Self-adaptive spraying control method and system for curved surface of ship

Abstract

The invention relates to the technical field of ship manufacturing, in particular to a ship curved surface self-adaptive spraying control method and system.The method comprises the steps that a target ship curved surface is scanned, three-dimensional point cloud data of the surface of the target ship curved surface is obtained, curved surface reconstruction and curvature calculation are conducted, and the ship curved surface is dynamically divided into spraying sub-areas according to curvature change characteristics; for each spraying sub-region, matching an optimal initial spraying parameter set from a pre-stored spraying process parameter database, generating a spraying path which ensures that the tail end of a spraying gun keeps a constant optimal distance from the curved surface by adopting equidistant bias based on the geometrical characteristics of each sub-region, and planning a global movement sequence of a robot; and controlling the mobile robot platform and the spray gun to execute spraying operation, monitoring spraying state parameters in real time through a sensor in the execution process, comparing the spraying state parameters with expected values, and dynamically adjusting spraying parameters through closed-loop control so as to realize uniform coating coverage, dynamically adjust execution parameters and ensure the spraying quality.

Description

Technical Field

[0001] This invention relates to the field of shipbuilding technology, and in particular to an adaptive spraying control method and system for ship curved surfaces. Background Technology

[0002] Ship painting is a crucial process in shipbuilding, and its quality directly affects the ship's corrosion resistance and service life. Traditional ship painting operations mainly rely on manual labor, with workers using handheld spray guns for rust removal and painting. This method has significant drawbacks: workers are exposed to harsh environments rich in organic solvents and dust for extended periods, seriously threatening their health; furthermore, the quality of manual work is affected by factors such as the worker's skill level and proficiency, making it difficult to guarantee the quality of the paint application.

[0003] With the development of automation technology, research institutions both domestically and internationally have begun to develop ship painting robots. Currently, the main types of painting robots include wall-climbing, track-mounted, and elevated-mounted robots. Wall-climbing robots typically use tracked permanent magnets to adhere to the ship's surface for operation; track-mounted robots move and paint via tracks pre-laid on or near the ship's surface; and elevated-mounted robots are mounted on elevated vehicles or similar platforms to complete their work. However, these robots have low levels of automation, poor painting quality, and require high control precision.

[0004] Especially in ship painting operations, modern ships are diverse in type, with varying hull sections and different sizes and curvatures of the painted surfaces. Existing painting robots can only adapt to large flat surfaces with simple, low-obstacle conditions and simple painting trajectories, as well as curved surfaces with small curvature variations. They cannot meet the painting requirements of complex curved surfaces, have complex trajectory perspectives, lack intelligent decision-making capabilities, and are prone to missed or over-painting. Therefore, developing intelligent painting systems adapted to the structural characteristics of ships is of significant practical importance. Summary of the Invention

[0005] To address the aforementioned issues, this invention provides a method and system for adaptive spraying control of ship curved surfaces. It deeply integrates a laser scanner, a binocular camera, and an inertial measurement unit. Through laser scanning, it rapidly acquires dense 3D point cloud data. After the robot is positioned, it performs a global 3D scan of the target ship hull sections, quickly generating a high-precision digital model of the working environment. The system automatically analyzes the model's curvature, uses a dynamic threshold method to partition the surface, and labels attributes for each region. Based on the partitioning results, the system matches optimal parameters from the process parameter MAP diagram and generates equidistant offset or optimized spraying paths for each region. Finally, it synthesizes the globally optimal working path. The robot moves along the planned path, and simultaneously, the closed-loop control system begins operation, dynamically adjusting execution parameters based on real-time sensed surface information and spraying status to ensure spraying quality.

[0006] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions: In a first aspect, the present invention provides an adaptive spraying control method for ship curved surfaces, comprising the following steps: The three-dimensional vision perception module mounted on the mobile robot platform is used to scan the curved surface of the target ship and obtain three-dimensional point cloud data of the surface of the target ship. Based on the three-dimensional point cloud data, surface reconstruction and curvature calculation are performed, and the ship surface is dynamically divided into multiple spraying sub-regions with different geometric characteristics according to the curvature change characteristics. For each of the spraying sub-regions, the optimal initial spraying parameter set is matched from the pre-stored spraying process parameter database. The spraying parameter set includes at least the spray gun moving speed, paint output, atomization pressure, and the nominal distance between the spray gun and the curved surface. Based on the geometric characteristics of each sub-region, an equidistant offset is used to generate the optimal spraying path that ensures a constant distance between the tip of the spray gun and the curved surface, and the robot's global movement sequence is planned. The mobile robot platform and spray gun are controlled to perform spraying operations. During the operation, the spraying status parameters are monitored in real time by sensors and compared with the expected values. The spraying parameters are dynamically adjusted using closed-loop control to achieve uniform coating coverage.

[0007] As a further aspect of the present invention, the ship surface is dynamically divided according to the curvature variation characteristics, including the following steps: Calculate the average curvature and Gaussian curvature of each triangular facet on the surface model; Based on the mean curvature and Gaussian curvature, the curvature variation characteristic of each triangular facet is calculated; Set curvature change thresholds. Regions with curvature change feature values ​​below the first threshold of the curvature change threshold are classified as planar regions. Regions with curvature change feature values ​​between the first and second thresholds of the curvature change threshold are classified as regular surface regions. Regions with curvature change feature values ​​above the second threshold of the curvature change threshold are classified as freeform surface regions.

[0008] As a further aspect of the present invention, when calculating the curvature change characteristic of each triangular facet, the curvature change characteristic is set as... The mean curvature is Gaussian curvature is The formula for calculating the characteristic quantity of curvature change is: ;in, The average curvature gradient, The maximum rate of change of the average curvature in the direction of the tangent plane of the surface is calibrated. The larger the value, the more significant the difference in the degree of curvature between adjacent regions. These are the weighting coefficients. Used to adjust Gaussian curvature Contribution to zoning decisions; This is an absolute bending type.

[0009] As a further aspect of the present invention, the curvature change threshold is set to... The curvature change characteristic quantity Below 0.5 The region is divided into planar regions, and the curvature variation characteristic quantity is... Between 0.5 With 1.5 The area between them is divided into regular curved surface regions, and the curvature variation characteristic quantity is... Above 1.5 The area is divided into freeform surface regions.

[0010] As a further aspect of the present invention, the curvature change threshold During setup, take the curvature variation characteristics of all triangular facets. mean Plus 10 times the standard deviation ,Right now ,in, .

[0011] As a further aspect of the present invention, the establishment of the spraying process parameter database includes: Simulation was performed in fluid dynamics software to establish a CFD model of the spray gun, simulate the paint mist field, and analyze the influence of moving speed, spraying pressure, spraying height, and paint output on the spray flow field and coating thickness distribution. Based on simulation data, an approximate relationship function between the average coating thickness and key process parameters is constructed. Based on the approximate relational function, with the goal of minimizing the coating thickness uniformity index, the response surface methodology or genetic algorithm is used to optimize the parameters and generate a MAP diagram of spraying process parameters covering different surface types. The MAP diagram of the spraying process parameters stores the optimal parameter combinations corresponding to the moving speed, spraying pressure, spraying height, and paint output, indexed by surface type and curvature value.

[0012] As a further aspect of the present invention, an approximate relationship function between the average coating thickness and key process parameters is constructed as follows: In the formula, The average thickness of the coating; These are coating characteristic constants related to coating density and solids content; The paint output from the spray gun per unit time, expressed in ml / min. The speed of the spray gun movement is expressed in m / s. To apply spray pressure and spraying height The deposition efficiency function of the coating material effectively deposited from the spray gun onto the workpiece surface.

[0013] As a further aspect of the present invention, an optimal spraying path is generated by equidistant offset to ensure that the tip of the spray gun maintains a constant distance from the curved surface, including the following steps: The divided freeform surface regions are then processed into triangular meshes; Using the boundary of the freeform surface area as the initial path, equidistant offsets are made along the normal of the triangular mesh surface. The offset distance is set according to the effective spray width of the spray gun, so that the overlap between adjacent paint marks meets the overlap rate. During the offset process, the shortest distance between the point on the offset path and the original surface is calculated in real time to ensure that the shortest distance is constant at the nominal distance, thereby generating a continuous path that ensures that the end of the spray gun maintains a constant distance from the surface.

[0014] As a further aspect of the present invention, when the offset distance is set according to the effective spray width of the spray gun, the offset distance... overlap rate ;in, The effective spray width of the spray gun is the width of the elliptical paint mark formed by the spray gun on the ground under standard conditions. The offset distance is the distance between the centerlines of two adjacent spray paths. Overlap rate, overlap rate Between 20% and 40%.

[0015] As a further aspect of the present invention, when planning the global movement sequence of the robot, the ant colony algorithm is used to solve the movement path sequence of the robot between each spraying sub-region, with the optimization objective being the shortest total path or the minimum operation time.

[0016] As a further aspect of the present invention, when dynamically adjusting the spraying parameters using closed-loop control, an adaptive PID control algorithm is employed for closed-loop control. The spraying status parameters monitored in real time by the sensor include the actual distance between the spray gun and the curved surface obtained by the laser sensor, the actual paint output obtained by the flow sensor, and the actual atomization pressure obtained by the pressure sensor.

[0017] Secondly, the present invention also provides a ship surface adaptive spraying control system, comprising: Mobile robot platforms are used to provide mobility and positioning capabilities in shipbuilding environments; A three-dimensional vision perception module is installed on the mobile robot platform to scan the curved surface of the target ship and obtain three-dimensional point cloud data of the surface of the target ship. The spraying execution module, including the spray gun and the material feeding system, is used to perform the spraying action; A sensor array is used to monitor the pose of the mobile robot platform, the attitude of the spray gun, and the spraying status parameters in real time. The central control unit is communicatively connected to the mobile robot platform, the three-dimensional vision perception module, the spraying execution module, and the sensor array, respectively. The central control unit is configured as follows: The system receives and processes the three-dimensional point cloud data, performs surface reconstruction and curvature calculation, and dynamically divides the ship surface into multiple spraying sub-regions based on the curvature change characteristics. For each sub-region, the optimal initial spraying parameter set is matched from the pre-stored spraying process parameter database; Based on the geometric characteristics of each sub-region, an equidistant offset algorithm is used to generate the spraying path, and the global movement sequence of the mobile robot platform is planned. The mobile robot platform and spraying execution module are controlled to perform spraying operations, and the spraying parameters are dynamically adjusted using a closed-loop control algorithm based on real-time data fed back from the sensor array to achieve uniform coating coverage.

[0018] As a further embodiment of the present invention, the three-dimensional vision perception module is a multi-sensor fusion system, including a laser scanner, a binocular vision camera, and an inertial measurement unit (IMU). The laser scanner is used to acquire high-precision three-dimensional point clouds, the binocular vision camera is used to acquire texture information, and the IMU is used to compensate for posture errors caused by robot motion.

[0019] As a further aspect of the present invention, the central control unit includes: The surface analysis and partitioning module is configured to calculate the average curvature at points on the surface model. and Gaussian curvature And based on the curvature change characteristic quantity Perform dynamic partitioning, where These are the weighting coefficients; The path and process planning module is configured to call the spraying process parameter database and generate equidistant offset paths for each partition, while using an optimization algorithm based on an evaluation function to plan the global movement sequence. The real-time closed-loop control module is configured to use an adaptive PID control algorithm for closed-loop control, dynamically adjusting the spray gun movement speed based on real-time coating thickness data fed back by the sensors.

[0020] Compared with existing technologies, the adaptive spraying control method and system for ship curved surfaces provided by this invention have the following beneficial effects: The adaptive spraying control method and system for ship curved surfaces of this invention sets spraying parameters for curved surfaces with different geometric characteristics through dynamic zoning based on curvature and optimization of zoning parameters. Through real-time closed-loop control, the system can dynamically adjust parameters such as spray gun speed to compensate for various interferences, ensuring that the actual spraying thickness always approaches the desired value. This fundamentally solves the problem of coating uniformity and avoids quality defects such as reduced corrosion resistance due to excessively thin coatings or sagging and waste caused by excessively thick coatings. This invention also calculates the angular deviation between the spray gun axis and the surface normal and adjusts the robot joints in real time to make the spray gun more perpendicular to the surface. By maintaining the minimum angle between the spray gun axis and the surface normal, the rebound loss of the coating is significantly reduced, thereby improving coating utilization and deposition efficiency. Simultaneously, since the coating thickness uniformity is fundamentally guaranteed, defects such as sagging and orange peel caused by improper thickness are avoided, indirectly improving the macroscopic appearance quality of the coating surface.

[0021] These or other aspects of the invention will become more apparent from the following description of embodiments. It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. In the drawings:

[0023] Figure 1 This is a flowchart of an adaptive spraying control method for ship curved surfaces according to the present invention.

[0024] Figure 2 This is a flowchart illustrating the dynamic division of a ship's curved surface in an adaptive spraying control method for ship curved surfaces according to the present invention.

[0025] Figure 3 This is a flowchart illustrating the establishment of a spraying process parameter database in an adaptive spraying control method for ship curved surfaces according to the present invention.

[0026] Figure 4 This is a flowchart illustrating the generation of the optimal distance spraying path in an adaptive spraying control method for ship curved surfaces according to the present invention.

[0027] Figure 5 This is a structural block diagram of a ship surface adaptive spraying control system according to the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0029] The technical solutions in the exemplary embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described exemplary 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.

[0030] Specifically, the embodiments of this application will be further described below with reference to the accompanying drawings.

[0031] See Figure 1 As shown, embodiments of this application also provide an adaptive spraying control method for ship curved surfaces, comprising the following steps: Step S10: Scan the surface of the target ship using the 3D vision perception module mounted on the mobile robot platform to obtain 3D point cloud data of the surface of the target ship.

[0032] In this step, the target ship's curved surface is scanned using a 3D vision perception module mounted on a mobile robot platform. This module employs a multi-sensor fusion scheme, including a laser scanner, a binocular vision camera, and an inertial measurement unit (IMU). For example, taking the hull's side curved surface as an example, the operation process is as follows: the mobile robot platform moves longitudinally along the hull at a speed of 0.5 m / s; the laser scanner emits scan lines at a frequency of 100 Hz to acquire a high-precision 3D point cloud; the binocular vision camera simultaneously acquires surface texture images with a resolution set to 2048×1536; the IMU monitors platform vibration and attitude changes in real time and performs motion compensation; finally, a dense point cloud containing 5 million points with a point spacing of 2 mm is generated.

[0033] Step S20: Based on the three-dimensional point cloud data, perform surface reconstruction and curvature calculation, and dynamically divide the ship surface into multiple spraying sub-regions with different geometric characteristics according to the curvature change characteristics.

[0034] In this step, see Figure 2 As shown, the dynamic division of the ship's surface based on curvature variation characteristics includes the following steps: Step S201: Calculate the average curvature and Gaussian curvature of each triangular facet on the surface model; Step S202: Calculate the curvature change characteristic of each triangular facet based on the mean curvature and Gaussian curvature; Step S203: Set curvature change thresholds, divide the region where the curvature change feature value is lower than the first threshold of the curvature change threshold into a planar region, divide the region where the curvature change feature value is between the first threshold and the second threshold of the curvature change threshold into a regular surface region, and divide the region where the curvature change feature value is higher than the second threshold of the curvature change threshold into a free surface region.

[0035] When calculating the curvature change characteristic of each triangular facet, let the curvature change characteristic be... The mean curvature is Gaussian curvature is The formula for calculating the characteristic quantity of curvature change is: ;in, The average curvature gradient, The maximum rate of change of the average curvature in the direction of the tangent plane of the surface is calibrated. The larger the value, the more significant the difference in the degree of curvature between adjacent regions. These are the weighting coefficients. Used to adjust Gaussian curvature Contribution to zoning decisions; This is an absolute bending type.

[0036] In this embodiment, the curvature change threshold is set to The curvature change characteristic quantity Below 0.5 The region is divided into planar regions, and the curvature variation characteristic quantity is... Between 0.5 With 1.5 The area between them is divided into regular curved surface regions, and the curvature variation characteristic quantity is... Above 1.5 The area is divided into freeform surface regions.

[0037] Among them, the curvature change threshold During setup, take the curvature variation characteristics of all triangular facets. mean Plus 10 times the standard deviation ,Right now ,in, .

[0038] In this embodiment, surface reconstruction and curvature calculation are performed based on the acquired 3D point cloud data, and the spraying sub-regions are dynamically divided according to the curvature change characteristics. For example, taking the processing of the complex curved surface of the bow of a ship as an example, the Poisson surface reconstruction algorithm is used to convert the point cloud into a triangular mesh model, and the average curvature of each triangular facet is calculated. and Gaussian curvature Apply the formula for the characteristic quantity of curvature change: Set threshold =0.5, =1.5, weighting coefficient =0.7; then the partitioning results are: planar regions (C<0.5) account for 40%, regular curved surface regions (0.5≤C≤1.5) account for 35%, and free-form surface regions (C>1.5) account for 25%.

[0039] Step S30: For each of the spraying sub-regions, match the optimal initial spraying parameter set from the pre-stored spraying process parameter database. The spraying parameter set includes at least the spray gun moving speed, paint output, atomization pressure, and the nominal distance between the spray gun and the curved surface.

[0040] In this embodiment, see Figure 3 As shown, the establishment of the spraying process parameter database includes: Step S301: Perform simulation in fluid dynamics software, establish a CFD model of the spray gun, simulate the paint mist field, and simulate and analyze the influence of moving speed, spraying pressure, spraying height, and paint output on the spray flow field and coating thickness distribution. Step S302: Construct an approximate relationship function between the average coating thickness and key process parameters using simulation data; Step S303: Based on the approximate relation function, with the goal of minimizing the coating thickness uniformity index, the response surface methodology or genetic algorithm is used to optimize the parameters and generate a MAP diagram of spraying process parameters covering different surface types. The MAP diagram of the spraying process parameters stores the optimal parameter combinations corresponding to the moving speed, spraying pressure, spraying height, and paint output, indexed by surface type and curvature value.

[0041] In step S302 of this embodiment, the approximate relationship function between the average coating thickness and key process parameters is constructed as follows: In the formula, The average thickness of the coating; These are coating characteristic constants related to coating density and solids content; The paint output from the spray gun per unit time, expressed in ml / min. The speed of the spray gun movement is expressed in m / s. To apply spray pressure and spraying height The deposition efficiency function of the coating material effectively deposited from the spray gun onto the workpiece surface.

[0042] Specifically, the optimal initial spraying parameter set is matched for each sub-region from a pre-stored spraying process parameter database, and parameters are matched for different surface types: Planar surface area: moving speed 0.8m / s, paint output 200ml / min, atomization pressure 0.4MPa, nominal distance 200mm Regular curved surface area: moving speed 0.5m / s, paint output 150ml / min, atomization pressure 0.3MPa, nominal distance 150mm; Freeform surface area: moving speed 0.3m / s, paint output 100ml / min, atomization pressure 0.25MPa, nominal distance 100mm.

[0043] Step S40: Based on the geometric characteristics of each sub-region, generate a spraying path that ensures the optimal distance between the end of the spray gun and the curved surface by using equidistant offset, and plan the robot's global movement sequence.

[0044] In this step, see Figure 4 As shown, the process of generating a spraying path that ensures a constant optimal distance between the spray gun tip and the curved surface using equidistant offset includes the following steps: Step S401: Perform triangular meshing on the divided freeform surface regions; Step S402: Using the boundary of the freeform surface area as the initial path, offset the paint lines at equal intervals along the normal of the triangular mesh surface. The offset distance is set according to the effective spray width of the spray gun, so that the overlap between adjacent paint marks meets the overlap rate. Step S403: During the offset process, the shortest distance between the point on the offset path and the original surface is calculated in real time to ensure that the shortest distance is constant at the nominal distance, and a continuous path is generated to ensure that the end of the spray gun maintains a constant distance from the surface.

[0045] Wherein, the offset distance is set according to the effective spray width of the spray gun, the offset distance overlap rate ;in, The effective spray width of the spray gun is the width of the elliptical paint mark formed by the spray gun on the ground under standard conditions. The offset distance is the distance between the centerlines of two adjacent spray paths. Overlap rate, overlap rate Between 20% and 40%.

[0046] In this embodiment, the ant colony algorithm is used to solve the robot's movement path sequence between each spraying sub-region when planning the robot's global movement sequence, with the optimization goal of minimizing the total path or the operation time.

[0047] Step S50: Control the mobile robot platform and spray gun to perform the spraying operation. During the operation, the spraying status parameters are monitored in real time by sensors and compared with the expected values. The spraying parameters are dynamically adjusted using closed-loop control to achieve uniform coating coverage.

[0048] In this step, when dynamically adjusting the spraying parameters using closed-loop control, an adaptive PID control algorithm is used for closed-loop control. The spraying status parameters monitored in real time by the sensor include the actual distance between the spray gun and the curved surface obtained by the laser sensor, the actual paint output obtained by the flow sensor, and the actual atomization pressure obtained by the pressure sensor.

[0049] Through the above-mentioned steps, this invention establishes a complete adaptive spraying control solution for ship curved surfaces, which has significant advantages in improving coating quality, operational efficiency and cost control, and provides important technical support for the intelligent development of the shipbuilding industry.

[0050] See Figure 5 As shown in the figure, this application embodiment also provides a ship surface adaptive spraying control system, the system including: Mobile robot platforms are used to provide mobility and positioning capabilities in shipbuilding environments; A three-dimensional vision perception module is installed on the mobile robot platform to scan the curved surface of the target ship and obtain three-dimensional point cloud data of the surface of the target ship. The spraying execution module, including the spray gun and the material feeding system, is used to perform the spraying action; A sensor array is used to monitor the pose of the mobile robot platform, the attitude of the spray gun, and the spraying status parameters in real time. The central control unit is communicatively connected to the mobile robot platform, the three-dimensional vision perception module, the spraying execution module, and the sensor array, respectively. The central control unit is configured as follows: The system receives and processes the three-dimensional point cloud data, performs surface reconstruction and curvature calculation, and dynamically divides the ship surface into multiple spraying sub-regions based on the curvature change characteristics. For each sub-region, the optimal initial spraying parameter set is matched from the pre-stored spraying process parameter database; Based on the geometric characteristics of each sub-region, an equidistant offset algorithm is used to generate the spraying path, and the global movement sequence of the mobile robot platform is planned. The mobile robot platform and spraying execution module are controlled to perform spraying operations, and the spraying parameters are dynamically adjusted using a closed-loop control algorithm based on real-time data fed back from the sensor array to achieve uniform coating coverage.

[0051] In this embodiment, the three-dimensional vision perception module is a multi-sensor fusion system, including a laser scanner, a binocular vision camera, and an inertial measurement unit (IMU). The laser scanner is used to acquire high-precision three-dimensional point clouds, the binocular vision camera is used to acquire texture information, and the IMU is used to compensate for posture errors caused by robot motion.

[0052] In this embodiment, the central control unit includes: The surface analysis and partitioning module is configured to calculate the average curvature at points on the surface model. and Gaussian curvature And based on the curvature change characteristic quantity Perform dynamic partitioning, where These are the weighting coefficients; The path and process planning module is configured to call the spraying process parameter database and generate equidistant offset paths for each partition, while using an optimization algorithm based on an evaluation function to plan the global movement sequence. The real-time closed-loop control module is configured to use an adaptive PID control algorithm for closed-loop control, dynamically adjusting the spray gun movement speed based on real-time coating thickness data fed back by the sensors.

[0053] The adaptive spraying control method and system for ship curved surfaces of this invention sets spraying parameters for curved surfaces with different geometric characteristics through dynamic zoning based on curvature and optimization of zoning parameters. Through real-time closed-loop control, the system can dynamically adjust parameters such as spray gun speed to compensate for various interferences, ensuring that the actual spraying thickness always approaches the desired value. This fundamentally solves the problem of coating uniformity and avoids quality defects such as reduced corrosion resistance due to excessively thin coatings or sagging and waste caused by excessively thick coatings. This invention also calculates the angular deviation between the spray gun axis and the surface normal and adjusts the robot joints in real time to make the spray gun more perpendicular to the surface. By maintaining the minimum angle between the spray gun axis and the surface normal, the rebound loss of the coating is significantly reduced, thereby improving coating utilization and deposition efficiency. Simultaneously, since the coating thickness uniformity is fundamentally guaranteed, defects such as sagging and orange peel caused by improper thickness are avoided, indirectly improving the macroscopic appearance quality of the coating surface.

[0054] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for adaptive spraying control of ship curved surfaces, characterized in that, Includes the following steps: The three-dimensional vision perception module mounted on the mobile robot platform is used to scan the curved surface of the target ship and obtain three-dimensional point cloud data of the surface of the target ship. Based on the three-dimensional point cloud data, surface reconstruction and curvature calculation are performed, and the ship surface is dynamically divided into multiple spraying sub-regions with different geometric characteristics according to the curvature change characteristics. For each of the spraying sub-regions, the optimal initial spraying parameter set is matched from the pre-stored spraying process parameter database. The spraying parameter set includes at least the spray gun moving speed, paint output, atomization pressure, and the nominal distance between the spray gun and the curved surface. Based on the geometric characteristics of each sub-region, an equidistant offset is used to generate the optimal spraying path that ensures a constant distance between the tip of the spray gun and the curved surface, and the robot's global movement sequence is planned. The mobile robot platform and spray gun are controlled to perform spraying operations. During the operation, the spraying status parameters are monitored in real time by sensors and compared with the expected values. The spraying parameters are dynamically adjusted using closed-loop control to achieve uniform coating coverage.

2. The adaptive spraying control method for ship curved surfaces as described in claim 1, characterized in that, The ship surface is dynamically divided based on its curvature variation characteristics, including the following steps: Calculate the average curvature and Gaussian curvature of each triangular facet on the surface model; Based on the mean curvature and Gaussian curvature, the curvature variation characteristic of each triangular facet is calculated; Set curvature change thresholds. Regions with curvature change feature values ​​below the first threshold of the curvature change threshold are classified as planar regions. Regions with curvature change feature values ​​between the first and second thresholds of the curvature change threshold are classified as regular surface regions. Regions with curvature change feature values ​​above the second threshold of the curvature change threshold are classified as freeform surface regions.

3. The adaptive spraying control method for ship curved surfaces as described in claim 2, characterized in that, During 3D reconstruction, when calculating the curvature change characteristic of each triangular facet, let the curvature change characteristic be... The mean curvature is Gaussian curvature is The formula for calculating the characteristic quantity of curvature change is: ;in, The average curvature gradient, The maximum rate of change of the average curvature in the direction of the tangent plane of the surface is calibrated. The larger the value, the more significant the difference in the degree of curvature between adjacent regions. These are the weighting coefficients. Used to adjust Gaussian curvature Contribution to zoning decisions; This is an absolute bending type.

4. The adaptive spraying control method for ship curved surfaces as described in claim 3, characterized in that, Set the curvature change threshold as The curvature change characteristic quantity Below 0.5 The region is divided into planar regions, and the curvature variation characteristic quantity is... Between 0.5 With 1.5 The area between them is divided into regular curved surface regions, and the curvature variation characteristic quantity is... Above 1.5 The area is divided into freeform surface regions.

5. The adaptive spraying control method for ship curved surfaces as described in claim 4, characterized in that, Curvature change threshold During setup, take the curvature variation characteristics of all triangular facets. mean Plus 10 times the standard deviation ,Right now ,in, .

6. The adaptive spraying control method for ship curved surfaces as described in claim 1, characterized in that, The establishment of the spraying process parameter database includes: Simulation was performed in fluid dynamics software to establish a CFD model of the spray gun, simulate the paint mist field, and analyze the influence of moving speed, spraying pressure, spraying height, and paint output on the spray flow field and coating thickness distribution. Based on simulation data, an approximate relationship function between the average coating thickness and key process parameters is constructed. Based on the approximate relational function, with the goal of minimizing the coating thickness uniformity index, the response surface methodology or genetic algorithm is used to optimize the parameters and generate a MAP diagram of spraying process parameters covering different surface types. The MAP diagram of the spraying process parameters stores the optimal parameter combinations corresponding to the moving speed, spraying pressure, spraying height, and paint output, indexed by surface type and curvature value.

7. The adaptive spraying control method for ship curved surfaces as described in claim 6, characterized in that, The approximate relationship function between the average coating thickness and key process parameters is constructed as follows: In the formula, This represents the average thickness of the coating. These are coating characteristic constants related to coating density and solids content; The paint output from the spray gun per unit time, expressed in ml / min. The speed of the spray gun movement is expressed in m / s. To apply spray pressure and spraying height The deposition efficiency function of the coating material effectively deposited from the spray gun onto the workpiece surface.

8. The adaptive spraying control method for ship curved surfaces as described in claim 1, characterized in that, The process of generating a spray path using equidistant offset to ensure a constant optimal distance between the spray gun tip and the curved surface includes the following steps: The divided freeform surface regions are then processed into triangular meshes; Using the boundary of the freeform surface area as the initial path, equidistant offsets are made along the normal of the triangular mesh surface. The offset distance is set according to the effective spray width of the spray gun, so that the overlap between adjacent paint marks meets the overlap rate. During the offset process, the shortest distance between the point on the offset path and the original surface is calculated in real time to ensure that the shortest distance is constant at the nominal distance, thereby generating a continuous path that ensures that the end of the spray gun maintains a constant distance from the surface.

9. The adaptive spraying control method for ship curved surfaces as described in claim 8, characterized in that, When the offset distance is set according to the effective spray width of the spray gun, the offset distance... overlap rate ;in, The effective spray width of the spray gun is the width of the elliptical paint mark formed by the spray gun on the ground under standard conditions. The offset distance is the distance between the centerlines of two adjacent spray paths. Overlap rate, overlap rate Between 20% and 40%.

10. A ship surface adaptive spraying control system, characterized in that, For performing the steps of the ship surface adaptive spraying control method according to any one of claims 1-9, the system includes: Mobile robot platforms are used to provide mobility and positioning capabilities in shipbuilding environments; A three-dimensional vision perception module is installed on the mobile robot platform to scan the curved surface of the target ship and obtain three-dimensional point cloud data of the surface of the target ship. The spraying execution module, including the spray gun and the material feeding system, is used to perform the spraying action; A sensor array is used to monitor the pose of the mobile robot platform, the attitude of the spray gun, and the spraying status parameters in real time. The central control unit is communicatively connected to the mobile robot platform, the three-dimensional vision perception module, the spraying execution module, and the sensor array, respectively. The central control unit is configured as follows: The system receives and processes the three-dimensional point cloud data, performs surface reconstruction and curvature calculation, and dynamically divides the ship surface into multiple spraying sub-regions based on the curvature change characteristics. For each sub-region, the optimal initial spraying parameter set is matched from the pre-stored spraying process parameter database; Based on the geometric characteristics of each sub-region, an equidistant offset algorithm is used to generate the spraying path, and the global movement sequence of the mobile robot platform is planned. The mobile robot platform and spraying execution module are controlled to perform spraying operations, and the spraying parameters are dynamically adjusted using a closed-loop control algorithm based on real-time data fed back from the sensor array to achieve uniform coating coverage.

Images