Ship assembly simulation path planning method and system, medium and terminal

Abstract

The invention provides a ship assembly simulation path planning method and system, a medium and a terminal.The ship assembly simulation path planning method comprises the steps that firstly, a simulation environment is established according to a simulation target, then geometric features of an assembly unit to be subjected to assembly path planning in the simulation environment are obtained, and assembly features are extracted to serve as positioning control points; then establishing a function relationship between the motion trail of the positioning control point and time to obtain an assembly path so as to obtain the position and posture of the assembly unit; and finally, performing path collision detection and real-time early warning, and calculating whether the nearest distance between any two assembly units at the same time point is within a safety threshold range or not. According to the path planning method, the actual construction assembly scene in the manufacturing process can be simulated, so that the installation problem is avoided in advance, the design scheme is optimized, the ship manufacturing efficiency and quality are further improved, and the production cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of shipbuilding, and in particular to a method for simulating and planning the assembly path of a ship for manufacturing. Background Art

[0002] With the rapid development and intelligent transformation of the global manufacturing industry, the shipbuilding industry has also faced unprecedented opportunities and challenges. In the process of shipbuilding, path planning is a key link to ensure the smooth production process and improve production efficiency. During the product assembly process, it is necessary to reasonably set the assembly paths of each part to ensure that there is no interference with other products and at the same time minimize the assembly time. Traditional path planning methods often rely on manual experience and paper drawings, and it is difficult to adapt to the complexity and variability of modern shipbuilding. In order to improve the efficiency and quality of shipbuilding, optimize and improve potential problems in advance, and reduce production costs, the simulation path planning method has emerged. Summary of the Invention

[0003] In view of the above-mentioned disadvantages of the prior art, the purpose of the present invention is to provide a method for simulating and planning the assembly path of a ship for manufacturing, which simulates the actual construction scenario during the manufacturing process and enables construction personnel to deeply participate at the design end, so as to improve the efficiency and quality of shipbuilding, avoid installation problems in advance, and optimize the design scheme.

[0004] To achieve the above purpose and other related purposes, the present invention provides a method for simulating and planning the assembly path of a ship, including the following steps:

[0005] S1. Obtain the simulation target and establish a simulation environment;

[0006] S2. Obtain the geometric model and dimensional parameters of the assembly unit; perform feature classification on the three-dimensional point cloud of the assembly unit through the PointNet++ feature classification algorithm, and identify the assembly features of the assembly unit as the reference points of the assembly path. The assembly features include assembly point features, assembly line features, and assembly surface features; screen several assembly features with the highest dispersion as positioning control points through DBSCAN clustering;

[0007] S3. Obtain the assembly process information of the assembly unit based on historical assembly data. The assembly process information includes assembly sequence requirements and reference assembly trajectories;

[0008] S4. Generate the assembly path of the assembly unit based on the assembly process information and the positioning control points, specifically including:

[0009] S41 Generate the functional relationship of the motion trajectory of the positioning control points with respect to time according to the reference assembly trajectory. By performing six-degree-of-freedom kinematic modeling on the positioning control points, obtain the functional relationship between the motion trajectory of the positioning control points and time, thereby learning the position and attitude of the assembly unit. The motion trajectory Path consists of the following parameters:

[0010] Path = P(t) + R(t) * v_rot_base;

[0011] Where the position vector P(t) = P_start + t * v_pos; the rotation vector R(t) = R_0 * e^(kθt);

[0012] P_start - Initial pose matrix; v_pos - Linear velocity vector (roughly planned moving speed);

[0013] R_0 - Initial rotation matrix; kθt - Angular velocity integration term; v_rot_base - Basic rotation direction vector.

[0014] S42 Generate a parameterized trajectory according to the functional relationship, connect the scattered points corresponding to different times in sequence, and generate a smooth assembly path through cubic spline interpolation, so that each point on the assembly path can be uniquely determined by different t values.

[0015] Optionally, it further includes step S5: Perform path collision detection and real-time warning through the GJK algorithm, specifically including:

[0016] S51 Construct a bounding box according to the assembly unit, and replace the assembly unit with a bounding box with simple characteristics; determine the sampling time step, and obtain the spatial range of the corresponding packaging box at each time point according to the assembly path in step S4;

[0017] S52 Calculate the GJK distance d = GilbertDistance(A, B) between any two packaging boxes A and B corresponding to the assembly units at the same time point, and judge whether d is within the safety threshold range. If d is greater than the safety threshold, it means that the two assembly units are far apart and there is no collision risk; if d is less than the safety threshold, an alarm is prompted, indicating that the two assembly units interfere with each other and the assembly path needs to be re-optimized.

[0018] Optionally, in step S1, the simulation targets include the construction process and its corresponding site and tooling; the construction process includes part assembly, equipment installation, sectional closure, overall section erection, and module unit assembly; the site includes the assembly workshop, general assembly workshop, erection workshop, dock, and unit workshop; the tooling includes general tooling and special tooling.

[0019] Optionally, in step S2, the assembly point features include reference points for assembly; the assembly line features include the edges and corners of the geometric model, the reference axis for assembly, and the axis of the cylindrical surface; the assembly surface features include the surface of the geometric model and the reference plane for assembly.

[0020] Optionally, in step S4, the bounding box includes an OBB bounding box and an AABB bounding box.

[0021] The present invention also provides a ship assembly simulation path planning system, which is used to implement the ship assembly simulation path planning method described above, and includes:

[0022] A simulation environment construction module, which is used to establish a simulation environment according to the simulation target;

[0023] A feature extraction module, which is used to extract assembly features according to the geometric features of the assembly unit;

[0024] An assembly information acquisition module, which is used to acquire the assembly process information of the assembly unit;

[0025] A path generation module, which is used to generate the functional relationship of the movement trajectory of the assembly unit with respect to time;

[0026] A collision warning module, which judges whether the closest distance between any two assembly units at the same time point is within the safety threshold range.

[0027] The present invention also provides a terminal, which includes a processor and a memory;

[0028] The memory is used to store a computer program;

[0029] The processor is connected to the memory and is used to execute the computer program stored in the memory, so that the terminal executes the ship assembly simulation path planning method according to any one of claims 1-5.

[0030] As described above, the present invention provides a ship assembly simulation path planning method, system, medium and terminal. The ship assembly simulation path planning method first establishes a simulation environment according to the simulation target, and then obtains the geometric features of the assembly units to be subjected to assembly path planning in the simulation environment, extracts the assembly features, and screens the assembly features as positioning control points; then generates the functional relationship of the motion trajectories of the positioning control points with respect to time, and by performing six-degree-of-freedom kinematic modeling on the positioning control points, establishes the functional relationship between the motion trajectories of the positioning control points and time to obtain the assembly path, so as to know the position and attitude of the assembly units; finally, performs path collision detection and real-time warning through the GJK algorithm, calculates the closest distance between any two assembly units at the same time point, and determines whether it is within the safety threshold range. If the assembly units interfere with each other, the assembly path needs to be re-optimized. The path planning method of the present invention can simulate the actual construction and assembly scenarios in the manufacturing process, so as to avoid installation problems in advance, optimize the design scheme, further improve the efficiency and quality of ship manufacturing, and reduce production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It shows a schematic flow chart of the ship assembly simulation path planning method in Embodiment 1 of the present invention.

[0032] Figure 2 It shows a schematic structural diagram of the terminal in Embodiment 1 of the present invention.

[0033] Description of Component Labels

[0034] Processor 31; Memory 32. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] The following uses specific specific examples to illustrate the embodiments of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention.

[0036] It should be noted that the diagrams provided in this embodiment only illustrate the basic concept of the present invention in a schematic manner. Therefore, only the components related to the present invention are shown in the diagrams, rather than being drawn according to the number, shape and size of the components in actual implementation. The types, quantities and proportions of the components in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0037] Embodiment 1

[0038] As Figure 1 shown, this embodiment provides a ship assembly simulation path planning method for manufacturing, including the following steps:

[0039] Step S1: Obtain the simulation target and establish a simulation environment. Specifically, it includes:

[0040] S11 The simulation target includes, but is not limited to, construction processes such as part assembly, equipment installation, sectional closure, overall section erection, and module unit assembly, as well as their corresponding sites and tooling; the sites include assembly workshops, general assembly workshops, erection workshops, docks, and unit workshops; the tooling includes general tooling, special tooling, etc.;

[0041] S12 Obtain the 3D models related to the above simulation target and construct a 3D assembly simulation environment.

[0042] Step S2: Obtain the geometric features of the assembly units to be planned for assembly paths in the simulation environment and extract assembly features. The assembly units include any equipment components to be assembled or tooling used for assembly, such as backing plates, bases, pipelines, positioning tooling, measuring tooling, etc. Here, the tooling is also regarded as an assembly unit to determine whether there is a path interference between the tooling and the equipment components.

[0043] Specifically, it includes:

[0044] S21: Obtain the geometric model and dimensional parameters of the assembly unit;

[0045] S22: Perform feature classification on the 3D point cloud of the assembly unit through the PointNet++ feature classification algorithm to identify the assembly features of the assembly unit, including assembly point features, assembly line features, and assembly surface features, and these assembly features will be used as key reference points for the path.

[0046] Obtain the assembly point features of the product target, specifically including: reference points for assembly; such as bolt holes, marking points;

[0047] Obtain the assembly line features of the product target, specifically including: edge lines of the geometric model, reference axes for assembly, and axes of cylindrical surfaces;

[0048] Obtain the assembly surface features of the product target, specifically including: surfaces of the geometric model, reference planes for assembly, etc.

[0049] Since in actual assembly, these assembly features are used as reference standards. Specifically, these assembly points / lines / surfaces are compared with the accuracy reference points to maintain the corresponding relative position relationship, thereby controlling the assembly accuracy. For example, when installing the anchor system equipment in the bow section, the sprocket shaft of the anchor winch is used as an assembly line and needs to maintain the corresponding relative position relationship with accuracy reference points such as the sectional center line and rib lines to ensure the installation accuracy. Therefore, these assembly features and accuracy reference points required for actual assembly need to be mapped into the simulation environment.

[0050] S23. Screen several assembly features with the highest dispersion through DBSCAN clustering as positioning control points. For example, calculate the local curvature (Laplacian of Gaussian operator) and the variance of the normal vector for all assembly features, and retain the 20 points with the highest dispersion as the positioning control points of the path.

[0051] Step S3. Obtain the assembly process information of the assembly unit based on historical assembly data. Specifically, it includes:

[0052] S31. Obtain the assembly sequence requirements and the reference assembly trajectory;

[0053] S32. Obtain the assembly accuracy control requirements and solutions;

[0054] S33. Obtain the equipment operation requirements, equipment capabilities, and performance parameters;

[0055] S34. Obtain the tooling usage requirements.

[0056] Step S4. Generate the assembly path of the assembly unit based on the assembly process information and the positioning control points.

[0057] S41. Generate the functional relationship of the motion trajectory of the positioning control points with respect to time according to the reference assembly trajectory, that is, the original path without being optimized by path optimization algorithms (such as RRT*, PRM). By performing six-degree-of-freedom kinematic modeling on the positioning control points, the functional relationship between the motion trajectory of the positioning control points and time is obtained, so as to know the position and attitude of the assembly unit; this step is essentially to map the real reference assembly trajectory into the simulation environment, and the motion trajectory consists of the following parameters:

[0058] Path = P(t) + R(t) * v_rot_base;

[0059] Where the position vector P(t) = P_start + t * v_pos; the rotation vector R(t) = R_0 * e^(kθt);

[0060] P_start - Initial pose matrix; v_pos - Linear velocity vector (roughly planned moving speed);

[0061] R_0 - Initial rotation matrix; kθt - Angular velocity integral term; v_rot_base - Basic rotation direction vector.

[0062] Here, a six-degree-of-freedom kinematic model is established by combining quaternions and translation vectors. During the assembly process of the assembly unit, its flipping attitude and position movement will continuously change. By establishing an accurate six-degree-of-freedom dynamic model, its accurate attitude and position can be obtained.

[0063] During the process, coordinate system alignment needs to be performed on different positioning control points, that is, obtaining the assembly path under the same reference coordinate system. Coordinate system alignment is achieved through a transformation matrix. The reference plane is defined by two positioning control points that are farthest apart (such as the plane determined by points P1, P2, and P3) to determine the reference coordinate system, and the rotation matrix R and translation vector T of the coordinate system where each positioning control point is located relative to the reference coordinate system are calculated.

[0064] S42 Generates a parametric trajectory according to the functional relationship, connects the scattered points corresponding to different moments in sequence, and generates a smooth assembly path through cubic spline interpolation, so that each point on the assembly path can be uniquely determined by different t values. Path smoothness index: curvature continuity C2 (cubic spline interpolation).

[0065] Step S5: Perform path collision detection and real-time warning through the GJK algorithm; the input of the GJK algorithm is the vertex sets of two objects. After a finite number of iterations, the final output result is the Euclidean distance between the two objects. Collision detection can be performed based on the Euclidean distance between the two objects. When the distance between the two objects is equal to or less than zero, it can be determined that the two objects collide. This step specifically includes:

[0066] S51 Constructs a bounding box according to the assembly unit, replaces the assembly unit with a bounding box that is slightly larger in volume and has simple characteristics; determines the sampling time step, for example, △t = 0.01s, and the sampling frequency is 100HZ. Obtain the spatial range of the packaging box corresponding to each time point according to the assembly path in step S4; the spatial range is [min x, max y] × [min y, max y] × [min z, max Z].

[0067] The bounding box can be an OBB bounding box or an AABB bounding box. Among them, the OBB bounding box approximates the object more closely than the AABB bounding box, so it is a preferred solution.

[0068] S52 Calculates the GJK distance d = GilbertDistance(A, B) between the packaging boxes A and B corresponding to any two assembly units at the same time point. Here, d can be understood as the closest distance between A and B, and determines whether d is within the safety threshold range. The safety threshold can be flexibly set according to the actual scenario, such as 2m. If d is greater than the safety threshold, it means that the two assembly units are far apart and there is no collision risk; if d is less than the safety threshold, an alarm is prompted, and at the same time, it is indicated that the two assembly units interfere with each other and the assembly path needs to be re-optimized, such as the RRT* and PRM path optimization algorithms mentioned above.

[0069] Based on the above ship assembly simulation path planning method, this embodiment also provides a ship assembly simulation path planning system for implementing the above ship assembly simulation path planning method. The ship assembly simulation path planning system includes:

[0070] A simulation environment construction module for establishing a simulation environment according to the simulation target;

[0071] A feature extraction module for extracting assembly features according to the geometric features of the assembly unit;

[0072] An assembly information acquisition module for acquiring the assembly process information of the assembly unit;

[0073] A path generation module for generating the functional relationship of the movement trajectory of the assembly unit with respect to time;

[0074] A collision warning module for judging whether the closest distance between any two assembly units at the same time point is within the safety threshold range.

[0075] It should be noted that it should be understood that the division of each module of the above system is only a logical function division. In actual implementation, it can be fully or partially integrated into a physical entity, or physically separated. And these modules can all be implemented in the form of software called by a processing element; they can also all be implemented in the form of hardware; they can also be partially implemented in the form of software called by a processing element and partially implemented in the form of hardware.

[0076] This embodiment also provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the above ship assembly simulation path planning method is implemented. The storage medium may include, but is not limited to, floppy disks, optical disks, CD-ROMs (English full name: CD-Read-Only Memory), magneto-optical disks, ROMs (English full name: Read-Only Memory), RAMs (English full name: Random Access Memory), EPROMs (erasable programmable read-only memories), EEPROMs (electrically erasable programmable read-only memories), magnetic cards or optical cards, flash memories, or other types of media / machine-readable media suitable for storing machine-executable instructions.

[0077] Furthermore, the storage medium can be a product not connected to a computer device, or a component already connected to a computer device for use.

[0078] As Figure 2 shown, this embodiment also provides a terminal. The terminal of the present invention includes a processor 31 and a memory 32.

[0079] The memory 32 is used to store computer programs; preferably, the memory 32 includes various media that can store program codes, such as ROM, RAM, magnetic disks, USB flash drives, memory cards, or optical discs.

[0080] The processor 31 is connected to the memory 32 and is configured to execute the computer programs stored in the memory 32, so that the terminal executes the above-mentioned ship assembly simulation path planning method.

[0081] Preferably, the processor 31 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0082] Furthermore, the number of the memories 32 may be one or more, and the number of the processors 31 may also be one or more. Figure 2 In this case, one of each is taken as an example.

[0083] In summary, the present invention provides a ship assembly simulation path planning method, system, medium, and terminal. The ship assembly simulation path planning method first establishes a simulation environment according to a simulation target, then obtains the geometric features of the assembly units to be subjected to assembly path planning in the simulation environment, extracts assembly features, and screens the assembly features as positioning control points; then generates a functional relationship between the motion trajectories of the positioning control points with respect to time, and by performing six-degree-of-freedom kinematic modeling on the positioning control points, establishes a functional relationship between the motion trajectories of the positioning control points and time to obtain an assembly path, thereby knowing the positions and postures of the assembly units; finally, performs path collision detection and real-time warning through the GJK algorithm, calculates the shortest distance between any two assembly units at the same time point, and determines whether it is within a safety threshold range. If the assembly units interfere with each other, the assembly path needs to be re-optimized. The path planning method of the present invention can simulate the actual construction and assembly scenarios in the manufacturing process, thereby avoiding installation problems in advance, optimizing the design scheme, further improving the efficiency and quality of ship manufacturing, and reducing production costs.

[0084] The above embodiments are only illustrative of the principles and effects of the present invention and are not intended to limit the present invention. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed by the present invention should still be covered by the claims of the present invention.

Claims

1. A ship assembly simulation path planning method, characterized in that: The steps include: S1. Obtain simulation target and establish simulation environment; S2. Obtain the geometric model and size parameters of the assembly unit; perform feature classification of the three-dimensional point cloud of the assembly unit using the PointNet++ feature classification algorithm, identify the assembly features of the assembly unit as reference points of the assembly path, and the assembly features include assembly point features, assembly line features, and assembly surface features; select several assembly features with the highest discreteness as positioning control points through DBSCAN clustering; S3, obtaining assembly process information of the assembly unit based on historical assembly data, where the assembly process information includes assembly sequence requirements and reference assembly trajectory; S4, generating an assembly path of the assembly unit based on the assembly process information and the positioning control points, specifically including: S41 generates the functional relationship of the motion trajectory of the positioning control point with respect to time according to the reference assembly trajectory. By performing six-degree-of-freedom kinematic modeling on the positioning control point, the functional relationship between the motion trajectory of the positioning control point and time is obtained, thereby obtaining the position and posture of the assembly unit; the motion trajectory Path is composed of the following parameters: Path=P(t)+R(t)*v_rot_base; Wherein the position vector P(t) = P_start + t*v_pos; the rotation vector R(t) = R_0*e^(kθt); P_start—initial pose matrix; v_pos—linear velocity vector (roughly planned moving speed); R_0—initial rotation matrix; kθt—angular velocity integral term; v_rot_base—basic rotation direction vector; S42 generates a parameterized trajectory according to the functional relationship, connects the scattered points corresponding to different times in sequence, and generates a smooth assembly path through cubic spline interpolation, so that each point on the assembly path can be uniquely determined by different t values.

2. The ship assembly simulation path planning method according to claim 1, characterized in that: The method also includes step S5, performing path collision detection and real-time warning by using the GJK algorithm, which specifically includes: S51 constructs a bounding box according to the assembly unit, and replaces the assembly unit with a bounding box with simple characteristics; determines the sampling time step, and obtains the spatial range of the packaging box corresponding to each time point according to the assembly path in step S4; S52 calculates the GJK distance d = GilbertDistance(A,B) of the packaging boxes A and B corresponding to any two assembly units at the same time point, and determines whether d is within the safety threshold range. If d is greater than the safety threshold, it means that the two assembly units are far apart and there is no risk of collision; if d is less than the safety threshold, an alarm is issued, indicating that the two assembly units interfere with each other and the assembly path needs to be re-optimized.

3. The ship assembly simulation path planning method according to claim 1, characterized in that: In step S1, the simulation target includes the construction process and its corresponding site and tooling; the construction process includes parts assembly, equipment installation, segment closure, overall segment loading, and module unit assembly; the site includes assembly workshop, overall assembly workshop, loading workshop, dock, and unit workshop; Tooling includes general tooling and special tooling.

4. The ship assembly simulation path planning method according to claim 1, characterized in that: In step S2, the assembly point features include assembly reference points; Assembly line features include geometric model corner lines, assembly reference axes, and cylindrical axis lines; Assembly surface features include geometric model surfaces and assembly reference planes.

5. The ship assembly simulation path planning method according to claim 1, characterized in that: In step S4, the bounding box includes an OBB bounding box and an AABB bounding box.

6. A ship assembly simulation path planning system, characterized by: The ship assembly simulation path planning system is used to implement the ship assembly simulation path planning method according to any one of claims 1 to 5, comprising: A simulation environment building module is used to build a simulation environment according to a simulation target; A feature extraction module is used to extract assembly features according to geometric features of assembly units; An assembly information acquisition module is used to acquire assembly process information of an assembly unit; A path generation module is used to generate the functional relationship of the assembly unit motion trajectory with respect to time; The collision warning module determines whether the closest distance between any two assembly units at the same time point is within the safety threshold.

7. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the ship assembly simulation path planning method according to any one of claims 1 to 5.

8. A terminal, characterized in that: The terminal includes a processor and a memory; The memory is used to store computer programs; The processor is connected to the memory and is used to execute the computer program stored in the memory so that the terminal executes the ship assembly simulation path planning method according to any one of claims 1-5.

Images