Double-Point Incremental Forming With Adaptive Support Paths
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing double-point incremental forming methods suffer from fixed supporting strategies of the auxiliary tool head, leading to low geometric accuracy and limited forming range, hindering wide industrial application.
Innovation Solution
A double-point incremental forming method utilizing deep reinforcement learning to dynamically adjust the supporting strategy of the slave robot by cyclically updating the main and supporting paths through a pre-trained deep reinforcement learning model, incorporating a digital simulation environment for training and real-time adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a fixed supporting strategy is used for the auxiliary tool head, then the device complexity is reduced, but the manufacturing precision deteriorates
Solution Approach 1:
The patent implements dynamic supporting strategies where the auxiliary tool head's supporting position and trajectory are no longer fixed but adaptively adjusted during the incremental forming process. The system uses real-time feedback from sensors to modify the supporting path dynamically, allowing the supporting strategy to change according to the actual forming state, thus improving geometric accuracy without excessive complexity increase
Solution Approach 2:
The patent introduces feedback mechanisms that continuously monitor the forming process and use this information to adjust the auxiliary tool head's supporting trajectory. The feedback loop enables the system to detect deviations and correct them by modifying the supporting path in real-time, resolving the contradiction between simple fixed strategies and precise adaptive strategies
2Ease of operation
If a fixed supporting strategy is used for the auxiliary tool head, then the ease of operation is improved, but the adaptability deteriorates
Solution Approach 1:
The patent changes the parameters of the supporting strategy from fixed values to variable parameters that can be adjusted during operation. The system modifies supporting position, trajectory, and timing parameters adaptively based on the forming task requirements, enabling the same equipment to handle a wider range of forming operations while maintaining ease of operation through automated parameter adjustment
Solution Approach 2:
The supporting strategy transitions from static to dynamic, allowing the auxiliary tool head to adapt its supporting behavior to different forming scenarios. This dynamic adaptation expands the forming range and versatility of the system while the underlying automated control maintains operational simplicity
3Manufacturing precision
If deep reinforcement learning is used to dynamically adjust supporting strategy, then the manufacturing precision is improved, but the device complexity increases
Solution Approach 1:
The patent introduces a deep reinforcement learning model as an intermediary between the control system and the auxiliary tool head. This intermediary processes complex decisions about supporting trajectory optimization, absorbing the computational complexity while presenting a relatively simple interface to the physical system. The model acts as a smart mediator that translates forming objectives into precise supporting actions
Solution Approach 2:
The patent uses digital simulation environments to create virtual copies of the incremental forming process for training the reinforcement learning model. This copying approach allows extensive training and optimization in a virtual space before deploying to the physical system, reducing the complexity burden on the actual device while achieving high precision through pre-trained intelligent algorithms
4Loss of substance
If digital simulation environment is used for training, then the loss of substance is reduced, but the time for training increases
Solution Approach 1:
The patent performs preliminary training actions in a digital simulation environment before actual physical experimentation. The reinforcement learning model is trained extensively in silico using virtual representations of the incremental forming process, allowing the system to learn optimal supporting strategies without consuming physical materials. This preliminary virtual training significantly reduces material consumption while the extended training time in simulation prepares the model for accurate physical operation
Data Source
AI summary
The present invention provides a double-point incremental forming manufacturing method and apparatus based on deep reinforcement learning. The method comprises: obtaining a three-dimensional model to be manufactured, performing layering to obtain a plurality of main working paths and a plurality of candidate supporting paths, and selecting an initial current main working path and a current supporting path; respectively cyclically controlling, according to the current main working path and the selected current supporting path, mechanical arms of a master robot and a slave robot for incremental forming in an actual application environment, to obtain a formed curved surface; and taking a deviation value of the formed curved surface and a target curved surface as a state vector, applying a pre-trained deep reinforcement learning model for reinforcement learning, cyclically outputting a supporting path corresponding to the next main working path, and cyclically updating the current main working path and the current supporting path according to the next main working path and the supporting path corresponding to the next main working path until incremental forming of the three-dimensional model is completed. According to the present invention, the support strategy of the slave robot can be adjusted, the flexibility is high, and the forming precision is high.