A waste disposal system and method for shipbuilding

Abstract

This invention relates to a waste treatment system and method for shipbuilding, belonging to the field of shipbuilding waste treatment technology. It includes an intelligent sorting module, a recyclable waste treatment module, a non-recyclable waste treatment module, and a central control platform. The intelligent sorting module includes a multimodal sensing unit and a vision-based sorting robotic arm. This invention enables automated and precise sorting of four types of solid waste, separating recyclable and non-recyclable materials for efficient recycling of recyclable materials such as metals, plastics, and wood. It also allows for the sorting of inert waste, combustible waste, hazardous waste, and non-recyclable materials by category, enabling rapid classification of shipbuilding waste for separate reuse. Automated sorting and grading of recyclable and non-recyclable materials is achieved through multimodal sensing and analysis decision-making, avoiding misjudgments inherent in traditional manual sorting. The sorting path is dynamically optimized based on the waste's morphology and physical characteristics, thereby effectively improving waste treatment efficiency.

Description

Technical Field

[0001] This invention relates to the field of ship waste treatment technology, and in particular to a ship manufacturing waste treatment system and method. Background Technology

[0002] Shipbuilding generates a variety of types of waste, and the methods of disposal vary depending on the nature of the waste and environmental regulations. Solid waste mainly includes: 1. Metal waste from steel cutting, welding, and machining processes, mainly including metal scraps (steel plates, aluminum, etc.), welding slag, metal dust, and waste steel shot (residue after sandblasting and rust removal); 2. Solid waste such as material packaging and construction waste, mainly including packaging materials such as plastic film, wooden boxes, and foam, waste insulation materials (such as glass wool and rock wool), waste cables, and rubber products; 3. Food scraps and plastic bottles generated by workers; 4. Waste from the demolition of temporary facilities (such as concrete and bricks).

[0003] Metal scrap can be sorted and sold to metal recycling companies for remelting into industrial raw materials. Recyclable materials such as plastics and cardboard are sorted and enter the recycling channel. Non-recyclable and harmless waste is disposed of according to local regulations. Traditional disposal methods usually involve manual sorting, which is inefficient and leads to the waste of recyclable resources. Mixed landfilling or incineration causes environmental pollution. To facilitate the disposal of the large amount of solid waste generated during shipbuilding, including: 1. Metal scraps, mainly steel and aluminum; 2. Packaging waste, mainly plastics, wood and foam. 3. Household waste mainly consists of organic waste and plastic bottles; 4. Construction waste mainly consists of concrete and bricks. Traditional treatment methods rely on manual sorting, which is inefficient and easily leads to the waste of recyclable resources. Non-recyclable waste is often mixed and landfilled or incinerated. This paper proposes a waste treatment system and method for shipbuilding, which can automatically and accurately sort four types of solid waste, separating recyclable and non-recyclable materials to enable efficient recycling of recyclable materials such as metal, plastic, and wood. It can also sort inert waste, combustible waste, hazardous waste, and non-recyclable materials by category for subsequent treatment. Summary of the Invention

[0004] This invention provides a waste treatment system and method for shipbuilding, which solves the problem of the lack of a "recyclable-non-recyclable" graded treatment system for shipbuilding scenarios in the prior art. It can automatically and accurately sort four types of solid waste, separating recyclable and non-recyclable materials, so as to carry out efficient recycling of recyclable materials such as metal, plastic and wood, and sort inert waste, combustible waste and hazardous waste into categories for subsequent processing.

[0005] The present invention provides the following solution to the above-mentioned technical problems: a waste treatment system for shipbuilding, comprising an intelligent sorting module, a recyclable waste treatment module, a non-recyclable waste treatment module, and a central control platform. The intelligent sorting module includes a multimodal sensing unit and a vision sorting robotic arm. The recyclable waste treatment module includes a metal recycling unit, a plastic recycling unit, and a wood / foam recycling unit. The non-recyclable waste treatment module includes an inert waste treatment line, a combustible waste incineration unit, and a hazardous waste temporary storage bin. The central control platform includes a digital twin system and a compliance management module.

[0006] The multimodal sensing unit includes a metal recognition submodule, a material sorting submodule, and a physical property detection submodule;

[0007] The metal identification submodule includes an electromagnetic induction sensor and a laser-induced breakdown spectroscopy (LIBS) instrument; the material sorting submodule includes a near-infrared spectroscopy (NIR) sensor and a hyperspectral imager; and the physical property detection submodule includes a weight-volume density analyzer and an air flotation separation device.

[0008] The vision sorting robotic arm includes a vision recognition system, a robotic arm sorting system, and a data interaction and control unit. The data interaction and control unit includes an industrial camera array and a deep learning model. The robotic arm sorting system includes a six-axis collaborative robotic arm and a path planning algorithm. The data interaction and control unit includes an edge computing gateway and a PLC control system.

[0009] The processing method includes the following steps:

[0010] S1: Waste input and initial screening: Waste is evenly spread on the conveyor belt by a vibrating feeder, with a conveying speed of 1-2m / s, and metal-containing waste is initially separated by a metal detection gate;

[0011] S2: Multimodal data acquisition: LIBS scans metal components, NIR identifies plastic / wood types, hyperspectral imaging distinguishes foam and composite materials, gravimetric-volume analyzer calculates density, and air flotation device pre-separates light / heavy materials;

[0012] S3: Classification Decision: The vision system generates a 3D point cloud model, and the CNN model outputs classification labels such as "304 stainless steel scraps" and "HDPE plastic film". The decision system integrates sensor data to determine whether the waste belongs to the category of recyclable or non-recyclable and the specific processing path.

[0013] S4: Robotic arm sorting execution: The robotic arm grabs the target waste according to the path planning and puts it into the corresponding collection bins according to the category. Recyclable metals are transferred to the metal recycling unit conveyor belt, recyclable plastics are transferred to the plastic granulator feed inlet, non-recyclable concrete is transferred to the construction waste crusher, and hazardous waste is transferred to the sealed hazardous waste container.

[0014] S5: Data Synchronization Sorting Results: Sorting results (such as missorting rate and processing speed) are uploaded to the central control platform, and the model automatically updates the weight parameters.

[0015] Based on the above technical solution, the present invention can be further improved as follows.

[0016] Furthermore, the electromagnetic induction sensor is used to detect the conductivity and magnetism of metals, thereby distinguishing between magnetic metals such as iron and steel and non-magnetic metals such as aluminum and copper.

[0017] Furthermore, the metal recycling unit includes an eddy current separator, a scrap steel shredder, and an electric arc furnace. The eddy current separator separates non-ferrous metals aluminum and copper, and the sorted metal shells are recycled into marine steel through smelting in the scrap steel shredder and electric arc furnace.

[0018] Furthermore, the near-infrared spectroscopy (NIR) sensor identifies organic materials and wood species, the hyperspectral imager distinguishes between foam (EPS, PU), plastic film, and composite materials based on the spectral reflectance characteristics in the 400-2500nm wavelength band, and the gravimetric-bulk density analyzer calculates the waste density and separates lightweight foam (density ≤30kg / m³). 3 ) and heavy concrete.

[0019] Furthermore, the plastic recycling unit includes an optical sorter and a twin-screw extruder. The optical sorter sorts plastic bottles according to resin type (PET, PE), and the twin-screw extruder generates recycled plastic granules. The wood / foam recycling unit crushes the wood and heat-presses it into biomass fuel, and the foam is dissolved in a solvent to recover polystyrene (PS) raw materials.

[0020] Furthermore, the air flotation separation device utilizes the difference in airflow velocity to separate lightweight materials (such as plastic films) into heavy materials (such as metal scraps).

[0021] Furthermore, the industrial camera array captures the form of waste from multiple angles, including size, color, and texture, generating 3D point cloud data. The deep learning model, based on a classification model (such as ResNet-50) trained by a convolutional neural network (CNN), determines the waste category in real time.

[0022] Furthermore, the six-axis collaborative robotic arm is equipped with an adaptive gripper, which includes a magnetic gripper and a vacuum suction cup. The magnetic gripper is used for metals, and the vacuum suction cup is used for films. The adaptive gripper has a response time of ≤0.5 seconds. The path planning algorithm combines the location of the waste with the speed of the conveyor belt to dynamically optimize the gripping path and avoid collisions.

[0023] Furthermore, the edge computing gateway processes sensor data in real time, reducing cloud latency, and the PLC control system coordinates the synchronous operation of the sensors, robotic arm, and conveyor belt.

[0024] The beneficial effects of this invention are as follows: This invention provides a waste treatment system and method for shipbuilding, which has the following advantages:

[0025] 1. It can automatically and accurately sort four types of solid waste, separating recyclable and non-recyclable materials, so as to efficiently recycle recyclable materials such as metal, plastic and wood. It can sort inert waste, combustible waste, hazardous waste and non-recyclable materials by category, so that the waste from shipbuilding can be quickly classified for separate reuse.

[0026] 2. It can achieve automated sorting and grading of recyclable and non-recyclable materials through multimodal sensing and analysis decision-making, avoiding misjudgments in traditional manual sorting;

[0027] 3. By dynamically optimizing the sorting path based on the form and physical characteristics of waste, waste processing efficiency can be effectively improved.

[0028] 4. Recycled metals can be directly used in the manufacture of ship structural components, forming a closed-loop resource system from "inside the factory to outside the factory". Recycled pellets can be used for ship pipes or interior parts. Wood waste can be compressed into biomass fuel to replace traditional fossil energy. Concrete and bricks can be crushed and used as roadbed aggregate or recycled building materials. Construction waste can be reused to reduce landfill volume, thus significantly improving the efficiency of resource utilization.

[0029] 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

[0030] 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:

[0031] Figure 1 A schematic diagram of a waste treatment system and method for shipbuilding provided in an embodiment of the present invention;

[0032] Figure 2 This is a flowchart illustrating a waste treatment system and method for shipbuilding, provided as an embodiment of the present invention. Detailed Implementation

[0033] The following is in conjunction with the appendix Figure 1-2The 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.

[0034] 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.

[0035] 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.

[0036] like Figure 1-2 As shown, the present invention provides a waste disposal system for shipbuilding, including an intelligent sorting module, a recyclable waste disposal module, a non-recyclable waste disposal module, and a central control platform. The intelligent sorting module includes a multimodal sensing unit and a vision sorting robotic arm. The recyclable waste disposal module includes a metal recycling unit, a plastic recycling unit, and a wood / foam recycling unit. The non-recyclable waste disposal module includes an inert waste disposal line, a combustible waste incineration unit, and a hazardous waste temporary storage bin. The central control platform includes a digital twin system and a compliance management module.

[0037] The multimodal sensing unit includes a metal recognition submodule, a material sorting submodule, and a physical property detection submodule;

[0038] The metal identification submodule includes an electromagnetic induction sensor and a laser-induced breakdown spectroscopy (LIBS) system; the material sorting submodule includes a near-infrared spectroscopy (NIR) sensor and a hyperspectral imager; and the physical property detection submodule includes a weight-volume density analyzer and an air flotation separation device.

[0039] The vision sorting robotic arm includes a vision recognition system, a robotic arm sorting system, and a data interaction and control unit. The data interaction and control unit includes an industrial camera array and a deep learning model. The robotic arm sorting system includes a six-axis collaborative robotic arm and a path planning algorithm. The data interaction and control unit includes an edge computing gateway and a PLC control system.

[0040] Preferably, the electromagnetic induction sensor is used to detect the conductivity and magnetism of the metal, thereby distinguishing magnetic metals iron and steel from non-magnetic metals aluminum and copper.

[0041] Preferably, the metal recycling unit includes an eddy current separator, a scrap steel shredder, and an electric arc furnace. The eddy current separator separates non-ferrous metals aluminum and copper, and the sorted metal shells are recycled into marine steel by smelting in the scrap steel shredder and electric arc furnace.

[0042] Preferably, a near-infrared spectroscopy (NIR) sensor identifies organic materials and wood species, a hyperspectral imager distinguishes foam (EPS, PU), plastic film, and composite materials through the spectral reflectance characteristics in the 400-2500nm wavelength range, and a weight-volume density analyzer calculates the waste density to separate lightweight foam (density ≤30kg / m³). 3 ) and heavy concrete.

[0043] Preferably, the plastic recycling unit includes an optical sorter and a twin-screw extruder. The optical sorter sorts plastic bottles according to resin type (PET, PE), and the twin-screw extruder generates recycled plastic granules. The wood / foam recycling unit crushes the wood and heat-presses it into biomass fuel, and the foam is dissolved in a solvent to recover polystyrene (PS) raw materials.

[0044] Preferably, the air flotation separator uses the difference in airflow velocity to separate lightweight materials (such as plastic film) into heavy materials (such as metal scraps).

[0045] Preferably, an industrial camera array captures the form of waste from multiple angles, including size, color, and texture, generating 3D point cloud data. A deep learning model, based on a classification model trained by a convolutional neural network (CNN) (such as ResNet-50), determines the waste category in real time.

[0046] Preferably, the six-axis collaborative robotic arm is equipped with an adaptive gripper, which includes a magnetic gripper and a vacuum suction cup. The magnetic gripper is used for metals, and the vacuum suction cup is used for films. The adaptive gripper has a response time of ≤0.5 seconds. The path planning algorithm combines the location of the waste with the speed of the conveyor belt to dynamically optimize the gripping path and avoid collisions.

[0047] Preferably, the edge computing gateway processes sensor data in real time, reducing cloud latency, and the PLC control system coordinates the synchronous operation of the sensors, robotic arm, and conveyor belt.

[0048] Example 1: Sorting of scrap metal (steel cutting scraps)

[0049] S1: Input: Mixed steel shavings, aluminum sheets, and plastic scraps enter the sorting area via conveyor belt;

[0050] S2: Multimodal data acquisition: Electromagnetic sensor triggers, determining the presence of metal; LIBS analysis shows Fe content of 95.2%, classifying it as low-carbon steel; hyperspectral imaging excludes metal with plastic adhering to the surface.

[0051] S3: Classification Decision: The classification label is "Recyclable - Carbon Steel", and the priority is set to high;

[0052] S4: Execution: The magnetic grippers grab steel chips and feed them into the feed inlet of the metal crusher;

[0053] S5: Data synchronization sorting results: sorting efficiency 200kg / h, metal recovery purity 99.3%; Example 2: Sorting of plastic film and foam

[0054] S1: Input: Mixed waste containing PE film, EPS foam, and wood chips;

[0055] S2: Multimodal data acquisition: NIR identifies the characteristic absorption peak of PE (1720nm), hyperspectral imaging distinguishes EPS (honeycomb structure), and the air flotation device blows the PE film and EPS foam to the upper lightweight area.

[0056] S3: Classification Decision: Classification labels are "Recyclable - PE Film" and "Recyclable - EPS Foam";

[0057] S4: Execution: The vacuum suction cup grabs the PE film to the hot melt machine, and the pneumatic pusher pushes the EPS into the solvent melting tank;

[0058] S5: Data synchronization sorting results: PE sorting speed 150 pieces / min, EPS recovery rate 98%.

[0059] Example 3: Sorting of construction waste (concrete blocks)

[0060] S1: Input: Mixed concrete blocks, bricks, metal bolts;

[0061] S2: Multimodal data acquisition: Density analyzer determined the concrete block density to be 2300 kg / m³. 3 LIBS detects no metal signal, and the vision system identifies the geometric shape as an irregular block.

[0062] S3: Classification Decision: The classification label is "non-recyclable - inert waste";

[0063] S4: Execution: The robotic arm grabs the concrete block and feeds it to the jaw crusher, where it is crushed into aggregate;

[0064] S5: Data synchronization sorting results: Aggregate particle size qualification rate (5-40mm) reaches 92%, used for shipyard road hardening.

[0065] Example 4: Sorting and Recycling of Wood Packaging Materials (Waste Wooden Crates)

[0066] S1: Input: Mixed waste: Pine wood crate fragments (including nails), plywood pieces, and plastic strapping enter the sorting area via conveyor belt;

[0067] S2: Multimodal data acquisition: The electromagnetic sensor detects iron nails (ferrous metal signal), triggering a second LIBS scan to confirm the presence of iron. NIR spectroscopy identifies pine wood (cellulose characteristic peak 1430nm) and plywood (urea-formaldehyde resin peak 1680nm). Hyperspectral imaging distinguishes wood chips from plastic strapping (difference in reflectance).

[0068] S3: Classification Decision: Classification labels are "Recyclable - Pine Wood (containing metal contamination)", "Recyclable - Plywood", and "Recyclable - PP Plastic Belt";

[0069] S4: Sorting execution: The robotic arm grabs pine wood fragments to the wood processing line, and the iron nails are automatically screened out by the metal separation roller. Plywood fragments are sent into the hot press by the pneumatic pusher. After being crushed, they are mixed with bio-resin and pressed into marine fireproof board substrate. Plastic strapping is optically sorted and then enters the granulator.

[0070] S5: Data synchronization sorting results: Wood recovery rate 92%, iron nail removal rate 100%, recycled fireproof board density 0.8g / cm³ 3 .

[0071] Example 5: Sorting of mixed household waste (food scraps + plastic bottles)

[0072] S1: Input mixed waste: food scraps (70% moisture content), PET plastic bottles (with labels), HDPE bottle caps, metal aluminum cans;

[0073] S2: Multimodal data acquisition: weight-volume analysis to determine low-density organic matter (food residue) and high-density plastic bottles, NIR spectroscopy to identify PET bottle body (characteristic peak 1712nm) and HDPE bottle cap (peak 1460nm), and electromagnetic induction to detect aluminum cans (aluminum material).

[0074] S3: Classification Decision: Classification labels are "Organic Waste - Kitchen Waste", "Recyclable - PET", "Recyclable - HDPE", and "Recyclable - Aluminum";

[0075] S4: Sorting execution: The air flotation device blows light food residue into the anaerobic fermentation tank, plastic bottles and aluminum cans enter the robotic arm operation area, the vacuum suction cup grabs the PET bottles to the label removal and cleaning line, and the bottle caps and aluminum cans enter the corresponding recycling channels respectively.

[0076] S5: Data synchronization and sorting results: Organic waste biogas production: 0.5m³ 3 / kg(TS), plastic bottle recycling purity 99.2%, aluminum can smelting energy consumption reduced by 95% compared to virgin aluminum (compliant with ISO 14040 life cycle assessment), wet waste pretreatment: air flotation separation avoids the high water consumption problem of traditional water washing, bottle cap-bottle body separation: utilizing the density difference between bottle cap and bottle body, automatic separation is achieved through centrifugal separation.

[0077] Example 6: Hazardous waste sorting (insulation material residue containing asbestos)

[0078] S1: Input mixed waste: asbestos insulation board fragments (particle size 10-50mm), ordinary rock wool fragments, metal fasteners;

[0079] S2: Multimodal data acquisition: LIBS detected asbestos characteristic elements (magnesium and silicon ratios conform to the chemical formula of chrysotile asbestos Mg3(Si2O5)(OH)4), and hyperspectral imaging identified fiber structure (asbestos fiber aspect ratio > 10:1);

[0080] S3: Classification Decision: Classification labels are "Hazardous Waste - Asbestos", "Recyclable - Rock Wool", and "Recyclable - Metals";

[0081] S4: Sorting execution: The robotic arm uses a closed negative pressure suction head to grab asbestos fragments, directly put them into HDPE sealed bags and bind RFID tags, while ordinary rock wool and metal parts enter the regular recycling line.

[0082] S5: Data synchronization sorting results: Asbestos sorting efficiency 50kg / h, sealed packaging leakage rate <0.01%, RFID tags are uploaded to the government hazardous waste supervision platform in real time to achieve full-chain traceability, contactless sorting: negative pressure adsorption avoids asbestos fiber escape, the work area maintains a -20Pa negative pressure environment, chemical fingerprint database: LIBS has a built-in database of 3,000 kinds of mineral spectra, and the asbestos identification accuracy rate is 99.9%.

[0083] Example 7: Sorting of composite materials (fiberglass waste)

[0084] S1: Input mixed waste: waste fiberglass (GFRP) hull fragments, aluminum alloy brackets, epoxy resin residue;

[0085] S2: Multimodal data acquisition: LIBS detection of characteristic peaks of silicon (glass fiber) and carbon element in epoxy resin in FRP, and hyperspectral imaging to identify the resin curing state (difference in reflectance of uncured epoxy resin);

[0086] S3: Classification Decision: Classification labels are "Non-recyclable - Thermosetting Composites", "Recyclable - Aluminum Alloys", and "Hazardous Waste - Uncured Resins";

[0087] S4: Sorting execution: The aluminum alloy bracket enters the metal recycling line, and the fiberglass fragments are put into the pyrolysis furnace (500℃ nitrogen environment for cracking and recycling of glass fiber) by the robotic arm. The uncured resin is sealed and transferred to the hazardous waste treatment plant.

[0088] S5: Data synchronization sorting results: Glass fiber recovery rate 85%, strength retention rate ≥80%, pyrolysis oil and gas calorific value 25MJ / m³ 3 Used for system self-powering, low-temperature pyrolysis technology: controlling temperature to avoid deterioration of glass fiber performance, epoxy resin state determination: hyperspectral imaging combined with resin curing degree model to distinguish hazardous waste from inert materials.

[0089] Example 8: Sorting of electronic waste (waste from ship equipment dismantling)

[0090] S1: Input mixed waste: waste circuit boards, copper cables, plastic casings, lead-containing solder;

[0091] S2: Multimodal data acquisition: LIBS detection of gold (Au), copper (Cu) and lead (Pb) elements in circuit boards, and X-ray fluorescence (XRF) quantitative analysis of heavy metal content (lead > 1000 ppm is classified as hazardous waste);

[0092] S3: Classification Decision: Classification labels are "Hazardous Waste - Lead Solder", "Recyclable - Copper", and "Recyclable - Engineering Plastics";

[0093] S4: Sorting execution: Lead-containing solder is transferred to a hazardous waste container by a robotic arm, copper cables are purified by an eddy current separator (copper purity 99.9%), and plastic shells are recycled into marine cable sheaths after being tested for flame retardants.

[0094] S5: Data synchronization and sorting results: Lead pollution control reaches lead content <1000ppm, recycled sheath plastic oxygen index ≥32% (meets the fire protection requirements of marine cables), online heavy metal detection: XRF and LIBS are used together to achieve rapid screening of heavy metals at the ppm level, flame retardant retention process: low temperature granulation (180℃) avoids decomposition of bromine flame retardants.

[0095] 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.

[0096] 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 waste disposal system for shipbuilding, comprising an intelligent sorting module, a recyclable waste disposal module, a non-recyclable waste disposal module, and a central control platform, characterized in that: The intelligent sorting module includes a multimodal sensing unit and a vision sorting robotic arm; the recyclable waste processing module includes a metal recycling unit, a plastic recycling unit, and a wood / foam recycling unit; the non-recyclable waste processing module includes an inert waste processing line, a combustible waste incineration unit, and a hazardous waste temporary storage bin; and the central control platform includes a digital twin system and a compliance management module. The multimodal sensing unit includes a metal recognition submodule, a material sorting submodule, and a physical property detection submodule; The metal identification submodule includes an electromagnetic induction sensor and a laser-induced breakdown spectroscopy (LIBS) instrument; the material sorting submodule includes a near-infrared spectroscopy (NIR) sensor and a hyperspectral imager; and the physical property detection submodule includes a weight-volume density analyzer and an air flotation separation device. The vision sorting robotic arm includes a vision recognition system, a robotic arm sorting system, and a data interaction and control unit. The vision recognition system includes an industrial camera array and a deep learning model. The robotic arm sorting system includes a six-axis collaborative robotic arm and a path planning algorithm. The data interaction and control unit includes an edge computing gateway and a PLC control system. The processing method includes the following steps: S1: Waste input and primary screening: Waste is evenly spread on the conveyor belt by a vibrating feeder, with a conveying speed of 1-2m / s, and metal-containing waste is initially separated by a metal detection gate; S2: Multimodal data acquisition: Laser-induced breakdown spectroscopy scans metal components, near-infrared spectroscopy identifies plastic / wood types, hyperspectral imaging distinguishes foam from composite materials, gravimetric-volume analyzer calculates density, and air flotation device pre-separates light / heavy materials; S3: Classification Decision: The vision system generates a 3D point cloud model, and the convolutional neural network model outputs classification labels such as "304 stainless steel scrap" and "HDPE plastic film". The decision system integrates sensor data to determine whether the waste belongs to the category of recyclable or non-recyclable and the specific processing path. S4: Robotic arm sorting execution: The robotic arm grabs the target waste according to the path planning and puts it into the corresponding collection bins according to the category. Recyclable metals are transferred to the metal recycling unit conveyor belt, recyclable plastics are transferred to the plastic granulator feed inlet, non-recyclable concrete is transferred to the construction waste crusher, and hazardous waste is transferred to the sealed hazardous waste container. S5: Data Synchronization Sorting Results: Sorting results are uploaded to the central control platform. These results include the missorting rate and processing speed, and the model automatically updates the weight parameters.

2. The waste disposal system for shipbuilding according to claim 1, characterized in that, The electromagnetic induction sensor detects the conductivity and magnetism of the metal.

3. The waste disposal system for shipbuilding according to claim 1, characterized in that, The metal recycling unit includes an eddy current separator, a scrap steel shredder, and an electric arc furnace. The eddy current separator separates non-ferrous metals aluminum and copper, and the sorted metal shells are recycled into marine steel through the scrap steel shredder and electric arc furnace.

4. The waste disposal system for shipbuilding according to claim 1, characterized in that, The near-infrared spectroscopy (NIR) sensor identifies organic materials and wood species. The hyperspectral imager distinguishes foam, plastic film and composite materials through the spectral reflectance characteristics of the 400-2500nm band. The foam is EPS and PU. The weight-volume density analyzer calculates the waste density and separates lightweight foam with a density ≤30kg / m³ from heavy concrete.

5. A waste disposal system for shipbuilding according to claim 1, characterized in that, The plastic recycling unit includes an optical sorter and a twin-screw extruder. The optical sorter sorts plastic bottles according to resin type, which is PET and PE. The twin-screw extruder generates recycled plastic granules. The wood / foam recycling unit crushes the wood and heat-presses it into biomass fuel. The foam is dissolved in a solvent to recover polystyrene (PS) raw materials.

6. The waste disposal system for shipbuilding according to claim 1, characterized in that, The air flotation separator uses the difference in airflow velocity to separate light materials into heavy materials. The light material is a plastic film, and the heavy material is metal scrap.

7. A waste disposal system for shipbuilding according to claim 1, characterized in that, The industrial camera array captures images of the waste from multiple angles, including its size, color, and texture, generating 3D point cloud data. The deep learning model, based on a classification model trained by a convolutional neural network (CNN), determines the waste category in real time. This classification model is ResNet-50.

8. A waste disposal system for shipbuilding according to claim 1, characterized in that, The six-axis collaborative robotic arm is equipped with an adaptive gripper, which includes a magnetic gripper and a vacuum suction cup. The magnetic gripper is used for metals, and the vacuum suction cup is used for films. The path planning algorithm combines the location of the waste with the speed of the conveyor belt to dynamically optimize the gripping path.

9. A waste disposal system for shipbuilding according to claim 1, characterized in that, The edge computing gateway processes sensor data in real time, reducing cloud latency, and the PLC control system coordinates the synchronous operation of the sensors, robotic arm, and conveyor belt.

Images