Digital Twin Creep Age Forming for Springback Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing creep age forming process for large thin-walled components in aerospace manufacturing lacks real-time monitoring and adjustment, leading to potential mismatches between simulated and actual fitting conditions, resulting in suboptimal precision and performance.
Innovation Solution
A creep age forming method and device utilizing digital twin technology, which includes sensor data acquisition, prediction models based on LSTM algorithms, and real-time process parameter adjustment to ensure precise fitting and performance through continuous monitoring and feedback loops.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If real-time monitoring and adjustment systems are implemented, then manufacturing precision and process adaptability improve, but device complexity and initial time investment increase
Solution Approach 1:
The patent creates a digital twin (virtual copy) of the physical forming process that runs in parallel with the actual process. This digital model receives real-time sensor data and allows for virtual testing of process adjustments without affecting the physical system, thereby improving precision while avoiding the complexity of directly modifying the physical equipment with multiple intervention systems.
Solution Approach 2:
The patent replaces complex mechanical adjustment systems with data-driven predictive models and control algorithms. Instead of using multiple physical sensors and actuators to continuously adjust the forming process, the system uses machine learning models to predict outcomes and guide adjustments, reducing mechanical complexity while maintaining or improving precision.
2Manufacturing precision
If traditional offline simulation methods are used, then device complexity remains low, but manufacturing precision deteriorates due to inability to adjust to actual process variations
Solution Approach 1:
The patent performs preliminary actions by training predictive models offline using historical data and simulation results before the actual forming process. These pre-trained models are then deployed to guide real-time process adjustments, combining the simplicity of offline preparation with the precision of adaptive control during execution.
Solution Approach 2:
The patent implements a feedback mechanism where sensor data from the actual forming process is continuously fed into the digital twin model, which then compares predicted versus actual outcomes and generates adjustment recommendations. This closed-loop feedback system enables precision improvement without requiring complex real-time computational infrastructure during the forming process itself.
3Measurement precision
If extensive sensor data collection and analysis systems are deployed, then measurement precision and process control improve, but loss of time for data processing increases
Solution Approach 1:
The patent performs data processing in advance by training machine learning models offline using extensive historical sensor data and simulation results. Once trained, these models can quickly predict process outcomes with high precision using minimal real-time data, thereby achieving accurate measurement without the time cost of processing extensive data during the actual forming process.
Solution Approach 2:
The patent uses a selective approach to data collection, focusing on key sensor measurements that have the greatest impact on forming precision. Rather than collecting and processing all possible sensor data, the system identifies and monitors only the most critical parameters, reducing data processing time while maintaining high measurement precision for the most important process variables.
Data Source
AI summary
A creep age forming method and device based on digital twin technology provided by the present disclosure. The method acquires sensor data of the aluminum alloy panel during a creep age forming process and inputs the sensor data into the first prediction model and obtains the predicted springback amount and yield strength output by the first prediction model. First difference values between the predicted springback amount and yield strength with the target springback amount and yield strength are determined. Based on the first difference values, first process parameters are determined for updating the process of the aluminum alloy panel by using the second prediction model. The first process parameters are sent to the autoclave, and the autoclave is controlled to perform a process operation with the first process parameters. The present disclosure can adjust the process based on real-time sensor data to obtain components with precise forming and target performance.