces of detection viewpoint information corresponding to different detection viewpoints according to the geometric feature information of the part; generating a motion path based on the multiple pieces of detection viewpoint information to obtain a data acquisition path; controlling a data acquisition module to perform data acquisition on the target part according to the data acquisition path to obtain actually measured parameters of the part; quality detection is carried out on the target part based on the actually measured parameters of the part, quality detection result information is obtained, multi-angle detection can be carried out according to the complex shape and size of the part, and the comprehensiveness and precision of part quality detection are improved.

Description

Technical Field

[0001] The present application relates to the field of automation technology, and in particular, to a method and device for detecting the quality of parts, an electronic device, and a storage medium. Background Art

[0002] With the continuous improvement of the degree of industrial manufacturing automation, the quality inspection of parts has become a core link to ensure product quality and improve production efficiency.

[0003] In related technologies, part inspection methods mainly rely on manual operation or a single inspection device with a fixed perspective. When facing parts with complex geometric shapes, it is difficult to achieve full-angle accurate inspection. Specific problems include incomplete coverage of inspection viewpoints, single sensor selection, limited automation, lack of flexibility in the inspection system, and insufficient inspection accuracy. Therefore, how to improve the comprehensiveness and accuracy of part quality inspection has become an urgent problem in the industry. Summary of the Invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. For this purpose, the present application provides a method and device for detecting the quality of parts, an electronic device, and a storage medium, which can perform accurate multi-angle detection according to the complex shape and size of the parts, and improve the comprehensiveness and accuracy of part quality inspection.

[0005] The method for detecting the quality of parts according to the first aspect embodiment of the present application is applied to a part quality inspection device, and the part quality inspection device is provided with a movable data acquisition module, including:

[0006] Obtain a computer-aided design model corresponding to the target part;

[0007] Perform geometric feature analysis on the target part based on the computer-aided design model to obtain part geometric feature information;

[0008] Generate a plurality of inspection viewpoint information corresponding to different inspection viewpoints according to the part geometric feature information;

[0009] Generate a motion path based on the plurality of inspection viewpoint information to obtain a data acquisition path;

[0010] Control the movable data acquisition module to perform data acquisition on the target part according to the data acquisition path to obtain part measured parameters;

[0011] Perform quality inspection on the target part based on the part measured parameters to obtain quality inspection result information.

[0012] According to some embodiments of the present application, the geometric feature analysis of the target component based on the computer-aided design model to obtain component geometric feature information includes:

[0013] Based on the computer-aided design model, determine the reference hole parameter equation and the reference plane parameter equation in the target component;

[0014] According to the reference hole parameter equation and the reference plane parameter equation, determine the spatial description coordinate system;

[0015] Based on the spatial description coordinate system, parametrically represent each component model in the computer-aided design model to obtain the component geometric feature information matching the target component.

[0016] According to some embodiments of the present application, the generation of multiple detection view point information corresponding to different detection view points based on the component geometric feature information includes:

[0017] Obtain the field of view acquisition parameters corresponding to the data acquisition module;

[0018] Based on the field of view acquisition parameters and the component geometric feature information, generate multiple detection view point information corresponding to different detection view points.

[0019] According to some embodiments of the present application, the component geometric feature information includes key component feature information, and the generation of multiple detection view point information corresponding to different detection view points based on the field of view acquisition parameters and the component geometric feature information includes:

[0020] Based on the field of view acquisition parameters and the component geometric feature information, generate preliminary view point information;

[0021] Based on the key component feature information and a preset view point distribution algorithm, perform optimization calculation on the preliminary view point information to obtain multiple detection view point information corresponding to different detection view points.

[0022] According to some embodiments of the present application, the generation of a data acquisition path based on multiple detection view point information includes:

[0023] According to multiple detection view point information, determine the view point position information and the view point shooting angle information corresponding to each detection view point;

[0024] Input the view point position information and the view point shooting angle information corresponding to each detection view point into a preset motion planning algorithm to obtain the data acquisition path.

[0025] According to some embodiments of the present application, the movable data acquisition module includes a multi-joint robotic arm and a sensor probe disposed at the end of the multi-joint robotic arm. The movable data acquisition module is controlled according to the data acquisition path to perform data acquisition on the target component, and the measured parameters of the component are obtained, including:

[0026] Input the data acquisition path into the kinematic model of the robotic arm to calculate the motion stroke, so as to determine the robotic arm motion stroke information matching the data acquisition path;

[0027] Based on the robotic arm motion stroke information, control the data acquisition module to perform data acquisition on the target component to obtain the measured parameters of the component.

[0028] According to some embodiments of the present application, the quality inspection of the target component is performed based on the measured parameters of the component, and the quality inspection result information is obtained, including:

[0029] Perform stitching and fusion processing on the measured parameters of the component collected from different inspection viewpoints to generate a measured three-dimensional model matching the target component;

[0030] Perform geometric measurement and surface defect detection on the measured three-dimensional model to perform quality inspection on the target component and obtain the quality inspection result information. [[ID=1;7]]

[0031] According to the component quality inspection device of the second aspect embodiment of the present application, the component quality inspection device is provided with a movable data acquisition module, and the component quality inspection device includes:

[0032] A component model acquisition module, configured to acquire a computer-aided design model corresponding to a target component;

[0033] A geometric feature analysis module, configured to perform geometric feature analysis on the target component based on the computer-aided design model to obtain component geometric feature information;

[0034] An inspection viewpoint generation module, configured to generate a plurality of inspection viewpoint information corresponding to different inspection viewpoints according to the component geometric feature information;

[0035] An acquisition path generation module, configured to generate a motion path based on the plurality of inspection viewpoint information to obtain a data acquisition path;

[0036] A motion control module, configured to control the movable data acquisition module to perform data acquisition on the target component according to the data acquisition path to obtain measured parameters of the component;

[0037] A quality inspection module, configured to perform quality inspection on the target component based on the actually measured parameters of the component to obtain quality inspection result information.

[0038] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the component quality inspection method according to any one of the embodiments of the first aspect of the present application is implemented.

[0039] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium. The storage medium stores a program, and when the program is executed by a processor, the component quality inspection method according to any one of the embodiments of the first aspect of the present application is implemented.

[0040] The component quality inspection method, device, electronic device, and storage medium according to the embodiments of the present application at least have the following beneficial effects:

[0041] The component quality inspection method according to the embodiment of the present application is applied to a component quality inspection device. The component quality inspection device is provided with a movable data acquisition module. First, a computer-aided design model corresponding to the target component needs to be obtained; based on the computer-aided design model, geometric feature analysis of the target component is performed to obtain component geometric feature information; according to the component geometric feature information, a plurality of detection view point information corresponding to different detection viewpoints is generated; based on the plurality of detection view point information, a motion path is generated to obtain a data acquisition path; according to the data acquisition path, the movable data acquisition module is controlled to perform data acquisition on the target component to obtain actually measured parameters of the component; based on the actually measured parameters of the component, quality inspection of the target component is performed to obtain quality inspection result information. In this way, accurate multi-angle inspection can be performed according to the complex shape and size of the component, improving the comprehensiveness and accuracy of component quality inspection.

[0042] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the description of the embodiments in conjunction with the following drawings, where:

[0044] Figure 1 is a structural example diagram of a component quality inspection device provided by an embodiment of the present application;

[0045] Figure 2 is a structural example diagram of a target component provided by an embodiment of the present application;

[0046] Figure 3 It is an exemplary diagram corresponding to multiple detection perspectives of the component quality detection device provided by the embodiment of the present application;

[0047] Figure 4 It is a schematic flowchart of the component quality detection method provided by the embodiment of the present application;

[0048] Figure 5 It is another schematic flowchart of the component quality detection method provided by the embodiment of the present application;

[0049] Figure 6 It is another schematic flowchart of the component quality detection method provided by the embodiment of the present application;

[0050] Figure 7 It is another schematic flowchart of the component quality detection method provided by the embodiment of the present application;

[0051] Figure 8 It is another schematic flowchart of the component quality detection method provided by the embodiment of the present application;

[0052] Figure 9 It is another schematic flowchart of the component quality detection method provided by the embodiment of the present application;

[0053] Figure 10 It is another schematic flowchart of the component quality detection method provided by the embodiment of the present application;

[0054] Figure 11 It is a schematic hardware structure diagram of the electronic device provided by the embodiment of the present application. Detailed implementation manners

[0055] The embodiments of the present application will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions from beginning to end. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present application, and should not be construed as a limitation to the present application.

[0056] In the description of the present application, the meaning of several is one or more, the meaning of multiple is more than two, greater than, less than, exceeding, etc. are understood as not including the present number, and above, below, within, etc. are understood as including the present number. If there is a description of first and second, it is only for the purpose of distinguishing technical features and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features or implicitly indicating the sequence relationship of the indicated technical features.

[0057] In the description of the present application, it should be understood that when it comes to orientation descriptions, such as the orientation or positional relationship indicated by up, down, left, right, front, back, etc., it is based on the orientation or positional relationship shown in the drawings. This is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or component referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present application.

[0058] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "schematic embodiments", "examples", "specific examples", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0059] In the description of the present application, it should be noted that unless otherwise clearly defined, terms such as setting, installation, connection, etc. should be understood in a broad sense. Those skilled in the art can reasonably determine the specific meanings of the above terms in the present application in combination with the specific content of the technical solution. In addition, the identification of specific steps in the following text does not represent a limitation on the step sequence and execution logic. The execution sequence and execution logic between each step should be understood and inferred with reference to the content described in the embodiments.

[0060] With the continuous improvement of the degree of industrial manufacturing automation, the quality inspection of parts has become a core link to ensure product quality and improve production efficiency.

[0061] In the related art, the part inspection methods mainly rely on manual operation or single inspection equipment with a fixed perspective. When facing parts with complex geometric shapes, it is difficult to achieve full - range and accurate inspection.

[0062] First of all, the incomplete coverage of inspection viewpoints is a significant problem. Traditional single - perspective inspection equipment can only inspect from a fixed angle. For parts with complex shapes or multi - dimensional surface structures, it is easy to have inspection blind spots, resulting in some key parts not being effectively inspected. This limitation not only affects the comprehensiveness of the inspection but also reduces the reliability of the inspection results.

[0063] Secondly, the singularity of sensor selection also limits the performance of the detection system. In related technologies, most are only equipped with a few specific types of sensors, such as 2D cameras or basic ranging devices, making it difficult to meet complex detection requirements. For components that require high-precision surface detail analysis, two-dimensional images may not provide sufficient information to comprehensively capture the key features of the components. This single sensor configuration proves inadequate when faced with diverse and complex detection tasks.

[0064] In addition, the related technologies for component detection have relatively limited automation levels and rely on manual intervention for perspective adjustment or sensor replacement. On the production line, with the frequent changes in the types and forms of components, the adjustment process of these systems is cumbersome and inefficient, and true automation and flexible adaptation cannot be achieved. This low automation level not only increases labor costs but also restricts the improvement of production efficiency.

[0065] Furthermore, the lack of flexibility in the detection system is also an important issue. The component detection algorithms in related technologies are usually customized for specific components. If the components are replaced, the algorithms often need to be readjusted. This algorithm design lacking flexibility and generality is difficult to meet the production requirements of multi-variety and small-batch production and cannot achieve flexible and efficient detection. In modern manufacturing, with the rapid product replacement and a wide variety of components, this detection system lacking flexibility obviously cannot meet the production needs.

[0066] Finally, the insufficient detection accuracy of components is another key drawback of related technologies. Due to the limitations of fixed perspectives or single sensors, related technologies often struggle to achieve the required detection accuracy in high-precision detection scenarios, especially for components with complex surfaces or minor geometric differences. This lack of accuracy directly affects the control of product quality and may lead to the outflow of unqualified products.

[0067] In summary, the component detection technologies in related technologies have obvious deficiencies in terms of detection viewpoint coverage, sensor selection, automation level, system flexibility, and detection accuracy, and are difficult to meet the requirements of modern industrial manufacturing for high-precision, high-efficiency, and high-flexibility detection.

[0068] The following will be further described with reference to the accompanying drawings.

[0069] This application aims to solve at least one of the technical problems existing in the prior art. For this purpose, this application proposes a component quality detection method, its device, an electronic device, and a storage medium, which can perform accurate multi-angle detection according to the complex shapes and sizes of components, and improve the comprehensiveness and accuracy of component quality detection.

[0070] A component quality inspection device according to an embodiment of the present application, the component quality inspection device is provided with a movable data acquisition module, and the component quality inspection device includes:

[0071] A component model acquisition module, configured to acquire a computer-aided design model corresponding to a target component;

[0072] A geometric feature analysis module, configured to perform geometric feature analysis on the target component based on the computer-aided design model to obtain component geometric feature information;

[0073] A detection view point generation module, configured to generate a plurality of detection view point information corresponding to different detection view points according to the component geometric feature information;

[0074] An acquisition path generation module, configured to generate a motion path based on the plurality of detection view point information to obtain a data acquisition path;

[0075] A motion control module, configured to control the movable data acquisition module to perform data acquisition on the target component according to the data acquisition path to obtain measured component parameters;

[0076] A quality inspection module, configured to perform quality inspection on the target component based on the measured component parameters to obtain quality inspection result information.

[0077] According to some more specific embodiments of the present application, the component quality inspection device may include:

[0078] Refer to Figure 1 , a multi-viewpoint motion mechanism 101, the multi-viewpoint motion mechanism 101 fixes a sensor probe 103 at the end of the motion mechanism through a flange 102, and the sensor probe 103 is used to acquire image data or three-dimensional point cloud data of a target component 105 to be measured; the multi-viewpoint motion mechanism 101 is connected to a host computer 104 through a connection line 110, and the host computer 104 is used to control the motion path of the multi-viewpoint motion mechanism 101, coordinate the data acquisition of the sensor probe 103 and give a detection result to ensure all-round and multi-angle precise detection of the target component 105. The target component 105 to be measured is placed on a conveyor belt 106, and the conveyor belt 106 includes a base 107, a first bracket 108 and a second bracket 109, wherein the base 107 provides stable support for the conveyor belt 106 to ensure the smooth operation of the conveyor belt 106, and the first bracket 108 and the second bracket 109 are used to stabilize the structure of the conveyor belt 106.

[0079] It should be understood that the sensor probe 103 may include, but is not limited to, 2D industrial cameras, 3D structured light cameras, laser scanners, line laser profilers, infrared thermal imagers, ultrasonic sensors, contact probes, etc. The appropriate sensor type can be selected according to the detection requirements and component characteristics to collect information such as image data, point cloud data, distance data, and surface topography.

[0080] In the component quality detection device according to the embodiment of the present application, the geometric feature analysis module can be controlled by the host computer 104. It can import the computer-aided design model (such as CAD model file) of the target component 105 to be measured, and analyze the geometric features of the target component 105 according to the computer-aided design protocol (such as STEP, IGES, STL, DWG, DXF, etc.), and generate multiple detection viewpoints based on the geometric feature information of the target component 105 to be measured.

[0081] Referring to Figure 2 Some of the illustrated embodiments, specifically:

[0082] First, the present application can analyze the first reference hole 201, the second reference hole 202, and the reference plane 203 in the target component 105, obtain their parametric representations, and generate a preliminary coordinate system based on the equations of the parametric representations to define the spatial position of the component.

[0083] Next, the component quality detection device according to the embodiment of the present application can perform parametric representations on the first cylinder 204 and the second cylinder 205 on the component 105, calculate and extract their normal vectors and tangent vectors to define the postures and positions of the first cylinder 204 and the second cylinder 205;

[0084] At the same time, the component quality detection device of the present application performs parametric representations on the first sphere 206 and the second sphere 2,07, and determines the center positions of the corresponding spheres, thereby providing a reference for subsequent measurements.

[0085] After generating the preliminary coordinate system and fitting the key components, the component quality detection device of the present application initially generates the viewpoints to be measured by calculating whether the camera view angle overlaps with the component according to the field of view angle and depth of field of the camera.

[0086] At the same time, in order to ensure that the generated viewpoints are as evenly distributed as possible, the component quality detection device of the present application can use optimization algorithms such as particle swarm optimization and genetic algorithms to generate multiple viewpoint coordinates, and consider factors such as the acquisition range, visible area of each viewpoint, and avoidance of mutual occlusion to ensure that all key parts can be comprehensively covered. Thereby improving the efficiency and comprehensiveness of the overall detection. This objective function can be expressed as:

[0087]

[0088] where d i represents the distance between each viewpoint.

[0089] Based on the generated multiple viewpoint coordinates, the component quality inspection device of the present application generates corresponding viewpoint position and attitude information, providing accurate path planning data for the subsequent multi-viewpoint motion mechanism 101, thereby ensuring that the sensor probe 103 can accurately detect the component from multiple angles in all-round and multi-angle manners.

[0090] It should be noted that the component quality inspection device of the present application detects the target component 105 to be measured through multiple perspectives.

[0091] Specifically, the target component 105 has a complex geometric structure and multiple key features, and a single perspective cannot capture all the key details at one time. If a large-field-of-view perspective is adopted, although a larger range can be covered, due to the low accuracy, the requirements for high-precision detection cannot be met.

[0092] Therefore, the present application adopts multiple small-field-of-view and high-precision perspectives for shooting to ensure that the details of each key area of the component can be accurately obtained from different angles.

[0093] Specifically, the multiple detection perspectives include but are not limited to:

[0094] The first detection perspective 301: used to capture key features such as the first reference hole 201 and the reference plane 203 in the target component 105, and fit the reference hole and the reference plane by collecting data through this perspective.

[0095] The second detection perspective 302: used to photograph the second reference hole 202 and other key areas on the target component 105, and establish a coordinate system by combining the data of the first reference hole 201 and the reference plane 203.

[0096] The third detection perspective 303: used to capture the first cylinder 204 and the second cylinder 205 on the target component 105, extract its normal vector and tangent vector by fitting the geometric features of the cylinder, and define the attitude and position of the component.

[0097] The fourth detection perspective 304: used to capture the first sphere 206 and the second sphere 207 on the target component 105, and determine the position of the sphere center by fitting the sphere.

[0098] It should be noted that the above Figures 1 to 3It is intended to introduce some representative embodiments provided by this application, aiming to explain the application of this application through these embodiments. However, this application has wide applicability and can perform general detection on parts with various different shapes and features. Therefore, the detection process and technical means can be applied to different types of parts, not limited to the specific embodiments mentioned above.

[0099] Referring to Figure 4 , according to the part quality detection method of this application, which is applied to a part quality detection device, the part quality detection device of the embodiments of this application is provided with a movable data acquisition module, which may include:

[0100] Step S401, obtaining a computer-aided design model corresponding to the target part;

[0101] Step S402, performing geometric feature analysis on the target part based on the computer-aided design model to obtain part geometric feature information;

[0102] Step S403, generating a plurality of detection view point information corresponding to different detection view points according to the part geometric feature information;

[0103] Step S404, generating a motion path based on the plurality of detection view point information to obtain a data acquisition path;

[0104] Step S405, controlling the movable data acquisition module to perform data acquisition on the target part according to the data acquisition path to obtain the measured parameters of the part;

[0105] Step S406, performing quality detection on the target part based on the measured parameters of the part to obtain quality detection result information.

[0106] In the field of industrial manufacturing, the quality detection of parts is a key link to ensure product quality and improve production efficiency. To achieve efficient, accurate, and comprehensive automated detection, this application proposes a part quality detection method based on a computer-aided design model. This method, through multiple key steps, combines computer-aided design model analysis, multi-viewpoint planning, motion path generation, data acquisition, and quality detection, etc., to solve the deficiencies in traditional part quality detection methods and significantly improve the comprehensiveness and accuracy of detection.

[0107] In some embodiments, step S401, obtaining a computer-aided design model corresponding to the target part;

[0108] It should be noted that, first of all, obtaining the computer-aided design model corresponding to the target component is the basis of the entire detection process. The computer-aided design model contains the detailed geometric information of the component, and this information is crucial for the subsequent detection process. By importing the computer-aided design model, the purpose of importing the computer-aided design model in the embodiments of the present application is to accurately understand the shape, size, and key features of the target component. This step provides the basic data for subsequent geometric feature analysis and detection view point generation, ensuring the accuracy and comprehensiveness of the detection.

[0109] In some embodiments, from step S402 to step S403, based on the computer-aided design model, geometric feature analysis is performed on the target component to obtain component geometric feature information, and according to the component geometric feature information, multiple detection view point information corresponding to different detection view points is generated;

[0110] It should be noted that next, based on the computer-aided design model, geometric feature analysis is performed on the target component to obtain component geometric feature information. This component geometric feature information involves the recognition and parametric representation of the shape, size, and key features (such as datum holes, datum planes, prisms, spheres, etc.) of the component. By analyzing the component geometric feature information corresponding to the computer-aided design model, the component quality detection device in the embodiments of the present application can generate detection view point information for multiple detection view points. The generation of these detection view point information is based on the geometric feature information of the component, and through an optimization algorithm, the uniform distribution and comprehensive coverage of the detection view points are ensured, thus avoiding the blind area problem in traditional detection methods. This step lays the foundation for subsequent multi-view detection, ensuring the comprehensiveness and accuracy of the detection.

[0111] Refer to Figure 5 , according to some embodiments of the present application, step S402 performs geometric feature analysis on the target component based on the computer-aided design model to obtain component geometric feature information, which may include:

[0112] Step S501, based on the computer-aided design model, determine the parametric equations of the datum holes and the parametric equations of the datum planes in the target component;

[0113] Step S502, according to the parametric equations of the datum holes and the parametric equations of the datum planes, determine the spatial description coordinate system;

[0114] Step S503, based on the spatial description coordinate system, perform parametric representation on each component model in the computer-aided design model to obtain component geometric feature information matching the target component.

[0115] In some embodiments of the present application, the process of parsing the geometric features of a target component based on a computer-aided design model to obtain component geometric feature information can be further refined into several key steps.

[0116] In step S501 of some embodiments, based on the computer-aided design model, determine the parametric equations of the reference holes and the parametric equations of the reference planes in the target component;

[0117] It should be noted that, first, based on the computer-aided design model, determine the parametric equations of the reference holes and the parametric equations of the reference planes in the target component. This step can be achieved by parsing the computer-aided design model to identify the key reference features in the component, such as reference holes and reference planes. In some embodiments, the reference holes and reference planes are important components of the geometric features of the component, and their parametric equations can provide basic data for subsequent geometric feature parsing. By determining the parametric equations of these reference features, the component quality inspection device of the present application can accurately describe the spatial position and geometric shape of the component, providing an accurate reference for subsequent detection viewpoint generation and motion path planning.

[0118] In step S502 of some embodiments, determine the spatial description coordinate system according to the parametric equations of the reference holes and the parametric equations of the reference planes;

[0119] It should be noted that, next, determine the spatial description coordinate system according to the parametric equations of the reference holes and the parametric equations of the reference planes. This step is to establish a spatial description coordinate system by using the parametric equations of the reference holes and reference planes to describe the position and attitude of the component in space. The determination of the spatial description coordinate system can provide a unified reference framework for subsequent geometric feature parsing and detection viewpoint generation. Through this coordinate system, the component quality inspection device of the present application can accurately calculate the spatial positions of each feature point of the component, providing accurate geometric information for subsequent detection processes.

[0120] In step S503 of some embodiments, parametrically represent each component model in the computer-aided design model based on the spatial description coordinate system to obtain component geometric feature information that matches the target component.

[0121] It should be noted that finally, based on the spatial description coordinate system, parametric representation is performed on each component model in the computer-aided design model to obtain the geometric feature information of the components matching the target component. This step is to parametrically represent each component model in the computer-aided design model by using the spatial description coordinate system, so as to obtain the geometric feature information of the components. Among them, parametric representation can transform the geometric features of the components into a computable parameter form, providing accurate data support for subsequent detection view point generation and motion path planning. Through parametric representation, the component quality detection device of the present application can accurately describe the geometric shape and size of the components, providing comprehensive geometric feature information for the subsequent detection process.

[0122] Referring Figure 6 , according to some embodiments of the present application, step S403 generates multiple detection view point information corresponding to different detection view points according to the geometric feature information of the components, which may include:

[0123] Step S601, obtaining the field of view acquisition parameters corresponding to the data acquisition module;

[0124] Step S602, generating multiple detection view point information corresponding to different detection view points based on the field of view acquisition parameters and the geometric feature information of the components.

[0125] In step S601 of some embodiments, obtaining the field of view acquisition parameters corresponding to the data acquisition module;

[0126] It should be noted that first, obtain the field of view acquisition parameters corresponding to the data acquisition module. This step is to obtain parameters such as the field of view angle and depth of field of the data acquisition module, providing basic data for subsequent detection view point generation. The field of view acquisition parameters determine the coverage range and acquisition accuracy that the data acquisition module can achieve, which is crucial for ensuring the rationality and effectiveness of the detection view points. By accurately obtaining these parameters, the component quality detection device of the present application can better plan the detection view points and ensure the comprehensiveness and accuracy of data acquisition.

[0127] In step S602 of some embodiments, generating multiple detection view point information corresponding to different detection view points based on the field of view acquisition parameters and the geometric feature information of the components.

[0128] It should be noted that next, based on the field of view acquisition parameters and the geometric feature information of the components, generate multiple detection view point information corresponding to different detection view points. This step is to calculate the three-dimensional coordinates and shooting angles of multiple detection view points by combining the field of view acquisition parameters and the geometric feature information of the components. The component quality detection device of the present application will consider factors such as the acquisition range, visible area of each view point, and avoiding mutual occlusion to ensure that all key parts can be comprehensively covered.

[0129] In some more specific embodiments, through optimization algorithms such as particle swarm optimization and genetic algorithms, the component quality detection device of the present application can generate multiple viewpoint coordinates to ensure the uniform distribution and comprehensive coverage of viewpoints, thereby improving the efficiency and comprehensiveness of overall detection.

[0130] Referring to Figure 7 , according to some embodiments of the present application, the geometric feature information of components includes key component feature information. Step S602 generates multiple detection viewpoint information corresponding to different detection viewpoints based on the field of view acquisition parameters and the geometric feature information of components, which may include:

[0131] Step S701, generating preliminary viewpoint information based on the field of view acquisition parameters and the geometric feature information of components;

[0132] Step S702, performing optimization calculation on the preliminary viewpoint information based on the key component feature information and a preset viewpoint distribution algorithm to obtain multiple detection viewpoint information corresponding to different detection viewpoints.

[0133] In step S701 of some embodiments, preliminary viewpoint information is generated based on the field of view acquisition parameters and the geometric feature information of components;

[0134] It should be noted that first, preliminary viewpoint information is generated based on the field of view acquisition parameters and the geometric feature information of components. This step is to initially determine the viewpoints that can cover the key areas of components by combining parameters such as the field of view angle and depth of field of the data acquisition module, as well as the geometric feature information of components. The generation of preliminary viewpoint information provides the basic data for subsequent viewpoint optimization, ensuring the rationality and effectiveness of detection viewpoints.

[0135] In step S702 of some embodiments, optimization calculation is performed on the preliminary viewpoint information based on the key component feature information and a preset viewpoint distribution algorithm to obtain multiple detection viewpoint information corresponding to different detection viewpoints.

[0136] It should be noted that next, optimization calculation is performed on the preliminary viewpoint information based on the key component feature information and a preset viewpoint distribution algorithm to obtain multiple detection viewpoint information corresponding to different detection viewpoints. This step is to optimize the initially generated viewpoint information by using the feature information of key components and combining a preset viewpoint distribution algorithm. During the optimization process, the component quality detection device of the present application will consider factors such as the acquisition range, visible area of each viewpoint, and avoiding mutual occlusion to ensure that all key parts can be comprehensively covered. Through optimization algorithms such as particle swarm optimization and genetic algorithms, the component quality detection device of the present application can generate multiple viewpoint coordinates to ensure the uniform distribution and comprehensive coverage of viewpoints, thereby improving the efficiency and comprehensiveness of overall detection.

[0137] In step S404 of some embodiments, a motion path is generated based on multiple detection viewpoint information to obtain a data acquisition path.

[0138] It should be noted that after multiple detection viewpoint information is generated, the component quality detection device of the embodiments of the present application generates a motion path based on these viewpoint information to obtain a data acquisition path. This process involves converting the three-dimensional coordinates and shooting angles of the viewpoints into specific motion instructions of the motion mechanism.

[0139] In some more specific embodiments, the motion control module can be used to control motion mechanisms such as multi-joint robotic arms for data acquisition. When the motion mechanism is specifically a multi-joint robotic arm, the component quality detection device of the embodiments of the present application can use the inverse kinematics algorithm to solve the angles required for each joint to ensure that the end effector of the robotic arm can accurately reach the specified position. During the motion planning process, the component quality detection device of the embodiments of the present application also comprehensively considers limitations such as the maximum rotation range, motion speed, and acceleration of the joints to achieve efficient and smooth motion. This step ensures the automation and accuracy of the detection process, reduces manual intervention, and improves the detection efficiency.

[0140] Refer to Figure 8 According to some embodiments of the present application, step S404 of generating a motion path based on multiple detection viewpoint information to obtain a data acquisition path may include:

[0141] Step S801: Determine the viewpoint position information and viewpoint shooting angle information corresponding to each detection viewpoint according to multiple detection viewpoint information;

[0142] Step S802: Input the viewpoint position information and viewpoint shooting angle information corresponding to each detection viewpoint into a preset motion planning algorithm to obtain a data acquisition path.

[0143] In step S801 of some embodiments, determine the viewpoint position information and viewpoint shooting angle information corresponding to each detection viewpoint according to multiple detection viewpoint information;

[0144] It should be noted that first, according to multiple detection viewpoint information, determine the viewpoint position information and viewpoint shooting angle information corresponding to each detection viewpoint. This step is to parse the detection viewpoint information and extract the specific position and shooting angle of each viewpoint. Multiple detection viewpoint information needs to correspond to the motion path of the data acquisition module, and the viewpoint position information and viewpoint shooting angle information are the basic data for motion path generation. They determine the specific position and shooting direction of the data acquisition module in space. By accurately obtaining this information, the component quality detection device of the embodiments of the present application can provide an accurate reference for subsequent motion planning to ensure that the data acquisition module can comprehensively detect the components from multiple angles.

[0145] In step S802 of some embodiments, the viewpoint position information and the viewpoint shooting angle information corresponding to each detection viewpoint are input into a preset motion planning algorithm to obtain a data acquisition path.

[0146] It should be noted that next, the viewpoint position information and the viewpoint shooting angle information corresponding to each detection viewpoint are input into a preset motion planning algorithm to obtain a data acquisition path. This step takes the viewpoint position information and the viewpoint shooting angle information as inputs, and uses the preset motion planning algorithm to calculate the motion path of the data acquisition module. The motion planning algorithm comprehensively considers the motion of the motion mechanism in the data acquisition module. In some embodiments, when the motion mechanism is specifically a robotic arm, the data acquisition path can also be configured with restrictions such as the motion range, speed, and acceleration of the robotic arm to generate a data acquisition path that can cover all detection viewpoints. This data acquisition path not only ensures the comprehensiveness and accuracy of data acquisition, but also improves the automation level and efficiency of the detection process.

[0147] In step S405 of some embodiments, the movable data acquisition module is controlled according to the data acquisition path to perform data acquisition on the target component to obtain the measured parameters of the component;

[0148] It should be noted that subsequently, the component quality detection device according to the embodiments of the present application controls the movable data acquisition module to perform data acquisition on the target component according to the generated data acquisition path to obtain the measured parameters of the component.

[0149] In some embodiments, the data acquisition module includes a variety of sensors, such as 2D industrial cameras, 3D structured light cameras, laser scanners, etc. By following the data acquisition path to perform data acquisition on the target component, high-quality measured parameters of the component can be obtained. Based on this, the embodiments of the present application can also dynamically select the most suitable sensor combination according to the geometric characteristics and detection requirements of the component. This step realizes multi-viewpoint and high-precision data acquisition of the component, providing a basis for subsequent data processing and analysis.

[0150] In step S406 of some embodiments, quality detection is performed on the target component based on the measured parameters of the component to obtain quality detection result information.

[0151] It should be noted that finally, the component quality inspection device of the present application inspects the target component based on the measured parameters of the component to obtain quality inspection result information. This process involves processing and analyzing the collected data, including data splicing, fusion, and the application of detection algorithms. The component quality inspection device of the embodiment of the present application splices and fuses the data collected by the sensor through the image / point cloud processing module to form a complete component data model. Combining the geometric features parsed from the computer-aided design model and the detection algorithm, the component quality inspection device of the embodiment of the present application can accurately detect the geometric parameters of the component (such as dimensions, flatness, position, etc.) and potential surface defects, thereby providing high-precision inspection results. This step realizes the high-precision inspection of the component through data splicing, fusion, and analysis, ensuring the accuracy and reliability of the inspection result.

[0152] The embodiment of the present application shown in steps S401 to S406 realizes the omni-directional, high-precision, and automated inspection of components with complex geometric shapes through steps such as obtaining a computer-aided design model, parsing geometric features, generating inspection viewpoints, planning a motion path, controlling data acquisition, and performing quality inspection. The omni-directional, high-precision, and automated inspection of components with complex geometric shapes is realized. This method not only improves the comprehensiveness and accuracy of the inspection, but also significantly improves the inspection efficiency and the flexibility of the component quality inspection device of the embodiment of the present application.

[0153] Referring to Figure 9 , according to some embodiments of the present application, the movable data acquisition module includes a multi-joint robotic arm and a sensor probe disposed at the end of the multi-joint robotic arm. Step S405 controls the movable data acquisition module to collect data from the target component according to the data acquisition path to obtain the measured parameters of the component, which may include:

[0154] Step S901, input the data acquisition path into the robotic arm kinematic model for motion stroke calculation to determine the robotic arm motion stroke information matching the data acquisition path;

[0155] Step S902, based on the robotic arm motion stroke information, control the data acquisition module to collect data from the target component to obtain the measured parameters of the component.

[0156] In step S901 of some embodiments, input the data acquisition path into the robotic arm kinematic model for motion stroke calculation to determine the robotic arm motion stroke information matching the data acquisition path;

[0157] It should be noted that, first, the data acquisition path is input into the robotic arm kinematic model for motion stroke calculation to determine the robotic arm motion stroke information matching the data acquisition path. This step is to use the pre-generated data acquisition path as the input and calculate it using the kinematic model of the robotic arm, so as to obtain the specific motion stroke of the robotic arm when performing the data acquisition task. The robotic arm kinematic model will consider the structural parameters of the robotic arm, joint angle range, motion speed, acceleration and other limiting conditions to ensure that the generated motion stroke information not only conforms to the physical characteristics of the robotic arm, but also accurately covers all predetermined detection viewpoints. This process not only ensures that the robotic arm can accurately reach each detection viewpoint, but also optimizes the motion path and improves the detection efficiency.

[0158] In step S902 of some embodiments, based on the robotic arm motion stroke information, the data acquisition module is controlled to perform data acquisition on the target component to obtain the measured parameters of the component.

[0159] It should be noted that next, based on the robotic arm motion stroke information, the data acquisition module is controlled to perform data acquisition on the target component to obtain the measured parameters of the component. This step is to convert the robotic arm motion stroke information into specific control instructions, drive the multi-joint robotic arm to move along the predetermined path, and at the same time control the sensor probe set at the end of the robotic arm to perform data acquisition. The sensor probe will perform high-precision data acquisition on the target component from multiple angles according to the viewpoint position information and shooting angle information. The acquired data includes information such as the geometric shape, size, and surface defects of the component, and these data will be used as the basis for subsequent quality inspection. Through this process, the component quality inspection device of the embodiment of the present application can comprehensively and accurately obtain the measured parameters of the component, providing reliable data support for subsequent quality inspection.

[0160] The embodiment of the present application shown in steps S901 to S902 realizes the all-round, high-precision and automatic inspection of components with complex geometric shapes. This method not only improves the comprehensiveness and accuracy of the inspection, but also significantly improves the inspection efficiency and the flexibility of the component quality inspection device of the embodiment of the present application.

[0161] Refer to Figure 10 , according to some embodiments of the present application, step S406 performs quality inspection on the target component based on the measured parameters of the component to obtain quality inspection result information, which may include:

[0162] Step S1001, performing splicing and fusion processing on the measured parameters of the component collected from different detection viewpoints to generate a measured three-dimensional model matching the target component;

[0163] Step S1002: Perform geometric measurement and surface defect detection on the measured three-dimensional model to conduct quality inspection on the target component and obtain quality inspection result information.

[0164] In step S1001 of some embodiments, perform splicing and fusion processing on the measured parameters of the component collected from different detection viewpoints to generate a measured three-dimensional model that matches the target component.

[0165] It should be noted that, first, perform splicing and fusion processing on the measured parameters of the component collected from different detection viewpoints to generate a measured three-dimensional model that matches the target component. This step is to integrate the data collected from multiple detection viewpoints and use the splicing and fusion algorithm to register and fuse the data from different perspectives to generate a complete three-dimensional model. This process not only ensures the integrity and consistency of the data but also provides an accurate data basis for subsequent geometric measurement and surface defect detection. Through the splicing and fusion processing, the component quality inspection device of the embodiments of the present application can comprehensively reflect the geometric shape and surface characteristics of the component and provide reliable data support for quality inspection.

[0166] In step S1002 of some embodiments, perform geometric measurement and surface defect detection on the measured three-dimensional model to conduct quality inspection on the target component and obtain quality inspection result information.

[0167] It should be noted that next, perform geometric measurement and surface defect detection on the measured three-dimensional model to conduct quality inspection on the target component and obtain quality inspection result information. This step is to precisely analyze the measured three-dimensional model by using geometric measurement algorithms and surface defect detection algorithms. Geometric measurement includes measuring parameters such as the size, flatness, and position of the component to ensure that the geometric dimensions of the component meet the design requirements. Surface defect detection is to identify possible defects, such as cracks, pits, and scratches, by analyzing the surface characteristics of the measured three-dimensional model. Through these detections, the component quality inspection device of the embodiments of the present application can comprehensively evaluate the quality of the component, generate detailed quality inspection result information, and provide a basis for subsequent production decisions.

[0168] Refer to Figure 11 , Figure 11 schematically shows the hardware structure of an electronic device in another embodiment. The electronic device includes:

[0169] The processor 1101 can be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0170] The memory 1102 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 1102 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1102 and are called by the processor 1101 to execute the component quality detection method of the embodiments of the present application;

[0171] The input / output interface 1103 is used to implement information input and output;

[0172] The communication interface 1104 is used to implement communication interaction between this device and other devices, and can implement communication through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WI FI, Bluetooth, etc.);

[0173] The bus 1105 transmits information between various components of the device (such as the processor 1101, the memory 1102, the input / output interface 1103, and the communication interface 1104);

[0174] Among them, the processor 1101, the memory 1102, the input / output interface 1103, and the communication interface 1104 are communicatively connected to each other inside the device through the bus 1105.

[0175] The embodiments of the present application also provide a computer program product, which includes a computer program. The processor of the computer device reads and executes this computer program, so that the computer device executes to implement the above-mentioned component quality detection method.

[0176] The terms "first", "second", "third", "fourth", etc. (if any) in the description of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "including" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily limit to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0177] It should be understood that in the present disclosure, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally means that the associated objects before and after are in an "or" relationship. "At least one (one) of the following" or a similar expression means any combination of these items, which can include any combination of single item (one) or plural items (ones). For example, at least one (one) of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0178] It should be understood that in the description of the embodiments of the present application, the meaning of "a plurality (or multiple items)" is more than two. Understandings such as greater than, less than, exceeding, etc. do not include the present number, and understandings such as above, below, within, etc. include the present number.

[0179] In several embodiments provided by the present disclosure, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of devices or units can be in electrical, mechanical or other forms.

[0180] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0181] In addition, in each embodiment of the present disclosure, each functional unit may be integrated in a processing unit, may exist separately as individual physical units, or two or more units may be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0182] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present disclosure, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and may include several instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of each embodiment of the present disclosure. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0183] It should also be understood that the various embodiments provided in this application can be combined arbitrarily to achieve different technical effects.

[0184] The above is a specific description of the embodiments of the present disclosure, but the present disclosure is not limited to the above embodiments. Those skilled in the art can also make various equivalent deformations or substitutions without departing from the spirit of the present disclosure, and these equivalent deformations or substitutions are all included within the scope defined by the claims of the present disclosure.

Claims

1. A method for detecting the quality of parts, characterized in that, Applied to a component quality inspection device, the component quality inspection device is provided with a movable data acquisition module, including: Obtain the computer-aided design model corresponding to the target component; Based on the computer-aided design model, perform geometric feature analysis on the target component to obtain component geometric feature information; According to the component geometric feature information, generate multiple detection view point information corresponding to different detection view points; Based on the multiple detection view point information, generate a motion path to obtain a data acquisition path; According to the data acquisition path, control the movable data acquisition module to perform data acquisition on the target component to obtain measured component parameters; Based on the measured component parameters, perform quality inspection on the target component to obtain quality inspection result information.

2. The method according to claim 1, characterized in that, The performing geometric feature analysis on the target component based on the computer-aided design model to obtain component geometric feature information includes: Based on the computer-aided design model, determine the parametric equations of the reference holes and the parametric equations of the reference planes in the target component; According to the parametric equations of the reference holes and the parametric equations of the reference planes, determine the spatial description coordinate system; Based on the spatial description coordinate system, perform parametric representation on each component model in the computer-aided design model to obtain the component geometric feature information matching the target component.

3. The method according to claim 1, characterized in that, The generating multiple detection view point information corresponding to different detection view points according to the component geometric feature information includes: Obtain the field-of-view acquisition parameters corresponding to the data acquisition module; Based on the field-of-view acquisition parameters and the component geometric feature information, generate multiple detection view point information corresponding to different detection view points.

4. The method according to claim 3, wherein The component geometric feature information includes key component feature information. The generating multiple detection view point information corresponding to different detection view points based on the field-of-view acquisition parameters and the component geometric feature information includes: Based on the field-of-view acquisition parameters and the component geometric feature information, generate preliminary view point information; Based on the key component feature information and a preset view point distribution algorithm, perform optimization calculation on the preliminary view point information to obtain multiple detection view point information corresponding to different detection view points.

5. The method according to claim 1, characterized in that, The generating a motion path based on the multiple detection view point information to obtain a data acquisition path includes: According to the multiple detection view point information, determine the view point position information and the view point shooting angle information corresponding to each detection view point; Input the view point position information and the view point shooting angle information corresponding to each detection view point into a preset motion planning algorithm to obtain the data acquisition path.

6. The method according to claim 1, wherein The movable data acquisition module includes a multi-joint robotic arm and a sensor probe arranged at the end of the multi-joint robotic arm. The controlling the movable data acquisition module to perform data acquisition on the target component according to the data acquisition path to obtain measured component parameters includes: Input the data acquisition path into a robotic arm kinematic model for motion stroke calculation to determine the robotic arm motion stroke information matching the data acquisition path; Based on the motion stroke information of the robotic arm, control the data acquisition module to perform data acquisition on the target component to obtain the measured parameters of the component.

7. The method according to claim 1, wherein Perform quality inspection on the target component based on the measured parameters of the component to obtain quality inspection result information, including: Perform splicing and fusion processing on the measured parameters of the component collected from different inspection viewpoints to generate a measured three-dimensional model matching the target component; Perform geometric measurement and surface defect detection on the measured three-dimensional model to perform quality inspection on the target component to obtain the quality inspection result information.

8. A component quality inspection device, characterized in that, The component quality inspection device is provided with a movable data acquisition module, and the component quality inspection device includes: A component model acquisition module for acquiring a computer-aided design model corresponding to the target component; A geometric feature analysis module for performing geometric feature analysis on the target component based on the computer-aided design model to obtain component geometric feature information; An inspection viewpoint generation module for generating a plurality of inspection viewpoint information corresponding to different inspection viewpoints according to the component geometric feature information; An acquisition path generation module for generating a motion path based on the plurality of inspection viewpoint information to obtain a data acquisition path; A motion control module for controlling the movable data acquisition module to perform data acquisition on the target component according to the data acquisition path to obtain the measured parameters of the component; A quality inspection module for performing quality inspection on the target component based on the measured parameters of the component to obtain quality inspection result information.

9. An electronic device, characterized in that, Including: A memory and a processor, the memory stores a computer program, and when the processor executes the computer program, it implements the component quality inspection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a program, and when the program is executed by the processor, it implements the component quality inspection method according to any one of claims 1 to 7.

Images