A method, device and storage medium for identifying assembly deviations of a body-in-white

Abstract

The present invention discloses a method, device and storage medium for identifying assembly deviations of a body in white, relating to the technical field of vehicle manufacturing, and capable of improving the accuracy of identifying assembly deviations of a body in white. The method includes: obtaining the attribute information of each first feature point among a plurality of first feature points of the body in white, where the attribute information includes an assembly deviation value, a tolerance range and coordinates; determining the region to which each first feature point belongs according to the target information of each first feature point, where the target information includes coordinates; adaptively determining the neighborhood corresponding to each region according to the coordinates, assembly deviation value and tolerance range of each first feature point in each region; determining the minimum number of sample points included in the neighborhood according to the neighborhood; and determining a target region based on a clustering algorithm according to the neighborhood and the minimum number of sample points, where the target region includes a plurality of first feature points with assembly deviations.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle manufacturing, and particularly to a method, device and storage medium for identifying assembly deviations of a white body in white (BIW). Background Art

[0002] A BIW refers to a welded assembly of body structural parts and covering parts, including front fenders, doors, engine hoods, and trunk lids, but not including unpainted bodies with accessories and decorative parts. The assembly deviation of a vehicle's BIW is an important factor affecting the overall vehicle manufacturing quality. The factors causing the assembly deviation of the BIW include factual factors that can be manually controlled (such as fixture wear or welding deformation, etc.), and accidental factors that cannot be manually controlled. In the prior art, there is a problem of low identification accuracy in the process of identifying the assembly deviation of the BIW. Summary of the Invention

[0003] The present invention provides a method, device and storage medium for identifying assembly deviations of a BIW, which can improve the identification accuracy of the assembly deviation of the BIW.

[0004] To achieve the above object, the present invention adopts the following technical solutions:

[0005] In a first aspect, the present invention provides a method for identifying assembly deviations of a BIW, the method comprising:

[0006] Obtaining the attribute information of each first feature point among a plurality of first feature points of the BIW, the attribute information including an assembly deviation value, a tolerance range and coordinates;

[0007] Determining the region to which each first feature point belongs according to the target information of each first feature point, the target information including coordinates;

[0008] Determining the neighborhood corresponding to each region according to the coordinates, assembly deviation value and tolerance range of each first feature point in each region;

[0009] Determining the minimum number of sample points included in the neighborhood according to the neighborhood;

[0010] Determining a target region according to the neighborhood and the minimum number of sample points, the target region including the feature points with assembly deviations among the plurality of first feature points.

[0011] When using the white body assembly deviation identification method provided by the present invention to identify the feature points with assembly deviations included in the white body, first, obtain the attribute information of multiple first feature points of the white body. The attribute information includes the assembly deviation value, the tolerance range, and the coordinates. Among them, the assembly deviation value and the tolerance range belong to non-spatial attribute information, and the coordinates belong to spatial attribute information. Secondly, according to the target information of each first feature point, determine the area to which each first feature point belongs, so that multiple first feature points can be divided into different areas. Then, according to the spatial attribute information and non-spatial attribute information of each first feature point in each area, determine the neighborhood corresponding to each area and the minimum number of sample points included in the neighborhood. In this way, according to the neighborhood and the minimum number of sample points, using the clustering algorithm, the feature points with assembly deviations in each area can be determined. As can be seen from the above, the white body assembly deviation identification algorithm provided by the embodiments of the present invention divides multiple first feature points into areas, and then respectively determines the center points included in each area and their corresponding neighborhoods and the minimum number of sample points, so as to determine the target area existing in each area. The target area includes the first feature points with assembly deviations. In this way, clustering analysis is carried out in different areas, which can not only improve the clustering efficiency, but also improve the accuracy of the results.

[0012] In a possible implementation manner, the above determining the neighborhood corresponding to each area according to the coordinates, assembly deviation value, and tolerance range of each first feature point in each area includes:

[0013] According to the assembly deviation value and tolerance range of each first feature point in each area, determine the second feature points and third feature points included in each area. The second feature points are abnormal feature points, and the third feature points are normal feature points;

[0014] According to the second feature points in each area, construct the first weighted undirected graph of each area;

[0015] According to the assembly deviation value and coordinates of each second feature point in each first weighted undirected graph, determine the neighborhood corresponding to each first weighted undirected graph.

[0016] In a possible implementation manner, the above determining the neighborhood corresponding to each first weighted undirected graph according to the assembly deviation value and coordinates of each second feature point in each first weighted undirected graph includes:

[0017] According to the second feature points with the same sign of the assembly deviation value in each first weighted undirected graph, generate the first weighted undirected subgraph, and the first weighted undirected subgraph includes the fourth feature points;

[0018] According to the coordinates of each fourth feature point in each first weighted undirected subgraph, determine the neighborhood corresponding to each first weighted undirected subgraph.

[0019] In a possible implementation, determining the neighborhood corresponding to each first weighted undirected subgraph according to the coordinates of each fourth feature point in each first weighted undirected subgraph includes:

[0020] Determining the first distance between each fourth feature point in each first weighted undirected subgraph and each other fourth feature point in the first weighted undirected subgraph;

[0021] Determining the average distance corresponding to each fourth feature point according to all the first distances;

[0022] Constructing at least one second weighted undirected subgraph according to all the first distances corresponding to each fourth feature point and the average distance, where the distance between any two fourth feature points in the second weighted undirected subgraph is less than the average distance;

[0023] Determining the neighborhood corresponding to each second weighted undirected subgraph according to the coordinates of each fourth feature point in each second weighted undirected subgraph.

[0024] In a possible implementation, determining the neighborhood corresponding to each second weighted undirected subgraph according to the coordinates of each fourth feature point in each second weighted undirected subgraph includes:

[0025] Determining the average distance corresponding to each fourth feature point in each second weighted undirected subgraph;

[0026] Determining the minimum average distance from all the average distances of the second weighted undirected subgraph;

[0027] Determining the minimum average distance as the neighborhood.

[0028] In a possible implementation, determining the minimum number of sample points included in the neighborhood according to the neighborhood includes:

[0029] Determining the fourth feature point corresponding to the neighborhood as the central feature point;

[0030] Determining the number of fourth feature points within the range corresponding to the neighborhood according to the central feature point and the neighborhood, and taking the number as the minimum number of sample points included in the neighborhood;

[0031] Determining the target area according to the neighborhood and the minimum number of sample points includes:

[0032] Performing clustering analysis on the fourth feature points of each second weighted undirected subgraph according to the neighborhood and the minimum number of sample points to obtain the target area corresponding to each second weighted undirected subgraph.

[0033] In a possible implementation, determining the second feature points and third feature points included in each region according to the assembly deviation value and tolerance range of each first feature point in each region includes:

[0034] For each first feature point in each region, the following operations are performed:

[0035] If the device deviation value of the first feature point is within the tolerance range, the first feature point is the third feature point;

[0036] If the assembly deviation value of the first feature point is not within the tolerance range, the first feature point is the second feature point.

[0037] In a possible implementation, after constructing the first weighted undirected graph of each region, the white body assembly deviation identification method further includes:

[0038] Determine the minimum second distance corresponding to the second feature point in each first weighted undirected graph, where the minimum second distance is the minimum value among the distances between each second feature point of each first weighted undirected graph and other second feature points in the first weighted undirected graph;

[0039] According to the minimum second distance corresponding to each second feature point, determine the number of second feature points and the number of third feature points within the range corresponding to each second feature point;

[0040] According to the number of second feature points and the number of third feature points within the range corresponding to each second feature point, determine whether to eliminate the second feature points within the range corresponding to each second feature point.

[0041] In a possible implementation, the white body assembly deviation identification method further includes:

[0042] Determine the minimum third distance corresponding to the second feature point in each first weighted undirected graph, where the minimum third distance is the minimum value among the distances between each second feature point of each first weighted undirected graph and other second feature points with the same sign of the assembly deviation value in the first weighted undirected graph;

[0043] According to the minimum third distance corresponding to each second feature point, determine the number of second feature points with the same sign of the assembly deviation value within the range corresponding to each second feature point, and the number of second feature points with different signs of the assembly deviation value;

[0044] According to the number of second feature points with the same sign of the assembly deviation value within the range corresponding to each second feature point, and the number of second feature points with different signs of the assembly deviation value, determine whether to eliminate the second feature points with the same sign of the assembly deviation value within the range corresponding to each second feature point, or to eliminate the second feature points with different signs of the assembly deviation value.

[0045] In a possible implementation, the above attribute information further includes a normal vector, and the above target information further includes a normal vector. Determining the region to which each first feature point belongs according to the target information of each first feature point includes:

[0046] Determining the position to which each first feature point belongs according to the coordinates of each first feature point;

[0047] Determining the region to which each first feature point belongs according to the position to which each first feature point belongs, the angle corresponding to the minimum value of the normal vector of each first feature point, and a preset angle value.

[0048] In a second aspect, the present invention provides a white body assembly deviation recognition device, and the white body assembly deviation recognition device includes:

[0049] An acquisition unit, configured to acquire the attribute information of each first feature point among a plurality of first feature points of a white body, where the attribute information includes an assembly deviation value, a tolerance range, and coordinates;

[0050] A processing unit, configured to determine the region to which each first feature point belongs according to the target information of each first feature point, where the target information includes the coordinates; determine the neighborhood corresponding to each region according to the coordinates, the assembly deviation value, and the tolerance range of each first feature point in each region; determine the minimum number of sample points included in the neighborhood; and determine a target region according to the neighborhood and the minimum number of sample points, where the target region includes the feature points with assembly deviations among the plurality of first feature points.

[0051] In a possible implementation, the above processing unit is specifically configured to:

[0052] Determine a second feature point and a third feature point included in each region according to the assembly deviation value and the tolerance range of each first feature point in each region, where the second feature point is an abnormal feature point and the third feature point is a normal feature point;

[0053] Construct a first weighted undirected graph for each region according to the second feature points in each region;

[0054] Determine the neighborhood corresponding to each first weighted undirected graph according to the assembly deviation value and the coordinates of each second feature point in each first weighted undirected graph.

[0055] In a possible implementation, the above processing unit is specifically configured to:

[0056] Generate a first weighted undirected subgraph according to the second feature points with the same sign of the assembly deviation value in each first weighted undirected graph, where the first weighted undirected subgraph includes fourth feature points;

[0057] Determine the neighborhood corresponding to each first weighted undirected subgraph according to the coordinates of each fourth feature point in each first weighted undirected subgraph.

[0058] In a possible implementation manner, the above processing unit is specifically configured to:

[0059] Determine the first distance between each fourth feature point in each first weighted undirected subgraph and each other fourth feature point in the first weighted undirected subgraph;

[0060] Determine the average distance corresponding to each fourth feature point according to all the first distances;

[0061] Construct at least one second weighted undirected subgraph according to all the first distances corresponding to each fourth feature point and the average distance, where the distance between the fourth feature points in the second weighted undirected subgraph and other fourth feature points in the second weighted undirected subgraph is less than the average distance;

[0062] Determine the neighborhood corresponding to each second weighted undirected subgraph according to the coordinates of each fourth feature point in each second weighted undirected subgraph.

[0063] In a possible implementation manner, the above processing unit is specifically configured to:

[0064] Determine the average distance corresponding to each fourth feature point in each second weighted undirected subgraph;

[0065] Determine the minimum average distance from all the average distances of the second weighted undirected subgraph;

[0066] Determine the minimum average distance as the neighborhood.

[0067] In a possible implementation manner, the above processing unit is specifically configured to:

[0068] Determine the fourth feature point corresponding to the neighborhood as the central feature point;

[0069] According to the central feature point and the neighborhood, determine the number of fourth feature points within the range corresponding to the neighborhood, and use the number as the minimum number of sample points included in the neighborhood;

[0070] The above processing unit is specifically configured to:

[0071] Perform clustering analysis on the fourth feature points of each second weighted undirected subgraph according to the neighborhood and the minimum number of sample points to obtain the target region corresponding to each second weighted undirected subgraph.

[0072] In a possible implementation manner, for each first feature point in each region, the above processing unit is specifically configured to:

[0073] If the device deviation value of the first feature point is within the tolerance range, the first feature point is the third feature point;

[0074] If the assembly deviation value of the first feature point is not within the tolerance range, the first feature point becomes the second feature point.

[0075] In a possible implementation, after constructing the first weighted undirected graph of each region, the processing unit is further used to determine the minimum second distance corresponding to the second feature point in each first weighted undirected graph, where the minimum second distance is the minimum value of the distances between each second feature point of each first weighted undirected graph and other second feature points in the first weighted undirected graph;

[0076] Determine the number of second feature points and the number of third feature points within the range corresponding to each second feature point according to the minimum second distance corresponding to each second feature point;

[0077] Whether to remove the second feature points within the range corresponding to each second feature point is determined according to the number of second feature points and the number of third feature points within the range corresponding to each second feature point.

[0078] In a possible implementation, the processing unit is further used to determine a minimum third distance corresponding to the second feature point in each first weighted undirected graph, the minimum third distance being the minimum value of the distances between each second feature point of each first weighted undirected graph and other second feature points in the first weighted undirected graph with the same sign as the assembly deviation values;

[0079] Determine, according to the minimum third distance corresponding to each second feature point, the number of second feature points with the same sign of assembly deviation values ​​within the range corresponding to each second feature point, and the number of second feature points with different signs of assembly deviation values;

[0080] Based on the number of second feature points with the same sign of assembly deviation values ​​within the range corresponding to each second feature point and the number of second feature points with different signs of assembly deviation values, it is determined whether to eliminate the second feature points with the same sign of assembly deviation values ​​within the range corresponding to each second feature point or to eliminate the second feature points with different signs of assembly deviation values.

[0081] In a possible implementation manner, the attribute information further includes a normal vector, and the target information further includes a normal vector; and the processing unit is specifically configured to:

[0082] According to the coordinates of each first feature point, determine the position to which each first feature point belongs;

[0083] The region to which each first feature point belongs is determined according to the position to which each first feature point belongs, the angle corresponding to the minimum value of the normal vector of each first feature point, and the preset angle value.

[0084] In a third aspect, the present invention provides a white body assembly deviation identification device, which includes: a processor and a memory. The memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the white body assembly deviation identification device executes the white body assembly deviation identification method as described in the first aspect and any possible implementation manner thereof.

[0085] In a fourth aspect, the present invention provides a computer-readable storage medium, on which computer instructions are stored. When the computer instructions run on the white body assembly deviation identification device, the white body assembly deviation identification device is caused to execute the white body assembly deviation identification method as described in any item of the first aspect or the possible implementation manners of the first aspect. Description of the Drawings

[0086] Figure 1 is one of the structural schematic diagrams of the white body assembly deviation identification device provided by the embodiment of the present invention;

[0087] Figure 2 is one of the flow schematic diagrams of the white body assembly deviation identification method provided by the embodiment of the present invention;

[0088] Figure 3 is the second of the flow schematic diagrams of the white body assembly deviation identification method provided by the embodiment of the present invention;

[0089] Figure 4 is the third of the flow schematic diagrams of the white body assembly deviation identification method provided by the embodiment of the present invention;

[0090] Figure 5 is the fourth of the flow schematic diagrams of the white body assembly deviation identification method provided by the embodiment of the present invention;

[0091] Figure 6 is the fifth of the flow schematic diagrams of the white body assembly deviation identification method provided by the embodiment of the present invention;

[0092] Figure 7 is the second of the structural schematic diagrams of the white body assembly deviation identification device provided by the embodiment of the present invention. Detailed Embodiments

[0093] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0094] Hereinafter, the terms "first" and "second" are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present disclosure, unless otherwise specified, the meaning of "a plurality of" is two or more. Additionally, the use of "based on" or "according to" implies openness and inclusiveness, because a process, step, calculation, or other action based on or according to one or more of the stated conditions or values may, in practice, be based on additional conditions or values beyond those stated.

[0095] In order to improve the recognition accuracy of the assembly deviation of a white body in white (BIW), embodiments of the present invention provide a method, apparatus, and storage medium for recognizing the assembly deviation of a BIW. First, attribute information of a plurality of first feature points of the BIW is obtained. The attribute information includes an assembly deviation value, a tolerance range, and coordinates. Among them, the assembly deviation value and the tolerance range belong to non-spatial attribute information, and the coordinates belong to spatial attribute information. Secondly, according to the target information of each first feature point, the region to which each first feature point belongs is determined, so that the plurality of first feature points can be divided into different regions. Then, according to the spatial attribute information and non-spatial attribute information of each first feature point in each region, the neighborhood corresponding to each region and the minimum number of sample points included in the neighborhood are determined. Thus, based on the neighborhood and the minimum number of sample points, using a clustering algorithm, the feature points with assembly deviations in each region can be determined. As can be seen from the above, the assembly deviation recognition algorithm provided by the embodiments of the present invention divides a plurality of first feature points into regions, and then respectively determines the neighborhood and the minimum number of sample points of each region, so as to determine the feature points with assembly deviations in each region. Performing clustering analysis by region in this way can not only improve the clustering efficiency but also improve the accuracy of the results.

[0096] The execution subject of the method for recognizing the assembly deviation of a BIW provided by the embodiments of the present invention is a device for recognizing the assembly deviation of a BIW. The device for recognizing the assembly deviation of a BIW can be a terminal device, or a central processing unit (CPU) in the terminal device, or a control module in the terminal device for recognizing the assembly deviation of a BIW, or a client in the terminal device for recognizing the assembly deviation of a BIW. In the embodiments of the present invention, taking the terminal device as an example to execute the method for recognizing the assembly deviation of a BIW, the method for recognizing the assembly deviation of a BIW provided by the present invention is described. Exemplarily, the terminal device can be a smart phone, a tablet computer, a desktop computer, or other devices.

[0097] The method for identifying the assembly deviation of a body-in-white provided by an embodiment of the present invention can be applicable to a system for identifying the assembly deviation of a body-in-white. The system for identifying the assembly deviation of a body-in-white can include a three-coordinates measuring machine (CMM) and the above-mentioned terminal device. The CMM and the terminal device are connected by means of wired communication or wireless communication.

[0098] The CMM is used to measure the body-in-white to obtain the attribute information of a plurality of first feature points of the body-in-white. It is also used to send the attribute information of the plurality of first feature points to the terminal device.

[0099] Among them, the first feature point can be an important detection point of the body-in-white. The important detection point can be divided into three categories, namely, the main positioning reference detection point, the key product feature detection point, and the key control feature detection point. The attribute information of the first feature point obtained by the CMM can include the name, coordinates, normal vector, measurement date, measurement personnel information, etc. of the feature point.

[0100] Exemplarily, when the CMM measures the body-in-white, the center point of the front axle center of the body-in-white is used as the coordinate origin, the positive direction of the X-axis is pointed to the rear of the vehicle, the positive direction of the Y-axis is pointed to the right side of the vehicle, the positive direction of the Z-axis is pointed to the upper side of the vehicle, and the coordinate unit is centimeter.

[0101] Figure 1 FIG. is one of the structural schematic diagrams of the device for identifying the assembly deviation of a body-in-white. As Figure 1 shown, the device for identifying the assembly deviation of a body-in-white can include: a processor 11, a memory 12, a communication interface 13, and a bus 14. The processor 11, the memory 12, and the communication interface 13 can be connected through the communication bus 14.

[0102] The processor 11 is the control center of the device for identifying the assembly deviation of a body-in-white. It can be a single processor 11 or a collective term for multiple processing elements. For example, the processor 11 can be a general-purpose CPU, or other general-purpose processors 11, etc. Among them, the general-purpose processor 11 can be a microprocessor 11 or any conventional processor 11, etc.

[0103] As an embodiment, the processor 11 can include one or more CPUs. For example, Figure 1 as shown, CPU0 and CPU1.

[0104] The memory 12 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a magnetic disk storage medium, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0105] In a possible implementation, the memory 12 can exist independently of the processor 11. The memory 12 can be connected to the processor 11 through the bus 14 and is used to store instructions or program code. When the processor 11 calls and executes the instructions or program code stored in the memory 12, the white body assembly deviation identification method provided in the following embodiments of the present invention can be implemented.

[0106] In another possible implementation, the memory 12 can also be integrated with the processor 11.

[0107] The communication interface 13 is used to connect the white body assembly deviation identification device to other devices through a communication network. The communication network can be an Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc. The communication interface 13 can include a receiving unit for receiving data and a sending unit for sending data.

[0108] The bus 14 can be an Industry Standard Architecture (ISA) bus 14, a Peripheral Component Interconnect (PCI) bus 14, or an Extended Industry Standard Architecture (EISA) bus 14, etc. The bus 14 can be divided into an address bus 14, a data bus 14, a control bus 14, etc. For ease of representation, Figure 1 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus 14 or one type of bus 14.

[0109] It should be noted that Figure 1 the structure shown in the figure does not constitute a limitation on the white body assembly deviation identification device, exceptFigure 1 In addition to the components shown, the white body assembly deviation identification device may include more or fewer components than those shown, or combine certain components, or have different component arrangements.

[0110] The following describes the white body assembly deviation identification method provided by the embodiments of the present invention with reference to the accompanying drawings.

[0111] As Figure 2 shown, the white body assembly deviation identification method provided by the embodiments of the present invention includes the following steps 201-step 205.

[0112] 201. The terminal device obtains the attribute information of each first feature point among multiple first feature points of the white body, and the attribute information includes an assembly deviation value, a tolerance range, and coordinates.

[0113] In the actual application process, a CMM is used to measure the white body. Specifically, first, the white body is placed in the measurement three-dimensional space allowed by the CMM, and the CMM detects the white body according to the probe system. The CMM sends information such as the name Feature of each first feature point, the measurement space coordinates (x, y, z), the normal vector (i, j, k), the measurement date, and the measurement personnel among the multiple first feature points on the white body to the terminal device. Secondly, the terminal device obtains the process data of the white body. The process data includes the standard space coordinates (X, Y, Z) of each first feature point included in the multiple first feature points, and the X-axis tolerance range (-T x , T x ), the Y-axis tolerance range (-T y , T y ), and the Z-axis tolerance range (-T z , T z ) of each first feature point. Finally, the terminal device processes the data of the multiple first feature points obtained through the CMM and the multiple first feature points included in the process data to obtain the useful information of each first feature point among the multiple first feature points, that is, the attribute information of each first feature point among the multiple first feature points.

[0114] Exemplarily, the attribute information may include: the name Feature of the feature point, the measurement space coordinates (x, y, z), the standard space coordinates (X, Y, Z), the X-axis tolerance range (-T x , T x ), the Y-axis tolerance range (-T y , T y ), the Z-axis tolerance range (-T z , T z ), the normal vector (i, j, k), the measurement date Date, and the assembly deviation value (Δx, Δy, Δz).

[0115] 202. The terminal device determines the area to which each first feature point belongs according to the target information of each first feature point, and the target information includes coordinates.

[0116] Optionally, the above areas may include four areas: upper, lower, left, and right, corresponding to the roof area, chassis area, left body area, and right body area of the white body respectively. The terminal device may determine to which of the above areas each first feature point belongs according to the measured spatial coordinates (x, y, z) of each first feature point.

[0117] Exemplarily, when the measured spatial coordinates (x, y, z) of a first feature point are (4000, -200, 1780), this first feature point belongs to the roof area, where the coordinate unit is cm.

[0118] 203. The terminal device determines the neighborhood corresponding to each area according to the coordinates, assembly deviation values, and tolerance ranges of each first feature point in each area.

[0119] 204. The terminal device determines the minimum number of sample points included in the neighborhood according to the neighborhood.

[0120] 205. The terminal device determines the target area according to the neighborhood and the minimum number of sample points. The target area includes the feature points with assembly deviations among the multiple first feature points.

[0121] Optionally, after determining the neighborhood Eps and the minimum number of sample points MinPts in this neighborhood, the first feature points in the neighborhood can be clustered and analyzed according to the neighborhood Eps and the minimum number of sample points MinPts by using a clustering algorithm, so as to obtain a target area containing multiple first feature points with assembly deviations.

[0122] Exemplarily, the above clustering algorithm may be a density-based clustering algorithm (Density—Based Spatial Clustering of Application with Noise, DBSCAN).

[0123] When using the white body assembly deviation identification method provided by the embodiment of the present invention to identify the feature points with assembly deviations included in the white body, first, obtain the attribute information of multiple first feature points of the white body. The attribute information includes the assembly deviation value, the tolerance range, and the coordinates. Among them, the assembly deviation value and the tolerance range belong to non-spatial attribute information, and the coordinates belong to spatial attribute information. Secondly, according to the target information of each first feature point, determine the area to which each first feature point belongs, so that multiple first feature points can be divided into different areas. Then, according to the spatial attribute information and non-spatial attribute information of each first feature point in each area, determine the neighborhood corresponding to each area and the minimum number of sample points included in the neighborhood. In this way, according to the neighborhood and the minimum number of sample points, using a clustering algorithm, the feature points with assembly deviations in each area can be determined. As can be seen from the above, the white body assembly deviation identification algorithm provided by the embodiment of the present invention divides multiple first feature points into areas, and then respectively determines the neighborhood and the minimum number of sample points of each area, so as to determine the feature points with assembly deviations in each area. In this way, clustering analysis is carried out in different areas, which can not only improve the clustering efficiency, but also improve the accuracy of the results.

[0124] Optionally, in order to more accurately determine the area to which each first feature point belongs, especially to determine the area to which the first feature point at the junction of two adjacent areas belongs, the terminal device can combine the normal vector and coordinates of each first feature point to determine the area to which each first feature point belongs.

[0125] Combine Figure 2 , such as Figure 3 shown, when the attribute information further includes a normal vector and the target information further includes a normal vector, step 202 above may specifically include the following steps 301 and 302.

[0126] 301. The terminal device determines the position to which each first feature point belongs according to the coordinates of each first feature point.

[0127] 302. The terminal device determines the area to which each first feature point belongs according to the position to which each first feature point belongs, the angle corresponding to the minimum value of the normal vector of each first feature point, and a preset angle value.

[0128] Taking a first feature point as an example, the normal vector of the first feature point refers to a vector that passes through the first feature point and is perpendicular to the plane where the feature point is located. Each value in the normal vector is the cosine value of the angle between the normal vector and the X-axis, Y-axis, and Z-axis respectively. Therefore, for each value in the normal vector, the angle corresponding to each value in the normal vector can be obtained through the inverse cosine function.

[0129] Exemplarily, taking the coordinates of the first feature point A as (4400, 600, 1700), the normal vector as (0.85, 0.08, 0.5), and the preset angle as 70° as an example, the first feature point A is located at the junction of the roof area and the right side area of the vehicle body. If only based on the coordinates of the first feature point A, it is impossible to accurately determine whether the first feature point A is located in the roof area or in the right side area of the vehicle body. And the minimum value 0.08 in the normal vector of the first feature point A is less than the cosine value of the preset angle, that is, cos(70°), then it can be determined that the first feature point A belongs to the roof area.

[0130] Combined with Figure 3 , such as Figure 4 shown, the above step 203 may specifically include the following steps 401-step 403.

[0131] 401. The terminal device determines the second feature points and third feature points included in each area according to the assembly deviation values and tolerance ranges of each first feature point in each area.

[0132] Optionally, the above second feature points are abnormal feature points, and the third feature points are normal feature points. For each first feature point in each area, by comparing the assembly deviation values (Δx, Δy, Δz) of each first feature point and the tolerance range, each first feature point can be distinguished as a second feature point or a third feature point. Specifically, if the device deviation value of the first feature point is within the tolerance range, the terminal device determines that the first feature point is a third feature point. If the assembly deviation value of the first feature point is not within the tolerance range, the terminal device determines that the first feature point is a second feature point.

[0133] 402. The terminal device constructs a first weighted undirected graph for each area according to the second feature points in each area.

[0134] For multiple second feature points in each area, connecting each second feature point to each other second feature point can construct a first weighted undirected graph for each area. The first weighted undirected graph is a fully connected weighted undirected graph. The weight of each edge of the first weighted undirected graph is the distance between the two second feature points forming each edge, and this distance can be determined by the coordinates of the two second feature points.

[0135] 403. The terminal device determines the neighborhood corresponding to each first weighted undirected graph according to the assembly deviation values and coordinates of each second feature point in each first weighted undirected graph.

[0136] Optionally, to further ensure the accuracy of the neighborhood corresponding to each first weighted undirected graph, after constructing the first weighted undirected graph of each region, the terminal device may optionally remove the second feature points within the range corresponding to the second feature points in each first weighted undirected graph. The specific process may include: First, the terminal device determines the minimum second distance corresponding to the second feature points in each first weighted undirected graph. The minimum second distance is the minimum value among the distances between each second feature point in each first weighted undirected graph and other second feature points in the first weighted undirected graph. Then, the terminal device determines the number of second feature points and the number of third feature points within the range corresponding to each second feature point according to the minimum second distance corresponding to each second feature point. Finally, the terminal device may determine whether to remove the second feature points within the range corresponding to each second feature point according to the number of second feature points and the number of third feature points within the range corresponding to each second feature point.

[0137] Exemplarily, the condition for the terminal device to determine to remove the second feature points within the range corresponding to each second feature point according to the number of second feature points and the number of third feature points within the range corresponding to each second feature point is: If the percentage of the number of second feature points within the range corresponding to each second feature point in the total number is less than a preset value, the terminal device may determine to remove the second feature points within the range corresponding to each second feature point. The total number is the sum of the number of second feature points and the number of third feature points within the range corresponding to each second feature point.

[0138] Optionally, to further ensure the accuracy of the neighborhood corresponding to each first weighted undirected graph, the terminal device may further optionally remove the second feature points within the range corresponding to the second feature points in each first weighted undirected graph. The specific process may include: The terminal device determines the minimum third distance corresponding to the second feature points in each first weighted undirected graph. The minimum third distance is the minimum value among the distances between each second feature point in each first weighted undirected graph and other second feature points with the same sign of the assembly deviation value in the first weighted undirected graph. The terminal device determines the number of second feature points with the same sign of the assembly deviation value and the number of second feature points with different signs of the assembly deviation value within the range corresponding to each second feature point according to the minimum third distance corresponding to each second feature point. The terminal device determines whether to remove the second feature points with the same sign of the assembly deviation value within the range corresponding to each second feature point or remove the second feature points with different signs of the assembly deviation value according to the number of second feature points with the same sign of the assembly deviation value and the number of second feature points with different signs of the assembly deviation value within the range corresponding to each second feature point.

[0139] Exemplarily, the above terminal device determines whether to eliminate the second feature points with the same sign of the assembly deviation value within the range corresponding to each second feature point or the second feature points with different signs of the assembly deviation value based on the number of second feature points with the same sign of the assembly deviation value within the range corresponding to each second feature point and the number of second feature points with different signs of the assembly deviation value. The condition is as follows: If the number of second feature points with the same sign of the assembly deviation value within the range corresponding to each second feature point is much greater than the number of second feature points with different signs of the assembly deviation value within the range corresponding to each second feature point, the terminal device eliminates the number of second feature points with different signs of the assembly deviation value within the range corresponding to each second feature point. Otherwise, the terminal device eliminates the number of second feature points with the same sign of the assembly deviation value within the range corresponding to each second feature point.

[0140] Combined with Figure 4 , as Figure 5 shown, the above step 403 may include the following steps 501 and 502.

[0141] 501. The terminal device generates a first weighted undirected subgraph according to the second feature points with the same sign of the assembly deviation value in each first weighted undirected graph. The first weighted undirected subgraph includes fourth feature points.

[0142] Optionally, if the sign of the assembly deviation value of a second feature point is positive, it indicates that the shape of the second feature point is "convex" compared with the corresponding standard feature point. Similarly, if the sign of the assembly deviation value of a second feature point is negative, it indicates that the shape of the second feature point is "concave" compared with the corresponding standard feature point.

[0143] Optionally, in order to make the obtained neighborhood more accurate and be able to distinguish whether the shape of the feature points with assembly deviation is "convex" or "concave", the terminal device can further divide each first weighted undirected graph in each region to obtain a first weighted undirected subgraph, and the first weighted undirected subgraph includes fourth feature points. The fourth feature points in the first weighted undirected subgraph belong to the second feature points in the corresponding first weighted undirected graph. During the division process, the sign of the assembly deviation value of the second feature points in each first weighted undirected graph can be referred to. Specifically, the second feature points with the same sign of the assembly deviation value in each first weighted undirected graph can be divided into the same first weighted undirected subgraph. Each first weighted undirected graph may include one or two first weighted undirected subgraphs.

[0144] It should be understood that the number of special points in the weighted undirected graph is greater than 3. That is, the specific number of first weighted undirected subgraphs included in each first weighted undirected graph is related to the number of second feature points with the same sign of the assembly deviation value in each first weighted undirected graph.

[0145] Exemplarily, if a first weighted undirected graph includes 10 second feature points, and there are 5 second feature points with a positive assembly deviation value and 5 second feature points with a negative assembly deviation value, then the first weighted undirected graph may include two first weighted undirected subgraphs.

[0146] Exemplarily, if a first weighted undirected graph includes 10 second feature points, and there are 8 second feature points with a positive assembly deviation value and 2 second feature points with a negative assembly deviation value, then the first weighted undirected graph may include only one first weighted undirected subgraph. That is, the two second feature points with a negative assembly deviation value can be removed.

[0147] 502. The terminal device determines the neighborhood corresponding to each first weighted undirected subgraph according to the coordinates of each fourth feature point in each first weighted undirected subgraph.

[0148] Optionally, for each first weighted undirected subgraph, when determining the neighborhood corresponding to the first weighted undirected subgraph, first, the terminal device needs to determine the first distance between each fourth feature point in the first weighted undirected subgraph and each other fourth feature point in the first weighted undirected graph; second, the terminal device obtains the average distance corresponding to each fourth feature point in the first weighted undirected subgraph according to all the first distances and the number of fourth feature points in the first weighted undirected subgraph; finally, the terminal device determines the minimum average distance from all the average distances in the first weighted undirected subgraph, and the minimum average distance is the neighborhood corresponding to the first weighted undirected subgraph.

[0149] Optionally, in order to make the obtained neighborhood more accurate, the first weighted undirected graph in each region can be further divided to obtain a second weighted undirected subgraph, and the neighborhood corresponding to each second weighted undirected subgraph is determined respectively.

[0150] Combined with Figure 5 , as Figure 6 shown, step 502 above may include the following steps 601 - step 604.

[0151] 601. The terminal device determines the first distance between each fourth feature point in each first weighted undirected subgraph and each other fourth feature point in the first weighted undirected subgraph.

[0152] 602. The terminal device determines the average distance corresponding to each fourth feature point according to all the first distances.

[0153] 603. The terminal device constructs at least one second weighted undirected subgraph according to all the first distances corresponding to each fourth feature point and the average distance.

[0154] Among them, the distance between the fourth feature point in the second weighted undirected subgraph and other fourth feature points in the second weighted undirected subgraph is less than the average distance.

[0155] 604. The terminal device determines the neighborhood corresponding to each second weighted undirected subgraph according to the coordinates of each fourth feature point in each second weighted undirected subgraph.

[0156] Optionally, when the terminal device determines the neighborhood corresponding to each second weighted undirected subgraph, it may specifically include: First, the terminal device determines the average distance corresponding to each fourth feature point in each second weighted undirected subgraph. Then, the terminal device determines the minimum average distance from all the average distances of the second weighted undirected subgraph. Finally, the terminal device determines the minimum average distance as the neighborhood.

[0157] Optionally, the above terminal device determines the minimum number of sample points included in the neighborhood, specifically: The terminal device determines the fourth feature point corresponding to the neighborhood as the central feature point, and determines the number of fourth feature points within the range corresponding to the neighborhood according to the central feature point and the neighborhood, and takes the number as the minimum number of sample points included in the neighborhood.

[0158] Optionally, the above terminal device determines the target area according to the neighborhood and the minimum number of sample points, specifically: The terminal device performs clustering analysis on the fourth feature points of each second weighted undirected subgraph according to the neighborhood and the minimum number of sample points to obtain the target area corresponding to each second weighted undirected subgraph.

[0159] It should be understood that when performing clustering analysis on the fourth feature points in the second weighted undirected subgraph, the clustering algorithm DBSCAN is used. As for how to perform clustering analysis on the fourth feature points in each second weighted undirected subgraph according to the neighborhood, the minimum number of sample points corresponding to the central feature point of each second weighted undirected subgraph, and the clustering algorithm DBSCAN, it is the same as the prior art and is not the focus of the embodiments of the present invention. Therefore, the embodiments of the present invention do not describe it in detail.

[0160] As can be seen from the above, when determining the feature points with assembly deviations on a body-in-white, all the first feature points included in a body-in-white can be divided into multiple second weighted undirected subgraphs, so that the number of fourth feature points included in each second weighted undirected graph is much smaller than the number of all first feature points. For each second weighted undirected subgraph, since the number of fourth feature points included in a second weighted undirected subgraph is small, the clustering speed can be accelerated during the clustering analysis process, thereby shortening the clustering time, that is, the efficiency of identifying the feature points with assembly deviations on the body-in-white can be improved. At the same time, each second weighted undirected subgraph corresponds to a neighborhood and the minimum number of sample points, which makes the accuracy of the feature points with assembly deviations determined in each second weighted undirected subgraph higher.

[0161] It should be understood that the above description is a detailed process of clustering analysis for all the first special points included in a body-in-white to determine the feature points with assembly deviations. For a body-in-white, after determining the feature points with assembly deviations, these feature points with assembly deviations can be displayed on the display screen of the terminal device in the form of a 3D scatter plot, so that industrial manufacturing engineers can clearly understand the feature points with assembly deviations.

[0162] Optionally, in order to determine whether the feature points with assembly deviations on a body-in-white are factual factors that can be artificially controlled (for example: fixture wear or welding deformation, etc.) or accidental factors that cannot be artificially controlled, N body-in-whites can be continuously identified, where N is an integer greater than or equal to 3.

[0163] Exemplarily, taking N = 3 as an example, if the areas of the feature points with assembly deviations of 3 consecutive body-in-whites are similar, it can be determined that the feature points with assembly deviations of the above body-in-whites are caused by factual factors that can be artificially controlled.

[0164] The above mainly introduces the solution provided by the embodiments of the present invention from the perspective of the device. It can be understood that in order for the device to implement the above functions, it includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combining the algorithm steps of each example described in the embodiments disclosed in this article, the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described function for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0165] Figure 7 Shows a possible composition schematic diagram of the body-in-white assembly deviation identification device 700 involved in the above embodiments, as Figure 7As shown in the figure, the white body assembly deviation identification device 700 may include: an acquisition unit 701 and a processing unit 702.

[0166] Among them, the acquisition unit 701 is used to acquire the attribute information of each first feature point among multiple first feature points of the white body, and the attribute information includes an assembly deviation value, a tolerance range, and coordinates. The processing unit 702 is used to determine the area to which each first feature point belongs according to the target information of each first feature point, where the target information includes coordinates; determine the neighborhood corresponding to each area according to the coordinates, assembly deviation value, and tolerance range of each first feature point in each area; determine the minimum number of sample points included in the neighborhood according to the neighborhood; and determine the target area according to the neighborhood and the minimum number of sample points, where the target area includes the feature points with assembly deviations among multiple first feature points.

[0167] Optionally, the above-mentioned processing unit 702 is specifically used for:

[0168] Determine the second feature points and third feature points included in each area according to the assembly deviation value and tolerance range of each first feature point in each area, where the second feature points are abnormal feature points and the third feature points are normal feature points;

[0169] Construct a first weighted undirected graph for each area according to the second feature points in each area;

[0170] Determine the neighborhood corresponding to each first weighted undirected graph according to the assembly deviation value and coordinates of each second feature point in each first weighted undirected graph.

[0171] Optionally, the above-mentioned processing unit 702 is specifically used for:

[0172] Generate a first weighted undirected subgraph according to the second feature points with the same sign of the assembly deviation value in each first weighted undirected graph, and the first weighted undirected subgraph includes fourth feature points;

[0173] Determine the neighborhood corresponding to each first weighted undirected subgraph according to the coordinates of each fourth feature point in each first weighted undirected subgraph.

[0174] Optionally, the above-mentioned processing unit 702 is specifically used for:

[0175] Determine the first distance between each fourth feature point in each first weighted undirected subgraph and each other fourth feature point in the first weighted undirected subgraph;

[0176] Determine the average distance corresponding to each fourth feature point according to all the first distances;

[0177] Construct at least one second weighted undirected subgraph according to all the first distances corresponding to each fourth feature point and the average distance, where the distance between each fourth feature point in the second weighted undirected subgraph and other fourth feature points in the second weighted undirected subgraph is less than the average distance;

[0178] Determine the neighborhood corresponding to each second weighted undirected subgraph according to the coordinates of each fourth feature point in each second weighted undirected subgraph.

[0179] Optionally, the above processing unit 702 is specifically configured to:

[0180] Determine the average distance corresponding to each fourth feature point in each second weighted undirected subgraph;

[0181] Determine the minimum average distance from all the average distances of the second weighted undirected subgraph;

[0182] Determine the minimum average distance as the neighborhood.

[0183] Optionally, the above processing unit 702 is specifically configured to:

[0184] Determine the fourth feature point corresponding to the neighborhood as the central feature point;

[0185] According to the central feature point and the neighborhood, determine the number of fourth feature points within the range corresponding to the neighborhood, and use the number as the minimum number of sample points included in the neighborhood;

[0186] Optionally, the above processing unit 702 is specifically configured to:

[0187] Perform clustering analysis on the fourth feature points of each second weighted undirected subgraph according to the neighborhood and the minimum number of sample points to obtain the target area in each second weighted undirected subgraph.

[0188] Optionally, for each first feature point in each area, the above processing unit 1002 is specifically configured to:

[0189] If the device deviation value of the first feature point is within the tolerance range, the first feature point is a third feature point;

[0190] If the assembly deviation value of the first feature point is not within the tolerance range, the first feature point is a second feature point.

[0191] Optionally, after constructing the first weighted undirected graph of each area, the above processing unit 702 is further configured to determine the minimum second distance corresponding to the second feature point in each first weighted undirected graph, where the minimum second distance is the minimum value among the distances between each second feature point in each first weighted undirected graph and other second feature points in the first weighted undirected graph;

[0192] Determine the number of second feature points and the number of third feature points within the range corresponding to each second feature point according to the minimum second distance corresponding to each second feature point;

[0193] Determine whether to eliminate the second feature points within the range corresponding to each second feature point according to the number of second feature points and the number of third feature points within the range corresponding to each second feature point.

[0194] Optionally, the above processing unit 702 is further configured to determine the minimum third distance corresponding to the second feature points in each first weighted undirected graph, where the minimum third distance is the minimum value among the distances between each second feature point in each first weighted undirected graph and the second feature points with the same sign of the assembly deviation value in the first weighted undirected graph;

[0195] Determine the number of second feature points with the same sign of the assembly deviation value and the number of second feature points with different signs of the assembly deviation value within the range corresponding to each second feature point according to the minimum third distance corresponding to each second feature point;

[0196] Determine whether to eliminate the second feature points with the same sign of the assembly deviation value within the range corresponding to each second feature point or to eliminate the second feature points with different signs of the assembly deviation value according to the number of second feature points with the same sign of the assembly deviation value and the number of second feature points with different signs of the assembly deviation value within the range corresponding to each second feature point.

[0197] Optionally, the above attribute information further includes a normal vector, and the above target information further includes a normal vector. The above processing unit 702 is specifically configured to:

[0198] Determine the position to which each first feature point belongs according to the coordinates of each first feature point;

[0199] Determine the region to which each first feature point belongs according to the position to which each first feature point belongs, the angle corresponding to the minimum value of the normal vector of each first feature point, and a preset angle value.

[0200] Of course, the white body assembly deviation recognition device 700 provided in the embodiments of the present invention includes but is not limited to the above modules.

[0201] Another embodiment of the present invention further provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions run on the white body assembly deviation recognition device 700, the white body assembly deviation recognition device 700 is caused to execute each step executed by the white body assembly deviation recognition device 700 in the method flow shown in the above method embodiments.

[0202] Another embodiment of the present invention further provides a chip system, which is applied to the white body assembly deviation recognition device 700. The chip system includes one or more interface circuits and one or more processors 11. The interface circuits and the processor 11 are interconnected by lines. The interface circuit is configured to receive signals from the memory 12 of the white body assembly deviation recognition device 700 and send the signals to the processor 11, and the signals include computer instructions stored in the memory 12. When the processor 11 executes the computer instructions, the white body assembly deviation recognition device 700 executes each step performed by the white body assembly deviation recognition device 700 in the method flow shown in the above method embodiment.

[0203] In another embodiment of the present invention, there is also provided a computer program product, which includes instructions that, when running on the white body assembly deviation recognition device 700, cause the white body assembly deviation recognition device 700 to execute each step performed by the white body assembly deviation recognition device 700 in the method flow shown in the above method embodiment.

[0204] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using a software program, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer execution instructions are loaded and executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from a website, a computer, a server, or a data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or a wireless manner (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, a data center, etc. that includes one or more integrated media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0205] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for identifying assembly deviations of a body-in-white, characterized in that, Including: Obtaining the attribute information of each first feature point among multiple first feature points of a white body in white, where the attribute information includes an assembly deviation value, a tolerance range, and coordinates; Determining the region to which each first feature point belongs according to the target information of each first feature point, where the target information includes the coordinates; Determining a second feature point and a third feature point included in each region according to the assembly deviation value and the tolerance range of each first feature point in each region, where the second feature point is an abnormal feature point and the third feature point is a normal feature point; constructing a first weighted undirected graph for each region according to the second feature points in each region; determining the neighborhood corresponding to each first weighted undirected graph according to the assembly deviation value and the coordinates of each second feature point in each first weighted undirected graph; Determining the minimum number of sample points included in the neighborhood according to the neighborhood; Determining a target region according to the neighborhood and the minimum number of sample points, where the target region includes the feature points with assembly deviations among the multiple first feature points.

2. The white body assembly deviation identification method according to claim 1, characterized in that The determining the neighborhood corresponding to each first weighted undirected graph according to the assembly deviation value and the coordinates of each second feature point in each first weighted undirected graph includes: Generating a first weighted undirected subgraph according to the second feature points with the same sign of the assembly deviation value in each first weighted undirected graph, where the first weighted undirected subgraph includes fourth feature points; Determining the neighborhood corresponding to each first weighted undirected subgraph according to the coordinates of each fourth feature point in each first weighted undirected subgraph.

3. The white body assembly deviation identification method according to claim 2, characterized in that, The determining the neighborhood corresponding to each first weighted undirected subgraph according to the coordinates of each fourth feature point in each first weighted undirected subgraph includes: Determining a first distance between each fourth feature point in each first weighted undirected subgraph and each other fourth feature point in the first weighted undirected subgraph; Determining an average distance corresponding to each fourth feature point according to all the first distances; Constructing at least one second weighted undirected subgraph according to all the first distances corresponding to each fourth feature point and the average distance, where the distance between each fourth feature point in the second weighted undirected subgraph and each other fourth feature point in the second weighted undirected subgraph is less than the average distance; Determining the neighborhood corresponding to each second weighted undirected subgraph according to the coordinates of each fourth feature point in each second weighted undirected subgraph.

4. The white body assembly deviation identification method according to claim 3, characterized in that, The determining the neighborhood corresponding to each second weighted undirected subgraph according to the coordinates of each fourth feature point in each second weighted undirected subgraph includes: Determining an average distance corresponding to each fourth feature point in each second weighted undirected subgraph; Determining the minimum average distance from all the average distances of the second weighted undirected subgraph; Determining the minimum average distance as the neighborhood.

5. The white body assembly deviation identification method according to claim 4, characterized in that The determining the minimum number of sample points included in the neighborhood according to the neighborhood includes: Determining the fourth feature point corresponding to the neighborhood as the central feature point; Determine the number of fourth feature points within the range corresponding to the neighborhood based on the central feature point and the neighborhood, and use this number as the minimum number of sample points included in the neighborhood; The determining the target region according to the neighborhood and the minimum number of sample points includes: Perform clustering analysis on the fourth feature points of each second weighted undirected subgraph according to the neighborhood and the minimum number of sample points to obtain the target region corresponding to each second weighted undirected subgraph.

6. The white body assembly deviation identification method according to any one of claims 2 to 5, characterized in that, The determining the second feature points and third feature points included in each region according to the assembly deviation value and tolerance range of each first feature point in each region includes: For each first feature point in each region, perform the following operations: If the device deviation value of the first feature point is within the tolerance range, then the first feature point is the third feature point; If the assembly deviation value of the first feature point is not within the tolerance range, then the first feature point is the second feature point.

7. The white body assembly deviation identification method according to any one of claims 2 to 5, characterized in that After constructing the first weighted undirected graph of each region, the white body assembly deviation identification method further includes: Determine the minimum second distance corresponding to the second feature points in each first weighted undirected graph, where the minimum second distance is the minimum value among the distances between each second feature point of each first weighted undirected graph and other second feature points in the first weighted undirected graph; Determine the number of second feature points and the number of third feature points within the range corresponding to each second feature point according to the minimum second distance corresponding to each second feature point; Determine whether to eliminate the second feature points within the range corresponding to each second feature point according to the number of second feature points and the number of third feature points within the range corresponding to each second feature point.

8. The method for identifying the assembly deviation of a white body according to claim 7, wherein, The white body assembly deviation identification method further includes: Determine the minimum third distance corresponding to the second feature points in each first weighted undirected graph, where the minimum third distance is the minimum value among the distances between each second feature point of each first weighted undirected graph and other second feature points with the same sign of the assembly deviation value in the first weighted undirected graph; Determine the number of second feature points with the same sign of the assembly deviation value and the number of second feature points with different signs of the assembly deviation value within the range corresponding to each second feature point according to the minimum third distance corresponding to each second feature point; Determine whether to eliminate the second feature points with the same sign of the assembly deviation value within the range corresponding to each second feature point or eliminate the second feature points with different signs of the assembly deviation value according to the number of second feature points with the same sign of the assembly deviation value and the number of second feature points with different signs of the assembly deviation value within the range corresponding to each second feature point.

9. The white body assembly deviation identification method according to any one of claims 1 to 5, characterized in that The attribute information further includes a normal vector, and the target information further includes the normal vector. The determining the region to which each first feature point belongs according to the target information of each first feature point includes: Determine the position to which each first feature point belongs according to the coordinates of each first feature point; Determine the region to which each first feature point belongs according to the position to which each first feature point belongs, the angle corresponding to the minimum value of the normal vector of each first feature point, and a preset angle value.

10. An assembly deviation identification device for a body-in-white, characterized in that, Includes: An acquisition unit, configured to acquire the attribute information of each first feature point among multiple first feature points of a body-in-white, where the attribute information includes an assembly deviation value, a tolerance range, and coordinates; A processing unit, configured to determine the region to which each first feature point belongs according to the target information of each first feature point, where the target information includes the coordinates; determine a second feature point and a third feature point included in each region according to the assembly deviation value and the tolerance range of each first feature point in each region, where the second feature point is an abnormal feature point and the third feature point is a normal feature point; construct a first weighted undirected graph for each region according to the second feature points in each region; and determine the neighborhood corresponding to each first weighted undirected graph according to the assembly deviation value and coordinates of each second feature point in each first weighted undirected graph; Determine the minimum number of sample points included in the neighborhood according to the neighborhood; and determine a target region according to the neighborhood and the minimum number of sample points, where the target region includes the feature points with assembly deviations among the multiple first feature points.

11. An assembly deviation identification device for a white body, characterized in that, The body-in-white assembly deviation identification device includes: a processor and a memory; the memory is used to store computer program code, and the computer program code includes computer instructions; when the processor executes the computer instructions, the body-in-white assembly deviation identification device executes the body-in-white assembly deviation identification method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, Including computer instructions, when the computer instructions run on the body-in-white assembly deviation identification device, the body-in-white assembly deviation identification device is caused to execute the body-in-white assembly deviation identification method according to any one of claims 1 to 9.

Images