Large-scale digital twinborn model automatic construction method

Abstract

The invention discloses a large-scale digital twinborn model automatic construction method, which comprises the following steps that S1, a three-dimensional model AI automatic identification system of a self-attention mechanism is adopted to sense a three-dimensional model, and the three-dimensional model AI automatic identification system comprises a down-sampling module, an up-sampling module and a 3D Transform extraction module; s2, adopting a down-sampling module for down-sampling the input data; the method belongs to the technical field of digital twinborn models, and achieves the technical effects of effectively reducing damage to local detail features of the model in a lightweight process, retaining key information of the model as far as possible, solving the problems in the aspects of storage, transmission, rendering and the like of the three-dimensional model, effectively improving the rendering efficiency and performance of the model in a large-scale digital twinborn scene, and improving the model rendering efficiency and performance in a large-scale digital twinborn scene. In addition, various lightweight methods are provided for the user according to different model scenes, and the controllability of lightweight is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twin models, and in particular to a method for automatically constructing a large-scale digital twin model. Background Art

[0002] Digital twin technology is a new type of processing technology. It is now used in aerospace, industrial production, oil field mining and other fields. By building a model for the system, the business system can be monitored in real time.

[0003] The defects of the prior art are as follows:

[0004] In the process of lightweighting, local detailed features of the model are easily destroyed, and less key information of the model is retained, resulting in problems such as the inability to store, transmit and render the three-dimensional model, making the rendering efficiency and performance of the model in the digital twin scenario low. Summary of the invention

[0005] To this end, the present invention provides a method for automatically constructing a large-scale digital twin model to solve the above-mentioned problems in the prior art.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] According to a first aspect of the present invention, a method for automatically constructing a large-scale digital twin model comprises the following steps:

[0008] S1: The downsampling module in the 3D model AI automatic recognition system is used to downsample the input 3D model;

[0009] S2: The upsampling module in the 3D model AI automatic recognition system is used to upsample the downsampled 3D model, and the Transition Up module in the upsampling module is used to generate new points;

[0010] S3: The 3D Transformer Extraction Module in the 3D Model AI Automatic Recognition System is used to position encode the new points generated by the Transition Up Module and establish the 3D Transformer layer;

[0011] S4: Use AI automatic recognition technology to batch map the position-encoded 3D Transformer layers to obtain a new digital twin model.

[0012] Furthermore, the S2 specifically includes the following steps:

[0013] M1: Use the farthest point sampling to select a subset P2 from the input 3D model point set P1 as the downsampling result, P2 belongs to P1;

[0014] M2: In P2, find its nearest k neighboring points in the original point set P1 through k-nearest neighbor search;

[0015] M3: For each sampled point, the features of its k neighboring points are merged together through maximum pooling;

[0016] M4: The aggregated features are further refined through a linear layer.

[0017] Furthermore, the S3 specifically includes the following steps:

[0018] N1: Assign features to the points generated by the Transition Up module through interpolation and feature propagation to restore or enhance local details;

[0019] N2: The Transition Up module is used in conjunction with the Transition Down module to form an encoding-decoding coordination to fully extract and utilize the features of the point cloud data.

[0020] Furthermore, the position coding in S4 specifically includes the following steps:

[0021] Q1: A multi-layer perceptron is used, and the dimension of its output vector is consistent with the dimension of the feature vector of the point;

[0022] Q2: The location information is effectively integrated into subsequent calculations;

[0023] Q3: The position encoding function is defined as follows:

[0024] δ=θ(p i -p j )

[0025] Q4: During the process, the model adjusts the parameters of position encoding according to task requirements.

[0026] Furthermore, the position coding in S4 specifically includes the following steps:

[0027] E1: Based on vector attention, the position encoding is added to the attention vector and the transformed features using a subtraction relationship;

[0028] E2: Define as:

[0029]

[0030] Among them, φ(x i ),Ψ(x j ) and α(x j) refer to Query, Key and Value in the attention mechanism respectively, γ is MLP, ρ is softmax, δ is position encoding, and ⊙ is the dot product operation.

[0031] The present invention has the following advantages: effectively reducing the damage to the local detail features of the model caused by the lightweight process, retaining the key information of the model as much as possible, solving the problems of three-dimensional model storage, transmission and rendering, and effectively improving the rendering efficiency and performance of the model in large-scale digital twin scenarios;

[0032] In addition, a variety of lightweighting methods are provided to users according to different model scenarios to improve the controllability of lightweighting. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A flowchart of a downsampling module in a large-scale digital twin model automatic construction method provided by the present invention.

[0034] Figure 2 A flowchart of an upsampling module in a large-scale digital twin model automatic construction method provided by the present invention.

[0035] Figure 3 This is a flowchart of 3DTransformer in the automatic construction method of a large-scale digital twin model provided by the present invention.

[0036] Figure 4 A flowchart of automatic batch mapping in a large-scale digital twin model automatic construction method provided by the present invention.

[0037] Figure 5 The overall architecture diagram provided for the present invention.

[0038] Figure 6 This is a diagram of the architecture provided by the present invention.

[0039] Figure 7 The present invention provides a 3D Transformer three-dimensional model based on the self-attention mechanism.

[0040] Figure 8 This is a flow chart of the AI-based automatic batch replacement technology for 3D models.

[0041] Fig. 9 It is a flow chart of the model multi-objective lightweight technology.

[0042] Fig.10 It is a diagram of the quadratic error calculation formula. DETAILED DESCRIPTION

[0043] The following is a description of the implementation of the present invention by means of specific embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification.

[0044] Example 1

[0045] like Figures 1 to 9 As shown, a method for automatically constructing a large-scale digital twin model in an embodiment of the first aspect of the present invention includes the following steps:

[0046] S1: The downsampling module in the 3D model AI automatic recognition system is used to downsample the input 3D model;

[0047] S2: The upsampling module in the 3D model AI automatic recognition system is used to upsample the downsampled 3D model, and the Transition Up module in the upsampling module is used to generate new points;

[0048] S3: The 3D Transformer Extraction Module in the 3D Model AI Automatic Recognition System is used to position encode the new points generated by the Transition Up Module and establish the 3D Transformer layer;

[0049] S4: Use AI automatic recognition technology to batch map the position-encoded 3D Transformer layers to obtain a new digital twin model.

[0050] In the above embodiments, it should be noted that standard classification, feature extraction, automatic identification, and intelligent construction of multi-source three-dimensional models are realized, the quality and efficiency of model construction are improved, and the construction needs of digital twin scenes in complex scenes are met;

[0051] The technical effect achieved by the above embodiment is: through the 3D transformer algorithm of the self-attention mechanism, the three-dimensional scene of the industrial digital twin is perceived, and the automatic AI recognition of different types of three-dimensional models in the scene is realized. Different types of models in the digital twin have different feature information. Based on the self-attention mechanism, the correlation between various model features is adaptively calculated, and feature aggregation is performed to achieve accurate recognition of 3D models;

[0052] For the multi-source 3D models produced by various professional 3D design software, the optimized 3D models are integrated with static attribute data, production dynamic data, simulation data, and AI data through automatic model reconstruction and automatic optimization processing methods to generate digital twin models of various equipment and facilities, realizing dynamic visualization management and control of the entire life cycle of equipment and facilities.

[0053] Example 2

[0054] like Figures 1 to 4 As shown, a method for automatically constructing a large-scale digital twin model includes all the contents of Example 1. In addition, S2 specifically includes the following steps:

[0055] M1: Use the farthest point sampling to select a subset P2 from the input 3D model point set P1 as the downsampling result, P2 belongs to P1;

[0056] M2: In P2, find its nearest k neighboring points in point set P1 through k nearest neighbor search;

[0057] M3: For each sampled point, the features of its k neighboring points are merged together through maximum pooling;

[0058] M4: The aggregated features are further refined through a linear layer.

[0059] In the above embodiment, it should be noted that the sampling point set is gradually reduced. The downsampling rate of each stage is [1, 4, 4, 4], so the point set generated in each stage is [N, N / 4, N / 16, N / 64, N / 256] of the input point set, where N is the number of input points. Among them, the up and down sampling module and the point cloud feature extraction module based on point transformer are the key modules of the network;

[0060] Automatic reconstruction of 3D models

[0061] In view of the similarity of a large number of models, we adopt methods such as instantiation technology, feature matching technology, and deep learning technology. Through the three-dimensional model AI automatic recognition technology with self-attention mechanism, we perceive the three-dimensional model, realize standard classification, feature extraction, automatic recognition, and intelligent construction of multi-source three-dimensional models, improve the quality and efficiency of model construction, and meet the construction needs of digital twin scenes in complex scenarios.

[0062] Example 3

[0063] like Figures 1 to 4 As shown, a method for automatically constructing a large-scale digital twin model includes all the contents of Example 1. In addition, S3 specifically includes the following steps:

[0064] N1: Assign features to the points generated by the Transition Up module through interpolation and feature propagation to restore or enhance local details;

[0065] N2: The Transition Up module is used in conjunction with the Transition Down module to form an encoding-decoding coordination to fully extract and utilize the features of the point cloud data;

[0066] The entire AI neural network architecture, such as Figure 7 As shown in the figure, it includes four modules: multi-layer perceptron MLP, downsampling module, upsampling module, and 3D Transformer. It is divided into five stages and acts on a gradually decreasing set of sampling points. The downsampling rate of each stage is [1, 4, 4, 4, 4], so the point set generated in each stage is [N, N / 4, N / 16, N / 64, N / 256] of the input point set, where N is the number of input points. Among them, the up and down sampling modules and the point cloud feature extraction module based on point Transformer are the key modules of the network.

[0067] Example 4

[0068] like Figures 1 to 4 As shown, a method for automatically constructing a large-scale digital twin model includes all the contents of Example 1. In addition, the position encoding in S4 specifically includes the following steps:

[0069] Q1: A multi-layer perceptron is used, and the dimension of its output vector is consistent with the dimension of the feature vector of the point;

[0070] Q2: The location information is effectively integrated into subsequent calculations;

[0071] Q3: The position encoding function is defined as follows:

[0072] δ=θ(p i -p j )

[0073] Q4: During the process, the model can adjust the parameters of position encoding according to task requirements.

[0074] In the above embodiment, it should be noted that in the 3D Transformer layer, each point interacts with other points to calculate attention weights. These weights determine the contribution of each point in the feature aggregation process. In this way, the 3D Transformer can learn the complex relationships and contextual information between points;

[0075] For industrial digital twin scenes, firstly, the 3D model AI automatic recognition technology based on the self-attention mechanism is used to perform efficient scene analysis and build a model-type database {model id: type}; users set mapping information for different types of models, such as color, highlight, glossiness, texture images, etc., to build a type-type-map database {type: map information}. Then, type matching is performed to obtain {model id: map information}. Finally, each model in the scene file is traversed to realize automatic batch mapping of 3D models, thereby improving the realism and fidelity of the digital twin scene;

[0076] Example 5

[0077] like Figures 1 to 4 As shown, a method for automatically constructing a large-scale digital twin model includes all the contents of Example 1. In addition, the position encoding in S4 specifically includes the following steps:

[0078] E1: Based on vector attention, the position encoding is added to the attention vector and the transformed features using a subtraction relationship;

[0079] E2: Define as:

[0080]

[0081] Among them, φ(x i ),Ψ(x j ) and α(x j ) refer to Query, Key and Value in the attention mechanism respectively, γ is MLP, ρ is softmax, δ is position encoding, and ⊙ is the dot product operation;

[0082] Model multi-objective lightweight technology

[0083] By studying an improved QEM (Quadric Error Mactrics) lightweight algorithm based on folding cost, the lightweight process can effectively reduce the damage to the local details of the model, retain the key information of the model as much as possible, solve the problems of 3D model storage, transmission and rendering, and effectively improve the rendering efficiency and performance of the model in large-scale digital twin scenarios. In addition, according to different model scenarios, users are provided with a variety of lightweight methods (edge ​​deletion, vertex aggregation, etc.) to improve the controllability of lightweighting.

[0084] Example 6

[0085] like Figures 1 to 4 As shown, a method for automatically constructing a large-scale digital twin model includes all the contents of Example 1, and further includes the following steps:

[0086] S6: For industrial digital twin scenarios, firstly, the 3D model AI automatic recognition technology based on the self-attention mechanism is used to perform efficient scenario analysis;

[0087] S7: Build model-type database {model id: type};

[0088] S8: The user sets the texture information for different types of models and builds a type-texture database {type: texture information};

[0089] S9: Perform type matching and obtain {model id: texture information}.

[0090] In the above embodiment, it should be noted that according to the replacement instruction, the replacement parameters given by the replacement model list are retrieved, the new model is loaded, and the corresponding new model is called to scale and rotate it to match the old model. The AI-based model automatic batch replacement technology improves the accuracy, efficiency and automation of the replacement, and improves the realism and fidelity of the digital twin scene.

[0091] The three-dimensional model AI automatic recognition technology based on the self-attention mechanism performs efficient scene analysis, parses the parameters of each model, and builds a model category database, including (model id, type, geometric information). The geometric information includes: coordinates, height, radius and rotation angle. According to the modification design requirements (original model id, original model type, target model id, target model type) and the model category database, the geometric parameters of the target model are calculated, and a replacement model list is built (original model id, original model type, geometric information of the original model, target model id, geometric information of the target model). According to the replacement instruction, the replacement parameters given in the replacement model list are retrieved, the new model is loaded, and the corresponding new model is called to scale and rotate to match the old model. This AI-based model automatic batch replacement technology improves the accuracy, efficiency and automation of replacement, and improves the realism and fidelity of the digital twin scene. Figure 5 This is a flow chart of the AI-based automatic batch replacement technology for 3D models.

[0092] Quadratic error calculation formula based on edge deletion collapse cost Fig.10 As shown, Cvi is the vertex curvature, SLR is the vertex area, and rvi is the vertex flatness.

Claims

1. A method for automatically constructing a large-scale digital twin model, characterized in that: The steps include: S1: The downsampling module in the 3D model AI automatic recognition system is used to downsample the input 3D model; S2: The upsampling module in the 3D model AI automatic recognition system is used to upsample the downsampled 3D model, and the Transition Up module in the upsampling module is used to generate new points; S3: Use the 3D Transformer extraction module in the 3D model AI automatic recognition system to position encode the new points generated by the TransitionUp module and establish the 3D Transformer layer; S4: Use AI automatic recognition technology to batch map the position-encoded 3D Transformer layers to obtain a new digital twin model.

2. The method for automatically constructing a large-scale digital twin model according to claim 1, characterized in that: The S2 specifically includes the following steps: M1: Use the farthest point sampling to select a subset P2 from the input 3D model point set P1 as the downsampling result, P2 belongs to P1; M2: In P2, find its nearest k neighboring points in point set P1 through k nearest neighbor search; M3: For each sampled point, the features of its k neighboring points are merged together through maximum pooling; M4: The aggregated features are further refined through a linear layer.

3. The method for automatically constructing a large-scale digital twin model according to claim 1, characterized in that: The S3 specifically includes the following steps: N1: Assign features to the points generated by the Transition Up module through interpolation and feature propagation to restore or enhance local details; N2: The Transition Up module is used in conjunction with the Transition Down module to form an encoding-decoding coordination to fully extract and utilize the features of the point cloud data.

4. The method for automatically constructing a large-scale digital twin model according to claim 1, characterized in that: The position coding in S4 specifically includes the following steps: Q1: A multi-layer perceptron is used, and the dimension of its output vector is consistent with the dimension of the feature vector of the point; Q2: The location information is effectively integrated into subsequent calculations; Q3: The position encoding function is defined as follows: δ=θ(p i -p j ) Q4: During the process, the model adjusts the parameters of position encoding according to task requirements.

5. The method for automatically constructing a large-scale digital twin model according to claim 1, characterized in that: The position coding in S4 specifically includes the following steps: E1: Based on vector attention, the position encoding is added to the attention vector and the transformed features using a subtraction relationship; E2: Define as: Among them, φ(x i ),Ψ(x j ) and α(x j ) refer to Query, Key and Value in the attention mechanism respectively, γ is MLP, ρ is softmax, δ is position encoding, and ⊙ is the dot product operation.

Images