Ship plate forming degree detection method and system based on point cloud technology

Abstract

The invention discloses a ship plate forming degree detection method and system based on a point cloud technology. According to the method, initial point cloud data of a formed plate is collected through a three-dimensional laser scanner, independent plate point cloud data is obtained through filtering noise reduction, block isolation and feature extraction, and then registration and alignment are carried out on the independent plate point cloud data and image library standard data through a three-dimensional transformation matrix; finally, multi-dimensional quantitative analysis of the forming degree is achieved based on the mean value error, the overall overlap ratio and difference point distribution. The matched system integrates a motion control module, a detection module, an analysis and calculation module and a human-computer interaction interface, and supports full-process automatic detection and result visualization. According to the method, the plate forming quality can be efficiently and accurately evaluated, manual intervention is reduced, and an intelligent solution is provided for ship manufacturing quality control.

Description

Technical Field

[0001] This invention belongs to the field of ship processing and inspection technology, and in particular relates to a method and system for detecting the formability of ship plate based on point cloud technology. Background Technology

[0002] In shipbuilding, there is a significant amount of processing and formability testing of ship plate materials. Traditional formability testing relies heavily on manual verification using templates or sample boxes. This method has low accuracy and is susceptible to subjective judgment, leading to errors in the test results. Furthermore, manual testing is cumbersome, time-consuming, and labor-intensive. For large or complex curved plates, the testing difficulty is even greater, resulting in low efficiency. Manufacturing a large number of templates requires substantial materials and time, and different curved plate materials require different templates, leading to high manufacturing costs. In addition, it demands a high level of technical skill from testing personnel, increasing human resource investment. Traditional methods lack objective data for scientifically evaluating training parameters and formability, making it difficult to record and analyze test results in detail, which is detrimental to the optimization and improvement of formability.

[0003] In conclusion, with the rapid development of modern shipbuilding, the requirements for the forming degree of ship plate processing are becoming increasingly stringent, and traditional inefficient testing methods can no longer meet production needs. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for detecting the formability of ship plate based on point cloud technology, which improves detection efficiency and accuracy and reduces production costs.

[0005] To achieve the objectives of this invention, on one hand, this invention provides a method for detecting the formability of ship plate based on point cloud technology, comprising the following steps:

[0006] Step 1: Use a 3D laser scanner to scan the molded sheet to obtain the initial point cloud data of the molded sheet;

[0007] Step 2: Filter the initial point cloud data to obtain accurate point cloud data for independently formed sheet materials;

[0008] Step 2-1: The initial point cloud data is processed to obtain the noise-reduced point cloud data of the molded sheet material;

[0009] Step 2-2: The denoised point cloud data is processed by block isolation to obtain multiple point cloud data, including the point cloud data of independent board materials;

[0010] Steps 2-3: Extract the mean features from the multiple point cloud data to obtain the mean features of the multiple point cloud data;

[0011] Steps 2-4: Identify the mean features of the multiple point cloud data and select to obtain the point cloud data of the independent molded plate.

[0012] Step 3: The point cloud data of the independently formed sheet material is registered with the point cloud data of the sheet material in the library. The point cloud data of the independently formed sheet material is transformed after registration to obtain the registered point cloud data of the independently formed sheet material.

[0013] Step 4: Perform a difference analysis between the registered independent board point cloud data and the board point cloud data in the library to obtain a difference analysis report, and complete the detection of board formability.

[0014] On the other hand, the present invention also provides a system for detecting the formability of ship plate based on point cloud technology, comprising the following modules:

[0015] The motion module is used to move the 3D laser scanner and the molded sheet to the designated working position.

[0016] The detection module is used for point cloud data acquisition of the formed sheet material;

[0017] The analysis and calculation module is used to process and analyze point cloud data and feed the analysis results back to the human-computer interaction interface.

[0018] The human-computer interaction interface display module is used by staff to control the detection module and motion module, and to obtain the difference analysis report of the point cloud data of the molded sheet material from the analysis and calculation module through the human-computer interaction interface.

[0019] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described method for detecting the formability of ship plate based on point cloud technology.

[0020] The significant advancement of this invention compared to existing technologies lies in:

[0021] (1) Achieve high-precision automated inspection and improve efficiency and reliability: This invention realizes automated and non-contact inspection of the forming degree of ship plates through the overall process; compared with traditional manual inspection or simple measuring tools, this method greatly improves the inspection accuracy, efficiency and repeatability and objectivity of the results;

[0022] (2) Precise quantitative assessment of forming quality: This invention provides a comprehensive and objective forming degree deviation report through difference analysis, which far exceeds the traditional qualitative or single index assessment.

[0023] (3) Constructing a highly integrated intelligent detection system: Through the integration of system modules, the present invention allows staff to control the entire detection process and obtain detailed reports through the control display interface, which significantly reduces the difficulty of operation and improves the intelligence level of the detection process and user experience.

[0024] This invention provides a complete detection method and system based on advanced point cloud technology, capable of quickly and accurately determining whether formed sheet metal meets design requirements. This is crucial for quality control in the critical sheet metal processing stage of shipbuilding, helping to promptly detect forming defects, reduce rework, ensure construction accuracy, and ultimately improve the overall quality and efficiency of shipbuilding.

[0025] To more clearly illustrate the functional characteristics and structural parameters of the present invention, further explanation is provided below in conjunction with the accompanying drawings and specific embodiments. Attached Figure Description

[0026] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0027] Figure 1 This is a flowchart of the method steps of the present invention;

[0028] Figure 2 This is a diagram of the detection platform of the present invention;

[0029] Figure 3 This is a framework diagram of the detection interaction system of the present invention;

[0030] Figure 4 This is a system framework diagram of the present invention;

[0031] Figure 5 This is a diagram of the system human-computer interaction interface according to an embodiment of the present invention. Detailed Implementation

[0032] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. 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.

[0033] This invention provides a method for detecting the formability of ship plate based on point cloud technology, combined with... Figure 1 This includes the following steps:

[0034] Step 1: Use a 3D laser scanner to scan the molded sheet to obtain the initial point cloud data of the molded sheet;

[0035] Step 2: The computer filters the initial point cloud data to obtain accurate point cloud data for independently formed sheet materials;

[0036] Step 3: The point cloud data of the independently formed sheet material is registered with the point cloud data of the sheet material in the library. The point cloud data of the independently formed sheet material is transformed after registration to obtain the registered point cloud data of the independently formed sheet material.

[0037] Step 4: Perform a difference analysis between the registered independent board point cloud data and the board point cloud data in the library to obtain a difference analysis report, and complete the detection of board formability.

[0038] Step 2 specifically includes the following steps:

[0039] Step 2-1: The initial point cloud data is processed to obtain the noise-reduced point cloud data of the molded sheet material;

[0040] Step 2-2: The denoised point cloud data is processed by block isolation to obtain multiple point cloud data, including the point cloud data of independent board materials;

[0041] Steps 2-3: Extract the mean features from the multiple point cloud data to obtain the mean features of the multiple point cloud data;

[0042] Steps 2-4: Identify the mean features of the multiple point cloud data and select to obtain the point cloud data of the independent molded plate.

[0043] Furthermore, the registration of the point cloud data involves placing the point cloud data from the image library and the point cloud data of the independently molded sheet material into the same coordinate system, and performing maximum overlap fitting to perform error analysis and data calibration on the point cloud data of the independently molded sheet material. The specific steps are shown in the following formula:

[0044]

[0045] Where T is the 3D transformation matrix, R is the rotation matrix, and R * Let t be the rotation matrix that minimizes the registration error, and t be the translation vector. * P is the translation vector that minimizes the registration error. s Point cloud data for independently molded sheet materials; p s Points in the point cloud data of independently molded sheet materials; p t Points in the point cloud data of the image library.

[0046] Furthermore, the difference analysis in step 4 includes the difference in the mean of point cloud data, the difference between the overall overlap of the board material and the difference points in the point cloud data;

[0047] The calculation of the cloud data mean difference and the overall overlap of the board material is shown in the following formula:

[0048]

[0049] Where ε is the mean error, ε x ε y ε z The mean error ε is represented by the components along the x, y, and z axes; O represents the overall overlap; P represents the mean error ε. s Point cloud data for independently molded sheet materials; P t Point cloud data for sheet metal in the image library; p s (x s x y x z () points in the point cloud data of independently molded sheet materials p is its mean; t (x t y t z t () represents points in the point cloud data of the image library. Let r be its mean; r is the spacing coefficient of the point cloud data. x r y r z It is the component of the spacing coefficient on the x, y, and z axes.

[0050] This invention provides a system for detecting the formability of ship plate based on point cloud technology, combined with... Figure 2-5 Includes the following modules:

[0051] The motion module is used to move the 3D laser scanner and the molded sheet to the designated working position.

[0052] The detection module is used for point cloud data acquisition of the formed sheet material;

[0053] The analysis and calculation module is used to process and analyze point cloud data and feed the analysis results back to the human-computer interaction interface.

[0054] The human-computer interaction interface display module is used by staff to control the detection module and motion module, and to obtain the difference analysis report of the point cloud data of the molded sheet material from the analysis and calculation module through the human-computer interaction interface.

[0055] The motion module includes an electrical control cabinet, an electric guide rail, and a conveyor belt;

[0056] The electrical control cabinet is used to receive human-machine interaction information and control the motion of the electric guide rail and conveyor belt.

[0057] The electric guide rail is used to move the 3D laser scanner to the designated working position;

[0058] The conveyor belt is used to carry the shaped sheet material to the designated working position;

[0059] The electrical control cabinet can acquire human-machine interaction information and can also run automatically according to the built-in program. When running automatically, it can control the electric guide rail and conveyor belt to move the 3D laser scanner and the molded plate to the designated working position. At the same time, when there is human-machine interaction information, it can control the electric guide rail and conveyor belt to move the 3D laser scanner and the molded plate to the position specified in the human-machine interaction information.

[0060] The detection module includes a three-dimensional laser scanner;

[0061] The 3D laser scanner is used for point cloud data acquisition of the shaped sheet material;

[0062] The 3D laser scanner is mounted on a moving platform on an electric guide rail and moves with the moving platform to the corresponding data acquisition point.

[0063] The analysis and calculation module includes a high-performance data processing computer;

[0064] The computer is used to process point cloud data obtained through the detection module;

[0065] The computer is interconnected with the detection module to receive point cloud data obtained by the detection module, and can send start and stop commands to the 3D laser scanner via USB interface.

[0066] The computer is interconnected with the electrical control cabinet for information transmission from the human-machine interface display module and for acquiring control information from the motion module.

[0067] The human-computer interaction interface display module includes a difference analysis report display interface and a control display interface;

[0068] The difference report display interface is used to obtain the difference analysis report of the point cloud data of the molded sheet material from the analysis and calculation module.

[0069] The control display interface is used by staff to control the detection module and the motion module through the corresponding buttons on the interface.

[0070] It should be noted that, in this document, 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 process, method, article, or apparatus.

[0071] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A ship plate forming degree detection method based on point cloud technology, characterized in that, The method comprises the following steps: Step 1: scanning the formed plate by a three-dimensional laser scanner to obtain initial point cloud data of the formed plate; Step 2: filtering the initial point cloud data to obtain accurate independent formed plate point cloud data; Step 3: performing point cloud data registration on the independent formed plate point cloud data and the library plate point cloud data to obtain registered independent plate point cloud data through three-dimensional transformation after registration; Step 4: performing difference analysis on the registered independent plate point cloud data and the library plate point cloud data to obtain a difference analysis report, and completing the detection of the forming degree of the plate.

2. The ship plate forming degree detection method based on point cloud technology according to claim 1, characterized in that, The step 2 specifically comprises the following steps: Step 2-1: obtaining denoised formed plate point cloud data through noise reduction processing of the initial point cloud data; Step 2-2: obtaining a plurality of point cloud data including independent plate point cloud data through block isolation processing of the denoised point cloud data; Step 2-3: extracting mean features of the plurality of point cloud data to obtain mean features of the plurality of point cloud data; Step 2-4: identifying and selecting the mean features of the plurality of point cloud data to obtain independent formed plate point cloud data.

3. The ship plate forming degree detection method based on point cloud technology according to claim 1, characterized in that, The registration of the point cloud data is to put the library point cloud data and the independent formed plate point cloud data into the same coordinate system, and to perform maximum coincidence degree fitting, which is used for data calibration for subsequent error analysis of the independent formed plate point cloud data, and is specifically shown in the following formula: Wherein, T is a three-dimensional transformation matrix, R is a rotation matrix, R * is a rotation matrix with minimum registration error, t is a translation vector, t * is a translation vector with minimum registration error, P s is an independently formed plate point cloud data p s is a point in the independently formed plate point cloud data; p t is a point in the library point cloud data.

4. The ship plate forming degree detection method based on point cloud technology according to claim 1, characterized in that, The difference analysis of the step 4 includes point cloud data mean difference, plate overall coincidence degree and difference points of the point cloud data; The calculation of the point cloud data mean difference and the plate overall coincidence degree is shown in the following formula: wherein ε is the mean error, ε x ε y ε z are the components of the mean error ε in the x y z three-axes; O is the overall coincidence degree; P s is the point cloud data of the independently shaped board; P t is the point cloud data of the library board; p s (x s x y x z ) is a point in the point cloud data of the independently shaped board is the mean thereof; p t (x t y t z t ) is a point in the point cloud data of the library is the mean thereof; r is the spacing coefficient r of the point cloud data x r y r z are the components of the spacing coefficient in the x y z three-axes.

5. The system for detecting the degree of forming of a plate of a ship based on point cloud technology according to any one of claims 1 to 4, characterized in that, The method comprises the following modules: A movement module for carrying the three-dimensional laser scanner and moving the formed plate to a specified working position; A detection module for point cloud data collection of the formed plate; An analysis and calculation module for processing and analyzing the point cloud data and feeding back the analysis result to a man-machine interaction interface; A man-machine interaction interface display module for controlling the detection module and the movement module by a worker and obtaining the difference analysis report of the analysis and calculation module on the point cloud data of the formed plate through the man-machine interaction interface.

6. The system for detecting the degree of forming of a plate of a ship based on point cloud technology according to claim 5, wherein The movement module comprises an electrical control cabinet, an electric guide rail and a conveyor belt; The electrical control cabinet is used for receiving man-machine interaction information and controlling the movement of the electric guide rail and the conveyor belt; The electric guide rail is used for carrying the three-dimensional laser scanner to move to a specified working position; The conveyor belt is used for carrying the formed plate to move to a specified working position.

7. The system for detecting the degree of forming of a plate of a ship based on point cloud technology according to claim 5, wherein The detection module comprises a three-dimensional laser scanner; The three-dimensional laser scanner is used for point cloud data collection of the formed plate; The three-dimensional laser scanner is installed on a moving platform on the electric guide rail and moves to a corresponding data collection point following the movement of the moving platform of the electric guide rail.

8. The system for detecting the degree of forming of a plate of a ship based on point cloud technology according to claim 5, wherein The analysis and calculation module comprises a high-performance data processing computer; The computer is used for processing the point cloud data obtained through the detection module; The computer and the detection module are connected to each other to receive the point cloud data obtained by the detection module, and can send start and stop instructions to the three-dimensional laser scanner through a USB interface. The computer and the electrical control cabinet are connected to each other for information transmission of a man-machine interactive interface display module, and control information of a motion module is acquired.

9. The system for detecting the degree of forming of a plate of a ship based on point cloud technology according to claim 5, wherein, The man-machine interactive interface display module comprises a difference analysis report display interface and a control display interface. The difference report display interface is used to obtain a difference analysis report of the analysis and calculation module on the point cloud data of the formed plate. The control display interface is used for a worker to control the detection module and the motion module through corresponding buttons of the interface.

10. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the method in any one of claims 1 to 4 when executing the program.

Images