A workpiece parallelism detection method and device, computer equipment and storage medium

Abstract

The application discloses a workpiece parallelism detection method and device, computer equipment and a storage medium, and the method comprises the steps of: projecting a grating pattern coded by a Gray code to different angles of a target workpiece through a 3D sensor; for each angle of the target workpiece, capturing the grating pattern through a surface array camera, converting the grating pattern into a digital signal, and forming an image sequence; extracting three-dimensional point cloud data from the image sequence based on a three-dimensional reconstruction technology; obtaining parallelism data of the target workpiece based on the three-dimensional point cloud data, and comparing the parallelism data with preset standard parallelism data. The application combines three-dimensional machine vision to detect the target workpiece, and has the advantages of high precision, rapidness, automation, flexibility and the like.

Description

Technical Field

[0001] This invention relates to the field of workpiece inspection technology, and in particular to a method, apparatus, computer equipment, and storage medium for workpiece parallelism detection. Background Technology

[0002] In existing technologies, there are generally three methods for parallelism testing of large workpieces:

[0003] 1. Level test method: Place the workpiece to be tested on a horizontal surface, use a level to test it, and calculate the parallelism error of the workpiece.

[0004] 2. Three-point method: Place the workpiece to be inspected at three points, measure the height difference between the three points, and calculate the parallelism error of the workpiece.

[0005] 3. Laser measurement method: A laser is used to measure the height of various points on the workpiece to calculate the parallelism error of the workpiece.

[0006] However, all of the above methods have certain drawbacks. For example, all three methods require specialized equipment and technicians to operate, are relatively difficult to perform, and have certain requirements for the measurement environment. Furthermore, due to the need for manual operation, the measurement speed is slow, leading to low efficiency. Additionally, the operator's skill level and experience can affect the accuracy of the test results. Summary of the Invention

[0007] This invention provides a method, apparatus, computer equipment, and storage medium for detecting the parallelism of workpieces, aiming to improve the detection efficiency and accuracy of workpieces.

[0008] In a first aspect, embodiments of the present invention provide a method for detecting the parallelism of a workpiece, comprising:

[0009] A grating pattern encoded with Gray code is projected onto the target workpiece from different angles using a 3D sensor;

[0010] For each angle of the target workpiece, the grating pattern is captured by an area scan camera, and the grating pattern is converted into a digital signal to form an image sequence;

[0011] Three-dimensional point cloud data is extracted from the image sequence based on three-dimensional reconstruction technology;

[0012] Parallelism data of the target workpiece is obtained based on the three-dimensional point cloud data, and the parallelism data is compared with preset standard parallelism data.

[0013] Secondly, embodiments of the present invention provide a workpiece parallelism detection device, comprising:

[0014] The pattern projection unit is used to project grating patterns encoded with Gray code onto the target workpiece at different angles via a 3D sensor.

[0015] The pattern capture unit is used to capture the grating pattern at each angle of the target workpiece using an area scan camera, and convert the grating pattern into a digital signal to form an image sequence.

[0016] The data extraction unit is used to extract three-dimensional point cloud data from the image sequence based on three-dimensional reconstruction technology;

[0017] The data comparison unit is used to obtain the size data of the target workpiece based on the three-dimensional point cloud data, and compare the size data with preset standard size data.

[0018] Thirdly, embodiments of the present invention provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the workpiece parallelism detection method as described in the first aspect.

[0019] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the workpiece parallelism detection method as described in the first aspect.

[0020] This invention provides a method, apparatus, computer device, and storage medium for detecting the parallelism of a workpiece. The method includes: projecting a grating pattern encoded with Gray code onto a target workpiece at different angles using a 3D sensor; capturing the grating pattern at each angle of the target workpiece using an area scan camera, and converting the grating pattern into a digital signal to form an image sequence; extracting three-dimensional point cloud data from the image sequence based on three-dimensional reconstruction technology; obtaining parallelism data of the target workpiece based on the three-dimensional point cloud data, and comparing the parallelism data with preset standard parallelism data. This invention combines three-dimensional machine vision for detecting target workpieces, offering advantages such as high precision, speed, automation, and flexibility. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A schematic flowchart of a workpiece parallelism detection method provided in an embodiment of the present invention;

[0023] Figure 2 This is a schematic diagram of a sub-process of a workpiece parallelism detection method provided in an embodiment of the present invention;

[0024] Figure 3 This is a schematic block diagram of a workpiece parallelism detection device provided in an embodiment of the present invention;

[0025] Figure 4 This is a schematic block diagram of a workpiece parallelism detection device provided in an embodiment of the present invention. Detailed Implementation

[0026] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0028] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0029] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0030] Please see below. Figure 1 , Figure 1 The flowchart of a workpiece parallelism detection method provided in an embodiment of the present invention specifically includes steps S101 to S104.

[0031] S101. A grating pattern encoded with Gray code is projected onto the target workpiece at different angles using a 3D sensor.

[0032] S102. For each angle of the target workpiece, the grating pattern is captured by an area array camera, and the grating pattern is converted into a digital signal to form an image sequence;

[0033] S103. Extract three-dimensional point cloud data from the image sequence based on three-dimensional reconstruction technology;

[0034] S104. Obtain the parallelism data of the target workpiece based on the three-dimensional point cloud data, and compare the parallelism data with the preset standard parallelism data.

[0035] In this embodiment, a grating image is first projected onto the target workpiece by a 3D sensor, and then the grating image is captured by an area array camera to obtain a corresponding image sequence. Then, the image sequence is converted into a 3D point cloud model by 3D reconstruction technology. The parallelism data of the target workpiece is accurately extracted based on the point cloud data in the 3D point cloud model, and then the parallelism data is used to determine whether the parallelism of the target workpiece meets the preset standard.

[0036] The purpose of this embodiment is to provide a solution for the inspection and measurement of novel large and complex workpieces. The rapid development and widespread adoption of 3D sensors have created the necessary conditions for this embodiment. A pain point of traditional large and complex workpiece inspection and measurement systems is the inability to simultaneously achieve accuracy and speed. For example, while large-stroke fixed-stroke coordinate measuring machines (CMMs) offer high accuracy and stability, their real-time performance is insufficient, resulting in low inspection efficiency. Similarly, line laser measuring instruments offer high flexibility, but their linear scanning speed is slow, leading to low inspection efficiency. This embodiment combines a structured light vision-based 3D sensor with an industrial robot to inspect and measure large and complex workpieces, achieving the advantages of high accuracy, high speed, and a wide inspection range. Furthermore, another major highlight of this embodiment is its ability to automatically plan the trajectory of the inspection points based on the workpiece's 3D model, thereby shortening the time the robotic arm spends traversing the points and further improving inspection efficiency.

[0037] In summary, compared with the prior art, this embodiment has the following advantages:

[0038] High precision: This embodiment uses optical measurement, which can obtain high-resolution images, thereby achieving more accurate parallelism measurement, with a detection accuracy of up to 0.01 mm.

[0039] High efficiency: This embodiment adopts an automated detection method, and the entire detection process only takes a few seconds, which can greatly improve detection efficiency compared with traditional mechanical measurement methods.

[0040] Automation: This embodiment uses digital image processing technology and computer vision algorithms to achieve automated detection of workpiece parallelism, reducing manual intervention and improving the accuracy and stability of detection results.

[0041] Flexibility: This embodiment can be applied to workpieces of different types and materials, and is not limited by the size and shape of the workpiece, thus having high flexibility and versatility.

[0042] In summary, this embodiment has advantages such as high precision, speed, automation, and flexibility, and can be widely used in machining and automobile manufacturing, possessing high practical value and market prospects.

[0043] In one embodiment, such as Figure 2 As shown, step S101 includes steps S201 to S203.

[0044] S201. The 3D sensor is driven to the current position of the target workpiece by a six-degree-of-freedom motion platform;

[0045] S202. Control the 3D sensor to project a grating pattern onto the current point;

[0046] S203. After completing the projection of the current point, the 3D sensor is driven to the next point of the target workpiece by the six-degree-of-freedom motion platform, and so on, until the projection of all points of the target workpiece is completed.

[0047] This embodiment utilizes a six-degree-of-freedom (DOF) motion platform's robotic arm to drive a 3D sensor and an area scan camera to perform projection and capture operations according to a given path and points. For example, after projection and capture at the current point are completed, the six-DOF motion platform moves to the next point to perform the corresponding operation. Once the imaging work at all points is completed, the six-DOF motion platform robotic arm returns to the home point (i.e., the initial position), and then executes the algorithm thread to calculate the parallelism of various parts of the workpiece based on the data from several points, storing the data in a database. If a large parallelism deviation occurs, the error in the workpiece can be directly displayed, thus achieving a timely feedback effect.

[0048] It should also be noted that a six-degree-of-freedom motion platform refers to an industrial robot with mounting flanges at the end of its six axes, and the 3D sensors are mounted on these flanges. The six-degree-of-freedom motion platform mainly performs two functions: first, it uses the 3D sensors to measure the workpiece from multiple angles within its motion range; second, it sends arrival signals to activate the 3D sensors, and after receiving a completion signal, it begins to move to the next location.

[0049] In one embodiment, step S103 includes:

[0050] Obtain grating pattern information from the image sequence; wherein, the grating pattern information includes pixels in the grating pattern;

[0051] The position of the pixel in the grating pattern is matched with the corresponding binary code value to obtain the binary code of the current angle;

[0052] The binary codes of all angles are aggregated into the three-dimensional point cloud data.

[0053] In this embodiment, the 3D sensor includes a 3D point cloud acquisition device consisting of an area scan camera and a grating projector. The main function of this device is to project a Gray code-encoded grating, while the area scan camera captures the projected pattern and transmits it back. The 3D sensor's projector projects a Gray code-encoded grating onto the target workpiece. Gray code is a binary encoding where adjacent codes differ by only one bit. The main advantage of this encoding is that only one code bit changes with any displacement, allowing for more precise displacement measurement. Projecting the Gray code grating onto the surface of the object forms a grating pattern. The area scan camera captures the grating pattern and converts it into a digital signal, forming an image sequence. The image sequence is then processed to extract the corresponding grating pattern information. Here, according to the Gray code grating encoding rules, the position of each pixel in the grating pattern is matched with its corresponding binary code value to obtain the binary code corresponding to the target object's surface in the grating pattern. By comparing and calculating grating patterns projected at different angles, the coordinates and shape information of the target workpiece surface in three-dimensional space can be obtained.

[0054] In some optional embodiments, before connecting different points of the target workpiece based on the three-dimensional point cloud data and obtaining the connected dimension data, the following steps are included:

[0055] The three-dimensional point cloud data is sequentially downsampled, filtered, and processed by pattern recognition to obtain the dimensional data of different points on the target workpiece.

[0056] By performing data processing and image recognition on the 3D point data, the accuracy of acquiring dimensional data can be improved, thereby further enhancing the final detection accuracy. For example, when performing data filtering, specific methods such as median filtering, arithmetic mean filtering, or amplitude limiting filtering can be used.

[0057] In one embodiment, step S104 includes:

[0058] Based on the three-dimensional point cloud data, different points of the target workpiece are connected to obtain the dimensional data after the connection.

[0059] Multiple parallelism data of the target workpiece are obtained by combining the dimensional data after connection, and each parallelism data is compared with the preset standard parallelism data.

[0060] Furthermore, step S104 also includes:

[0061] If the parallelism data is the same as the preset standard parallelism data, then the parallelism data is retained and stored.

[0062] If the parallelism data is the same as the preset standard parallelism data, then calculate the data error between the parallelism data and the preset standard parallelism data;

[0063] Determine whether the data error is within a preset error range;

[0064] If the data error is determined to be within the preset error range, the corresponding parallelism data is retained and stored.

[0065] If the data error is determined to be outside the preset error range, an early warning will be issued.

[0066] In this embodiment, parallelism data at different angles of the target workpiece are obtained by connecting different points on the target workpiece. Then, the parallelism data at each angle is compared with preset standard parallelism data to determine whether the target workpiece is qualified. Specifically, during the comparison, if the parallelism data at each angle is the same as the preset standard parallelism data, then the target workpiece can be considered to meet the production standard. If the parallelism data at any angle or multiple angles is different from the preset standard parallelism data, then it can be initially considered that the target workpiece has a production error. This production error is then further obtained and compared with a preset error range to determine whether the error of the target workpiece is within an acceptable range. If the error of the target workpiece is within the preset error range, then the target workpiece can be considered qualified, and vice versa.

[0067] In some preferred embodiments, step S104 further includes:

[0068] A multi-threaded approach is used to simultaneously compare each parallelism data point on the target workpiece with a preset standard parallelism data point.

[0069] Multithreading refers to the technique of implementing concurrent execution of multiple threads through software or hardware. Computers with multithreading capabilities can execute more than one thread at a time due to hardware support, thereby improving overall processing performance. This embodiment uses multithreading to compare parallel data simultaneously, which can further improve detection efficiency.

[0070] Figure 3 This is a schematic block diagram of a workpiece parallelism detection device 300 provided in an embodiment of the present invention. The device 300 includes:

[0071] The pattern projection unit 301 is used to project grating patterns encoded by Gray code onto the target workpiece at different angles via a 3D sensor.

[0072] The pattern capture unit 302 is used to capture the grating pattern for each angle of the target workpiece using an area scan camera, and convert the grating pattern into a digital signal to form an image sequence.

[0073] Data extraction unit 303 is used to extract three-dimensional point cloud data from the image sequence based on three-dimensional reconstruction technology;

[0074] The data comparison unit 304 is used to obtain the size data of the target workpiece based on the three-dimensional point cloud data, and compare the size data with the preset standard size data.

[0075] In one embodiment, such as Figure 4 As shown, the pattern projection unit 301 includes:

[0076] The first operating unit 401 is used to drive the 3D sensor to the current position of the target workpiece through a six-degree-of-freedom motion platform;

[0077] The projection control unit 402 is used to control the 3D sensor to project a grating pattern onto the current point.

[0078] The second operating unit 403 is used to drive the 3D sensor to the next point of the target workpiece through a six-degree-of-freedom motion platform after completing the projection of the current point. This process is repeated until the projection of all points of the target workpiece is completed.

[0079] In one embodiment, the data extraction unit 303 includes

[0080] An information acquisition unit is used to acquire grating pattern information in the image sequence; wherein, the grating pattern information includes pixels in the grating pattern;

[0081] A position matching unit is used to match the position of the pixel in the grating pattern with the corresponding binary code value to obtain the binary code of the current angle;

[0082] The encoding and summarization unit is used to summarize the binary codes of all angles into the three-dimensional point cloud data.

[0083] In one embodiment, the data comparison unit 304 includes:

[0084] The point connection unit is used to connect different points of the target workpiece according to the three-dimensional point cloud data, and obtain the dimension data after connection.

[0085] The first comparison unit is used to obtain multiple parallelism data of the target workpiece by combining the dimensional data after connection, and compare each parallelism data with the preset standard parallelism data.

[0086] In one embodiment, the data comparison unit 304 further includes:

[0087] The first storage unit is used to retain and store the parallelism data if the parallelism data is the same as the preset standard parallelism data.

[0088] An error calculation unit is used to calculate the data error between the parallelism data and the preset standard parallelism data if the parallelism data is the same as the preset standard parallelism data.

[0089] An error judgment unit is used to determine whether the data error is within a preset error range;

[0090] The second storage unit is used to retain and store the corresponding parallelism data if the data error is determined to be within a preset error range.

[0091] The early warning unit is used to issue an early warning if it determines that the data error is not within a preset error range.

[0092] In one embodiment, the data comparison unit 304 further includes:

[0093] The data processing unit is used to perform downsampling, filtering, and pattern recognition processing on the three-dimensional point cloud data in sequence to obtain the size data of different points on the target workpiece.

[0094] In one embodiment, the data comparison unit 304 further includes:

[0095] The second comparison unit is used to simultaneously compare each parallelism data on the target workpiece with the preset standard parallelism data using a multi-threaded approach.

[0096] Since the embodiments of the apparatus and the embodiments of the method correspond to each other, please refer to the description of the embodiments of the method for the embodiments of the apparatus, which will not be repeated here.

[0097] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed, can perform the steps provided in the above embodiments. The storage medium may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0098] This invention also provides a computer device, which may include a memory and a processor. The memory stores a computer program, and when the processor calls the computer program in the memory, it can implement the steps provided in the above embodiments. Of course, the computer device may also include various network interfaces, power supplies, and other components.

[0099] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0100] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for detecting the parallelism of a workpiece, characterized in that, include: A grating pattern encoded with Gray code is projected onto the target workpiece from different angles using a 3D sensor; For each angle of the target workpiece, the grating pattern is captured by an area scan camera, and the grating pattern is converted into a digital signal to form an image sequence; Three-dimensional point cloud data is extracted from the image sequence based on three-dimensional reconstruction technology; Parallelism data of the target workpiece is obtained based on the three-dimensional point cloud data, and the parallelism data is compared with preset standard parallelism data. The projection of grating patterns encoded with Gray code onto the target workpiece at different angles via a 3D sensor includes: The 3D sensor is driven to the current position of the target workpiece by a six-degree-of-freedom motion platform; Control the 3D sensor to project a grating pattern onto the current point; After completing the projection of the current point, the 3D sensor is driven to the next point of the target workpiece by the six-degree-of-freedom motion platform, and so on, until the projection of all points of the target workpiece is completed. The extraction of 3D point cloud data from the image sequence based on 3D reconstruction technology includes... Obtain grating pattern information from the image sequence; wherein, the grating pattern information includes pixels in the grating pattern; The position of the pixel in the grating pattern is matched with the corresponding binary code value to obtain the binary code of the current angle; The binary codes of all angles are aggregated into the three-dimensional point cloud data; The step of obtaining parallelism data of the target workpiece based on the three-dimensional point cloud data, and comparing the parallelism data with preset standard parallelism data, includes: Based on the three-dimensional point cloud data, different points of the target workpiece are connected to obtain the dimensional data after the connection. Multiple parallelism data of the target workpiece are obtained by combining the dimensional data after connection, and each parallelism data is compared with the preset standard parallelism data. Before connecting different points of the target workpiece based on the three-dimensional point cloud data and obtaining the dimensional data after connection, the process includes: The three-dimensional point cloud data is sequentially downsampled, filtered, and pattern recognized to obtain the size data of different points on the target workpiece. The step of obtaining parallelism data of the target workpiece based on the three-dimensional point cloud data and comparing the parallelism data with preset standard parallelism data further includes: If the parallelism data is the same as the preset standard parallelism data, then the parallelism data is retained and stored. If the parallelism data is the same as the preset standard parallelism data, then calculate the data error between the parallelism data and the preset standard parallelism data; Determine whether the data error is within a preset error range; If the data error is determined to be within the preset error range, the corresponding parallelism data is retained and stored. If the data error is determined to be outside the preset error range, an early warning will be issued.

2. The workpiece parallelism detection method according to claim 1, characterized in that, The step of obtaining parallelism data of the target workpiece based on the three-dimensional point cloud data and comparing the parallelism data with preset standard parallelism data further includes: A multi-threaded approach is used to simultaneously compare each parallelism data point on the target workpiece with a preset standard parallelism data point.

3. A workpiece parallelism detection device, characterized in that, include: The pattern projection unit is used to project grating patterns encoded with Gray code onto the target workpiece at different angles via a 3D sensor. The pattern capture unit is used to capture the grating pattern at each angle of the target workpiece using an area scan camera, and convert the grating pattern into a digital signal to form an image sequence. The data extraction unit is used to extract three-dimensional point cloud data from the image sequence based on three-dimensional reconstruction technology; The data comparison unit is used to obtain the size data of the target workpiece based on the three-dimensional point cloud data, and compare the size data with preset standard size data. The pattern projection unit includes: The first operating unit is used to drive the 3D sensor to the current position of the target workpiece via a six-degree-of-freedom motion platform; The projection control unit is used to control the 3D sensor to project a grating pattern onto the current point. The second operating unit is used to drive the 3D sensor to the next point of the target workpiece through a six-degree-of-freedom motion platform after the projection of the current point is completed, and so on, until the projection of all points of the target workpiece is completed. The data extraction unit includes An information acquisition unit is used to acquire grating pattern information in the image sequence; wherein, the grating pattern information includes pixels in the grating pattern; A position matching unit is used to match the position of the pixel in the grating pattern with the corresponding binary code value to obtain the binary code of the current angle; The encoding and summarization unit is used to summarize the binary codes of all angles into the three-dimensional point cloud data; The data comparison unit includes: The point connection unit is used to connect different points of the target workpiece according to the three-dimensional point cloud data, and obtain the dimension data after connection. The first comparison unit is used to obtain multiple parallelism data of the target workpiece by combining the dimension data after the connection, and compare each parallelism data with the preset standard parallelism data. The data processing unit is used to perform downsampling, filtering and pattern recognition processing on the three-dimensional point cloud data in sequence to obtain the size data of different points on the target workpiece. The data comparison unit further includes: The first storage unit is used to retain and store the parallelism data if the parallelism data is the same as the preset standard parallelism data. An error calculation unit is used to calculate the data error between the parallelism data and the preset standard parallelism data if the parallelism data is the same as the preset standard parallelism data. An error judgment unit is used to determine whether the data error is within a preset error range; The second storage unit is used to retain and store the corresponding parallelism data if the data error is determined to be within a preset error range. The early warning unit is used to issue an early warning if it determines that the data error is not within a preset error range.

4. A computer device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the workpiece parallelism detection method as described in claim 1 or 2.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the workpiece parallelism detection method as described in claim 1 or 2.

Images