A hull fouling removal system and its removal process

Abstract

The application relates to a ship bottom dirt cleaning system and a cleaning process thereof, and belongs to the technical field of ship bottom dirt cleaning, which comprises an underwater robot platform, multiple-degree-of-freedom mechanical arms, high-pressure water jet nozzles, shower type coating nozzles, underwater motors, ultrasonic wave generators, the multiple-degree-of-freedom mechanical arms are provided with four, the four multiple-degree-of-freedom mechanical arms are all installed at the underwater robot platform, the underwater robot platform is installed with an underwater holder, the underwater holder is installed with a high-definition underwater camera, and the underwater robot platform is installed with a water jet pump, a liquid storage tank and a conveying pump. In the application, the underwater robot which is designed by an algorithm can realize dirt identification, multi-modal collaborative cleaning (high-pressure water jet + biological enzyme + ultrasonic wave), and self-repairing coating spraying, the system has the advantages of high efficiency, environmental protection and long-term antifouling capability, and can significantly reduce the ship maintenance cost and the risk of marine pollution.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ship bottom fouling removal, in particular to a ship bottom fouling removal system and a removal process thereof. BACKGROUND

[0002] The existing ship bottom fouling removal system mainly includes mechanical removal method, chemical removal method, biological control method and dry dock cleaning method, wherein the mechanical removal method mainly includes: 1, manual scraping: using scraper, steel wire brush and other tools to clean manually, suitable for small area or local fouling; 2, high pressure water jet: through high pressure water gun (pressure is usually 2000-3000 psi) to flush the ship bottom, which can quickly remove soft fouling (such as algae) and part of hard biological; 3, robot / automation equipment: underwater robot or dock cleaning equipment, suitable for large ships or hard-to-reach areas, and the ship bottom fouling is not removed, which will increase the fuel consumption (up to 40%), accelerate the corrosion of the ship body and affect the navigation stability.

[0003] The existing ship bottom fouling removal system mainly has the following problems: 1, mechanical scraping is easy to damage the anti-rust layer, and the high pressure water jet has limited effect on hard biological (such as barnacles); 2, chemical cleaning agent may contain toxic ingredients, which does not comply with international environmental regulations; 3, traditional antifouling paint needs to be recoated regularly, and long-term moored ships are still prone to fouling; lack of intelligence, the existing robot cleaning equipment lacks the ability to adapt to the type of fouling and the ship body surface, therefore, the present application provides a ship bottom fouling removal system and a removal process thereof, which realizes multi-modal collaborative removal, combines high pressure water jet, biological enzyme decomposition and ultrasonic loosening, dynamically adjusts the removal strategy for different fouling types, optimizes the path and removal parameters in real time through algorithm, adapts to complex ship body surface, reduces manual intervention, the biological enzyme cleaning agent is degradable, which complies with IMO environmental standards; the self-repairing coating fills the scratches through nano materials, and the effective period of antifouling is extended to 5-7 years, which is not only suitable for ocean freighters, yachts but also suitable for offshore drilling platforms, does not need to enter the dry dock and supports underwater in-situ operation. SUMMARY

[0004] The present application provides a ship bottom fouling removal system and a removal process thereof, which solves the problems raised in the above background art, integrates dynamic monitoring, multi-modal removal and long-term antifouling functions, reduces maintenance cost and prolongs the service life of the ship.

[0005] The technical problems are solved by the following scheme: a ship bottom dirt removal system, comprising an underwater robot platform, a multi-degree-of-freedom manipulator, a high-pressure water jet nozzle, a shower-type coating nozzle, an underwater motor, and an ultrasonic generator, wherein four multi-degree-of-freedom manipulators are arranged, the four multi-degree-of-freedom manipulators are all installed on the underwater robot platform, the underwater robot platform is installed with an underwater holder, the underwater holder is installed with a high-definition underwater camera, the underwater robot platform is installed with a water jet pump, a liquid storage tank, and a delivery pump, and the driving end of the underwater motor is installed with a cleaning scraper through bolts, and the high-pressure water jet nozzle, the shower-type coating nozzle, the underwater motor, and the ultrasonic generator are respectively installed on the driving end of the multi-degree-of-freedom manipulator.

[0006] The removal process comprises the following steps:

[0007] S1: The underwater robot platform scans the bottom of the ship through the high-definition underwater camera of the underwater holder, collects high-definition images of the ship bottom dirt including algae, barnacles, shellfish and the like, labels the categories and position boundary boxes to build a data set, transmits the data set to a dirt classification model, uses a lightweight convolutional neural network through a main network to balance the calculation efficiency and recognition accuracy, performs a classification branch, outputs the dirt category, performs a semantic segmentation branch, generates a pixel-level dirt distribution mask, and finally performs transfer learning on the basis of a pre-trained ImageNet model and fine-tunes the ship bottom dirt data set;

[0008] S2: path planning algorithm design: 1. dirt distribution modeling, converting the semantic segmentation result into a two-dimensional grid map, each grid is marked with a pollution level and a dirt type, the pollution level: according to the dirt density, such as algae coverage, divided into low, medium and high, the dirt type: corresponding to the removal strategy, such as high-pressure water jet coverage area and accurate positioning of barnacles; 2. optimization target and constraint condition: target function, minimizing the total operation time (moving time + removal time), constraint condition, robot kinematics limit (turning radius, speed), removal efficiency difference (such as barnacle single-point processing time > algae area coverage), upper limit of energy consumption (battery capacity limit); 3. hybrid path planning strategy: global planning, generating a preliminary path, preferentially traversing high-pollution level areas;

[0009] S3: algorithm implementation process: 1. image input and real-time processing, the camera carried by the robot captures 10 frames of images per second, which are input into the classification model after preprocessing, and the inference time is < 50ms / frame; 2. dirt map update, mapping the recognition result to the ship three-dimensional curved surface model through SLAM technology, dynamically updating the pollution grid; 3. path generation and execution: decision tree logic: if a barnacle aggregation area (single area > 0.5m 2 ) is detected, the "high-frequency water jet + ultrasonic wave" mode is triggered;

[0010] S4: The water jet pump can pump seawater into the high-pressure water jet nozzle of the multi-degree-of-freedom manipulator to spray high-pressure water jet, first clean the conch gathering area of the ship bottom through the high-pressure water jet nozzle of the multi-degree-of-freedom manipulator and the ultrasonic generator, the delivery pump can spray the chitinase in the liquid storage tank from the shower type coating nozzle to adhere to the ship bottom, smear the chitinase to decompose the conch mucus, start the underwater motor to rotate the cleaning scraper, and the combination of the shower type coating nozzle and the cleaning scraper can perform secondary cleaning and spraying of the self-repairing coating on the cleaning part, and finally replace the nano silicon-based material and zinc oxide particles in the liquid storage tank and spray them from the shower type coating nozzle to adhere to the ship bottom, and the self-repairing coating releases zinc oxide particles when encountering seawater to inhibit the attachment of algae spores.

[0011] On the basis of the above technical scheme, the application can also be improved as follows.

[0012] Further, in step S1, the underwater image is enhanced, the underwater light attenuation is compensated using adaptive histogram equalization, the image blur caused by turbid water is eliminated using a deep learning denoising model, and the color distortion caused by water absorption is restored through a color correction algorithm.

[0013] Further, in step S2, local optimization: reinforcement learning (RL) dynamic adjustment: training a DQN (Deep Q-Network) model, adjusting the path weight in real time according to the remaining power and dirt distribution, and bionic algorithm assistance: introducing an ant colony algorithm to optimize the access order of multiple target points and reduce repeated paths.

[0014] Further, in step S3, the path adopts spiral coverage, and the algae dispersed area adopts "Z" shape traversal, combined with high-pressure water jet wide-area cleaning, and real-time obstacle avoidance: detecting protrusions (such as rivets) through laser radar and adjusting the posture of the manipulator to avoid collision.

[0015] The application has the following advantages:

[0016] 1. Multi-modal collaborative cleaning is realized, combined with high-pressure water jet, biological enzyme decomposition and ultrasonic loosening, the cleaning strategy is dynamically adjusted for different types of dirt, the path and cleaning parameters are optimized in real time through an algorithm, the complex ship body curve is adapted, and manual intervention is reduced;

[0017] 2. The biological enzyme cleaning agent is degradable and meets the IMO environmental protection standard; the self-repairing coating fills in scratches through nano materials, and the antifouling effective period is extended to 5-7 years, which is not only suitable for ocean freighters, yachts, but also suitable for offshore drilling platforms, without the need to enter a dry dock, and supports underwater in-situ operation;

[0018] 3. The underwater robot, designed with an algorithm, can identify dirt, perform multimodal collaborative cleaning (high-pressure water jet + biological enzyme + ultrasound), and apply self-healing coatings. This system combines high efficiency, environmental friendliness, and long-lasting anti-fouling capabilities, which can significantly reduce ship maintenance costs and marine pollution risks.

[0019] 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

[0020] 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:

[0021] Fig. 1 A process flow diagram of a ship bottom fouling removal system and its removal process provided in an embodiment of the present invention;

[0022] Fig. 2 This is a schematic diagram of a ship bottom dirt removal system and its removal process provided in an embodiment of the present invention;

[0023] Fig. 3 This is a front view of a ship bottom dirt removal system and its cleaning process provided in an embodiment of the present invention.

[0024] The attached diagram lists the components represented by each number as follows:

[0025] 1. Underwater robot platform; 2. Multi-degree-of-freedom robotic arm; 3. Underwater gimbal; 4. High-definition underwater camera; 5. Water jet pump; 6. Liquid storage tank; 7. Transfer pump; 8. High-pressure water jet nozzle; 9. Shower-type coating nozzle; 10. Underwater motor; 11. Ultrasonic generator; 12. Cleaning scraper. Detailed Implementation

[0026] The following is in conjunction with the appendix Figs. 1-3 The 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.

[0027] It should be understood that when an element, referred to as a "fixed" to another element, it can be directly on another element or there can be a middle element. When an element is considered to be "connected" to another element, it can be directly connected to another element or there can be a middle element. When an element is considered to be "disposed" to another element, it can be directly disposed on another element or there can be a middle element. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0028] 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 application belongs. The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0029] As shown in Figs. 1-3 The present application provides a ship bottom dirt cleaning system, comprising an underwater robot platform 1, a multi-degree-of-freedom manipulator 2, a high-pressure water jet nozzle 8, a shower type coating nozzle 9, an underwater motor 10, an ultrasonic generator 11, the multi-degree-of-freedom manipulator 2 is provided with four, the four multi-degree-of-freedom manipulators 2 are all installed at the underwater robot platform 1, the underwater robot platform 1 is installed with an underwater holder 3, the underwater holder 3 is installed with a high-definition underwater camera 4, the underwater robot platform 1 is installed with a water jet pump 5, a liquid storage tank 6 and a delivery pump 7, the driving end of the underwater motor 10 is installed with a cleaning scraper 12 through bolts, the high-pressure water jet nozzle 8, the shower type coating nozzle 9, the underwater motor 10 and the ultrasonic generator 11 are respectively installed at the driving end of the multi-degree-of-freedom manipulator 2.

[0030] The specific working principle and use method of the present application are as follows:

[0031] S1: The underwater robot platform 1 scans the bottom of the ship through the high-definition underwater camera 4 of the underwater holder 3, collects high-definition images of the ship bottom dirt including algae, barnacles, shellfish and the like, labels the categories and position boundary boxes to build a data set, the data set is transmitted to a dirt classification model, the dirt classification model balances the calculation efficiency and recognition accuracy through a lightweight convolutional neural network of a backbone network, performs a classification branch, outputs the dirt category, performs a semantic segmentation branch, generates a pixel-level dirt distribution mask, and finally performs transfer learning, fine-tunes the ImageNet model based on pre-training, performs image enhancement on the underwater image, compensates for underwater light attenuation using adaptive histogram equalization, eliminates image blur caused by turbid water bodies using a deep learning denoising model, and restores color distortion caused by water absorption through a color correction algorithm.

[0032] S2: Path planning algorithm design: 1. Dirt distribution modeling, convert semantic segmentation results into a two-dimensional grid map, each grid is marked with pollution level and dirt type, pollution level: according to dirt density, such as algal coverage, divided into low, medium and high, dirt type: corresponding to cleaning strategy, such as high-pressure water jet needs to cover the area, barnacles need accurate positioning; 2. Optimization objectives and constraints: objective function, minimize total operation time moving time + cleaning time, constraint conditions, robot kinematics limit turning radius, speed, cleaning efficiency difference such as barnacle single point processing time > algal area coverage, upper limit of energy consumption battery capacity limit; 3. Hybrid path planning strategy: global planning, generate initial path, preferentially traverse high pollution level area, local optimization: reinforcement learning RL dynamic adjustment: train DQN Deep Q-Network model, adjust path weight in real time according to remaining power, dirt distribution, bionic algorithm auxiliary: introduce ant colony algorithm to optimize multi-objective point access sequence, reduce repeated paths;

[0033] S3: Algorithm implementation process: 1. Image input and real-time processing, the camera mounted on the robot captures 10 frames of images per second, which are input into the classification model after preprocessing, with an inference time < 50ms / frame; 2. Dirt map update, map the recognition results to the ship's three-dimensional curved surface model through SLAM technology, dynamically update the pollution grid; 3. Path generation and execution: decision tree logic: if barnacle aggregation area > 0.5m 2 , trigger "high-frequency water jet + ultrasonic wave" mode, path uses spiral coverage, algal dispersed area uses "zigzag" traversal, combined with high-pressure water jet wide-area cleaning, real-time obstacle avoidance: detect protrusions such as rivets through laser radar, adjust the mechanical arm posture to avoid collision;

[0034] S4: The water jet pump 5 can pump seawater through the high-pressure water jet nozzle 8 of the multi-degree-of-freedom manipulator 2 to perform high-pressure water jetting. First, the high-pressure water jet nozzle 8 of the multi-degree-of-freedom manipulator 2 and the ultrasonic wave generator 11 are used to clean the barnacle aggregation area on the ship bottom. The delivery pump 7 can spray the chitinase contained in the liquid tank 6 through the shower-type coating nozzle 9 to adhere to the ship bottom, apply the chitinase to decompose the barnacle mucus, start the underwater motor 10 to rotate the cleaning scraper 12, and through the combination of the shower-type coating nozzle 9 and the cleaning scraper 12, the cleaned area can be cleaned and sprayed with a self-repairing coating. Finally, replace the nano-silicon-based material and zinc oxide particles in the liquid tank 6 and spray them through the shower-type coating nozzle 9 to adhere to the ship bottom. When the self-repairing coating encounters seawater, it releases zinc oxide particles to inhibit the attachment of algal spores.

[0035] Example 1: Recognition and removal of mixed pollution scenarios of algae and barnacles

[0036] 1. Input parameters and conditions:

[0037] Image input: Resolution: 1920x1080 pixels, underwater RGB-NIR multispectral image (near-infrared band range: 700-1000nm);

[0038] Lighting conditions: Simulated water depth 5 meters, visibility 2 meters, red channel attenuation coefficient 0.8;

[0039] Fouling distribution: Algae coverage: 40% (uniform distribution), barnacle aggregation area: 0.3m 2 (3 places in total);

[0040] Robot parameters: Moving speed: 0.5m / s, high-pressure water jet coverage width: 0.2m, mechanical arm positioning accuracy ±5mm, battery capacity: 10kWh, work power consumption: 500W (moving) + 1500W (cleaning);

[0041] 2. Algorithm processing flow:

[0042] Image preprocessing:

[0043] Apply CLAHE to enhance contrast, red channel gain compensation coefficient 1.5;

[0044] Use U-Net denoising model (training data: 100,000 turbid underwater images), PSNR improved to 28dB;

[0045] Fouling classification and segmentation:

[0046] Input EfficientNet-B4 model (pre-trained weights + fine-tuning dataset: 50,000 labeled images);

[0047] Output results:

[0048] Algae classification confidence: 96.2%, segmentation IoU: 89.5%.

[0049] Barnacle classification confidence: 88.7%, segmentation IoU: 83.1%.

[0050] Multispectral fusion: NIR band enhances barnacle edge detection, misjudgment rate reduced by 12%;

[0051] 3. Path planning:

[0052] Global path:

[0053] Priority: Barnacle aggregation area (weight coefficient 1.5) > high-density algae area (weight 1.2) > medium and low-density area (weight 1.0);

[0054] Initial path length: 18.7m, estimated time 37.4 minutes;

[0055] Dynamic adjustment of reinforcement learning (DQN model):

[0056] Real-time detection of battery power (8.2kWh), reducing low-density area stay time (single area from 30 seconds to 15 seconds);

[0057] Optimized path length: 14.2m, time-consuming 28.4 minutes, energy saving 24%;

[0058] 4、Verification of cleaning effect:

[0059] Algae removal rate: 94.3% (high-pressure water jet pressure 2500psi, coverage rate 98%);

[0060] Barnacle removal rate: 91.5% (pulsed water jet 3000psi + 80kHz ultrasound, mechanical arm residual rate <5%);

[0061] Example 2: Path planning optimization of complex curved hull (yacht)

[0062] 1、Input parameters and conditions:

[0063] Hull model:

[0064] Curvature radius of curved surface: 0.5-3m (local concave and convex area);

[0065] Type of dirt: dense attachment of shellfish (size 5-15cm), coverage rate 25%.

[0066] Sensor configuration:

[0067] 3D laser radar (accuracy ±2mm), SLAM positioning error <1cm.

[0068] Algorithm parameters:

[0069] Path safety distance: 10cm (to avoid collision with hull protrusions).

[0070] Maximum extension length of mechanical arm: 1.2m;

[0071] 2、Algorithm processing flow:

[0072] Three-dimensional dirt map construction:

[0073] SLAM generates hull curved surface point cloud (resolution 1cm 3 ), mapping dirt distribution to 3D grid;

[0074] Dirt density analysis: areas with shellfish aggregation area curvature >1.5m-1 account for 70%;

[0075] Path planning:

[0076] Global planning:

[0077] Ant colony algorithm optimizes the access order and reduces the number of mechanical arm posture adjustments (from 32 times to 18 times);

[0078] Initial path length: 22.5m, time-consuming 45 minutes;

[0079] Local obstacle avoidance:

[0080] Detect rivets (height 2cm), trigger avoidance path (radius of 15cm);

[0081] Dynamically adjust the water jet angle (angle with the curved surface normal <30°) to ensure uniform cleaning pressure;

[0082] Performance comparison:

[0083] Traditional loop path: time-consuming 58 minutes, mechanical arm collision 2 times;

[0084] This algorithm path: time-consuming 41 minutes, zero collision, surface area cleaning rate increased to 88.6%;

[0085] Example 3: extreme environment (low visibility + dynamic addition of dirt)

[0086] 1. Input parameters and conditions:

[0087] Environment simulation:

[0088] Visibility: 0.5m, suspended particle concentration: 200mg / L.

[0089] Dynamic addition of dirt: simulate the addition of 5% algae coverage every 10 minutes during navigation.

[0090] Algorithm robustness test:

[0091] Initial dirt distribution: 30% algae, 10% barnacles.

[0092] Operation time: 60 minutes, battery capacity limit 8kWh.

[0093] 2. Algorithm processing flow:

[0094] Image enhancement and recognition:

[0095] PSNR of turbid image from 18dB to 25dB (U-Net denoising + multispectral compensation).

[0096] Classification accuracy: algae 92%, barnacles 85% (lower than in clean water environment but meets operation requirements);

[0097] Dynamic path re-planning;

[0098] Update the dirt map every 5 minutes to detect new areas;

[0099] Reinforcement learning model response:

[0100] New algae area weight automatically increased to 1.3 and inserted into the current path queue;

[0101] Replanning time-consuming: 1.8 seconds, path change amplitude < 15%;

[0102] 3、Results statistics:

[0103] Final clearance rate: initial dirt 91% + new dirt 87%.

[0104] Total energy consumption: 7.8 kWh (battery utilization rate 97.5%), no power protection interruption triggered;

[0105] It should be noted that in this paper, relational terms such as first and second are used merely to distinguish one entity or action from another, and do not necessarily require or imply that there is any such actual relationship or order between the entities or actions. The contents not described in detail in the specification are the prior art known to those skilled in the art.

[0106] The above is only the preferred embodiment of the present application, and does not limit the present application in any form; any person skilled in the art can easily implement the present application according to the drawings and the above description; however, any equivalent changes, modifications and evolution made by those skilled in the art within the scope of the technical solutions of the present application, using the technical content disclosed above, are equivalent embodiments of the present application; at the same time, any equivalent changes, modifications and evolution made according to the essence of the present application to the above embodiments are still within the protection scope of the technical solutions of the present application.

Claims

1. A system for cleaning fouling from the bottom of a ship, comprising an underwater robot platform (1), a multi-degree-of-freedom manipulator arm (2), a high-pressure water jet nozzle (8), a shower-type coating nozzle (9), an underwater motor (10), an ultrasonic generator (11), characterized in that: Four multi-degree-of-freedom mechanical arms (2) are arranged, and the four multi-degree-of-freedom mechanical arms (2) are all installed at the underwater robot platform (1), the underwater robot platform (1) is installed with an underwater holder (3), the underwater holder (3) is installed with a high-definition underwater camera (4), the underwater robot platform (1) is installed with a water jet pump (5), a liquid storage tank (6) and a conveying pump (7), the driving end of the underwater motor (10) is installed with a cleaning scraper (12) through bolts, the high-pressure water jet nozzle (8), the shower type coating nozzle (9), the underwater motor (10) and the ultrasonic generator (11) are respectively installed at the driving end of the multi-degree-of-freedom mechanical arm (2); The cleaning process comprises the following steps: S1: The underwater robot platform (1) scans the bottom of the ship through the high-definition underwater camera (4) of the underwater holder (3), collects high-definition images of the ship bottom dirt including algae, barnacles and shellfish, labels the categories and position boundary boxes to build a data set, the data set is transmitted to a dirt classification model, the dirt classification model balances the calculation efficiency and recognition accuracy by using a lightweight convolutional neural network through a main network, performs a classification branch, outputs the dirt category, performs a semantic segmentation branch, generates a pixel-level dirt distribution mask, and finally performs transfer learning based on a pre-trained ImageNet model and fine-tunes the ship bottom dirt data set; S2: Path planning algorithm design:

1. Dirt distribution modeling: convert the semantic segmentation result into a two-dimensional grid map, each grid is marked with a pollution level and a dirt type, the pollution level: according to the dirt density, divided into low, medium and high; the dirt type: corresponding to the cleaning strategy; 2. Optimization target and constraint condition: objective function, minimize total operation time, total operation time: moving time + cleaning time, constraint condition, robot kinematics is limited by turning radius and speed, cleaning efficiency difference, upper limit of energy consumption: battery capacity limit; 3. Hybrid path planning strategy: global planning, generate a preliminary path, preferentially traverse high pollution level areas; S3: Algorithm implementation process:

1. Image input and real-time processing: the camera carried by the robot captures 10 frames of images per second, which are input into the classification model after preprocessing, and the inference time is < 50ms / frame; 2. Dirt map update: map the recognition result to the ship three-dimensional curved surface model through SLAM technology, and dynamically update the pollution grid; 3. Path generation and execution: decision tree logic: if a barnacle aggregation area is detected: single area > 0.5m², trigger "high-frequency water jet + ultrasonic wave" mode; S4: The water jet pump (5) can pump seawater into the high-pressure water jet nozzle (8) of the multi-degree-of-freedom manipulator (2) to spray high-pressure water jet. First, the high-pressure water jet nozzle (8) and the ultrasonic generator (11) of the multi-degree-of-freedom manipulator (2) are used to clean the conch gathering area on the ship bottom. The delivery pump (7) can spray the chitinase-containing conch slime in the liquid storage tank (6) from the shower coating nozzle (9) to the ship bottom, and the chitinase-containing conch slime is applied. Starting the underwater motor (10) can rotate the cleaning scraper (12). The combination of the shower coating nozzle (9) and the cleaning scraper (12) can perform secondary cleaning and spraying of the self-repairing coating on the cleaned part. Finally, replace the nano silicon-based material and zinc oxide particles in the liquid storage tank (6) and spray them from the shower coating nozzle (9) to the ship bottom. The self-repairing coating releases zinc oxide particles when it comes into contact with seawater, inhibiting the attachment of algae spores.

2. A hull fouling removal system according to claim 1, wherein, In step S1, the underwater image is enhanced, the adaptive histogram equalization is used to compensate for underwater light attenuation, the deep learning denoising model is used to eliminate image blur caused by turbid water, and the color correction algorithm is used to restore color distortion caused by water absorption.

3. The hull fouling removal system of claim 1, wherein, In step S2, local optimization: reinforcement learning (RL) dynamic adjustment: train the DQN (Deep Q-Network) model, adjust the path weight in real time according to the remaining power and dirt distribution, and use bionic algorithm assistance: introduce ant colony algorithm to optimize the access order of multiple target points, and reduce repeated paths.

4. The hull fouling removal system of claim 1, wherein, In step S3, the path adopts spiral coverage, and the "Z-shaped" traversal is used in the dispersed algae area. Combined with high-pressure water jet wide-area cleaning, real-time obstacle avoidance: detect protrusions through laser radar and adjust the manipulator attitude to avoid collision.

Images