Part structure detection method, device, equipment and storage medium

Abstract

The present invention belongs to the field of vehicle detection technology, and discloses a part structure detection method, device, equipment and storage medium. The present invention obtains the digital model of the part to be detected and the historical part digital model corresponding to the part to be detected according to the digital model root directory when the digital model root directory is obtained; performs similarity comparison on the digital model of the part to be detected and the historical part digital model to obtain a similarity comparison result; when the similarity comparison result is a preset similarity result, performs posture constraints on the digital model to be detected and the historical part digital model; and determines the structural detection result of the part to be detected based on the posture constraint result. Through the above method, the structured management of the final assembly inspection standard rules of product design and the batch inspection of parts are realized, while effectively improving the efficiency and accuracy of inspection, saving human resources and time costs.

Description

Technical Field

[0001] The present invention relates to the field of vehicle detection technology, and in particular to a part structure detection method, device, equipment and storage medium. Background Art

[0002] Currently, vehicle parts inspection utilizes NX software. Developed by Siemens PLM Software, NX is an integrated computer-aided design (CAD), computer-aided manufacturing (CAM), and computer-aided engineering (CAE) software. It is widely used in engineering design, manufacturing, and simulation, and can be applied to product design, CNC programming, process planning, engineering analysis, and other areas. However, automated inspection using NX software requires obtaining the bill of materials (BOP) and performing inspection based on the BOP. This presupposes that the BOP contains 3D BOM digital model information, which requires manual matching to connect the 3D BOM digital model to the BOP. This technical implementation is costly and not readily scalable.

[0003] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of the present invention is to provide a part structure detection method, device, equipment and storage medium, aiming to solve the technical problem of how to improve the efficiency and accuracy of part structure detection.

[0005] To achieve the above object, the present invention provides a method for detecting a part structure, the method comprising the following steps:

[0006] When the digital model root directory is obtained, the digital model of the part to be detected and the historical part digital model corresponding to the part to be detected are obtained according to the digital model root directory;

[0007] Performing a similarity comparison based on the digital model of the part to be tested and the digital model of the historical part to obtain a similarity comparison result;

[0008] When the similarity comparison result is a preset similarity result, constraining the posture of the digital model to be tested and the historical part digital model;

[0009] The structural detection result of the part to be detected is determined according to the posture constraint result.

[0010] Optionally, performing similarity comparison based on the digital model of the part to be inspected and the digital model of the historical part to obtain a similarity comparison result includes:

[0011] Determine a bounding box to be detected based on the digital model to be detected of the part to be detected;

[0012] Determining a historical part bounding box according to the historical part digital model;

[0013] A similarity comparison is performed based on the bounding volume to be detected of the bounding box to be detected and the historical bounding volume of the historical part bounding box to obtain a similarity comparison result.

[0014] Optionally, performing a similarity comparison based on the bounding volume to be detected of the bounding box to be detected and the historical bounding volume of the historical part bounding box to obtain a similarity comparison result includes:

[0015] Determining a volume relationship between the bounding volume to be detected and the historical bounding volume according to the bounding volume to be detected of the bounding box to be detected and the historical bounding volume of the historical part bounding box;

[0016] determining part similarity based on the volumetric relationship;

[0017] The part similarity is compared with a similarity threshold to obtain a similarity comparison result.

[0018] Optionally, constraining the posture of the digital model to be inspected and the historical part digital model includes:

[0019] Marking the digital model to be tested, and determining the marked test digital model;

[0020] Performing position selection on the marked inspection digital model and the historical part digital model to determine an alignment position on the marked inspection digital model and an alignment position on the historical part digital model;

[0021] Position constraints are performed based on the alignment positions on the marked detection digital model and the alignment positions on the historical part digital model.

[0022] Optionally, performing pose constraint according to the alignment position on the marked detection digital model and the alignment position on the historical part digital model includes:

[0023] Establishing a coordinate system according to the alignment positions on the marked inspection digital model and the alignment positions on the historical part digital model to obtain the alignment coordinate system of the marked inspection digital model and the alignment coordinate system of the historical part digital model;

[0024] Determining a transformation matrix between the alignment coordinate system of the annotated inspection digital model and the alignment coordinate system of the historical part digital model;

[0025] The position and posture constraints are performed on the marked detection digital model and the historical part digital model according to the transformation matrix.

[0026] Optionally, before marking the digital model to be detected and determining the labeled detection digital model, the method further includes:

[0027] Check whether there is a component digital model in the current display interface;

[0028] When a component digital model exists in the current display interface, generating a hiding instruction;

[0029] The component digital model is hidden according to the hiding instruction.

[0030] Optionally, after determining the structural detection result of the part to be detected according to the posture constraint result, the method further includes:

[0031] Obtaining a part installation position corresponding to the historical part digital model according to a structural inspection result of the part to be inspected;

[0032] Determining the target installation position of the part to be inspected according to the part installation position corresponding to the historical part digital model;

[0033] The part to be inspected is installed according to the target installation position.

[0034] In addition, to achieve the above-mentioned purpose, the present invention further proposes a part structure detection device, the part structure detection device comprising:

[0035] An acquisition module, configured to acquire, when a digital model root directory is obtained, the digital model of the part to be detected and the historical part digital model corresponding to the part to be detected according to the digital model root directory;

[0036] A comparison module, configured to perform a similarity comparison based on the digital model of the part to be detected and the digital model of the historical part to obtain a similarity comparison result;

[0037] A constraint module, configured to constrain the posture of the digital model to be tested and the historical part digital model when the similarity comparison result is a preset similarity result;

[0038] The processing module is used to determine the structural detection result of the part to be detected according to the posture constraint result.

[0039] In addition, to achieve the above-mentioned purpose, the present invention also proposes a part structure detection device, which includes: a memory, a processor, and a part structure detection program stored on the memory and runnable on the processor, and the part structure detection program is configured to implement the steps of the part structure detection method described above.

[0040] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a part structure detection program is stored. When the part structure detection program is executed by a processor, the steps of the part structure detection method described above are implemented.

[0041] The present invention obtains the digital model of the part to be detected and the digital model of the historical part corresponding to the part to be detected according to the digital model root directory when the digital model root directory is obtained; performs similarity comparison on the digital model of the part to be detected and the digital model of the historical part to be detected to obtain a similarity comparison result; performs posture constraints on the digital model to be detected and the digital model of the historical part when the similarity comparison result is a preset similarity result; and determines the structural detection result of the part to be detected according to the posture constraint result. In the above manner, based on the similarity comparison result between the digital model to be detected and the digital model of the historical part corresponding to the digital model to be detected, the posture constraints are performed on the digital model to be detected and the digital model of the historical part, and the structural detection result of the part to be detected can be obtained based on the posture constraint result, thereby realizing the structured management of the final assembly inspection standard rules of product design and the batch detection of part structure, while effectively improving the efficiency and accuracy of inspection and saving human resources and time costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a structural diagram of a parts structure detection device in a hardware operating environment involved in an embodiment of the present invention;

[0043] Figure 2 Schematic diagram of the process of the first embodiment of the part structure detection method of the present invention;

[0044] Figure 3 This is a schematic diagram of the operation of a plug-in according to an embodiment of the part structure detection method of the present invention;

[0045] Figure 4 A schematic diagram of an operation interface of an embodiment of a part structure detection method of the present invention;

[0046] Figure 5 A schematic diagram of a bounding box of an embodiment of a part structure detection method of the present invention;

[0047] Figure 6 Schematic diagram of the process of the second embodiment of the part structure detection method of the present invention;

[0048] Figure 7 A schematic diagram of the posture constraints of an embodiment of a part structure detection method of the present invention;

[0049] Figure 8 This is a structural block diagram of the first embodiment of the part structure detection device of the present invention.

[0050] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0051] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0052] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a parts structure detection device in the hardware operating environment involved in the embodiment of the present invention.

[0053] like Figure 1 As shown, the part structure detection 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. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display and an input unit, such as a keyboard. Optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also be a storage device independent of the processor 1001.

[0054] Those skilled in the art will understand that Figure 1 The structure shown in does not constitute a limitation on the part structure detection equipment, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0055] 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 a part structure detection program.

[0056] exist Figure 1In the part structure detection device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the part structure detection device of the present invention can be set in the part structure detection device, and the part structure detection device calls the part structure detection program stored in the memory 1005 through the processor 1001, and executes the part structure detection method provided by the embodiment of the present invention.

[0057] The embodiment of the present invention provides a method for detecting a part structure, referring to Figure 2 , Figure 2 This is a flow chart of a first embodiment of a method for detecting part structure according to the present invention.

[0058] In this embodiment, the part structure detection method includes the following steps:

[0059] Step S10: When the digital model root directory is obtained, the digital model of the part to be detected and the historical part digital model corresponding to the part to be detected are obtained according to the digital model root directory.

[0060] It should be noted that the executor of this embodiment is a part structure detection device, wherein the part structure detection device has functions such as data processing, data communication and program running. The part structure detection device can be an integrated controller, a control computer and other devices. Of course, it can also be other devices with similar functions. This embodiment does not limit this.

[0061] It is understood that the part structure inspection equipment utilizes both NX and TCM software. The TCM software stores digital models of parts for new and existing vehicle models. NX uses a complete data load method to obtain the data's geometric features. The data is downloaded from the TCM software to the local digital model root directory, which contains folders named with the same bitcode. In this embodiment, the folder name bitcode is 7 digits, but other values are also possible and are not a limitation of this embodiment.

[0062] In the specific implementation, the design parts contained in the new car model in the digital model root directory are the parts to be tested. The digital model of the parts to be tested is loaded, and the part digital model of the existing model parts with the same bit code is obtained. The part digital model of the existing model parts with the same bit code is the historical part digital model.

[0063] It should be noted that, using NX software to create a new blank assembly in a custom path, the assembly name is also customized, after the new assembly is created, run the plug-in as follows Figure 3 As shown, select the "General Assembly Inspection" option and click the "Error Prevention Inspection" button to run the error prevention inspection plug-in. The user interface of the plug-in is as follows: Figure 4As shown. Specify the local digital model root directory for data downloaded from the TCM and set the maximum allowable memory usage. In this embodiment, the default value is 90%, but other values can also be set, which are not limited in this embodiment. The purpose of setting the maximum allowable memory usage is to stop the program from loading the digital model when the computer's memory usage exceeds the set value, preventing the computer from running out of memory and causing a system crash.

[0064] Step S20: performing a similarity comparison based on the digital model of the part to be inspected and the digital model of the historical part to obtain a similarity comparison result.

[0065] It should be noted that the bounding box volume of the digital model to be tested and the bounding box volume of the historical part digital model are calculated respectively, and a similarity comparison is performed based on the bounding box volumes of the two to obtain the similarity between the part to be tested and the existing vehicle parts. The similarity comparison result reflects whether the digital model to be tested and the historical part digital model are similar.

[0066] It can be understood that in order to ensure the accuracy of the comparison process, further, the similarity comparison is performed based on the digital model of the part to be detected and the digital model of the historical part to obtain a similarity comparison result, including: determining the bounding box to be detected based on the digital model of the part to be detected; determining the bounding box of the historical part based on the digital model of the historical part; performing a similarity comparison based on the bounding volume to be detected of the bounding box to be detected and the historical bounding volume of the bounding box of the historical part to obtain a similarity comparison result.

[0067] In the specific implementation, the bounding box corresponding to the digital model to be detected is determined, and the bounding box corresponding to the digital model to be detected is the bounding box to be detected. The bounding box corresponding to the digital model of the historical part is determined, and the bounding box corresponding to the digital model of the historical part is the bounding box of the historical part. The volume of the bounding box of the historical part and the volume of the bounding box to be detected are calculated, and a similarity comparison is performed based on the volumes of the two to determine the similarity comparison result.

[0068] It should be noted that in order to ensure the accuracy of the similarity comparison based on volume, further, the similarity comparison is performed based on the bounding volume to be detected of the bounding box to be detected and the historical bounding volume of the historical part bounding box to obtain a similarity comparison result, including: determining the volume relationship between the bounding volume to be detected and the historical bounding volume based on the bounding volume to be detected of the bounding box to be detected and the historical bounding volume of the historical part bounding box; determining the part similarity based on the volume relationship; comparing the part similarity with a similarity threshold to obtain a similarity comparison result.

[0069] It can be understood that the size relationship between the bounding volume to be detected and the historical bounding volume is compared, and the size relationship between the bounding volume to be detected and the historical bounding volume is the volume relationship between the two. Based on the volume relationship between the two, the maximum and minimum values between the two are determined. The ratio of the minimum value to the maximum value in the two volumes obtained by dividing the minimum value by the maximum value is the part similarity between the digital model to be detected and the historical part digital model. For example, Figure 5 As shown, the left side is the digital model to be tested, and the right side is the digital model of the historical part. The similarity between the two is determined based on the volumes corresponding to the bounding boxes of the two.

[0070] In a specific implementation, if the part similarity exceeds the similarity threshold, it indicates that the historical part model and the model to be tested are similar, and further error prevention checks are required. If the part similarity does not exceed the similarity threshold, the model to be tested and the historical part model are filtered and the next round of judgment is performed. In this embodiment, the similarity threshold is set to 50%, but it can also be set to other values according to actual circumstances, and this embodiment is not limited to this.

[0071] Step S30: When the similarity comparison result is a preset similarity result, pose constraints are performed on the digital model to be detected and the historical part digital model.

[0072] It should be noted that when the part similarity is greater than the similarity threshold, it means that the similarity comparison result is the preset similarity result. At this time, posture constraints are required to make the digital model to be tested and the historical part digital model overlap according to the constraint characteristics.

[0073] Step S40: determining the structural detection result of the part to be detected according to the posture constraint result.

[0074] It should be noted that the pose constraint result refers to the result of the overlap between the digital model to be inspected and the digital model of the historical part. After the digital model to be inspected and the digital model of the historical part overlap, the difference coloring is performed, and then the user judges whether it meets the error prevention requirements and records the user's judgment result. Finally, the structural inspection result of the part to be inspected is obtained, thereby completing the inspection of the part to be inspected.

[0075] It can be understood that in order to ensure that the part to be inspected can be installed in the correct position later, further, after determining the structural detection result of the part to be inspected based on the posture constraint result, it also includes: obtaining the part installation position corresponding to the historical part digital model based on the structural detection result of the part to be inspected; determining the target installation position of the part to be inspected based on the part installation position corresponding to the historical part digital model; and installing the part to be inspected according to the target installation position.

[0076] In a specific implementation, if the structural inspection results of the part to be inspected are consistent with existing vehicle model parts, the part installation position corresponding to the historical part digital model is obtained and used as the target installation position for the part to be inspected. The part to be inspected is then installed based on the target installation position. This approach can identify design features that prevent the part from being assembled in incorrect positions when the part has multiple assembly positions.

[0077] This embodiment obtains the historical part digital model corresponding to the part to be inspected when the part to be inspected is obtained; performs similarity comparison between the digital model to be inspected and the historical part digital model of the part to be inspected to obtain a similarity comparison result; performs posture constraints on the digital model to be inspected and the historical part digital model when the similarity comparison result is a preset similarity result; and determines the structural detection result of the part to be inspected based on the posture constraint result. In the above manner, based on the similarity comparison result between the digital model to be inspected and the historical part digital model corresponding to the digital model to be inspected, posture constraints are performed on the digital model to be inspected and the historical part digital model, and the structural detection result of the part to be inspected can be obtained based on the posture constraint result, thereby realizing the structured management of the final assembly inspection standard rules of product design and the batch detection of part structure, while effectively improving the efficiency and accuracy of inspection and saving human resources and time costs.

[0078] refer to Figure 6 , Figure 6 This is a flow chart of a second embodiment of a part structure detection method according to the present invention.

[0079] Based on the first embodiment described above, the part structure detection method of this embodiment includes, in step S30:

[0080] Step S31: marking the digital model to be detected and determining the marked detection digital model.

[0081] It should be noted that after loading the digital model to be inspected and the historical part digital model, the NX assembly tree will display the loaded data. At this time, the "Load Digital Model" button and the selection box for the digital model root directory are disabled to prevent repeated loading of digital models; the "Initialize Checklist" button is activated. If a loaded digital model exists in the assembly itself, the state of the operating controls is the same as above. To avoid repeated initialization, the "Initialize Checklist" button is disabled after initialization.

[0082] It is understood that in order to facilitate user comparison, the digital model to be inspected is marked, and the marked digital model to be inspected is the marked inspection digital model. In this embodiment, the marking method can be to color the digital model to be inspected, for example, the appearance of the digital model to be inspected can be changed to red to distinguish it from the historical part digital model.

[0083] In a specific implementation, in order to enable the user to obtain relevant information intuitively and clearly when performing comparison, further, the digital model to be detected is identified, and before the labeled detection digital model is determined, it also includes: detecting whether there is a component digital model in the current display interface; when there is a component digital model in the current display interface, generating a hiding instruction; hiding the component digital model according to the hiding instruction.

[0084] It should be noted that the current display interface refers to the graphics window of the NX software. It detects whether there are other component digital models in the current display interface. If there are other component digital models in the current display interface, a hiding instruction is generated. The component digital models are hidden based on the hiding instruction, and only the digital models to be tested and historical parts digital models that are currently in the detection state are displayed on the current display interface.

[0085] Step S32: Position selection is performed on the marked inspection digital model and the historical part digital model to determine the alignment position on the marked inspection digital model and the alignment position on the historical part digital model.

[0086] It should be noted that on the annotation inspection digital model and the historical part digital model, faces with similar shapes, sizes, and relative positions within the part are selected. The faces selected on the annotation inspection digital model are the alignment positions on the annotation inspection digital model, and the faces selected on the historical part digital model are the alignment positions on the historical part digital model.

[0087] Step S33: performing posture constraints according to the alignment positions on the marked detection digital model and the alignment positions on the historical part digital model.

[0088] It should be noted that the alignment positions on the marked detection digital model and the alignment positions on the historical part digital model are subjected to posture constraints. In order to ensure that the two can be accurately aligned, further, the posture constraints are performed based on the alignment positions on the marked detection digital model and the alignment positions on the historical part digital model, including: establishing a coordinate system based on the alignment positions on the marked detection digital model and the alignment positions on the historical part digital model to obtain the alignment coordinate system of the marked detection digital model and the alignment coordinate system of the historical part digital model; determining the transformation matrix between the alignment coordinate system of the marked detection digital model and the alignment coordinate system of the historical part digital model; and performing posture constraints on the marked detection digital model and the historical part digital model according to the transformation matrix.

[0089] It can be understood that a coordinate system related to the alignment position on the marked inspection digital model is generated to obtain the alignment coordinate system of the marked inspection digital model, and a coordinate system related to the alignment position on the historical part digital model is generated to obtain the alignment coordinate system of the historical part digital model.

[0090] In the specific implementation, the transformation matrix between the two coordinate systems is determined based on the alignment coordinate system of the annotation inspection digital model and the alignment coordinate system of the historical part digital model. According to this transformation matrix, the annotation inspection digital model and the historical part digital model can be moved to fit in the selected alignment position to achieve the purpose of alignment. For example, after the annotation inspection digital model and the historical part digital model are aligned, Figure 7 shown.

[0091] It should be noted that when the similarity comparison result between the digital model to be tested and the historical part digital model is a preset similarity result, if the user can directly obtain the comparison result when performing part comparison, there is no need to select the alignment position on the two digital models and perform posture constraints; if the user cannot directly obtain the comparison result when performing part comparison, it is necessary to select the alignment position on the two digital models and perform the relevant steps of posture constraints.

[0092] This embodiment identifies the digital model to be inspected and determines a labeled inspection digital model; aligns the labeled inspection digital model with the historical part digital model to determine the alignment position on the labeled inspection digital model and the alignment position on the historical part digital model; and then applies pose constraints based on the alignment positions on the labeled inspection digital model and the historical part digital model. This ensures accuracy during pose constraints, laying the foundation for subsequent accurate inspection results.

[0093] In addition, an embodiment of the present invention further provides a storage medium, on which a part structure detection program is stored. When the part structure detection program is executed by a processor, the steps of the part structure detection method described above are implemented.

[0094] Reference Figure 8 , Figure 8 This is a structural block diagram of the first embodiment of the part structure detection device of the present invention.

[0095] like Figure 8 As shown, the part structure detection device proposed in the embodiment of the present invention includes:

[0096] The acquisition module 10 is configured to acquire the digital model of the part to be detected and the historical part digital model corresponding to the part to be detected according to the digital model root directory when the digital model root directory is acquired.

[0097] The comparison module 20 is used to perform a similarity comparison based on the digital model of the part to be detected and the digital model of the historical part to obtain a similarity comparison result.

[0098] The constraint module 30 is used to constrain the posture of the digital model to be detected and the historical part digital model when the similarity comparison result is a preset similarity result.

[0099] The processing module 40 is used to determine the structural detection result of the part to be detected according to the posture constraint result.

[0100] This embodiment obtains the historical part digital model corresponding to the part to be inspected when the part to be inspected is obtained; performs similarity comparison between the digital model to be inspected and the historical part digital model of the part to be inspected to obtain a similarity comparison result; performs posture constraints on the digital model to be inspected and the historical part digital model when the similarity comparison result is a preset similarity result; and determines the structural detection result of the part to be inspected based on the posture constraint result. In the above manner, based on the similarity comparison result between the digital model to be inspected and the historical part digital model corresponding to the digital model to be inspected, posture constraints are performed on the digital model to be inspected and the historical part digital model, and the structural detection result of the part to be inspected can be obtained based on the posture constraint result, thereby realizing the structured management of the final assembly inspection standard rules of product design and the batch detection of part structure, while effectively improving the efficiency and accuracy of inspection and saving human resources and time costs.

[0101] In one embodiment, the comparison module 20 is further configured to determine a bounding box to be detected based on the digital model to be detected of the part to be detected;

[0102] Determining a historical part bounding box according to the historical part digital model;

[0103] A similarity comparison is performed based on the bounding volume to be detected of the bounding box to be detected and the historical bounding volume of the historical part bounding box to obtain a similarity comparison result.

[0104] In one embodiment, the comparison module 20 is further configured to determine a volume relationship between the bounding volume to be detected and the historical bounding volume based on the bounding volume to be detected of the bounding box to be detected and the historical bounding volume of the historical part bounding box;

[0105] determining part similarity based on the volumetric relationship;

[0106] The part similarity is compared with a similarity threshold to obtain a similarity comparison result.

[0107] In one embodiment, the constraint module 30 is further configured to identify the digital model to be detected and determine a marked detection digital model;

[0108] Performing position selection on the marked inspection digital model and the historical part digital model to determine an alignment position on the marked inspection digital model and an alignment position on the historical part digital model;

[0109] Position constraints are performed based on the alignment positions on the marked detection digital model and the alignment positions on the historical part digital model.

[0110] In one embodiment, the constraint module 30 is further configured to establish a coordinate system based on the alignment position on the marked inspection digital model and the alignment position on the historical part digital model, thereby obtaining the alignment coordinate system of the marked inspection digital model and the alignment coordinate system of the historical part digital model;

[0111] Determining a transformation matrix between the alignment coordinate system of the annotated inspection digital model and the alignment coordinate system of the historical part digital model;

[0112] The position and posture constraints are performed on the marked detection digital model and the historical part digital model according to the transformation matrix.

[0113] In one embodiment, the constraint module 30 is further configured to detect whether a component digital model exists in the current display interface;

[0114] When a component digital model exists in the current display interface, generating a hiding instruction;

[0115] The component digital model is hidden according to the hiding instruction.

[0116] In one embodiment, the processing module 40 is further configured to obtain a part installation position corresponding to the historical part digital model according to a structural detection result of the part to be detected;

[0117] Determining the target installation position of the part to be inspected according to the part installation position corresponding to the historical part digital model;

[0118] The part to be inspected is installed according to the target installation position.

[0119] It should be understood that the above is only an example and does not constitute any limitation to the technical solution of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any limitation on this.

[0120] It should be understood that, although the various steps in the flowchart in the embodiment of the present application are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless clearly stated herein, the execution of these steps is not strictly limited in order, and they can be performed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and their execution order is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0121] 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 it according to actual needs to achieve the purpose of the embodiment scheme, and no limitation is made here.

[0122] In addition, it should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0123] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0124] Through the above description of the embodiments, those skilled in the art will clearly understand that the methods of the above embodiments can be implemented using software plus the necessary general-purpose hardware platform. Of course, hardware can also be used, but in many cases the former is the more preferred implementation method. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, a magnetic disk, or an optical disk) and includes a number of instructions for enabling a terminal device (such as a mobile phone, computer, server, or network device) to execute the methods described in the various embodiments of the present invention.

[0125] 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 description 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. A method for detecting a part structure, characterized in that: The part structure detection method comprises: When the digital model root directory is obtained, the digital model of the part to be tested and the historical part digital model corresponding to the part to be tested are obtained according to the digital model root directory, where the historical part digital model is the part digital model of the existing vehicle model part with the same bit code as the part to be tested; Performing a similarity comparison based on the digital model of the part to be tested and the digital model of the historical part to obtain a similarity comparison result; When the similarity comparison result is a preset similarity result, constraining the posture of the digital model to be tested and the historical part digital model; Determine the structural detection result of the part to be detected according to the posture constraint result; The similarity comparison between the digital model of the part to be inspected and the digital model of the historical part to be inspected is performed to obtain a similarity comparison result, including: Determine a bounding box to be detected based on the digital model to be detected of the part to be detected; Determining a historical part bounding box according to the historical part digital model; Performing a similarity comparison based on the bounding volume to be detected of the bounding box to be detected and the historical bounding volume of the historical part bounding box to obtain a similarity comparison result; The step of constraining the posture of the digital model to be inspected and the historical part digital model includes: Marking the digital model to be tested, and determining the marked test digital model; Performing position selection on the marked inspection digital model and the historical part digital model to determine an alignment position on the marked inspection digital model and an alignment position on the historical part digital model; Position constraints are performed based on the alignment positions on the marked detection digital model and the alignment positions on the historical part digital model.

2. The part structure detection method according to claim 1, wherein: The performing similarity comparison based on the bounding volume to be detected of the bounding box to be detected and the historical bounding volume of the historical part bounding box to obtain a similarity comparison result includes: Determining a volume relationship between the bounding volume to be detected and the historical bounding volume according to the bounding volume to be detected of the bounding box to be detected and the historical bounding volume of the historical part bounding box; determining part similarity based on the volumetric relationship; The part similarity is compared with a similarity threshold to obtain a similarity comparison result.

3. The part structure detection method according to claim 1, wherein: The performing pose constraint according to the alignment position on the marked detection digital model and the alignment position on the historical part digital model includes: Establishing a coordinate system according to the alignment positions on the marked inspection digital model and the alignment positions on the historical part digital model to obtain the alignment coordinate system of the marked inspection digital model and the alignment coordinate system of the historical part digital model; Determining a transformation matrix between the alignment coordinate system of the annotated inspection digital model and the alignment coordinate system of the historical part digital model; The position and posture constraints are performed on the marked detection digital model and the historical part digital model according to the transformation matrix.

4. The part structure detection method according to claim 1, wherein: Before the digital model to be detected is marked and the digital model to be detected is determined, the method further includes: Check whether there is a component digital model in the current display interface; When a component digital model exists in the current display interface, generating a hiding instruction; The component digital model is hidden according to the hiding instruction.

5. The part structure detection method according to any one of claims 1 to 4, characterized in that: After determining the structural detection result of the part to be detected according to the posture constraint result, the method further includes: Obtaining a part installation position corresponding to the historical part digital model according to a structural inspection result of the part to be inspected; Determining the target installation position of the part to be inspected according to the part installation position corresponding to the historical part digital model; The part to be inspected is installed according to the target installation position.

6. A parts structure detection device, characterized in that: The part structure detection device comprises: an acquisition module, configured to, upon obtaining a digital model root directory, acquire, according to the digital model root directory, a digital model of a part to be detected and a historical part digital model corresponding to the part to be detected, wherein the historical part digital model is a part digital model of a part of an existing vehicle model having the same bit code as the part to be detected; A comparison module, configured to perform a similarity comparison based on the digital model of the part to be detected and the digital model of the historical part to obtain a similarity comparison result; A constraint module, configured to constrain the posture of the digital model to be tested and the historical part digital model when the similarity comparison result is a preset similarity result; A processing module, configured to determine a structural detection result of the part to be detected according to a posture constraint result; The comparison module is further configured to determine a bounding box to be detected based on the digital model to be detected of the part to be detected; determine a historical part bounding box based on the digital model of the historical part; and perform a similarity comparison based on the bounding volume to be detected of the bounding box to be detected and the historical bounding volume of the historical part bounding box to obtain a similarity comparison result. The constraint module is also used to identify the digital model to be inspected and determine the marked inspection digital model; select the positions of the marked inspection digital model and the historical part digital model to determine the alignment positions on the marked inspection digital model and the historical part digital model; and perform posture constraints based on the alignment positions on the marked inspection digital model and the historical part digital model.

7. A parts structure detection device, characterized in that, The device includes: a memory, a processor, and a part structure detection program stored in the memory and executable on the processor, wherein the part structure detection program is configured to implement the part structure detection method according to any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium stores a part structure detection program, which, when executed by a processor, implements the part structure detection method according to any one of claims 1 to 5.

Images