A shipbuilding flatness inspection apparatus and method of use thereof

Abstract

The present application relates to a kind of ship construction flatness inspection equipment and its use method, belong to ship flatness inspection technical field, including magnetic adsorption type mobile robot platform, magnetic adsorption type mobile robot platform, high-precision vision module, edge computing unit, cloud data management platform, magnetic adsorption type mobile robot platform is provided with track type walking mechanism and adaptive vacuum adsorption unit.In the present application, efficient, high-precision full-ship flatness intelligent detection can be realized by multi-sensor fusion and adaptive robot platform, suitable for real-time quality monitoring of hull block construction, deck assembly and outfitting stage, can perform local fine scanning along the weld area in the hull block detection scene, simultaneously mark the welding deformation out-of-tolerance area, can be switched to global fast scanning mode for non-key plane area, in deck assembly stage, cloud platform can integrate data in real time, assist in carrying out assembly misalignment correction scheme.

Description

Technical Field

[0001] This invention relates to the field of ship smoothness inspection technology, and in particular to a ship construction smoothness inspection device and its usage method. Background Technology

[0002] Ships are a general term for all kinds of vessels. They are means of transportation that can navigate or anchor in waterways for transport or operations. Different vessels have different technical specifications, equipment, and structural forms depending on their intended use. In shipbuilding and maintenance, the inspection of the deck's flatness is a crucial step, thus requiring a flatness inspection device.

[0003] Traditional ship flatness inspection relies on manual labor using tools such as rulers and levels, which is inefficient and susceptible to subjective factors. While existing digital equipment (such as laser scanners) offers high precision, it is complex to operate, costly, and difficult to adapt to the complex curved surfaces of ship hulls. Therefore, this paper proposes a ship construction flatness inspection device and its usage method. Through multi-sensor fusion and an adaptive robotic platform, it achieves efficient and high-precision intelligent inspection of the entire ship's flatness. It is suitable for real-time quality monitoring during hull section construction, deck assembly, and outfitting stages. In hull section inspection scenarios, it can perform localized fine scanning along weld seams, simultaneously marking areas with welding deformation exceeding tolerances. For non-critical planar areas, it can switch to a global rapid scanning mode. During deck assembly, data can be integrated in real-time via a cloud platform to assist in developing assembly misalignment correction schemes. Summary of the Invention

[0004] This invention provides a ship construction flatness inspection device and its usage method, which solves the problems mentioned in the background technology. It can achieve efficient and high-precision intelligent detection of the flatness of the whole ship through multi-sensor fusion and adaptive robot platform, and is suitable for real-time quality monitoring in the ship section construction, deck assembly and outfitting stages.

[0005] The present invention provides the following solution to the above-mentioned technical problems: a shipbuilding flatness inspection device, comprising a magnetic adsorption mobile robot platform, a high-precision vision module, an edge computing unit, and a cloud data management platform. The magnetic adsorption mobile robot platform is equipped with a tracked walking mechanism and an adaptive vacuum adsorption unit. A multi-line lidar array is installed on the magnetic adsorption mobile robot platform, and the multi-line lidar array includes a 16-line vertical scanning radar and a 360° rotating horizontal radar. The high-precision vision module is installed on the magnetic adsorption mobile robot platform, and the magnetic adsorption mobile robot platform includes a binocular stereo camera and an infrared thermal imager. The edge computing unit has a built-in FPGA acceleration chip and an AI inference engine.

[0006] The cloud-based data management platform includes a data acquisition and transmission layer, a data storage and management layer, a data processing and analysis engine, an AI model and algorithm platform, and a visualization and interaction layer. The data acquisition and transmission layer is equipped with a network transmission protocol. The data storage and management layer is equipped with a distributed database and a data lake architecture. The data processing and analysis engine is equipped with a multimodal data fusion algorithm and a dynamic benchmark calibration module. The AI ​​model and algorithm platform is equipped with a deep learning framework module and a generative adversarial network module. The visualization and interaction layer is equipped with a 3D deviation heatmap generation module and a compliance report generation module.

[0007] The usage method includes the following steps:

[0008] S1: Adaptive Adsorption and Path Planning: The magnetic adsorption mobile robot platform can vertically adhere to the surface of the ship through an adaptive vacuum adsorption unit. It can acquire three-dimensional point cloud data of the ship surface through a 16-line vertical scanning radar and a 360° rotating horizontal radar. Based on the SLAM algorithm, a three-dimensional map of the ship is constructed, and the optimal scanning path is automatically generated according to the preset detection priority, dividing the local detection grid and the global key area.

[0009] S2: Multimodal data synchronous acquisition: Multi-line lidar array scans the surface geometry, high-precision vision module captures texture images, and IMU records robot pose data;

[0010] S3: Real-time edge processing: The edge computing unit has a built-in multimodal data fusion algorithm that fuses laser point clouds, visual images and IMU inertial data, eliminates motion errors through Kalman filtering, calculates surface curvature, slope and deviation values ​​relative to the design model, and generates a surface flatness model with sub-millimeter accuracy.

[0011] S4: AI Defect Diagnosis: Call the pre-trained ResNet-3D network to classify abnormal regions and output defect types and repair suggestions;

[0012] S5: Global Data Integration: The cloud-based data management platform receives real-time data from mobile robots, LiDAR, and vision modules through edge computing units, including 3D point clouds, image textures, and IMU poses. It then stitches together multi-robot detection data to generate a 3D flatness heat map and compliance report for the entire ship.

[0013] Based on the above technical solution, the present invention can be further improved as follows.

[0014] Furthermore, the multi-line lidar array employs wavelength diversity technology to simultaneously emit 905nm and 1550nm laser beams, which are used for high-precision close-range detection and long-range anti-interference scanning, respectively.

[0015] Furthermore, the cloud platform integrates a deep learning anomaly detection model, which, based on a convolutional neural network and point cloud Transformer architecture, automatically identifies defects such as uneven welds, warped plates, and misaligned assembly, and labels the risk level.

[0016] Furthermore, in step S3, dynamic reference surface calibration technology is used to dynamically adjust the local flatness evaluation reference based on the theoretical curvature of the hull line, thereby eliminating misjudgment of surfaces with large curvature.

[0017] Furthermore, the cloud-based data management platform employs 5G or Industrial Internet of Things (IIoT) protocols (such as MQTT and OPCUA) to achieve low-latency data transmission, ensuring data real-time performance and integrity.

[0018] Furthermore, the distributed database uses a time-series database (such as InfluxDB) to store frequently collected sensor data, and combines a relational database (such as PostgreSQL) to manage structured detection reports and metadata. The data lake architecture supports the raw storage of unstructured data (such as point clouds and images) and enables batch processing through Hadoop or Spark.

[0019] Furthermore, the multimodal data fusion algorithm of the data processing and analysis engine utilizes Kalman filtering or particle filtering techniques to fuse lidar, visual images, and inertial data, eliminating motion errors and generating a surface model with sub-millimeter precision. The dynamic reference surface calibration module dynamically adjusts the local flatness evaluation benchmark according to the theoretical curvature of the hull to avoid misjudgment of surfaces with large curvature.

[0020] Furthermore, the AI ​​model and algorithm platform integrates TensorFlow or PyTorch deep learning frameworks, supporting pre-trained ResNet-3D and point cloud Transformer models for defect classification such as uneven welds and plate warping. The generative adversarial network module optimizes the model's ability to identify small sample defects through generative adversarial training, thereby improving generalization.

[0021] Furthermore, the 3D deviation heatmap generation module of the visualization and interaction layer renders a global 3D model based on WebGL or Unity engine, and intuitively displays the flatness deviation distribution through color gradient. The compliance report generation module automatically matches ISO 484 and DNV GL-ST-0111 standards to generate test reports in PDF or Excel format.

[0022] The beneficial effects of this invention are as follows: This invention provides a ship construction flatness inspection device and its usage method, which have the following advantages:

[0023] 1. Compared with the traditional method of monitoring that relies on manual operation of rulers and laser scanners, this application adopts a magnetic adsorption robot for autonomous navigation, which covers the surface of the ship (including the vertical surface) without human intervention, thereby improving the detection efficiency. Through the collaborative operation of multiple robots, large sections can be scanned in parallel, thereby effectively shortening the detection period.

[0024] 2. Employing multi-sensor fusion, it balances accuracy and coverage. Compared to traditional single devices such as laser scanners that cannot simultaneously meet local high-precision requirements, it uses a multi-line lidar + vision module to achieve 0.1mm-level weld seam detection at close range using a 1550nm laser and to complete hull line scanning at long range using a 905nm laser. Through dynamic reference plane calibration, it automatically adapts to the hull curvature, avoiding misjudgments of large curved surfaces caused by traditional fixed reference planes.

[0025] 3. Compared to traditional manual experience-based defect judgment, which is prone to overlooking hidden problems, the AI ​​multi-model collaborative ResNet-3D identification of geometric deformation and infrared thermal imaging detection of stress anomalies can provide real-time repair suggestions, generate a 3D heat map in the cloud and mark the repair priority to guide workers to accurately rework.

[0026] 4. This ship construction flatness inspection equipment can achieve efficient and high-precision intelligent inspection of the flatness of the entire ship through multi-sensor fusion and adaptive robot platform. It is suitable for real-time quality monitoring in the ship section construction, deck assembly and outfitting stages. In the ship section inspection scenario, it can perform local fine scanning along the weld area and mark the welding deformation deviation area at the same time. For non-critical plane areas, it can switch to global fast scanning mode. In the deck assembly stage, the cloud platform can integrate data in real time to assist in the assembly misalignment correction scheme.

[0027] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Specific embodiments of the present invention are given in detail below with reference to the accompanying drawings. Attached Figure Description

[0028] 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:

[0029] Figure 1 This is a flowchart illustrating a ship construction flatness inspection device and its usage method, provided as an embodiment of the present invention. Detailed Implementation

[0030] The following is in conjunction with the appendix Figure 1The principles and features of the present invention are described below. The examples given are for illustrative purposes only and are not intended to limit the scope of the invention. The invention is described more specifically in the following paragraphs by way of example with reference to the accompanying drawings. The advantages and features of the invention will become clearer from the following description and claims. It should be noted that the drawings are in a very simplified form and use non-precise proportions, and are only used to facilitate and clarify the illustration of the embodiments of the invention.

[0031] It should be noted that when a component is described as "fixed to" another component, it can be directly on the other component or may have a component in between. When a component is considered "connected to" another component, it can be directly connected to the other component or may have a component in between. When a component is considered "set on" another component, it can be directly set on the other component or may have a component in between. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0033] like Figure 1 As shown, the present invention provides a shipbuilding flatness inspection device, including a magnetic adsorption mobile robot platform, a high-precision vision module, an edge computing unit, and a cloud data management platform. The magnetic adsorption mobile robot platform is equipped with a tracked walking mechanism and an adaptive vacuum adsorption unit. A multi-line lidar array is installed on the magnetic adsorption mobile robot platform, which includes a 16-line vertical scanning radar and a 360° rotating horizontal radar. The high-precision vision module is installed on the magnetic adsorption mobile robot platform, which includes a binocular stereo camera and an infrared thermal imager. The edge computing unit has a built-in FPGA acceleration chip and an AI inference engine.

[0034] The cloud-based data management platform includes a data acquisition and transmission layer, a data storage and management layer, a data processing and analysis engine, an AI model and algorithm platform, and a visualization and interaction layer. The data acquisition and transmission layer is equipped with network transmission protocols, the data storage and management layer is equipped with a distributed database and data lake architecture, the data processing and analysis engine is equipped with a multimodal data fusion algorithm and a dynamic benchmark calibration module, the AI ​​model and algorithm platform is equipped with a deep learning framework module and a generative adversarial network module, and the visualization and interaction layer is equipped with a 3D deviation heatmap generation module and a compliance report generation module.

[0035] Preferably, the multi-line lidar array employs wavelength diversity technology to simultaneously emit 905nm and 1550nm laser beams, which are used for high-precision short-range detection and long-range anti-interference scanning, respectively.

[0036] Preferably, the cloud platform integrates a deep learning anomaly detection model, which is based on a convolutional neural network and point cloud Transformer architecture to automatically identify defects such as uneven welds, warped plates, and misaligned assembly, and to label the risk level.

[0037] Preferably, the cloud-based data management platform uses 5G or Industrial Internet of Things (IIoT) protocols (such as MQTT, OPC UA) to achieve low-latency data transmission, ensuring data real-time performance and integrity.

[0038] Preferably, the distributed database uses a time-series database (such as InfluxDB) to store high-frequency sensor data, combined with a relational database (such as PostgreSQL) to manage structured detection reports and metadata. The data lake architecture supports the raw storage of unstructured data (such as point clouds and images) and enables batch processing through Hadoop or Spark.

[0039] Preferably, the multimodal data fusion algorithm of the data processing and analysis engine uses Kalman filtering or particle filtering technology to fuse lidar, visual images and inertial data, eliminate motion errors and generate a surface model with sub-millimeter accuracy. The dynamic reference surface calibration module dynamically adjusts the local flatness evaluation benchmark according to the theoretical curvature of the hull to avoid misjudgment of large curvature surfaces.

[0040] Preferably, the deep learning framework of the AI ​​model and algorithm platform integrates TensorFlow or PyTorch, supports pre-trained ResNet-3D and point cloud Transformer models for defect classification such as uneven welds and warped plates, and the generative adversarial network module optimizes the model's ability to identify defects in small samples through generative adversarial training, thereby improving generalization.

[0041] Preferably, the 3D deviation heatmap generation module of the visualization and interaction layer renders a global 3D model based on WebGL or Unity engine, and intuitively displays the flatness deviation distribution through color gradient. The compliance report generation module automatically matches ISO484 and DNV GL-ST-0111 standards to generate test reports in PDF or Excel format.

[0042] The specific working principle and usage method of this invention are as follows:

[0043] S1: Adaptive Adsorption and Path Planning: The magnetic adsorption mobile robot platform can vertically adhere to the ship's surface through an adaptive vacuum adsorption unit. It can acquire three-dimensional point cloud data of the ship's surface through a 16-line vertical scanning radar and a 360° rotating horizontal radar. Based on the SLAM algorithm, a three-dimensional map of the ship's hull is constructed, and the optimal scanning path is automatically generated according to the preset detection priority. Local detection grids and global key areas are divided. The dynamic path planning algorithm is based on SLAM global planning. It uses LiDAR-SLAM to construct a three-dimensional map of the ship's hull and combines AI algorithms to generate the optimal detection path. SLAM-based global planning: DWA (Dynamic Window Method) is used to adjust the robot's movement trajectory in real time to avoid collisions with obstacles.

[0044] S2: Multimodal Data Synchronous Acquisition: A multi-line lidar array scans the surface geometry, a high-precision vision module captures texture images, an IMU records robot pose data, and lidar point clouds (geometric shape), visual images (texture and stress distribution), and IMU pose data (motion compensation) are input into a multimodal data fusion algorithm. The ICP (Iterative Closest Point) algorithm aligns multiple frames of point clouds to a unified coordinate system to complete point cloud registration. SLAM (Simultaneous Localization and Mapping) technology is used to map image feature points to point clouds for image-point cloud association. Kalman filtering is combined to eliminate jitter errors caused by robot motion and perform dynamic error correction.

[0045] S3: Real-time edge processing: The edge computing unit has a built-in multimodal data fusion algorithm that fuses laser point clouds, visual images and IMU inertial data. It eliminates motion errors through Kalman filtering, calculates the surface curvature, slope and deviation values ​​relative to the design model, generates a surface flatness model with sub-millimeter accuracy, and adopts dynamic reference surface calibration technology to dynamically adjust the local flatness evaluation benchmark according to the theoretical curvature of the hull line, eliminating misjudgment of large curvature surfaces;

[0046] S4: AI Defect Diagnosis: This algorithm uses a pre-trained ResNet-3D network to classify abnormal regions, outputting defect types and repair suggestions. The model architecture of the AI ​​defect diagnosis algorithm includes: a ResNet-3D network designed for 3D point cloud data, extracting multi-scale geometric features through residual structures; PointNet++ for processing non-uniform density point clouds and identifying local defects (such as pits and protrusions); and a Transformer module for capturing long-distance dependencies and global analysis of assembly misalignments. The training strategy uses transfer learning, pre-training the model based on standard ship component datasets (such as ISO standard models); and real-time model updates via online learning to adapt to the process differences of different shipyards.

[0047] S5: Global Data Integration: The cloud-based data management platform receives real-time data from mobile robots, LiDAR, and vision modules through edge computing units, including 3D point clouds, image textures, and IMU poses. It then stitches together multi-robot detection data to generate a 3D flatness heat map and compliance report for the entire ship.

[0048] It should be noted that, in this document, relational terms such as "first" and "second" are used merely 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. Content not described in detail in this specification is prior art known to those skilled in the art.

[0049] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Those skilled in the art can readily implement the present invention based on the accompanying drawings and the above description. However, any modifications, alterations, or variations made by those skilled in the art without departing from the scope of the present invention, utilizing the disclosed technical content, are equivalent embodiments of the present invention. Furthermore, any modifications, alterations, or variations made to the above embodiments based on the essential technology of the present invention are still within the protection scope of the present invention.

Claims

1. A shipbuilding flatness inspection device, comprising a magnetic adsorption mobile robot platform, a multi-line lidar array, a high-precision vision module, an edge computing unit, and a cloud data management platform, characterized in that: The magnetic adsorption mobile robot platform is equipped with a tracked walking mechanism and an adaptive vacuum adsorption unit. The multi-line lidar array is installed on the magnetic adsorption mobile robot platform. The multi-line lidar array includes a 16-line vertical scanning radar and a 360° rotating horizontal radar. The high-precision vision module is installed on the magnetic adsorption mobile robot platform. The magnetic adsorption mobile robot platform includes a binocular stereo camera and an infrared thermal imager. The edge computing unit has a built-in FPGA acceleration chip and an AI inference engine. The cloud-based data management platform includes a data acquisition and transmission layer, a data storage and management layer, a data processing and analysis engine, an AI model and algorithm platform, and a visualization and interaction layer. The data acquisition and transmission layer is equipped with a network transmission protocol. The data storage and management layer is equipped with a distributed database and a data lake architecture. The data processing and analysis engine is equipped with a multimodal data fusion algorithm and a dynamic benchmark calibration module. The AI ​​model and algorithm platform is equipped with a deep learning framework module and a generative adversarial network module. The visualization and interaction layer is equipped with a 3D deviation heatmap generation module and a compliance report generation module. The usage method includes the following steps: S1: Adaptive Adsorption and Path Planning: The magnetic adsorption mobile robot platform can vertically adhere to the surface of the ship through an adaptive vacuum adsorption unit. It can acquire three-dimensional point cloud data of the ship surface through a 16-line vertical scanning radar and a 360° rotating horizontal radar. Based on the SLAM algorithm, a three-dimensional map of the ship is constructed, and the optimal scanning path is automatically generated according to the preset detection priority, dividing the local detection grid and the global key area. S2: Multimodal data synchronous acquisition: Multi-line lidar array scans the surface geometry, high-precision vision module captures texture images, and IMU records robot pose data; S3: Real-time edge processing: The edge computing unit has a built-in multimodal data fusion algorithm that fuses laser point clouds, visual images and IMU inertial data, eliminates motion errors through Kalman filtering, calculates surface curvature, slope and deviation values ​​relative to the design model, and generates a surface flatness model with sub-millimeter accuracy. S4: AI Defect Diagnosis: Calls a pre-trained ResNet-3D network to classify abnormal regions and outputs defect types and repair suggestions; S5: Global Data Integration: The cloud-based data management platform receives real-time data from mobile robots, LiDAR, and vision modules through edge computing units, including 3D point clouds, image textures, and IMU poses. It then stitches together multi-robot detection data to generate a 3D flatness heat map and compliance report for the entire ship.

2. The ship construction flatness inspection equipment according to claim 1, characterized in that, The multi-line lidar array employs wavelength diversity technology to simultaneously emit 905nm and 1550nm laser beams.

3. The ship construction flatness inspection equipment according to claim 1, characterized in that, The cloud-based data management platform integrates a deep learning anomaly detection model, based on a convolutional neural network and point cloud Transformer architecture.

4. The ship construction flatness inspection equipment according to claim 1, characterized in that, In step S3, dynamic reference surface calibration technology is used to dynamically adjust the local flatness evaluation benchmark based on the theoretical curvature of the hull line.

5. The ship construction flatness inspection equipment according to claim 1, characterized in that, The cloud-based data management platform uses 5G or Industrial Internet of Things (IIoT) protocols, such as MQTT and OPC UA.

6. The ship construction flatness inspection equipment according to claim 1, characterized in that, The distributed database uses a time-series database (nfluxDB) to store frequently collected sensor data, and combines it with a relational database (PostgreSQL) to manage structured detection reports and metadata. The data lake architecture supports the raw storage of unstructured data, such as point clouds and images, and enables batch processing through Hadoop or Spark.

7. The ship construction flatness inspection equipment according to claim 1, characterized in that, The multimodal data fusion algorithm of the data processing and analysis engine uses Kalman filtering or particle filtering technology to fuse lidar, visual images and inertial data, eliminate motion errors and generate a surface model with sub-millimeter accuracy. The dynamic reference surface calibration module dynamically adjusts the local flatness evaluation benchmark according to the theoretical curvature of the hull.

8. The ship construction flatness inspection equipment according to claim 1, characterized in that, The AI ​​model and algorithm platform integrates TensorFlow or PyTorch deep learning frameworks, supporting pre-trained ResNet-3D and point cloud Transformer models for defect classification. The generative adversarial network module optimizes the model's ability to identify defects in small samples through generative adversarial training, thereby improving generalization.

9. The ship construction flatness inspection equipment according to claim 1, characterized in that, The visualization and interaction layer's 3D deviation heatmap generation module renders a global 3D model based on WebGL or Unity engine, and intuitively displays the flatness deviation distribution through color gradients. The compliance report generation module automatically matches ISO 484 and DNV GL-ST-0111 standards to generate test reports in PDF or Excel format.

Images