Intelligent detection method and device for passenger car pretreatment model problem, terminal and storage medium

Abstract

The invention belongs to the technical field of automobiles, and particularly relates to a passenger car pretreatment model problem intelligent detection method and device, a terminal and a storage medium. Comprising the following steps of 1, establishing a vehicle body model with topological structure errors, and performing data analysis and reading on the vehicle body model; step 2, preprocessing the vehicle body model, including de-noising and simplifying; and step 3, detecting the vehicle body model, determining the type of the topological structure error, and correspondingly marking. According to the method, all possible topological structure errors can be identified, so that an accurate basis is provided for a subsequent repair step, and the topological structure error detection problem of a complex curved surface model under an engineering scene is solved.

Description

Technical Field

[0001] The present invention belongs to the field of automobile technology, and in particular to a method, a device, a terminal and a storage medium for intelligently detecting problems in a pre-processing model of a passenger car. Background Art

[0002] The body model pre-processing task in the field of automotive aerodynamics requires repairing geometric models with topological errors. According to the basic principles and characteristics of existing methods, they can be classified into two types: manual methods and data-driven methods.

[0003] There are two common manual methods: first, import the car body model into the pre-processing software, determine the type of problem by checking the model point by point and surface by surface, and then repair the problem based on experience; second, after importing the model into the pre-processing software, use the plug-in designed by other designers to detect and repair a certain problem. Although the manual repair method can repair the model well to meet the requirements of simulation calculation, the process requires a lot of manpower and material resources, resulting in a waste of resources.

[0004] Data-driven methods can be divided into traditional methods and large model-based methods. By training and optimizing data through algorithms, the body model can be repaired more quickly than manual methods.

[0005] However, the existing pre-processing research on car body models has many shortcomings: the repair method of existing research is simply based on the geometric structure, without combining it with engineering development experience. There is no unified evaluation method for the results of topological structure error detection and repair, and there is no quantitative standard. Many existing methods repair individual problems, but when many problems arise, repairing the current problem will generate new problems, which will affect subsequent simulation calculations.

[0006] In engineering applications, especially when it comes to complex surface inspection of automobile body models, we often face the challenge of detecting and repairing a large number of topological errors. The body model is usually composed of thousands or even tens of thousands of complex surfaces of different shapes and sizes. These complex geometric structures make it a difficult task to comprehensively and accurately identify all topological errors during the inspection process. Summary of the invention

[0007] The present invention provides an intelligent detection method for passenger car pre-processing model problems, which ensures that all possible topological structure errors can be identified, thereby providing an accurate basis for subsequent repair steps and solving the problem of topological structure error detection of complex surface models in engineering scenarios.

[0008] The technical solution of the present invention is described as follows in conjunction with the accompanying drawings:

[0009] In a first aspect, an embodiment of the present invention provides a method for intelligently detecting problems in a pre-processing model of a passenger vehicle, comprising the following steps:

[0010] Step 1: Establish a car body model with topological structure errors, and perform data analysis and reading on the car body model;

[0011] Step 2: Preprocess the car body model, including denoising and simplification;

[0012] Step 3: Detect the vehicle body model, determine the type of topological structure error, and mark it accordingly.

[0013] Furthermore, in the step 1, the vehicle body model is established by using boundary representation, namely B-Rep, as a basic structure.

[0014] Furthermore, the B-Rep structure is composed of elements of different orders, namely vertices, edges and faces, and topological relationships between the elements.

[0015] Furthermore, in step 2, the preprocessing includes denoising and simplification.

[0016] Furthermore, in the step three, the error types detected on the vehicle body model include: detection of redundant faces, detection of repeated faces, detection of intersecting faces, detection of holes, and detection of gaps.

[0017] Furthermore, the detection sequence is: detection of redundant surfaces, detection of repeated surfaces, detection of intersecting surfaces, detection of holes and detection of gaps.

[0018] Furthermore, the specific method for detecting the redundant faces is as follows:

[0019] Define non-functional faces, tiny faces, and isolated faces;

[0020] Detect the features of non-functional faces, tiny faces and isolated faces. If the matching features are detected, it is determined that the redundant faces are detected and marked;

[0021] The specific method for detecting repeated faces is as follows:

[0022] Define the surfaces with overlapping positions and surfaces with the same geometric shapes;

[0023] Detect the features of the surfaces with overlapping positions and surfaces with the same geometric shapes, identify the two surfaces that completely overlap, and then identify the surfaces that partially overlap;

[0024] The specific method for detecting the intersecting surface is as follows:

[0025] Define the intersection faces;

[0026] According to the structural division of the body model, the overall body model containing a large number of faces is converted into multiple sets of low order of magnitude;

[0027] The BRepAlgoAPI_Common function in the Pythonocc library is used to perform Boolean intersection calculation. The returned value is the result of the Boolean intersection calculation. If the result is an empty set, it means that the two input faces have no intersection. If the output result is not empty, the two input faces are intersection faces and are marked.

[0028] The specific method for detecting the holes is as follows:

[0029] Define holes;

[0030] According to the characteristics of the hole, first find a boundary edge, start looking for the next boundary edge from one end point of the boundary edge, and then iterate from the end point of the next boundary edge until all the selected boundary edges can form a closed loop. This closed loop surrounded by the boundary edges is the hole and is marked;

[0031] The specific method for detecting the gap is as follows:

[0032] Define the gap;

[0033] According to the characteristics of the gap, the distance between every two boundary edges is first calculated. If the distance between two boundary edges is less than the set threshold, the distance between the two boundary edges is a gap and is marked.

[0034] In a second aspect, an embodiment of the present invention further provides an intelligent detection device for a pre-processing model problem of a passenger car, comprising:

[0035] The data parsing and reading module is used to establish a body model with topological errors and to parse and read the data of the body model;

[0036] A preprocessing module is used to preprocess the car body model, including denoising and simplification;

[0037] The detection module is used to detect the vehicle body model, determine the type of topological structure error, and mark it accordingly.

[0038] In a third aspect, a terminal is provided, including:

[0039] one or more processors;

[0040] a memory for storing the one or more processor-executable instructions;

[0041] Wherein, the one or more processors are configured to:

[0042] Execute the method described in the first aspect of the embodiment of the present invention.

[0043] In a fourth aspect, a non-temporary computer-readable storage medium is provided. When the instructions in the storage medium are executed by a processor of a terminal, the terminal is enabled to execute the method described in the first aspect of an embodiment of the present invention.

[0044] In a fifth aspect, an application product is provided. When the application product is running on a terminal, the terminal executes the method described in the first aspect of the embodiment of the present invention.

[0045] The beneficial effects of the present invention are:

[0046] 1) Starting from the data structure represented by the boundary, the present invention can more accurately detect the location of the topological structure error and then repair it, and it can also reduce a lot of computational costs, realize fully automatic detection and repair, and does not require manual operation, saving more time;

[0047] 2) The present invention adopts the supremum to include as few redundant elements as possible while ensuring that all problems are detected; secondly, for the sequentiality of each fully automatic detection algorithm, a reasonable arrangement is made through multiple experiments to ensure that running the current algorithm will not have redundant effects on subsequent algorithms;

[0048] 3) The present invention improves the pre-processing efficiency of the vehicle body model; this method classifies and sorts similar problems through intelligent identification, and with the automatic repair algorithm, the pre-processing efficiency can be improved by 85%;

[0049] 4) The present invention reduces resource loss; it does not require additional manpower and material resources, and only requires running the system to uniformly process a series of topological structure errors that appear in the vehicle body model according to the standard. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0051] Figure 1 A schematic diagram of a process of an intelligent detection method for a passenger car pre-processing model problem according to the present invention;

[0052] Figure 2 Schematic diagram of isolated points and boundary edges;

[0053] Figure 3a It is a schematic diagram of the non-functional surface;

[0054] Figure 3b is a schematic diagram of an isolated surface;

[0055] Figure 4 is a schematic diagram of multiple edges;

[0056] Figure 5a It is a schematic diagram of the full repeat surface;

[0057] Figure 5b is a schematic diagram of a semi-repeated surface;

[0058] Figure 6 is a schematic diagram of the intersecting surface;

[0059] Figure 7 is a schematic diagram of the hole;

[0060] Figure 8 is a schematic diagram of the gap;

[0061] Fig. 9 It is a structural schematic diagram of an intelligent detection device for a passenger car pre-processing model problem according to the present invention;

[0062] Fig.10 The present invention is a schematic block diagram of a terminal structure. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0065] Embodiment 1

[0066] This embodiment provides a method for intelligently detecting problems in a pre-processing model of a passenger car. The method can be performed by an intelligent detection device for problems in a pre-processing model of a passenger car in an embodiment of the present invention. The device can be implemented in software and / or hardware, as follows:

[0067] See also Figure 1 , an intelligent detection method for a passenger car pre-processing model problem, comprising the following steps:

[0068] Step 1: Create a car body model with topological errors, and parse and read the data of the car body model, as follows:

[0069] The boundary representation (B-Rep) is used as the basic structure. The B-Rep structure consists of elements of different orders, namely vertices, edges and faces, as well as the topological relationship between the elements. Although it is difficult to operate the overall body model based on the boundary representation method, and the index structure sometimes faces problems such as huge storage data volume and long reading time, the boundary representation method can store the relationship between faces, edges and vertices very well, so that the task can be accurately positioned and the details can be modified.

[0070] Step 2: Preprocess the car body model, including denoising and simplification;

[0071] Step 3: Detect the vehicle body model, determine the type of topological structure error, and mark it accordingly;

[0072] The present invention extracts the point, edge, and surface structures where topological errors occur, wherein topological extraction and restricted geometry are achieved through index structure supervision. First, a definition and description are given based on the geometric features of each topological error, explaining why the current problem occurs and the necessity of dealing with the current problem, and examples are given for related situations; then, for each topological error, a corresponding fully automatic detection algorithm is designed, which can detect all corresponding problems at one time, and the relevant steps are explained. In addition, combined with experiments, the designed fully automatic detection algorithm is evaluated to verify the effectiveness and practicality of the process. Finally, a marked vehicle body model is output, wherein each topological error is marked by category to facilitate the next step of problem handling.

[0073] The error types detected in the vehicle body model in step three include: detection of redundant faces, detection of repeated faces, detection of intersecting faces, detection of holes and detection of gaps.

[0074] A. The specific method for detecting the redundant surfaces is as follows:

[0075] In the design and manufacturing process of automobile body models, redundant faces (also called redundant faces or invalid faces) refer to those faces that do not meet the design intent, do not participate in the final product form, or do not contribute positively to the product performance and appearance. These redundant faces may be caused by design errors, automatic operation errors of modeling software, loss of accuracy during data conversion, or other technical reasons. Defining and identifying these redundant faces is a key step in optimizing models, improving manufacturing efficiency and product quality.

[0076] In order to realize the automatic detection of several types of redundant faces, we first need to introduce the following definitions:

[0077] Isolated point: In the car body model, an isolated point is a point that is only connected to one face and is not indexed by other faces. The definition in topology is as follows: Let A be a subset in a topological space X. If there exists a point x∈A such that x has no other points in the neighborhood U of A, then x is called an isolated point of the set A. Formally, a point x∈A is an isolated point of A if and only if there exists an open set So that U∩A={x}. Figure 2 The blue vertices shown in the figure are isolated points.

[0078] Boundary edge: In the car body model, a boundary edge is an edge that is connected to only one face and is not indexed by other faces. The definition in topology is as follows: Let P be a polyhedron or a mesh, and E be the set of its edges. An edge e∈E is a boundary edge if and only if e belongs to only one face or to a boundary. Formally, let F be the set of faces of the polyhedron P. If an edge e belongs to only one face f∈F, then the following conditions are satisfied: and Then e is called the boundary edge of P. For a subset A in a more general topological space, the boundary edge can be described as follows: Let A be a subset in a topological space X, represents the boundary of A. An edge e is a boundary edge of A if like Figure 2 The red edges shown in the figure are boundary edges.

[0079] Redundant faces can be defined and identified from the following aspects:

[0080] 1. Non-functional surfaces: These surfaces have no role in the actual function and structural integrity of the vehicle body, for example, internal surfaces that do not participate in load bearing, do not affect aerodynamic performance or are not visible. Non-functional surfaces, such as Figure 3a As shown, there may be multiple isolated points and boundary edges, and they may be connected to other non-functional faces, so an iterative method is required during detection to detect and delete them one by one.

[0081] 2. Micro faces: extremely small faces, usually caused by improper modeling accuracy or calculation errors. These faces cannot be realized in the actual manufacturing process and do not affect the performance or appearance of the product. Set a threshold s. When the area of ​​a face is less than s, it can be defined as a micro face.

[0082] 3. Isolated faces: faces that are not connected to other parts of the model. These faces may be auxiliary faces or useless fragments left over from the design process. All edges of this type of face are boundary edges, and all points are isolated points, such as Figure 3b shown.

[0083] The following is the algorithm flow of fully automatic detection of redundant faces:

[0084]

[0085]

[0086] In this algorithm flow, the goal is to detect according to the characteristics of each redundant surface. The algorithm first detects the redundant surfaces of some surfaces. In the subsequent deletion process, an iterative process will be carried out, and further detection and deletion will be performed.

[0087] B. The specific method for detecting repeated surfaces is as follows:

[0088] Duplicate faces are those where two or more geometrically identical or very similar faces are inadvertently created in the model; these faces may occupy the same spatial position, or be so close that the difference between them is minimal and cannot be distinguished by the naked eye. The existence of duplicate faces not only increases the complexity of the model, but also may lead to errors and unnecessary computational burdens in subsequent processing. Therefore, defining and identifying these duplicate faces is of great significance for optimizing the model, improving modeling efficiency and final product quality; in order to achieve automatic detection of several types of redundant faces, the following definitions are first introduced:

[0089] Multiple edges; in the car body model, multiple edges refer to an edge that is shared by three or more faces at the same time. Let P be a geometric object, such as a polygon or a polyhedron, with a vertex set V and an edge set E. If the edges e = (vi, vj) and e′ = (vi, vj) exist in E and e≠e′, then e and e′ are called multiple edges. Figure 4 As shown, the blue edge in the figure is shared by three faces, that is, it is a multiple edge;

[0090] Duplicate faces can be defined based on the following characteristics:

[0091] 1. Overlapping faces: Two or more faces completely overlap, that is, they occupy the same spatial position, and their edges and vertices are also consistent. The edges of this type of face are all multiple edges. Figure 5a As shown, it can be seen that the faces surrounded by blue edges in the figure are two faces that completely overlap.

[0092] 2. Geometrically identical faces: The geometric shapes of the faces are identical or very close, even though they may be located slightly differently in space, or most of the areas of the two faces overlap, with only parts not overlapping, e.g. Figure 5b As shown;

[0093] The following is the algorithm flow for fully automatic detection of duplicate faces:

[0094]

[0095]

[0096] In the algorithm flow, two completely overlapping faces are first identified, and then the partially overlapping faces are identified and further deleted in subsequent steps.

[0097] C. The specific method for detecting the intersecting surface is as follows:

[0098] Intersection surfaces refer to the common areas where two or more geometric bodies (usually different parts of the model) intersect in space. This situation is common in complex automotive body design, especially when combining, modifying or optimizing the design. The treatment of intersection surfaces is very important to ensure the geometric consistency of the model, avoid manufacturing problems, and improve simulation accuracy.

[0099] The intersection of two planes is a positional relationship between two planes in space. Here the definition is expanded to the relationship between surfaces. If two surfaces in space have at least one common curve, and this common curve is excluding the boundary, then the two surfaces are defined as an intersection relationship, and the two surfaces are a set of intersecting faces. The mathematical description in topology is as follows: Let P be a polyhedron, and its face set is F. Each face f∈F can be represented as a set of its boundary and internal points. Two faces f1, f2∈F are intersecting faces if and only if their intersection f1∩f2 is non-empty, and the intersection is not a set of their common edge nodes or common vertices.

[0100] Formally, let faces f1 and f2 be faces of a polyhedron P. If there exists a point set The following conditions are met: 1. I = f1 ∩ f2, 2. 3. If I is not a set of common boundaries or vertices of f1 and f2, then f1 and f2 are said to be intersecting faces. Figure 6 As shown, it can be seen that the two gray patches in the figure are intersecting surfaces.

[0101] The following is the algorithm flow for fully automatic detection of intersecting surfaces:

[0102]

[0103] In the algorithm flow, in order to reduce the amount of calculation, we must first divide the body model into multiple low-order sets according to the preliminary structure of the body model. In this way, when performing the intersection calculation in the next step, we can avoid problems such as calculation termination or long calculation time due to the large amount of data. In the intersection calculation process of step 2, the BRepAlgoAPI_Common function in the Pythonocc library is used. This function can perform Boolean intersection calculation on the two input modules. The returned value is the result after the Boolean intersection calculation. If the result is an empty set, it means that the two input faces have no intersection; if the output result is not empty, then the two input faces are intersecting faces, which can be saved in a new set for use in the next repair process.

[0104] D. The specific method for detecting the holes is as follows:

[0105] Holes refer to spaces or parts of a model that are not filled with material. These holes may be intentional in design for weight reduction, ventilation, wiring, etc., or they may be inadvertent errors in the modeling process. In either case, the definition and processing of holes are an important part of 3D modeling and computer-aided design.

[0106] In a 3D model based on a polygonal mesh, a hole can be defined as a closed boundary on the surface of the model, where the area surrounded by this boundary is not covered by any face. More specifically, a hole is a closed loop consisting of a series of boundary edges, which belong to only one polygonal face. Suppose there is a polygonal mesh model (M), which consists of a series of vertices (V), edges (E) and faces (F). A hole (H) can be defined as: a sequence of boundary edges that constitute a closed loop of the hole, each boundary edge belongs to only one face, and these edges are connected in a certain order to form a closed path that is not covered by any face.

[0107] In a topological space X, holes can be defined by the concept of homology or homology. Let X be a topological space whose subset is a closed subset. A hole in a topological space X is a subset Let H be a closed set of X, and the complement of H, X\H, is not simply connected, that is, there is an irretractable closed path in X\H. Figure 7 As shown, we can see that the area surrounded by the red edge is a hole.

[0108] The following is the algorithm flow of fully automatic detection of holes:

[0109]

[0110]

[0111] In this algorithm, according to the characteristics of the hole, first find a boundary edge, start looking for the next boundary edge from one of its endpoints, and then iterate from the endpoint of the next boundary edge until all the selected boundary edges can form a closed loop. This closed loop surrounded by boundary edges is the hole we want. As shown in the figure, after the algorithm runs, it locates boundary edge 1, and then starts from its endpoint. The detection algorithm can traverse a circle of boundary edges surrounding the hole in the order of 1, 2, 3, and 4, so that the hole is detected.

[0112] E. The specific method for detecting the gap is as follows:

[0113] A gap refers to an unfilled space between two or more parts. These spaces may be due to design considerations (such as to ensure that there is enough tolerance between parts, to prevent thermal expansion, etc.), or they may be caused by inaccuracies in the modeling process. The treatment of gaps is very important to ensure the neatness of the car's appearance, improve the air tightness and water tightness of the vehicle, and reduce noise. In a three-dimensional model based on polygonal meshes, a gap can be defined as a linear or nonlinear gap between two geometric surfaces. This gap is usually a space defined by two adjacent but non-intersecting geometric surfaces. In topology, a gap usually refers to a partition resulting from removing a closed subset from a topological space, which results in a change in the connectivity of the space. The mathematical description of the gap is as follows: Let X be a topological space, is a closed subset. A gap S is a closed subset such that after removing S, the topological space X is divided into two or more disconnected parts.

[0114] Formally, gap The following conditions are satisfied: 1. S is a closed subset of X, that is, S is a closed set in the topological space of X, 2. X\S is not connected, that is, after removing S, X is divided into two or more disconnected parts. Specifically, suppose X\S is divided into multiple connected branches C1, C2,..., Ck (where k≥2), then: X\S=∪ki=1Ci, and for all i≠j, there is In other words, a gap S is a space that is separated into two or more disconnected parts after S is removed from the topological space X. The gap S can be a line, a curve, or a more complex closed subset in the space. Figure 8 As shown, when the distance between two boundary edges is less than a preset threshold, the distance between the two boundary edges can be defined as a gap.

[0115] The following is the algorithm flow of fully automatic detection of gaps:

[0116]

[0117]

[0118] In this algorithm, according to the characteristics of the gap, the distance between each two boundary edges is first calculated. If the distance between two boundary edges is less than the set threshold, then the distance between the two boundary edges is a gap, and the two boundary edges are recorded as a group for subsequent repair processing. Figure 8 As shown in FIG. 1 , a set of detected boundary edges are shown, and the gaps between them are the gaps to be repaired. The distance between the midpoints of the two edges is less than l.

[0119] In summary, first, the actual problems in engineering are transformed into mathematical problems, and the corresponding algorithms are designed accordingly. In the process of algorithm design, after many experiments and optimizations, a set of algorithm flows as described above are finally determined.

[0120] Model import and preprocessing: Import complex surface models and preprocess the models, including denoising and simplification.

[0121] Topology Error Detection: Utilizes an improved topology analysis algorithm to perform a detailed check on every surface and boundary in the model.

[0122] Special detection modules are designed for different types of topology errors to ensure comprehensiveness and accuracy of detection.

[0123] False detection handling: Although the algorithm is designed to minimize the occurrence of false detections, it is inevitable that some non-problem areas will be detected.

[0124] These false detections will be reconfirmed and processed during the subsequent repair process to ensure the accuracy of the final result.

[0125] The effectiveness of the algorithm was verified through multiple experiments and adjustments. The experimental results show that the algorithm can efficiently and comprehensively detect all topological errors. Even if there are a few false positives, they can be effectively handled in the subsequent repair process, thus ensuring the accuracy and completeness of the overall detection.

[0126] The detection algorithm targets the following five topological errors: redundant face detection, repeated face detection, intersecting face detection, hole detection, and gap detection. During the algorithm design process, multiple experiments and optimizations were conducted to determine the best operating order to ensure that all problems can be fully detected.

[0127] During the experiment, the algorithm's running order was repeatedly adjusted and optimized, and the current order was finally determined; this order can detect all topological errors to the maximum extent and effectively reduce the situation where old problems cause new problems. Through multiple experimental verifications, the algorithm has demonstrated excellent detection capabilities and stability, and can comprehensively identify all potential problems in the car body model, providing a solid foundation for subsequent repair work.

[0128] Embodiment 2

[0129] See also Fig. 9 , this embodiment provides an intelligent detection device for a passenger car pre-processing model problem, comprising:

[0130] The data parsing and reading module is used to establish a body model with topological errors and to parse and read the data of the body model;

[0131] A preprocessing module is used to preprocess the car body model, including denoising and simplification;

[0132] The detection module is used to detect the vehicle body model, determine the type of topological structure error, and mark it accordingly.

[0133] Embodiment 3

[0134] Fig.10 1 is a block diagram of a terminal provided in an embodiment of the present application, and the terminal may be a terminal in the above embodiment. The terminal may be a portable mobile terminal, such as a smart phone or a tablet computer. The terminal may also be referred to as a user device, a portable terminal, or other names.

[0135] Typically, the terminal includes: a processor 301 and a memory 302 .

[0136] The processor 301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 301 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 301 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 301 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 301 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0137] The memory 302 may include one or more computer-readable storage media, which may be tangible and non-transitory. The memory 302 may also include high-speed random access memory, and non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 302 is used to store at least one instruction, which is used to be executed by the processor 301 to implement a passenger car pre-processing model problem intelligent detection method provided in this application.

[0138] In some embodiments, the terminal may further include: a peripheral device interface 303 and at least one peripheral device. Specifically, the peripheral device includes: at least one of a radio frequency circuit 304 , a touch display screen 305 , a camera 306 , an audio circuit 307 , a positioning component 308 and a power supply 309 .

[0139] The peripheral device interface 303 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 301 and the memory 302. In some embodiments, the processor 301, the memory 302, and the peripheral device interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 301, the memory 302, and the peripheral device interface 303 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0140] The radio frequency circuit 304 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 304 communicates with the communication network and other communication devices through electromagnetic signals. The radio frequency circuit 304 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the radio frequency circuit 304 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The radio frequency circuit 304 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to: the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 304 may also include circuits related to NFC (Near Field Communication), which is not limited in this application.

[0141] The touch display screen 305 is used to display the UI (User Interface). The UI may include graphics, text, icons, videos and any combination thereof. The touch display screen 305 also has the ability to collect touch signals on the surface or above the surface of the touch display screen 305. The touch signal can be input to the processor 301 as a control signal for processing. The touch display screen 305 is used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the touch display screen 305 can be one, and the front panel of the terminal is set; in other embodiments, the touch display screen 305 can be at least two, which are respectively set on different surfaces of the terminal or are folded; in some other embodiments, the touch display screen 305 can be a flexible display screen, which is set on the curved surface or folded surface of the terminal. Even, the touch display screen 305 can also be set to a non-rectangular irregular shape, that is, a special-shaped screen. The touch display screen 305 can be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode, organic light-emitting diode).

[0142] The camera assembly 306 is used to capture images or videos. Optionally, the camera assembly 306 includes a front camera and a rear camera. Typically, the front camera is used to realize video calls or selfies, and the rear camera is used to realize the shooting of photos or videos. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, and a wide-angle camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, and the fusion of the main camera and the wide-angle camera to realize panoramic shooting and VR (Virtual Reality) shooting functions. In some embodiments, the camera assembly 306 may also include a flash. The flash can be a monochrome temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0143] The audio circuit 307 is used to provide an audio interface between the user and the terminal. The audio circuit 307 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into the processor 301 for processing, or input them into the radio frequency circuit 304 to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the terminal. The microphone may also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from the processor 301 or the radio frequency circuit 304 into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 307 may also include a headphone jack.

[0144] The positioning component 308 is used to locate the current geographical location of the terminal to implement navigation or LBS (Location Based Service). The positioning component 308 can be a positioning component based on the US GPS (Global Positioning System) or China's Beidou system.

[0145] The power supply 309 is used to power various components in the terminal. The power supply 309 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 309 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery charged through a wired line, and a wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0146] Those skilled in the art will understand that Fig.10The structure shown in the figure does not constitute a limitation on the terminal, and may include more or less components than those shown in the figure, or combine certain components, or adopt a different component arrangement.

[0147] Embodiment 4

[0148] In an exemplary embodiment, a computer-readable storage medium is also provided, on which a computer program is stored. When the program is executed by a processor, an intelligent detection method for a passenger car pre-processing model problem is implemented as provided in all the inventive embodiments of the present application.

[0149] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device.

[0150] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0151] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0152] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0153] Embodiment 5

[0154] In an exemplary embodiment, an application product is also provided, including one or more instructions, which can be executed by the processor 301 of the above-mentioned device to complete the above-mentioned intelligent detection method for pre-processing model problems of a passenger car.

[0155] Although the embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and implementation mode. It can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily realized. Therefore, without departing from the general concept defined by the claims and equivalent scope, the present invention is not limited to the specific details and the illustrations shown and described here.

Claims

1. An intelligent detection method for passenger car pre-processing model problems, characterized in that: The following steps are involved: Step 1: Establish a car body model with topological structure errors, and perform data analysis and reading on the car body model; Step 2: Preprocess the car body model, including denoising and simplification; Step 3: Detect the vehicle body model, determine the type of topological structure error, and mark it accordingly.

2. The intelligent detection method for passenger car pre-processing model problems according to claim 1 is characterized in that: In the step 1, a vehicle body model is established by using a boundary representation, namely B-Rep, as a basic structure.

3. The intelligent detection method for passenger car pre-processing model problems according to claim 2 is characterized in that: The B-Rep structure is composed of elements of different orders, namely vertices, edges and faces, and topological relationships between the elements.

4. The intelligent detection method for passenger car pre-processing model problems according to claim 1 is characterized in that: In the step 2, the preprocessing includes denoising and simplification.

5. The intelligent detection method for passenger car pre-processing model problems according to claim 1 is characterized in that: In the step three, the error types detected in the vehicle body model include: detection of redundant faces, detection of repeated faces, detection of intersecting faces, detection of holes, and detection of gaps.

6. The intelligent detection method for passenger car pre-processing model problems according to claim 5 is characterized in that: The detection sequence is: detection of redundant surfaces, detection of repeated surfaces, detection of intersecting surfaces, detection of holes and detection of gaps.

7. The intelligent detection method for passenger car pre-processing model problems according to claim 5 is characterized in that: The specific method for detecting the redundant faces is as follows: Define non-functional faces, tiny faces, and isolated faces; Detect the features of non-functional faces, tiny faces and isolated faces. If the matching features are detected, it is determined that the redundant faces are detected and marked; The specific method for detecting repeated faces is as follows: Define the surfaces with overlapping positions and surfaces with the same geometric shapes; Detect the features of the surfaces with overlapping positions and surfaces with the same geometric shapes, identify the two surfaces that completely overlap, and then identify the surfaces that partially overlap; The specific method for detecting the intersecting surface is as follows: Define the intersection faces; According to the structural division of the body model, the overall body model containing a large number of faces is converted into multiple sets of low order of magnitude; The BRepAlgoAPI_Common function in the Pythonocc library is used to perform Boolean intersection calculation. The returned value is the result of the Boolean intersection calculation. If the result is an empty set, it means that the two input faces have no intersection. If the output result is not empty, the two input faces are intersection faces and are marked. The specific method for detecting the holes is as follows: Define holes; According to the characteristics of the hole, first find a boundary edge, start looking for the next boundary edge from one end point of the boundary edge, and then iterate from the end point of the next boundary edge until all the selected boundary edges can form a closed loop. This closed loop surrounded by the boundary edges is the hole and is marked; The specific method for detecting the gap is as follows: Define the gap; According to the characteristics of the gap, the distance between every two boundary edges is first calculated. If the distance between two boundary edges is less than the set threshold, the distance between the two boundary edges is a gap and is marked.

8. An intelligent detection device for passenger car pre-processing model problems, characterized in that: include: The data parsing and reading module is used to establish a body model with topological errors and to perform data parsing and reading on the body model; A preprocessing module, used to preprocess the car body model, including denoising and simplification; The detection module is used to detect the vehicle body model, determine the type of topological structure error, and mark it accordingly.

9. A terminal, characterized in that: include: one or more processors; a memory for storing the one or more processor-executable instructions; Wherein, the one or more processors are configured to: Execute an intelligent detection method for passenger car pre-processing model problems as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that: When the instructions in the storage medium are executed by the processor of the terminal, the terminal is enabled to execute the intelligent detection method for passenger car pre-processing model problems as described in any one of claims 1 to 7.

Images