Ship body assembling and welding auxiliary method based on AI and knowledge graph

Abstract

The invention relates to the technical field of ship assembling and welding, in particular to a ship body assembling and welding auxiliary method based on AI and a knowledge graph, and a ship body assembling and welding scheme can be given more quickly and accurately through construction of a field large model and a knowledge graph network. And constructors conduct construction according to the assembling and welding scheme, so that the accuracy and efficiency of ship body assembling and welding are both improved. In addition, through the AR glasses, a good man-machine interaction interface is provided for the constructors, and therefore work of the constructors is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of ship welding, and in particular to an auxiliary method for ship hull welding based on AI and knowledge graph. Background Art

[0002] Hull welding is one of the most important activities in the shipbuilding process. At present, domestic ships are moving towards large-scale and high-value-added, and the number of parts they contain is also increasing. The segmented welding process is becoming more and more complicated. For example, the selection of the hull welding sequence is not unique, but there are multiple possibilities, and there are forms such as forward / reverse installation. How to ensure the efficient execution of welding is a big problem. For some specific processes, such as welding, different groove types and plate materials must be selected according to specific standards. Specific models and specifications of welding materials, corresponding to fixed weld leg heights. This requires that some links in the hull welding process must be flexible enough to adapt to different situations, and must ensure strict standardization to ensure safety and reliability. The traditional hull welding guidance method mainly relies on experience, and manual welding planning and execution, which makes the accuracy and efficiency of hull welding low. Summary of the invention

[0003] In view of the shortcomings of the prior art mentioned above, the purpose of the present invention is to provide a ship hull welding auxiliary method based on AI and knowledge graph, which is used to solve the problem that the planning and execution of hull welding are manually performed based on experience in the prior art, resulting in low accuracy and efficiency of hull welding.

[0004] To achieve the above objectives and other related objectives, the present invention provides a ship hull welding auxiliary method based on AI and knowledge graph, comprising:

[0005] Construct a large model in the field of ship hull welding to provide sequence planning, process definition, and auxiliary decision-making for ship hull welding;

[0006] Construct a knowledge graph network for ship hull welding to provide process push, audio and video guidance, document review, and model loading for ship hull welding;

[0007] Select the welding object;

[0008] Acquire relevant data of the welding object through the knowledge graph network;

[0009] According to the relevant data and the conditions at the construction site, a welding plan is given using the domain large model;

[0010] According to the welding plan, guide the construction personnel to carry out hull welding.

[0011] Optionally, the selection of welding objects is achieved by using AR glasses.

[0012] Optionally, the method of selecting the welding object includes voice interaction, gesture selection and eye tracking.

[0013] Optionally, guiding the construction personnel to perform hull welding according to the welding plan is achieved by using AR glasses.

[0014] Optionally, the method of guiding the construction personnel to perform hull welding is to use the knowledge graph network to associate the welding plan with each work step and the corresponding part model, and guide the on-site construction personnel to perform hull welding by AR virtual-reality superposition.

[0015] Optionally, the welding plan includes whether welding work is currently being carried out and welding requirements and sequence.

[0016] Optionally, the step of constructing a large model of the ship hull welding field includes:

[0017] Record the pipe size, rule requirements, welding sequence, cycle time, number of people, tooling, and site resources during the welding process of different hull sections;

[0018] The incorrect combinations of the information are marked, and the large model of the ship hull welding field is obtained through training in combination with the relevant terms of ship welding.

[0019] Optionally, the relevant data includes welding process documents, three-dimensional models, welding positioning requirements, relevant construction standards, and reference operation videos.

[0020] Optionally, the conditions of the construction site include the size of each hull part, spatial position, incoming material conditions, welding material type and quantity, cradle resources, dynamic interference conditions, static interference conditions, welding difficulty and danger conditions.

[0021] In a ship hull welding auxiliary method based on AI and knowledge graph of the present invention, by constructing a large domain model and a knowledge graph network, a ship hull welding scheme can be given more quickly and accurately. The construction personnel carry out construction according to the welding scheme, so that the accuracy and efficiency of the hull welding are improved. In addition, through AR glasses, a good human-computer interaction interface is provided for the construction personnel, thereby facilitating the work of the construction personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of a ship hull welding auxiliary method based on AI and knowledge graph according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] Refer to the following Figure 1To describe a ship hull welding auxiliary method based on AI and knowledge graph of the present invention. In the description of this embodiment, it should be understood that the terms "first" and "second" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features, that is, include one or more of the features. In the description of the present invention, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. When a feature "includes or contains" one or some of the features it covers, unless otherwise specifically described, this indicates that other features are not excluded and may further include other features.

[0024] Unless otherwise clearly defined and limited, the terms "set", "install", "connect", "connect", "fix", "couple" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral one; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. A person skilled in the art should be able to understand the specific meanings of the above terms in the present invention according to the specific circumstances.

[0025] In addition, in the description of this embodiment, the first feature being "above" or "below" the second feature may include the first and second features being in direct contact, or may include the first and second features not being in direct contact but being in contact through another feature between them. That is, in the description of this embodiment, the first feature being "above", "above", and "above" the second feature includes the first feature being directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. The first feature being "below", "below", or "below" the second feature may mean that the first feature is directly below or obliquely below the second feature, or simply indicates that the first feature is lower in level than the second feature.

[0026] In the description of the present embodiment, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0027] like Figure 1As shown, an embodiment of the present invention provides a ship hull welding auxiliary method based on AI and knowledge graph, including:

[0028] Step S1: Construct a large model in the field of ship hull welding to provide sequence planning, process definition, and auxiliary decision-making for ship hull welding. The steps of constructing a large model in the field of ship hull welding include recording the pipe size, rule requirements, welding sequence, cycle, number of people, tooling, and site resources in the process of welding different hull sections. Combine the various information and mark the wrong combination. Combined with the relevant terms of ship welding, a large model in the field of ship hull welding can be obtained through training.

[0029] Step S2: Construct a knowledge graph network for ship hull welding to provide process push, audio and video guidance, document review, and model loading for ship hull welding.

[0030] Step S3: Select the welding object, that is, select the object to be welded.

[0031] Step S4: Obtain relevant data of the welding object through the knowledge graph network. The relevant data includes welding process documents, three-dimensional models, welding positioning requirements, relevant construction standards and reference operation videos.

[0032] Step S5: According to the relevant data, combined with the situation of the construction site, the domain big model is used to give the welding scheme. Among them, the situation of the construction site includes the size, spatial position, incoming material situation, welding material type and quantity, tire frame resources, dynamic interference situation, static interference situation, welding difficulty and danger situation of each hull part. The assembly plan includes whether the welding work is currently carried out and the welding requirements and sequence. That is, according to the size, spatial position, incoming material situation, welding material type and quantity, tire frame resources, dynamic interference situation, static interference situation, welding difficulty and danger situation of each hull part, it is judged whether the assembly work can be carried out at present. And, according to the situation of the construction site, the requirements and sequence of welding are given. For example, after the analysis of the domain big model, it is dangerous to carry out the welding work at present, so the hull welding work is temporarily suspended. According to the incoming material situation and tire frame resources, the welding work that can be carried out at this stage is given, and the quantity of materials that need to be supplemented later is given.

[0033] Step S6: According to the welding plan, guide the construction personnel to carry out the welding of the hull.

[0034] By building a large domain model and knowledge graph network, a plan for ship hull welding can be given more quickly and accurately. Construction workers carry out construction according to the welding plan, which improves the accuracy and efficiency of hull welding.

[0035] Furthermore, the selection of welding objects and the guidance of construction personnel to weld the hull according to the welding plan are all achieved by using AR glasses. Among them, the methods of selecting welding objects include voice interaction, gesture selection and eye tracking. The method of guiding construction personnel to weld the hull is to use the knowledge graph network to associate the requirements and sequence of the welding plan with each work step and the corresponding part model, and guide the on-site construction personnel to weld the hull through the AR virtual-real superposition method.

[0036] AR glasses can provide construction workers with a good human-computer interaction interface, making their work more convenient. Of course, other human-computer interaction methods can also be used.

[0037] Optionally, when the welding object is selected as "DK1A segment", the construction worker wears the AR glasses and speaks the name of the object to be welded "DK1A segment" through voice interaction. After the AR glasses recognize the voice, they feed the information back to the knowledge graph network.

[0038] Based on the knowledge graph network, the relevant documents required for the DK1A hull assembly and welding are quickly retrieved, including: DK1A segmented 3D model and annotation, DK1A parts installation pallet table, relevant standards for assembly and welding process requirements, flat welding video diagram, overhead welding video diagram, vertical welding video diagram, and AR safety use precautions and other documents.

[0039] According to the hull information retrieved from the knowledge graph network, DK1A needs to weld 5 large assemblies, 2 small assemblies, 50 brackets, and the size, welding material type, and weld length of each hull. Combined with the on-site construction personnel scanning the QR code of each hull part to count the incoming materials, it was found that only 5 large assemblies, 2 small assemblies, and 46 brackets were delivered. After comprehensive judgment of dynamic interference, static interference, assembly difficulty and danger, the domain large model will give a welding plan for nearly 2 days based on the existing materials. The welding order is as follows: No. 1 large assembly, No. 2 large assembly, No. 1 medium assembly, No. 1-10 brackets, No. 3 large assembly, No. 4 medium assembly, No. 11-30 brackets, No. 4 large assembly, No. 5 large assembly, No. 31-46 brackets. At this time, the system infers and associates the welding process requirements, models, annotations, positive and negative states, welding material requirements, and welding current and voltage according to the welding plan. Through AR virtual-reality superposition and display of corresponding models of welding parts according to the welding plan, the welding safety specification documents, standards, process requirements, operation demonstration videos, and 3D annotations are matched and displayed to guide on-site construction personnel to complete the hull welding work in turn.

[0040] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A ship hull welding auxiliary method based on AI and knowledge graph, characterized in that: include: Construct a large model for ship hull welding to provide sequence planning, process definition, and auxiliary decision-making for ship hull welding; Construct a knowledge graph network for ship hull welding to provide process push, audio and video guidance, document review, and model loading for ship hull welding; Select the welding object; Acquire relevant data of the welding object through the knowledge graph network; According to the relevant data and the conditions at the construction site, a welding plan is given using the domain large model; According to the welding plan, guide the construction personnel to carry out hull welding.

2. The ship hull welding auxiliary method based on AI and knowledge graph according to claim 1 is characterized in that: The selection of welding objects is achieved by using AR glasses.

3. The ship hull welding auxiliary method based on AI and knowledge graph according to claim 2 is characterized in that: The methods for selecting the welding object include voice interaction, gesture selection and eye tracking.

4. The ship hull welding auxiliary method based on AI and knowledge graph according to claim 1 is characterized in that: The guiding of the construction personnel to carry out the hull welding according to the welding plan is achieved by using AR glasses.

5. The ship hull welding auxiliary method based on AI and knowledge graph according to claim 4 is characterized in that: The method of guiding construction personnel to perform hull welding is to use the knowledge graph network to associate the welding plan with each work step and the corresponding part model, and guide on-site construction personnel to perform hull welding through AR virtual-real superposition.

6. The ship hull welding auxiliary method based on AI and knowledge graph according to claim 1 is characterized in that: The welding plan includes whether welding work is currently being carried out and the welding requirements and sequence.

7. The ship hull welding auxiliary method based on AI and knowledge graph according to claim 1 is characterized in that: The steps of constructing a large model of the ship hull welding field include: Record the pipe size, rule requirements, welding sequence, cycle time, number of people, tooling, and site resources during the welding process of different hull sections; The incorrect combinations of the information are marked, and the large model of the ship hull welding field is obtained through training in combination with the relevant terms of ship welding.

8. The ship hull welding auxiliary method based on AI and knowledge graph according to claim 1 is characterized in that: The relevant data include welding process documents, three-dimensional models, welding positioning requirements, relevant construction standards, and reference operation videos.

9. The ship hull welding auxiliary method based on AI and knowledge graph according to claim 1 is characterized in that: The conditions of the construction site include the size of each hull part, spatial position, incoming material conditions, welding material type and quantity, cradle resources, dynamic interference conditions, static interference conditions, welding difficulty and danger conditions.

Images