Automatic detection method, device and equipment and storage medium

Abstract

The invention belongs to the technical field of vehicle design, and discloses an automatic detection method, device and equipment and a storage medium. The coating vehicle structure is constructed according to the vehicle assembly data; carrying out discrete treatment on a gluing line in the coated vehicle structure to obtain a plurality of gluing discrete points, and carrying out discrete treatment on a sheet body boundary in the coated vehicle structure to obtain a plurality of boundary discrete points; matching the gluing discrete points with the boundary discrete points to generate gluing boundary data; and carrying out qualification detection on each assembled vehicle part according to the gluing boundary data. Due to the fact that point discretization and other processing are adopted, original gluing lines are converted into discrete points to be associated with boundary points of pictures contained in components through matching, complex analysis between lines is converted into key detection between points, complex problems are simplified, and it is guaranteed that elements can be automatically detected.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle design, and in particular to an automatic detection method, device, equipment and storage medium. Background Art

[0002] In the simultaneous painting engineering of vehicles (the engineering that involves the painting process in the design and development and is carried out simultaneously with the vehicle development process), the inspection of key components (important components in the vehicle) is an important part of the process design. However, the current inspection of key components is generally carried out by manually comparing the design documents. The inspection effect is limited by the professionalism of the inspectors, and the inspection cost is high and time-consuming. Summary of the invention

[0003] The main purpose of the present invention is to provide an automatic detection method, device, equipment and storage medium, aiming to solve the technical problems of high cost and long time consumption of key inspection in the existing painting synchronization project.

[0004] To achieve the above object, the present invention provides an automatic detection method, which comprises the following steps:

[0005] Constructing a painted vehicle structure according to the vehicle assembly data, wherein the painted vehicle structure includes a glue coating line and a sheet boundary of a sheet included in each vehicle component;

[0006] Discrete the glue coating lines in the painted vehicle structure to obtain a plurality of glue coating discrete points, and discretize the sheet boundaries in the painted vehicle structure to obtain a plurality of boundary discrete points;

[0007] Matching the glue coating discrete points with the boundary discrete points to generate glue coating boundary data, wherein the glue coating boundary data stores the glue coating discrete points and the boundary discrete points corresponding to the glue coating discrete points;

[0008] The conformity of each assembled vehicle component is tested according to the glue coating boundary data.

[0009] Optionally, constructing a painted vehicle structure according to vehicle assembly data includes:

[0010] Detecting whether there is gluing assembly data in the vehicle assembly data;

[0011] If the gluing assembly data exists, extracting the gluing assembly data from the vehicle assembly data, and obtaining the gluing identification of each gluing assembly data;

[0012] Matching the gluing identification of each gluing assembly data with the gluing identification corresponding to each gluing design data in the gluing design document to determine the gluing design data corresponding to each gluing assembly data;

[0013] Generate glue coating line data according to the glue coating assembly data and the glue coating design data corresponding to each glue coating assembly data;

[0014] A painted vehicle structure is constructed according to the vehicle assembly data and the glue coating line data.

[0015] Optionally, after detecting whether there is glue coating assembly data in the vehicle assembly data, the method further includes:

[0016] If the glue coating assembly data does not exist, the glue coating design data is extracted from the glue coating design document;

[0017] Obtain vehicle component identification corresponding to each gluing design data;

[0018] Constructing glue coating line data according to the vehicle component identification and the glue coating design data;

[0019] A painted vehicle structure is constructed according to the vehicle assembly data and the glue coating line data.

[0020] Optionally, the performing of a conformity test on each assembled vehicle component according to the glue coating boundary data includes:

[0021] Extracting target glue coating discrete points and target boundary discrete points corresponding to the target glue coating discrete points from the glue coating boundary data;

[0022] Draw rays according to the target glue coating discrete points and the target boundary discrete points;

[0023] Obtaining a collision point corresponding to the ray, wherein the collision point is an intersection point between the ray and a sheet member included in the vehicle component;

[0024] Setting a corresponding feature type for a target glue coating discrete point in the glue coating boundary data according to the collision point;

[0025] The conformity of each assembled vehicle component is tested according to the glue coating boundary data and the feature type corresponding to each glue coating discrete point in the glue coating boundary data.

[0026] Optionally, setting a corresponding feature type for a target glue coating discrete point in the glue coating boundary data according to the collision point includes:

[0027] Acquire collision judgment data corresponding to the collision point, wherein the collision judgment data includes at least one of the number of sheet metal parts penetrated by the collision point, the first penetration surface attribute of the collision point, the height of the collision point relative to the glue coating line, the boundary change position of the collision point, and the curvature change position of the collision point;

[0028] A corresponding feature type is set for the target glue coating discrete point in the glue coating boundary data according to the collision judgment data.

[0029] Optionally, the obtaining collision judgment data corresponding to the collision point includes:

[0030] Obtaining the glue coating line type of the glue coating line to which the target glue coating discrete point belongs;

[0031] Determining a collision judgment index according to the type of the glue coating line;

[0032] Collision judgment data corresponding to the collision point is obtained based on the collision judgment index.

[0033] Optionally, the performing of qualification inspection on each assembled vehicle component according to the glue coating boundary data and the feature type corresponding to each glue coating discrete point in the glue coating boundary data includes:

[0034] Obtain the glue line type of the glue line to which each glue discrete point in the glue boundary data belongs;

[0035] Searching in the detection rule library according to the glue coating line type, determining the detection rule corresponding to each glue coating discrete point set in the glue coating boundary data;

[0036] Based on the detection rules and the glue coating boundary data, each assembled vehicle component is tested for its conformity.

[0037] In addition, to achieve the above object, the present invention also provides an automatic detection device, the automatic detection device comprising:

[0038] A construction module, used to construct a painted vehicle structure according to the vehicle assembly data, wherein the painted vehicle structure includes a glue coating line and a sheet boundary of a sheet included in each vehicle component;

[0039] A discrete module is used to discretize the glue coating lines in the painted vehicle structure to obtain a plurality of discrete glue coating points, and to discretize the sheet boundaries in the painted vehicle structure to obtain a plurality of discrete boundary points;

[0040] A matching module, used for matching the glue coating discrete points with the boundary discrete points to generate glue coating boundary data, wherein the glue coating boundary data stores the glue coating discrete points and the boundary discrete points corresponding to the glue coating discrete points;

[0041] The detection module is used to perform a conformity detection on each assembled vehicle component according to the glue coating boundary data.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also proposes an automatic detection device, which includes: a processor, a memory, and an automatic detection program stored in the memory and executable on the processor, and the automatic detection program implements the steps of the automatic detection method described above when executed by the processor.

[0043] In addition, to achieve the above-mentioned purpose, the present invention further proposes a computer-readable storage medium, on which an automatic detection program is stored, and when the automatic detection program is executed, the steps of the automatic detection method described above are implemented.

[0044] The present invention constructs a painted vehicle structure according to vehicle assembly data; discretizes the glue lines in the painted vehicle structure to obtain a plurality of glue discrete points, and discretizes the sheet boundaries in the painted vehicle structure to obtain a plurality of boundary discrete points; matches the glue discrete points with the boundary discrete points to generate glue boundary data; and performs qualification inspection on each assembled vehicle component according to the glue boundary data. Due to point discretization and other processing, and through matching, the original glue lines are converted into discrete points and associated with the boundary points of the pictures contained in the parts, and the complex analysis between lines is converted into key points between points for detection, which simplifies complex problems and ensures that automatic detection can be performed on the requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of the structure of an electronic device in a hardware operating environment involved in an embodiment of the present invention;

[0046] Figure 2 It is a flowchart of the first embodiment of the automatic detection method of the present invention;

[0047] Figure 3 It is a flow chart of the second embodiment of the automatic detection method of the present invention;

[0048] Figure 4 It is a flowchart of a third embodiment of the automatic detection method of the present invention;

[0049] Figure 5 A schematic diagram of an automatic detection execution flow according to an embodiment of the present invention;

[0050] Figure 6 A schematic diagram of a process for constructing glue coating boundary data according to an embodiment of the present invention;

[0051] Figure 7 A schematic diagram of a feature type determination process according to an embodiment of the present invention;

[0052] Figure 8 A schematic diagram of discrete point generation according to an embodiment of the present invention;

[0053] Fig. 9 A schematic diagram of discrete point matching according to an embodiment of the present invention;

[0054] Fig.10 It is a structural block diagram of the first embodiment of the automatic detection device of the present invention.

[0055] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0056] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0057] Reference Figure 1 , Figure 1 The figure is a schematic diagram of the structure of the automatic detection device of the hardware operating environment involved in the embodiment of the present invention.

[0058] like Figure 1 As shown, the electronic device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0059] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0060] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and an automatic detection program.

[0061] exist Figure 1In the electronic device shown, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the electronic device of the present invention can be set in an automatic detection device, and the electronic device calls the automatic detection program stored in the memory 1005 through the processor 1001, and executes the automatic detection method provided by an embodiment of the present invention.

[0062] The embodiment of the present invention provides an automatic detection method, referring to Figure 2 , Figure 2 The figure is a flow chart of a first embodiment of an automatic detection method of the present invention.

[0063] In this embodiment, the automatic detection method includes the following steps:

[0064] Step S10: constructing a painted vehicle structure according to the vehicle assembly data.

[0065] It should be noted that the executor of this embodiment can be the automatic detection device, and the automatic detection device can be an electronic device such as a personal computer or a server, or other devices that can achieve the same or similar functions. This embodiment does not limit this. In this embodiment and the following embodiments, the automatic detection method of the present invention is described by taking the automatic detection device as an example.

[0066] It should be noted that the vehicle assembly data may be data related to vehicle assembly designed during the simultaneous painting process, and may include data on various vehicle components, internal structures of components (such as sheets included in the components, and data such as the structure and contour of the sheets), gluing line installation data, etc. The painted vehicle structure includes the gluing line and the sheet boundaries of the sheets included in each vehicle component, wherein the gluing line may be a portion or area that needs to be glued when connecting or closing each vehicle component in the vehicle painting process; the sheet boundary of the sheet may be relevant data used to characterize the contour of the sheet.

[0067] In actual use, in order to facilitate subsequent processing and to be able to present it to relevant designers or managers when necessary, modeling can be performed in 3D modeling software (such as NX (Next Generation) platform) based on vehicle assembly data to obtain the painted vehicle structure.

[0068] Step S20: discretizing the glue coating lines in the painted vehicle structure to obtain a plurality of glue coating discrete points, and discretizing the sheet boundaries in the painted vehicle structure to obtain a plurality of boundary discrete points.

[0069] It should be noted that the glue coating line involves too many areas, and direct detection is highly complex and difficult to achieve. In order to ensure automatic detection, its complexity needs to be reduced. Therefore, the glue coating line can be discretized and divided into multiple discrete glue coating points, and the sheet boundary can be discretized and divided into multiple discrete boundary points. This ensures that the analysis of complex lines or areas can be converted into point-to-point analysis, thereby simplifying complex problems and reducing their complexity, which facilitates automatic detection.

[0070] In actual use, the glue coating line in the painted vehicle structure can be discretized into a plurality of glue coating discrete points at intervals of the first preset length, and the sheet boundary in the painted vehicle structure can be discretized into a plurality of boundary discrete points at intervals of the second preset length. The first preset length and the second preset length can both be pre-set by the manager of the automatic detection equipment, and the first preset length and the second preset length can be the same or different.

[0071] For example: assuming that the first preset length and the second preset length are both set to 1mm, the glue lines in the painted vehicle structure can be discretely divided into multiple glue discrete points at intervals of 1mm, and the sheet boundaries in the painted vehicle structure can be discretely divided into multiple boundary discrete points at intervals of 1mm.

[0072] Step S30: matching the glue coating discrete points with the boundary discrete points to generate glue coating boundary data.

[0073] It should be noted that the glue coating boundary data stores the glue coating discrete points and the boundary discrete points corresponding to each glue coating discrete point.

[0074] In actual use, the glue coating discrete points can be matched with each boundary discrete point to determine the boundary discrete points corresponding to each glue coating discrete point, and then the glue coating boundary data can be constructed based on the glue coating discrete points and the boundary discrete points corresponding to each glue coating discrete point.

[0075] Among them, when matching the glue-coated discrete points with each boundary discrete point, the nearest neighbor search matching can be used, and the boundary discrete points whose distance between the glue-coated discrete point and the glue-coated discrete point is less than the preset search length are used as the boundary discrete points corresponding to the glue-coated discrete point. The preset search length can be pre-set by the manager of the automatic detection equipment; when performing the nearest neighbor search, relevant tools or software can be used, such as using the nearest neighbor search function of the PCL point cloud library for nearest neighbor search matching.

[0076] For example: Assuming that the preset search length is set to 1mm, then for each discrete glue point, the neighbor search function of the PCL point cloud library can be used to perform neighbor search and matching at 1mm to obtain the boundary discrete points corresponding to each discrete glue point.

[0077] Step S40: performing a conformity test on each assembled vehicle component according to the glue coating boundary data.

[0078] It should be noted that the glue coating boundary data may include glue coating discrete points and boundary discrete points corresponding to each glue coating discrete point, and the glue coating discrete points belong to a specific glue coating line, and the boundary discrete points belong to a sheet in a specific vehicle component. At this time, the specific relationship between the corresponding glue coating line and the sheet can be determined based on the glue coating discrete points in the glue coating boundary data and the boundary discrete points corresponding to each glue coating discrete point. At this time, it can be compared with the glue coating requirements of each vehicle component during design to determine whether the coating process of the vehicle component is qualified, thereby ensuring that automatic qualification testing can be performed.

[0079] Among them, the gluing requirements may be set using natural language, and it may be difficult to directly compare based on the gluing requirements. In order to ensure the efficiency and accuracy of the inspection, the management personnel of the automatic inspection equipment can also set corresponding inspection rules according to the gluing requirements of each vehicle component, and perform qualification inspection on the assembled vehicle components based on the inspection rules and gluing boundary data.

[0080] This embodiment constructs a painted vehicle structure according to vehicle assembly data; discretizes the glue lines in the painted vehicle structure to obtain multiple glue discrete points, and discretizes the sheet boundaries in the painted vehicle structure to obtain multiple boundary discrete points; matches the glue discrete points with the boundary discrete points to generate glue boundary data; and performs qualification inspection on each assembled vehicle component according to the glue boundary data. Due to point discretization and other processing, and through matching, the original glue lines are converted into discrete points and associated with the boundary points of the pictures contained in the parts, and the complex analysis between lines is converted into key points between points for detection, which simplifies complex problems and ensures that automatic detection can be performed on the requirements.

[0081] refer to Figure 3 , Figure 3 It is a flow chart of a second embodiment of an automatic detection method of the present invention.

[0082] Based on the first embodiment, step S10 of the automatic detection method of this embodiment includes:

[0083] Step S101: Detect whether there is glue coating assembly data in the vehicle assembly data.

[0084] It should be noted that in the simultaneous painting engineering work of the vehicle, the assembly design and painting design of the vehicle may be separated and performed by different departments or personnel. At this time, the corresponding gluing assembly data may not exist in the vehicle assembly data. If the painted vehicle structure is directly constructed based on the vehicle assembly data without detection, the gluing line may be missing in the painted vehicle structure. In order to avoid this phenomenon, the vehicle assembly data can be detected first to determine whether it contains gluing assembly data, where the gluing assembly data can be data related to the gluing line during the assembly process.

[0085] In actual use, the gluing assembly data may be stored through specific attributes. Therefore, detecting whether the vehicle assembly data contains the gluing assembly data can be performed by detecting whether the vehicle assembly data contains a specific attribute field and whether the data corresponding to the attribute field is empty to determine whether the vehicle assembly data contains the gluing assembly data.

[0086] For example: assuming that the gluing assembly data is stored in the attribute field "P_NAME", then it can be detected whether the attribute field "P_NAME" exists in the vehicle assembly data. If the attribute field does not exist, it is determined that the gluing assembly data does not exist in the vehicle assembly data; if the attribute field exists, but the data corresponding to the attribute field is empty, it can still be determined that the gluing assembly data does not exist in the vehicle assembly data; if the attribute field exists and the data corresponding to the attribute field is not empty, then it can be determined that the gluing assembly data exists in the vehicle assembly data.

[0087] Step S102: if the gluing assembly data exists, extracting the gluing assembly data from the vehicle assembly data, and obtaining the gluing identification of each gluing assembly data.

[0088] It should be noted that even if there is glue coating assembly data in the vehicle assembly data, the glue coating assembly data contained in the vehicle assembly data may be relatively simple data, and may only contain partial information. Directly combining this with the vehicle assembly data to construct a painted vehicle structure may result in incomplete properties of the glue coating lines in the painted vehicle structure, which may affect subsequent automatic detection. In order to avoid this phenomenon, it is necessary to obtain data related to the completed glue coating line. Therefore, the glue coating mark of the glue coating assembly data can be obtained.

[0089] In a specific implementation, there are generally specific naming rules for the naming of glue-coated assembly data. For example, the data naming of glue-coated assembly data needs to contain specific keywords, or start or end with specific keywords. Therefore, in order to avoid the impact caused by incorrect data storage, before obtaining the gluing identification of each glue-coated assembly data, the data name of each glue-coated assembly data can be first subjected to keyword detection. Only when the keyword detection passes, the gluing identification of each glue-coated assembly data can be obtained. Among them, the gluing identification of the glue-coated assembly data can be the data name of the glue-coated assembly data, or it can be a unique identification that is unrelated to the data name.

[0090] For example: assuming that the data naming of the gluing assembly data needs to contain the specific keyword "SEAL", then you can first check whether the name of the gluing assembly data contains the keyword "SEAL". If it does, get the gluing identifier of the gluing assembly data; if not, determine that the gluing assembly data is not data related to the gluing line.

[0091] Step S103: matching the gluing marks of each gluing assembly data with the gluing marks corresponding to each gluing design data in the gluing design document, and determining the gluing design data corresponding to each gluing assembly data.

[0092] It should be noted that the gluing design document can be a document used by designers to record gluing line related data during painting design. The gluing design document can include gluing design data for each gluing line. The gluing design data can at least include data such as related vehicle parts, gluing methods, and gluing functions.

[0093] In actual use, if the gluing mark of the gluing assembly data is consistent with the gluing mark corresponding to the gluing design data in the gluing design document, it means that the gluing line corresponding to the gluing assembly data and the gluing design data is the same. Therefore, the gluing design data can be used as the gluing design data corresponding to the gluing assembly data.

[0094] Step S104: generating glue coating line data according to the glue coating assembly data and the glue coating design data corresponding to each glue coating assembly data.

[0095] In actual use, the gluing assembly data and the gluing design data corresponding to each gluing assembly data can be assembled in a preset data format to generate the gluing line data. The preset data format can be pre-set by the manager of the automatic testing equipment.

[0096] Step S105: constructing a painted vehicle structure according to the vehicle assembly data and the glue coating line data.

[0097] It can be understood that after obtaining the vehicle assembly data and the gluing line data, the vehicle components can be constructed in the three-dimensional modeling software according to the vehicle assembly data, and the constructed components can be assembled to obtain the vehicle structure. Afterwards, the position of each gluing line in the vehicle structure is determined according to the gluing assembly data in the gluing line data, and the gluing lines are set in the vehicle structure according to the gluing design data in the gluing line data, thereby obtaining the painted vehicle structure.

[0098] In a specific implementation, in order to ensure that the painted vehicle structure can still be constructed when the vehicle assembly data does not contain the painting assembly data, after step S101 described in this embodiment, the following may also be included:

[0099] If the glue coating assembly data does not exist, the glue coating design data is extracted from the glue coating design document;

[0100] Obtain vehicle component identification corresponding to each gluing design data;

[0101] Constructing glue coating line data according to the vehicle component identification and the glue coating design data;

[0102] A painted vehicle structure is constructed according to the vehicle assembly data and the glue coating line data.

[0103] It should be noted that if the vehicle assembly data does not include painting assembly data, then the gluing design data can be extracted from the gluing design document first, and then the related vehicle parts in the gluing design data can be read to obtain the vehicle part identification corresponding to each gluing design data. Thereafter, the vehicle part identification and the gluing design data can be assembled into gluing line data in a preset data format. Finally, the vehicle parts can be constructed in the three-dimensional modeling software according to the vehicle assembly data, and the constructed parts can be assembled to obtain the vehicle structure. Afterwards, the position of each gluing line can be determined by the vehicle part identification in the gluing line data, and the gluing lines can be set in the vehicle structure according to the gluing design data in the gluing line data, thereby obtaining the painted vehicle structure.

[0104] This embodiment will first detect whether there is glue assembly data in the vehicle assembly data, and construct the painted vehicle structure in different ways according to the detection results to ensure that the generated painted vehicle structure can correctly include the glue coating line and the sheet structure of the vehicle parts.

[0105] refer to Figure 4 , Figure 4 It is a flow chart of a third embodiment of an automatic detection method of the present invention.

[0106] Based on the first embodiment above, step S40 of the automatic detection method of this embodiment includes:

[0107] Step S401: extracting target glue coating discrete points and target boundary discrete points corresponding to the target glue coating discrete points from the glue coating boundary data.

[0108] It should be noted that extracting the target glue discrete points from the glue boundary data may be to use the glue discrete points included in the glue boundary data as the target glue discrete points, or to use some of the glue discrete points included in the glue boundary data as the target glue discrete points, for example: to use the last glue discrete point and the first glue discrete point on each glue line as the target glue discrete point. The target boundary discrete point corresponding to the target glue discrete point may be a boundary discrete point that has been successfully matched with the target glue discrete point during the previous matching.

[0109] Step S402: Draw rays according to the target glue coating discrete points and the target boundary discrete points.

[0110] It should be noted that the rays may include forward rays and / or reverse rays.

[0111] In actual use, the target glue coating discrete point can be used as the ray starting point, and the target boundary discrete point can be used as the ray positive direction as the forward ray. The reverse ray can be a ray with the same ray starting point as the forward ray but with a related direction.

[0112] Step S403: Obtain the collision point corresponding to the ray.

[0113] It should be noted that the collision point corresponding to the ray may be the intersection between the ray and the sheet material included in the vehicle component, wherein the sheet material included in the vehicle component may be a sheet body included in the vehicle component, or a partial sheet body with specific properties in the sheet body included in the vehicle component.

[0114] Step S404: setting a corresponding feature type for the target glue coating discrete point in the glue coating boundary data according to the collision point.

[0115] It should be noted that the feature type may be feature classification data used to characterize the position of the target discrete glue coating point on the glue coating line.

[0116] In a specific implementation, in order to ensure that the feature type can be reasonably set, step S404 in this embodiment may include:

[0117] Acquiring collision judgment data corresponding to the collision point;

[0118] A corresponding feature type is set for the target glue coating discrete point in the glue coating boundary data according to the collision judgment data.

[0119] It should be noted that the collision judgment data may include at least one of the number of sheet metal parts penetrated by the collision point, the first penetration surface attribute of the collision point, the height of the collision point relative to the glue coating line, the boundary change position of the collision point, and the curvature change position of the collision point.

[0120] In a specific implementation, single-point features can also be combined with local features, key points can be extracted from collision points based on collision judgment data, and then corresponding feature types can be set for target glue discrete points in the glue boundary data based on the features of the key points.

[0121] Among them, single-point features may include: three-dimensional coordinates (X, Y, Z), normals (Nx, Ny, Nz), principal curvatures (PCx, PCy, PCz), etc.; local features may include: line features and structural features; ordered point cloud: the serial number of each point, positive and negative information; ray collision point: each point penetrating the sheet metal information.

[0122] In actual use, the key point extraction method may include one or more of the following:

[0123] A. Extract the first point and the last point as key points;

[0124] B. Determine the normal angle according to the sequence of collision points from small to large, and extract the corner key points through the angle change;

[0125] C. According to the curvature of the point on the surface, determine the R angle, and extract the key points when R is less than 10;

[0126] D. Extract the number of penetrating sheet metal parts at the launch point at the starting point as the key point.

[0127] Of course, the method of selecting key points may include more methods, which may be pre-set by the manager of the automatic detection equipment, and this embodiment does not limit this.

[0128] To facilitate understanding of the setting of feature types, an example is given. If the key point meets the following conditions, the feature type is set to the first type: a. The first point position penetrates two sheet metal parts; b. There is a small R feature point at the forward emission point, and the R normal is opposite to the normal of the glue detection point;

[0129] If the key point meets the following conditions, the feature type is set to the second category: a. The first point position penetrates two sheet metal parts; b. There is a small R feature point at the forward emission point, and the R normal is the same as the normal of the glue coating detection point; There is an approximate plane feature point at the cR corner feature point.

[0130] The above conditions that need to be met when determining the two types of features are only illustrative and not specific. The specific number of feature types and the conditions that need to be met when determining the feature types can be set in advance by the manager of the automatic detection equipment.

[0131] It should be noted that when judging different types of glue coating lines, the data required for judgment may also be different. In order to ensure that the collision judgment data can be reasonably obtained, the step of obtaining the collision judgment data corresponding to the collision point in this embodiment may include:

[0132] Obtaining the glue coating line type of the glue coating line to which the target glue coating discrete point belongs;

[0133] Determining a collision judgment index according to the type of the glue coating line;

[0134] Collision judgment data corresponding to the collision point is obtained based on the collision judgment index.

[0135] It should be noted that the glue coating line type may be type data used to characterize the classification of the glue coating line; the glue coating line to which the target glue coating discrete point belongs may be the glue coating line where the target glue coating discrete point is located.

[0136] In actual use, determining the collision judgment index according to the type of glue coating line can be done by searching the collision judgment index corresponding to the glue coating line type in the type indicator mapping table. The type indicator mapping table can store the correspondence between the glue coating line type and the collision judgment index, which can be pre-set by the manager of the automatic detection equipment.

[0137] In a specific implementation, acquiring the collision judgment data corresponding to the collision point based on the collision judgment index may be acquiring data corresponding to the collision judgment index at the collision point, thereby obtaining the collision judgment data corresponding to the collision point.

[0138] Step S405: performing a conformity test on each assembled vehicle component according to the glue coating boundary data and the feature type corresponding to each glue coating discrete point in the glue coating boundary data.

[0139] It should be noted that after obtaining the glue boundary data and the feature type corresponding to each discrete glue point in the glue boundary data, the relevant characteristics of the position of each discrete glue point on the glue line can be determined according to the feature type. Based on this concrete feature type data, it is combined with the inspection rules set by the management personnel of the automatic inspection equipment to ensure that the assembled vehicle parts can be quickly inspected for conformity.

[0140] In a specific implementation, in order to ensure that the qualification test can be performed reasonably, step S405 in this embodiment may include:

[0141] Obtain the glue line type of the glue line to which each glue discrete point in the glue boundary data belongs;

[0142] Searching in the detection rule library according to the glue coating line type, determining the detection rule corresponding to each glue coating discrete point set in the glue coating boundary data;

[0143] Based on the detection rules and the glue coating boundary data, each assembled vehicle component is tested for its conformity.

[0144] It should be noted that different types of glue coating lines may play different roles in the coating process. In order to ensure that the detection can be carried out reasonably, the glue coating line type of each glue coating discrete point in the glue coating boundary data can be obtained first, and then the detection rule library is searched for the detection rule required for reasonable detection of each glue coating discrete point set in the glue coating boundary data according to the glue coating line type. Then, the glue coating boundary data is detected according to the detection rules to determine whether the assembled vehicle components are qualified.

[0145] The glue line type may be type data used to characterize the classification of glue lines; the glue line to which the glue discrete point belongs may be the glue line where the glue discrete point is located. The detection rule library may store detection rules pre-set by the automatic detection device according to design requirements.

[0146] For ease of understanding, now combined Figure 5 , 6 , 7, 8 and 9 are used to illustrate but not to limit this solution. Figure 5 This is a schematic diagram of the automatic detection execution flow of this embodiment. Figure 6 This is a schematic diagram of the process of constructing the glued boundary data in this embodiment. Figure 7 Schematic diagram of the feature type determination process of this embodiment. Figure 8 This is a schematic diagram of discrete point generation in this embodiment. Fig. 9 Schematic diagram of discrete point matching in this embodiment.

[0147] like Figure 5 As shown, the gluing line can be searched for the assembly data structure (i.e., vehicle assembly data) to determine whether the relevant data of the gluing line (i.e., gluing assembly data) has been set therein. If the relevant data of the gluing line has not been set, the attribute value is read from the NOTE data structure (i.e., the gluing design document) and stored in the gluing line data structure (i.e., the gluing line data);

[0148] If the relevant data of the glue coating line has been set, the assembly data structure can be traversed first to determine whether it contains the attribute field "P_NAME". If it does, it means that there is a glue coating line. At this time, whether the glue coating assembly data is the glue coating line related data can be determined based on whether the name contains the keyword "SEAL". If it does not contain the keyword, it is determined that it is not a glue coating line;

[0149] If the name keyword exists, the gluing identifier of the gluing assembly data is searched in the NOTE data structure (i.e., the gluing design document), and matched with the gluing identifier "A_NAME" of the gluing design data in the NOTE data structure to determine whether the gluing design data corresponding to the gluing assembly data exists in the gluing design document. If the gluing design data corresponding to the gluing assembly data exists, the data in the corresponding NOTE data structure (i.e., the gluing design data, including relevant components, methods, functions, etc.) is matched, and stored in the gluing line data structure (i.e., the gluing line data). Afterwards, it can also be detected whether the gluing line type is set for each gluing line in the gluing line data structure. If not, it can be detected by the automatic detection equipment. The manager manually sets the glue line type, and then can search for all the sheets in the displayed parts (search for sheets in the painted vehicle structure), calculate the boundaries of all sheets (contours, not edges), and then discretize the glue lines and sheet boundaries in the painted vehicle structure into points. Then, match the discrete glue discrete points with the boundary discrete points, and perform automatic detection based on the matching results (i.e., glue boundary data). Then, the detection results can be calculated and judged, and the calculation results can be matched with data such as "B_Parts" in the NOTE structure data. Finally, a qualification test is performed according to the detection rules of special requirements to determine whether it is qualified (i.e., NG / OK, OK means qualified, NG means unqualified).

[0150] In this process, the process of constructing the glue boundary data can be executed as follows Figure 6 As shown, the glue coating line data and boundary data (i.e., the sheet boundaries of each sheet) are first obtained, and they are discretized respectively to obtain the glue coating line discrete points and the boundary discrete points. Then, the glue coating line discrete points are matched with the boundary discrete points, and the direction is extracted according to the matching results (to facilitate subsequent ray drawing). Finally, the glue coating line and boundary data (i.e., glue coating boundary data) are synthesized.

[0151] The process of setting the feature type in the automatic detection process can be as follows Figure 7 As shown, firstly, the target glue line discrete points and the target boundary discrete points corresponding to the target glue line discrete points are extracted from the glue boundary data as forward rays and reverse rays to determine the collision point. Then, the corresponding feature type is set for the target glue discrete point according to the collision judgment data of the collision point (i.e., the number of sheet metals penetrated by the collision point, the first penetration surface attribute of the collision point, the height of the collision point relative to the glue line, the boundary change position of the collision point, the curvature change position of the collision point, etc.).

[0152] In the above automatic detection execution process, the generation of discrete points of the glue coating line can be as follows: Figure 8 As shown in a, the generation of boundary discrete points can be as follows Figure 8 b, while discrete point matching can be done as Fig. 9As shown, the selected discrete points of the glue coating line (i.e. Fig. 9 The glue line point in the middle is taken as the center. Based on the PCL point cloud library, KD_TREE is used to search for 1mm matches by nearest neighbor. The boundary discrete points found are Fig. 9 The boundary points of the sheet.

[0153] This embodiment extracts target glue discrete points and target boundary discrete points corresponding to the target glue discrete points from the glue boundary data; draws rays according to the target glue discrete points and the target boundary discrete points; obtains the collision point corresponding to the ray, which is the intersection between the ray and the sheet metal included in the vehicle component; sets the corresponding feature type for the target glue discrete point in the glue boundary data according to the collision point; and performs qualification inspection on each assembled vehicle component according to the glue boundary data and the feature type corresponding to each glue discrete point in the glue boundary data. Since the data is further analyzed and the feature type corresponding to each glue discrete point in the glue boundary data is determined, more detection basis is provided for subsequent automatic detection, thereby improving the feasibility and accuracy of automatic detection.

[0154] In addition, an embodiment of the present invention further provides a storage medium, on which an automatic detection program is stored. When the automatic detection program is executed by a processor, the steps of the automatic detection method described above are implemented.

[0155] Reference Fig.10 , Fig.10 It is a structural block diagram of the first embodiment of the automatic detection device of the present invention.

[0156] like Fig.10 As shown, the automatic detection device proposed in the embodiment of the present invention includes:

[0157] A construction module 10 is used to construct a painted vehicle structure according to the vehicle assembly data, wherein the painted vehicle structure includes a glue coating line and a sheet boundary of a sheet included in each vehicle component;

[0158] A discrete module 20 is used to discretize the glue coating lines in the painted vehicle structure to obtain a plurality of discrete glue coating points, and to discretize the sheet boundaries in the painted vehicle structure to obtain a plurality of discrete boundary points;

[0159] A matching module 30, for matching the glue coating discrete points with the boundary discrete points to generate glue coating boundary data, wherein the glue coating boundary data stores the glue coating discrete points and the boundary discrete points corresponding to the glue coating discrete points;

[0160] The detection module 40 is used to perform a conformity detection on each assembled vehicle component according to the glue coating boundary data.

[0161] This embodiment constructs a painted vehicle structure according to vehicle assembly data; discretizes the glue lines in the painted vehicle structure to obtain multiple glue discrete points, and discretizes the sheet boundaries in the painted vehicle structure to obtain multiple boundary discrete points; matches the glue discrete points with the boundary discrete points to generate glue boundary data; and performs qualification inspection on each assembled vehicle component according to the glue boundary data. Due to point discretization and other processing, and through matching, the original glue lines are converted into discrete points and associated with the boundary points of the pictures contained in the parts, and the complex analysis between lines is converted into key points between points for detection, which simplifies complex problems and ensures that automatic detection can be performed on the requirements.

[0162] Furthermore, the construction module 10 is also used to detect whether there is gluing assembly data in the vehicle assembly data; if there is gluing assembly data, the gluing assembly data is extracted from the vehicle assembly data, and the gluing identification of each gluing assembly data is obtained; the gluing identification of each gluing assembly data is matched with the gluing identification corresponding to each gluing design data in the gluing design document, and the gluing design data corresponding to each gluing assembly data is determined; gluing line data is generated according to the gluing assembly data and the gluing design data corresponding to each gluing assembly data; and a painted vehicle structure is constructed according to the vehicle assembly data and the gluing line data.

[0163] Furthermore, the construction module 10 is also used to extract the gluing design data from the gluing design document if the gluing assembly data does not exist; obtain the vehicle component identification corresponding to each gluing design data; construct the gluing line data according to the vehicle component identification and the gluing design data; and construct the painted vehicle structure according to the vehicle assembly data and the gluing line data.

[0164] Furthermore, the detection module 40 is also used to extract target glue discrete points and target boundary discrete points corresponding to the target glue discrete points from the glue boundary data; make rays according to the target glue discrete points and the target boundary discrete points; obtain collision points corresponding to the rays, wherein the collision points are intersection points between the rays and the sheet metal included in the vehicle components; set corresponding feature types for the target glue discrete points in the glue boundary data according to the collision points; and perform qualification inspection on each assembled vehicle component according to the glue boundary data and the feature types corresponding to each glue discrete point in the glue boundary data.

[0165] Furthermore, the detection module 40 is also used to obtain collision judgment data corresponding to the collision point, and the collision judgment data includes at least one of the number of sheet materials penetrated by the collision point, the first penetration surface attribute of the collision point, the height of the collision point relative to the glue line, the boundary change position of the collision point, and the curvature change position of the collision point; and according to the collision judgment data, a corresponding feature type is set for the target glue discrete point in the glue boundary data.

[0166] Furthermore, the detection module 40 is also used to obtain the glue line type of the glue line to which the target discrete glue point belongs; determine a collision judgment index according to the glue line type; and obtain collision judgment data corresponding to the collision point based on the collision judgment index.

[0167] Furthermore, the detection module 40 is also used to obtain the glue line type of the glue line to which each discrete glue point in the glue boundary data belongs; search in the detection rule library according to the glue line type to determine the detection rule corresponding to each set of discrete glue points in the glue boundary data; and perform qualification inspection on each assembled vehicle component based on the detection rule and the glue boundary data.

[0168] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0169] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0170] In addition, for technical details that are not described in detail in this embodiment, reference can be made to the automatic detection method provided in any embodiment of the present invention, and will not be repeated here.

[0171] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0172] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0173] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0174] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An automatic detection method, characterized in that: The automatic detection method comprises: Constructing a painted vehicle structure according to the vehicle assembly data, wherein the painted vehicle structure includes a glue coating line and a sheet boundary of a sheet included in each vehicle component; Discrete the glue coating lines in the painted vehicle structure to obtain a plurality of glue coating discrete points, and discretize the sheet boundaries in the painted vehicle structure to obtain a plurality of boundary discrete points; Matching the glue coating discrete points with the boundary discrete points to generate glue coating boundary data, wherein the glue coating boundary data stores the glue coating discrete points and the boundary discrete points corresponding to the glue coating discrete points; The conformity of each assembled vehicle component is tested according to the glue coating boundary data.

2. The automatic detection method according to claim 1, characterized in that: The step of constructing a painted vehicle structure according to vehicle assembly data comprises: Detecting whether there is gluing assembly data in the vehicle assembly data; If the gluing assembly data exists, extracting the gluing assembly data from the vehicle assembly data, and obtaining the gluing identification of each gluing assembly data; Matching the gluing identification of each gluing assembly data with the gluing identification corresponding to each gluing design data in the gluing design document to determine the gluing design data corresponding to each gluing assembly data; Generate glue coating line data according to the glue coating assembly data and the glue coating design data corresponding to each glue coating assembly data; A painted vehicle structure is constructed according to the vehicle assembly data and the glue coating line data.

3. The automatic detection method according to claim 2, characterized in that: After detecting whether there is glue coating assembly data in the vehicle assembly data, the method further includes: If the glue coating assembly data does not exist, the glue coating design data is extracted from the glue coating design document; Obtain vehicle component identification corresponding to each gluing design data; Constructing glue coating line data according to the vehicle component identification and the glue coating design data; A painted vehicle structure is constructed according to the vehicle assembly data and the glue coating line data.

4. The automatic detection method according to claim 1, characterized in that: The method of performing qualification inspection on each assembled vehicle component according to the glue coating boundary data comprises: Extracting target glue coating discrete points and target boundary discrete points corresponding to the target glue coating discrete points from the glue coating boundary data; Draw rays according to the target glue coating discrete points and the target boundary discrete points; Obtaining a collision point corresponding to the ray, wherein the collision point is an intersection point between the ray and a sheet member included in the vehicle component; Setting a corresponding feature type for a target glue coating discrete point in the glue coating boundary data according to the collision point; The conformity of each assembled vehicle component is tested according to the glue coating boundary data and the feature type corresponding to each glue coating discrete point in the glue coating boundary data.

5. The automatic detection method according to claim 4, characterized in that: The step of setting a corresponding feature type for a target glue coating discrete point in the glue coating boundary data according to the collision point includes: Acquire collision judgment data corresponding to the collision point, wherein the collision judgment data includes at least one of the number of sheet metal parts penetrated by the collision point, the first penetration surface attribute of the collision point, the height of the collision point relative to the glue coating line, the boundary change position of the collision point, and the curvature change position of the collision point; A corresponding feature type is set for the target glue coating discrete point in the glue coating boundary data according to the collision judgment data.

6. The automatic detection method according to claim 5, characterized in that: The obtaining of collision judgment data corresponding to the collision point includes: Obtaining the glue coating line type of the glue coating line to which the target glue coating discrete point belongs; Determining a collision judgment index according to the type of the glue coating line; Collision judgment data corresponding to the collision point is obtained based on the collision judgment index.

7. The automatic detection method according to claim 4, characterized in that: The method of performing qualification inspection on each assembled vehicle component according to the glue coating boundary data and the feature type corresponding to each glue coating discrete point in the glue coating boundary data includes: Obtain the glue line type of the glue line to which each glue discrete point in the glue boundary data belongs; Searching in the detection rule library according to the glue coating line type, determining the detection rule corresponding to each glue coating discrete point set in the glue coating boundary data; Based on the detection rules and the glue coating boundary data, each assembled vehicle component is tested for its conformity.

8. An automatic detection device, characterized in that: The automatic detection device comprises: A construction module, used to construct a painted vehicle structure according to the vehicle assembly data, wherein the painted vehicle structure includes a glue coating line and a sheet boundary of a sheet included in each vehicle component; A discrete module is used to discretize the glue coating lines in the painted vehicle structure to obtain a plurality of discrete glue coating points, and to discretize the sheet boundaries in the painted vehicle structure to obtain a plurality of discrete boundary points; A matching module, used for matching the glue coating discrete points with the boundary discrete points to generate glue coating boundary data, wherein the glue coating boundary data stores the glue coating discrete points and the boundary discrete points corresponding to the glue coating discrete points; The detection module is used to perform a conformity detection on each assembled vehicle component according to the glue coating boundary data.

9. An automatic detection device, characterized in that: The automatic detection device comprises: a processor, a memory, and an automatic detection program stored in the memory and executable on the processor, wherein the automatic detection program implements the steps of the automatic detection method according to any one of claims 1 to 7 when executed by the processor.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an automatic detection program, which, when executed, implements the steps of the automatic detection method according to any one of claims 1 to 7.

Images