Digital twinborn visual modeling method and system based on neural network

Abstract

The invention relates to the field of digital twinborn modeling, and discloses a digital twinborn visual modeling method and system based on a neural network, and the method comprises the steps: collecting the multi-dimensional perception data of a target physical system, carrying out the format unification and normalization processing of the original data of a sensor through a heterogeneous data fusion module, and obtaining a data fusion module; constructing a high-dimensional input feature set for neural network modeling by combining a structured embedding algorithm; carrying out stability pre-evaluation on the constructed input feature set, and screening core features by adopting a disturbance sensitivity analysis mechanism; a dynamic residual feedback mechanism is introduced to carry out enhanced training on the preliminary twin model, and modeling is carried out on the space-time dependency relationship of different components through a graph neural network; tracking a stability index of visual representation in real time in a model training process; and according to a multi-dimensional visualization result output by the final twin model, performing interpretation in combination with an industrial scene semantic rule base. The method has the advantage of improving the practicability of the twin model in the industrial scene.

Description

Technical Field

[0001] The present invention relates to the field of digital twin modeling, and specifically to a digital twin visualization modeling method and system based on neural networks. Background Art

[0002] In the process of digital twin modeling of industrial systems, neural networks are widely used in the modeling of physical entity behavior and state prediction due to their powerful non-linear fitting ability and adaptive learning characteristics. The current mainstream methods usually combine sensor data and use feedforward neural networks, convolutional neural networks or recurrent neural networks to build virtual models corresponding to actual devices or systems. However, there is generally a problem in the prior art that in the model training stage, neural networks are highly sensitive to changes in the input feature distribution. Once there are minor offsets or noise disturbances in the sensor data in the actual environment, it may lead to a significant decrease in the prediction accuracy of the twin model. This lack of robustness to feature perturbations limits the long-term stable operation and visual credible display of digital twin systems in complex industrial sites, especially in scenarios that require high-frequency dynamic visual interaction. Therefore, it is necessary to design a digital twin visualization modeling method and system based on neural networks to improve the practicality of twin models in industrial scenarios. Summary of the Invention

[0003] Aiming at the deficiencies of the prior art, the present invention provides a digital twin visualization modeling method and system based on neural networks, which has the advantage of improving the practicality of twin models in industrial scenarios and solves the problems in the above background art.

[0004] To achieve the above purpose of improving the practicality of twin models in industrial scenarios, the present invention provides the following technical solutions: A digital twin visualization modeling method based on neural networks, comprising the following steps: Collect multi-dimensional perception data of the target physical system, unify the format and normalize the original sensor data through a heterogeneous data fusion module, and construct a high-dimensional input feature set for neural network modeling in combination with a structured embedding algorithm; Conduct a stability pre-evaluation on the constructed input feature set, screen core features using a perturbation sensitivity analysis mechanism, extract system behavior features in combination with a temporal convolutional network, and generate a preliminary twin model structure; Introduce a dynamic residual feedback mechanism to enhance the training of the preliminary twin model, model the spatio-temporal dependence relationship of different components through a graph neural network, and combine a perturbation injection training strategy; During the model training process, real-time track the stability index of the visual performance, and dynamically adjust the parameter settings of the visual interaction layer according to the index feedback; According to the multi-dimensional visualization results output by the final twin model, combined with the industrial scenario semantic rule base for interpretation, an interpretable analysis report is automatically generated.

[0005] Preferably, the process of constructing a high-dimensional input feature set for neural network modeling by combining the structured embedding algorithm is as follows: Standardize the format of the raw data collected from multiple sensors; normalize the data with unified format; according to the structural characteristics of the target physical system, use the structured embedding algorithm to express the relationship between each sub-component in the system in the form of vectors; fuse the structured information with the time series data so that the input features can reflect both the static structure information and the dynamic behavior pattern of the system; align and splice the structured embedding vectors and the sensor data in the time dimension; finally, form a high-dimensional input feature set containing structure, behavior, and context semantics.

[0006] Preferably, the process of screening core features using the perturbation sensitivity analysis mechanism is as follows: Without introducing any perturbation, input the high-dimensional input feature set into the preliminarily constructed neural network model to obtain the system output as the benchmark response result; for each input feature, apply a small perturbation in turn, and the perturbation range can be set according to the numerical range of the feature; record the output change caused by each perturbation, and construct a feature-output change mapping relationship: for each feature, statistically analyze the output change amplitude corresponding to the perturbation, and calculate the perturbation sensitivity index.

[0007] Preferably, the process of combining the temporal convolutional network to extract system behavior features and generate the structure of the preliminary twin model is as follows: Organize the core features screened by the perturbation sensitivity analysis into an input tensor in the time series format, retaining the time context information; Construct a temporal convolutional network based on one-dimensional convolution; Input the time series features into the temporal convolutional network model: Each layer extracts the feature changes within the local time window through the convolutional kernel; The output is the high-level behavior feature representation corresponding to each time step; Pool the temporal behavior features output by the temporal convolutional network to generate a unified representation of the entire input sequence, serving as the behavior encoding for predicting the state.

[0008] Preferably, the process of enhancing the training of the preliminary twin model by introducing the dynamic residual feedback mechanism is as follows: Input the filtered input feature sequence into the preliminarily constructed digital twin model to obtain the behavior prediction output; compare the model prediction output with the actual system observation value to calculate the residual; use the historical residual sequence as a new type of input signal, introduce residual-related features to re-encode and form a residual feedback vector; construct a feedback module to fuse the residual feedback vector with the original features of the main model to generate an enhanced input feature representation.

[0009] Preferably, the process of modeling the spatio-temporal dependence relationship of different components through a graph neural network and combining with the perturbation injection training strategy is as follows: Model the target physical system as a graph structure; introduce weights to represent the strength of the edges; assign a feature vector to each node; use the graph neural network for information propagation and aggregation, and each node updates its own state by aggregating the features of adjacent nodes.

[0010] Preferably, the process of dynamically adjusting the parameter settings of the visualization interaction layer according to the index feedback is as follows: Embed a visualization performance evaluation module in the twin modeling system to continuously monitor the following key stability indicators; Integrate a performance collection script through the front-end rendering engine; Regularly feedback the collected indicators to the back-end control logic; Use a dynamic threshold to judge and evaluate the visualization performance trend; Establish an index-parameter mapping rule library; Automatically update the parameter configuration of the interaction layer according to the feedback result.

[0011] Preferably, the process of interpreting in combination with the industrial scenario semantic rule library and automatically generating an interpretability analysis report is as follows: Bind the visualized structured data to the entities in the industrial semantic rule library; Enable a rule-based semantic engine for matching; The matching result generates event tags; Bind the identified events to the original data to construct the content of the analysis report.

[0012] Preferably, the process of adopting a multi-scale model fusion strategy to improve the prediction accuracy of the twin model is as follows: Input the input data with different resolutions into multiple sub-models respectively; Each sub-model is independently trained and outputs local prediction results; Through a weighted fusion strategy, combine the prediction results of different sub-models to form a global prediction output; Optimize the accuracy and stability of the twin model according to the weighted output.

[0013] A digital twin visualization modeling system based on neural network, including: Feature construction module: performs unified format conversion and normalization processing on multi-source sensor data, and generates a high-dimensional input feature set required for the neural network through a structured embedding algorithm; Behavior extraction module: performs perturbation sensitivity analysis on the input feature set to screen core features, and extracts key behavior patterns of the system through a temporal convolutional network; Enhanced training module: introduces a dynamic residual feedback mechanism to improve the model accuracy, and models the spatio-temporal dependencies between system components through a graph neural network, and combines a perturbation injection strategy to enhance the model robustness; Adaptive regulation module: monitors the visualization stability index during the training process, and dynamically adjusts the parameters of the interaction layer according to the feedback; Report generation module: combines the output results of the twin model with the industrial scenario rule base for semantic understanding, and automatically generates an interpretability analysis report.

[0014] Compared with the prior art, the present invention provides a digital twin visualization modeling method and system based on a neural network, having the following beneficial effects: The present invention collects multi-dimensional perception data and performs heterogeneous data fusion to construct a high-dimensional input feature set, thereby realizing accurate modeling of the physical system. System behavior features are extracted through perturbation sensitivity analysis and a temporal convolutional network to generate a preliminary twin model structure, and the spatio-temporal dependence modeling ability of the model is enhanced through a dynamic residual feedback mechanism and a graph neural network, further improving the prediction accuracy and robustness of the model. The visualization stability of the model is tracked in real time and the parameters of the interaction layer are dynamically adjusted, and an interpretability analysis report generated in combination with the industrial scenario semantic rule base ensures that the multi-dimensional visualization results output by the model are easy to understand and support decision-making. The modeling accuracy, real-time performance and interpretability of the digital twin system are improved, effectively supporting prediction and decision-making in complex industrial scenarios. Description of the drawings

[0015] Figure 1 It is a schematic diagram of the method of the present invention; Figure 2 It is a schematic diagram of the structure of the present invention. Detailed implementation manners

[0016] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention. Embodiment

[0017] Please refer to Figure 1As shown in the figure, a digital twin visualization modeling method based on a neural network according to an embodiment of the present invention includes the following steps: S1: Collect multi-dimensional perception data of the target physical system, perform format unification and normalization processing on the original sensor data through a heterogeneous data fusion module, and construct a high-dimensional input feature set for neural network modeling in combination with a structured embedding algorithm.

[0018] The process of constructing a high-dimensional input feature set for neural network modeling by combining the structured embedding algorithm in S1 is as follows: Perform format standardization on the original data collected from multiple sensors, unify the timestamp, sampling frequency, data type, etc., to ensure the comparability of heterogeneous data on a unified time scale; perform normalization processing on the data with unified format to eliminate the influence of dimensions between different data dimensions and improve the stability and convergence speed of neural network training; for the structural characteristics of the target physical system, use the structured embedding algorithm to express the relationship between each sub-component in the system in the form of a vector; use technologies such as sliding window and time decay function to fuse the structured information with time series data, so that the input features can reflect both the static structure information and dynamic behavior patterns of the system; splice the structured embedding vector and the sensor data after aligning them in the time dimension to generate a multi-dimensional, context-aware composite input feature, which constitutes the high-dimensional input tensor required for neural network modeling; finally, form a multi-dimensional feature set including structure, behavior, and context semantics, providing a rich information basis for subsequent feature screening, time series modeling, and residual feedback training.

[0019] Perform format unification and normalization processing on the original data from different types of sensors through a heterogeneous data fusion module, effectively eliminate the structural differences and scale inconsistencies between data, fully exploit the spatial structure and functional association information of the target physical system in combination with the structured embedding algorithm, construct a high-dimensional input feature set with both time series characteristics and system topology semantics, significantly improve the accuracy and generalization ability of the neural network for system behavior modeling, and provide a high-quality input basis for the stable construction of the subsequent twin model.

[0020] S2: Perform a stability pre-evaluation on the constructed input feature set, use a perturbation sensitivity analysis mechanism to screen core features, and extract system behavior features in combination with a temporal convolutional network to generate a preliminary twin model structure.

[0021] The process of screening core features using the perturbation sensitivity analysis mechanism in S2 is as follows: Without introducing any perturbations, input the high-dimensional input feature set into the preliminarily constructed neural network model to obtain the system output as the benchmark response result. For each input feature, apply a small perturbation in sequence. The perturbation range can be set according to the numerical range of the feature to ensure that the perturbation is representative and under control. Input the input feature set with a single perturbation into the model respectively, record the output changes caused by each perturbation, and construct a feature-output change mapping relationship: for each feature, statistically calculate the amplitude of the output change corresponding to its perturbation, and calculate the perturbation sensitivity index, such as: mean output deviation, normalized change rate, variance change rate, etc. These indices reflect the degree of influence of the feature on the model output. Sort all features according to the calculated sensitivity indices. Select the top several features with higher sensitivity as the core input feature set, and eliminate redundant or less influential features on the output.

[0022] In step S2, the process of combining a temporal convolutional network to extract system behavior features and generate a preliminary twin model structure is as follows: Organize the core features screened by perturbation sensitivity analysis into an input tensor in time series format to retain time context information; Construct a temporal convolutional network based on one-dimensional convolution, including: Causal convolution: Ensure that the output depends only on the current and past time steps, satisfying the time causality of the actual system.

[0023] Dilated convolution: Adopt an exponentially increasing dilation rate to expand the receptive field to capture long-term dependencies.

[0024] Residual connection: Introduce a skip connection structure to alleviate the training difficulty of deep networks and improve stability; Input the time series features into the temporal convolutional network model: Each layer extracts the feature changes within a local time window through a convolutional kernel; Multiple layers are stacked to achieve comprehensive modeling of short-term and long-term dynamic patterns; The output is the high-level behavior feature representation corresponding to each time step; Pool the temporal behavior features output by the temporal convolutional network to generate a unified representation of the entire input sequence as the behavior encoding of the current or predicted state of the system; Use the above behavior encoding as the backbone modeling basis, combine the input-output mapping relationship, and generate a preliminary digital twin model structure. The model has the following characteristics: It can capture the behavior patterns of the system evolving over time; it can serve as the infrastructure for subsequent introduction of graph neural networks and residual feedback mechanisms; it provides a basis for the dynamic response of system state changes at the visualization level. The output of the preliminary twin model includes: prediction of the current system state; short-term trend prediction; identification of key behavior events.

[0025] By pre - evaluating the stability of the constructed high - dimensional input feature set, using the perturbation sensitivity analysis mechanism to screen out the core features that have a significant impact on the system behavior, effectively reducing redundant dimensions and noise interference; further combining with a temporal convolutional network to extract key time - behavior patterns, realizing efficient modeling of the system's dynamic response, thereby generating a preliminary digital twin model with good temporal perception ability and structural scalability, and improving the adaptability and prediction accuracy of the model to complex working conditions.

[0026] S3: Introduce a dynamic residual feedback mechanism to enhance the training of the preliminary twin model. Model the spatio - temporal dependence relationships of different components through a graph neural network, and combine a perturbation injection - based training strategy.

[0027] The process of introducing the dynamic residual feedback mechanism to enhance the training of the preliminary twin model in S3 is as follows: Input the screened input feature sequence into the preliminarily constructed digital twin model (system behavior features extracted based on a temporal convolutional network) to obtain the predicted output of the system state or behavior; compare the model's predicted output with the actual system observation value to calculate the residual, that is, the prediction error; use the historical residual sequence as a new type of input signal, introduce residual - related features to re - encode and form a residual feedback vector to enhance the model's perception ability of prediction error changes; construct a feedback module to fuse the residual feedback vector with the original features of the main model to generate an enhanced input feature representation: dynamically adjust the feature weights; focus on compensating for dimensions or time periods with large deviations in model prediction; use a joint loss function to perform end - to - end training on the model after fusing the residual feedback. The dynamic residual mechanism is updated in each training iteration, gradually guiding the model to correct prediction blind spots, improving the global fitting ability and stability; continuously monitor the residual evolution trend of the model on the validation set. When the residual distribution tends to be stable or drops to a set threshold, it is regarded as the convergence of the enhanced training, and a digital twin model with optimized performance is obtained.

[0028] The process of modeling the spatio - temporal dependence relationships of different components through a graph neural network and combining a perturbation injection - based training strategy in S3 is as follows: Model the target physical system as a graph structure, where: nodes represent the key components or sensing units of the system; edges represent the spatial connection relationships, functional coupling relationships, or data correlations between them; introduce weights or attributes to represent the strength of the edges; assign a feature vector to each node, including: sensor input data of each component; temporal behavior features (from the extraction results of the temporal convolutional network); residual feedback vector; use a graph neural network for information propagation and aggregation: each node updates its own state by aggregating the features of adjacent nodes; the aggregation method uses algorithms such as GCN, GAT, GraphSAGE, etc.; support multi - layer propagation to capture a wider system dependence structure; Introduce a temporal expansion method, including: Dynamic graph modeling: Nodes and edges change over time; Spatio-temporal graph convolutional network: Combine convolution on the graph structure to extract time series dependencies; Modeling the evolution of node states: Introduce recurrent units in the time dimension to represent the change of states over time.

[0029] Construct multiple types of perturbations for training enhancement, including: Input perturbation: Add noise or simulate abnormal fluctuations in sensor data; Structure perturbation: Perturb the edge weights in the graph structure to simulate connection failures or structural changes; Time perturbation: Adjust the rhythm of the input sequence to simulate non-stationary dynamics.

[0030] Generate multiple training copies through perturbations to enhance the model's robustness to abnormal inputs and structural changes, and improve the generalization ability; Combine the outputs of the perturbed version and the original version, and design corresponding training objectives: Use contrastive loss functions or consistency regularization terms; Ensure the stability and consistency of the model output under perturbation conditions.

[0031] The technical solution of this embodiment is as follows: Based on the preliminary constructed digital twin model, introduce a dynamic residual feedback mechanism to monitor the model prediction error in real time and feedback the residual information to the model input to dynamically adjust the feature weights and optimize the learning path; At the same time, construct a graph structure between the key components of the system, and use graph neural networks to model their spatio-temporal dependence relationships to capture the complex structural couplings and behavioral associations inside the system; Combine the perturbation injection training strategy to enhance the diversity and robustness of training data through perturbations of input data, graph structure and time dimension, and further improve the adaptability and generalization performance of the model under complex working conditions. It realizes the error self-adaptive adjustment ability, system structure relationship modeling ability and anti-interference robustness of the digital twin model in the face of high-dimensional dynamic data, improves the sensitive response ability and prediction accuracy of the model to multi-source data changes, makes the modeling results closer to the real system behavior, and is applicable to the dynamic perception, behavior prediction and visual analysis requirements under high-complexity industrial scenarios. Embodiment

[0032] As Figure 1 shown, a digital twin visualization modeling method based on neural networks further includes the following steps: S4: During the model training process, continuously track the stability index of the visualization performance, and dynamically adjust the parameter settings of the visualization interaction layer according to the index feedback.

[0033] The process of dynamically adjusting the parameter settings of the visualization interaction layer according to the index feedback in S4 is as follows: Embed a visualization performance evaluation module in the twin modeling system, and continuously monitor the following key stability indicators: Frame rate: Measures the smoothness of visual rendering; Response latency: Reflects the response time after an interactive operation; Error heat distribution consistency: Compares the distribution deviation between the predicted results and the actual data in the visualization; User interaction frequency and area heat: Reflects the areas of user attention and operation habits; Color jitter rate: Measures the stability of color changes in the visualization.

[0034] Integrate a performance collection script through the front-end rendering engine; Regularly feedback the collected metrics to the back-end control logic; Use methods such as sliding window statistics and dynamic threshold judgment to evaluate the trend of visual performance.

[0035] Establish a mapping rule library between metrics and parameters to implement a feedback-driven automatic parameter adjustment mechanism, for example: FPS below the threshold: Reduce the rendering precision and simplify the graphic elements; Increasing interaction latency: Reduce the dynamic refresh frequency and use a local refresh strategy; Inconsistent visual distribution of errors: Adjust the color mapping strategy or enhance the prediction error prompt; Frequent interaction in hotspots: Increase the resolution of this area or the frequency of label prompts.

[0036] The system automatically updates the parameter configuration of the interaction layer according to the feedback results, such as: view resolution (switch between high / low precision modes); color gradient range (improve recognition); rendering refresh period (balance between low latency and low resource consumption); animation switch and simplified logic (improve interaction efficiency); data loading method (full volume vs incremental vs cache refresh).

[0037] S5: According to the multi-dimensional visualization results output by the final twin model, combined with the industrial scenario semantic rule library for interpretation, automatically generate an interpretability analysis report.

[0038] The process of interpreting and automatically generating an interpretability analysis report by combining with the industrial scenario semantic rule library in S5 is as follows: Bind the visual structured data to the entities in the industrial semantic rule library, such as: Data field → Physical quantity (temperature → heat exchange unit); Trend change → Semantic event (continuous temperature rise → cooling failure trend); Spatial area → Equipment or process section name.

[0039] Enable a rule-based semantic engine to match the following patterns: Abnormal trend recognition: For example, the indicator continuously rises by 20% within 15 minutes; State change detection: if the current pressure exceeds the safety upper limit; Multi-index joint analysis: such as temperature + vibration + flow anomaly → failure risk; Generate event tags for the matching results, such as warning: the pump body may malfunction, recommended maintenance: the heat exchanger efficiency has decreased.

[0040] Bind the identified events to the original data to construct the content of the analysis report, including: Overview section: the time range of this round of analysis and the system coverage; Abnormality analysis: list all detected abnormal events and their data supports; Semantic interpretation: refer to the description in the rule library to explain the meaning of the event and its possible causes; Impact assessment: deduce the potential impact path by combining the operation map of the equipment or system; Suggested measures: call the expert rules or experience library to provide operation suggestions, risk levels, handling time limits, etc.

[0041] Use a preset template + dynamic filling method to automatically generate text with strong readability: Example: "At 14:35 on May 11, 2025, it was detected that the temperature at the outlet of the heat exchanger continued to rise (+8.2 °C for 12 minutes), which has exceeded the upper limit threshold. Combining with the semantic rule R_302, it is judged as abnormal cooling efficiency. It is recommended to check the cooling water flow and the operation status of the pump body." Support the generation of a report combining text and graphics, embedding chart screenshots, highlighted abnormal point diagrams, process trends, etc.

[0042] By combining the multi-dimensional visualization results output by the digital twin model with the industrial scenario semantic rule library, the automatic semantic interpretation of the model prediction data and intelligent event recognition are realized. It can accurately identify key abnormal trends, working condition changes and potential failure risks, and generate a structured, text-graphic combined interpretable analysis report in natural language form, thereby greatly improving the understanding efficiency and operability of the model results, and strengthening the intelligent diagnosis ability and decision support ability of the system. Embodiment

[0043] Please refer to Figure 2 As shown, a digital twin visualization modeling system based on a neural network described in an embodiment of the present invention includes: Feature construction module: perform unified format conversion and normalization processing on multi-source sensor data, and generate a high-dimensional input feature set required by the neural network through a structured embedding algorithm; Behavior extraction module: perform perturbation sensitivity analysis on the input feature set to screen core features, and extract the key behavior patterns of the system through a temporal convolutional network; Enhanced Training Module: Introduce a dynamic residual feedback mechanism to improve model accuracy, model the spatio-temporal dependencies between system components through a graph neural network, and enhance model robustness by combining a perturbation injection strategy; Adaptive Regulation Module: Monitor the visualization stability index during training and dynamically adjust the parameters of the interaction layer according to the feedback; Report Generation Module: Combine the output results of the siamese model with the industrial scenario rule base for semantic understanding and automatically generate an interpretability analysis report.

[0044] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0045] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A digital twin visualization modeling method based on a neural network, characterized in that, It includes the following steps: Collect multi-dimensional perception data of the target physical system, unify the format and normalize the original sensor data through the heterogeneous data fusion module, and construct a high-dimensional input feature set for neural network modeling by combining the structured embedding algorithm; Conduct a stability pre-evaluation on the constructed input feature set, screen core features using the perturbation sensitivity analysis mechanism, extract system behavior features by combining the temporal convolutional network, and generate a preliminary twin model structure; Introduce a dynamic residual feedback mechanism to enhance the training of the preliminary twin model, model the spatio-temporal dependence relationship of different components through the graph neural network, and combine the perturbation injection training strategy; During the model training process, real-time track the stability index of the visualization performance, and dynamically adjust the parameter settings of the visualization interaction layer according to the index feedback; According to the multi-dimensional visualization results output by the final twin model, combine the industrial scenario semantic rule library for interpretation, and automatically generate an interpretability analysis report.

2. The digital twin visualization modeling method based on neural network according to claim 1, characterized in that, The process of constructing a high-dimensional input feature set for neural network modeling by combining the structured embedding algorithm is as follows: Standardize the format of the original data collected from multiple sensors; normalize the data with unified format; according to the structural characteristics of the target physical system, use the structured embedding algorithm to express the relationship between each sub-component in the system in the form of a vector; fuse the structured information with the time series data so that the input features can reflect both the static structure information and the dynamic behavior pattern of the system; Align and splice the structured embedding vector and the sensor data in the time dimension; finally form a high-dimensional input feature set containing structure, behavior and context semantics.

3. A digital twin visualization modeling method based on a neural network according to claim 1, characterized in that, The process of screening core features using the perturbation sensitivity analysis mechanism is as follows: Without introducing any perturbation, input the high-dimensional input feature set into the preliminarily constructed neural network model to obtain the system output as the benchmark response result; for each input feature, apply a small perturbation in turn, and the perturbation range can be set according to the numerical range of the feature; record the output change caused by each perturbation, and construct a feature-output change mapping relationship: for each feature, statistically calculate the output change amplitude corresponding to the perturbation, and calculate the perturbation sensitivity index.

4. A digital twin visualization modeling method based on a neural network according to claim 1, characterized in that, The process of extracting system behavior features by combining the temporal convolutional network and generating a preliminary twin model structure is as follows: Organize the core features screened by the perturbation sensitivity analysis into an input tensor in the time series format, and retain the time context information; Construct a temporal convolutional network based on one-dimensional convolution; Input the time series features into the temporal convolutional network model: Each layer extracts the feature changes within the local time window through the convolutional kernel; The output is the high-level behavior feature representation corresponding to each time step; Pool the temporal behavior features output by the temporal convolutional network to generate a unified representation of the entire input sequence as the behavior encoding of the prediction state.

5. A digital twin visualization modeling method based on a neural network according to claim 1, characterized in that The process of introducing a dynamic residual feedback mechanism to enhance the training of the preliminary twin model is as follows: Input the filtered input feature sequence into the preliminarily constructed digital twin model to obtain the behavior prediction output; compare the model prediction output with the actual system observation value to calculate the residual; use the historical residual sequence as a new type of input signal, introduce residual-related features to re-encode and form a residual feedback vector; construct a feedback module to fuse the residual feedback vector with the original features of the main model to generate an enhanced input feature representation.

6. The digital twin visualization modeling method based on a neural network according to claim 1, characterized in that, The process of modeling the spatio-temporal dependence relationship of different components through a graph neural network and combining the perturbation injection training strategy is as follows: Model the target physical system as a graph structure; introduce weights to represent the strength of the edges; assign a feature vector to each node; use the graph neural network for information propagation and aggregation, and each node updates its own state by aggregating the features of adjacent nodes.

7. A digital twin visualization modeling method based on a neural network according to claim 1, characterized in that, The process of dynamically adjusting the parameter settings of the visualization interaction layer according to the index feedback is as follows: Embed a visualization performance evaluation module in the twin modeling system to continuously monitor the following key stability indicators; Integrate a performance collection script through the front-end rendering engine; Regularly feedback the collected indicators to the back-end control logic; Use dynamic thresholds to judge and evaluate the visualization performance trend; Establish an index-parameter mapping rule library; Automatically update the parameter configuration of the interaction layer according to the feedback result.

8. A digital twin visualization modeling method based on a neural network according to claim 1, characterized in that, The process of automatically generating an interpretability analysis report by combining with the industrial scenario semantic rule library is as follows: Bind the visualized structured data with the entities in the industrial semantic rule library; Enable a rule-based semantic engine for matching; The matching result generates event tags; Bind the identified events with the original data to construct the content of the analysis report.

9. A digital twin visualization modeling method based on a neural network according to claim 1, characterized in that, Adopt a multi-scale model fusion strategy to improve the prediction accuracy of the twin model. The process is as follows: Input the input data with different resolutions into multiple sub-models respectively; Each sub-model is independently trained and outputs local prediction results; Through a weighted fusion strategy, combine the prediction results of different sub-models to form a global prediction output; Optimize the accuracy and stability of the twin model according to the weighted output.

10. A digital twin visualization modeling system based on a neural network, applied to the method according to any one of claims 1-9, characterized in that, Include: Feature Construction module: perform unified format conversion and normalization processing on multi-source sensor data, and generate a high-dimensional input feature set required by the neural network through a structured embedding algorithm; Behavior extraction module: perform perturbation sensitivity analysis on the input feature set to screen core features, and extract the key behavior patterns of the system through a temporal convolutional network; Enhanced training module: introduce a dynamic residual feedback mechanism to improve the model accuracy, and model the spatio-temporal dependence relationship between system components through a graph neural network, and combine the perturbation injection strategy to enhance the model robustness; Adaptive regulation module: monitor the visualization stability indicators during the training process, and dynamically adjust the parameters of the interaction layer according to the feedback; Report generation module: perform semantic understanding by combining the output results of the twin model with the industrial scenario rule library, and automatically generate an interpretability analysis report.

Images