Physics-Inspired Neural Networks in the Evaluation, Generation and Design of Frame Structures
物理启发的神经网络在框架结构的评估、生成和设计中的应用
基本信息
- 批准号:523871886
- 负责人:
- 金额:--
- 依托单位:
- 依托单位国家:德国
- 项目类别:Research Grants
- 财政年份:
- 资助国家:德国
- 起止时间:
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
Structural optimization represents an economical and effective lightweight design method, especially when full material utilization in terms of strength and stiffness is desired. The design and evaluation of truss structures is one of the most common tasks in practice, often by using numerical simulation with beam or truss elements. In this work, alternative design and evaluation procedures of such 1D idealizations based on so-called physical-inspired neural networks (PINN) are the focus of research. Thereby, mainly 3D simulation data and 3D topology optimization results shall serve as a training basis to improve the predictive behaviour of the 1D idealizations. In total, three different PINNs will be investigated. The first PINN is expected to lead to improved prediction of physical quantities such as deformation and strain of 1D models. The second PINN is intended to derive optimal cross-section parameters based on a given 1D frame structure. The third PINN will use training data from 3D optimizations to predict optimal design proposals for frame structures so that, for example, regions with multi-axial states can be directly optimized and derived as a parametric model without the need for complex topology optimization. In addition to the training of PINNs, a method based on the so-called skeletonization for the fully automatic transfer of results from a 3D simulation to a 1D model is also investigated. This fully automatic transfer is necessary to generate the synthetic data sets for the respective PINNs. Finally, the trained PINNs are combined to realize an automated evaluation, cross-section dimensioning and locally optimized regions in real time (a few seconds) for a bicycle frame, for example.
结构优化是一种经济有效的轻量化设计方法,特别是当需要充分利用材料的强度和刚度时。桁架结构的设计和评估是实际工程中最常见的任务之一,通常使用梁或桁架单元进行数值模拟。在这项工作中,替代设计和评估程序的基础上,所谓的物理启发神经网络(PINN)的这种一维理想化的研究重点。因此,主要是3D仿真数据和3D拓扑优化结果将用作训练基础,以改善1D理想化的预测行为。总共将研究三种不同的PINN。第一个PINN预计将导致改进的物理量,如变形和应变的一维模型的预测。第二个PINN旨在基于给定的1D帧结构导出最佳横截面参数。第三个PINN将使用来自3D优化的训练数据来预测框架结构的最佳设计方案,例如,具有多轴状态的区域可以直接优化并导出为参数模型,而无需复杂的拓扑优化。除了PINN的训练之外,还研究了一种基于所谓的非线性化的方法,用于将结果从3D模拟完全自动地转移到1D模型。这种全自动传输对于生成各个PINN的合成数据集是必要的。最后,将训练的PINN组合以实现例如自行车车架的真实的时间(几秒)的自动评估、横截面尺寸和局部优化区域。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Professor Dr.-Ing. Sandro Wartzack其他文献
Professor Dr.-Ing. Sandro Wartzack的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Professor Dr.-Ing. Sandro Wartzack', 18)}}的其他基金
Form synthesis at early embodiment design stage: A computer-aided method to model preliminary embodiment designs
早期实施例设计阶段的形式合成:对初步实施例设计进行建模的计算机辅助方法
- 批准号:
401324164 - 财政年份:2018
- 资助金额:
-- - 项目类别:
Research Grants
CAD features to model physical aspects of human-machine interactions
用于模拟人机交互的物理方面的 CAD 功能
- 批准号:
396858371 - 财政年份:2018
- 资助金额:
-- - 项目类别:
Research Grants
TopoRestruct – Converting topology optimization results into a design geometry, which meets the requirements for manufacturability, functionality and mechanical stress in the product development process
TopoRestruct â 将拓扑优化结果转换为设计几何形状,满足产品开发过程中对可制造性、功能性和机械应力的要求
- 批准号:
411012054 - 财政年份:2018
- 资助金额:
-- - 项目类别:
Research Grants
Shape aware Computer Aided Tolerancing: A new methodical and computational framework for the assembly and mobility simulation based on Skin Model Shapes (ShapeCAN)
形状感知计算机辅助公差:基于蒙皮模型形状 (ShapeCAN) 的装配和移动模拟的新方法和计算框架
- 批准号:
278389853 - 财政年份:2015
- 资助金额:
-- - 项目类别:
Research Grants
[ProPro 2.0] - Product-oriented process management - Computer-aided modeling as well as graph-based analysis and visualization of the matrix-based product description
[ProPro 2.0] - 以产品为导向的流程管理 - 计算机辅助建模以及基于矩阵的产品描述的基于图形的分析和可视化
- 批准号:
211191171 - 财政年份:2012
- 资助金额:
-- - 项目类别:
Research Grants
Functional product validation and optimization of technical systems in motion as a part of product lifecycle oriented tolerance management
作为面向产品生命周期的公差管理的一部分,功能产品验证和动态技术系统优化
- 批准号:
165053436 - 财政年份:2009
- 资助金额:
-- - 项目类别:
Research Grants
Development of a methodology for plausibility checks for linear structural mechanic finite element simulations using Deep Learning
使用深度学习开发线性结构力学有限元模拟的合理性检查方法
- 批准号:
456585803 - 财政年份:
- 资助金额:
-- - 项目类别:
Research Grants
UPREN USED – User, product and environmental influences on usability and emotional product design
UPREN USED â 用户、产品和环境对可用性和情感产品设计的影响
- 批准号:
398054801 - 财政年份:
- 资助金额:
-- - 项目类别:
Research Grants
相似海外基金
Revealing the circuit mechanisms of altered conscious perception with neuropixels recordings and biophysically-inspired neural networks.
通过神经像素记录和生物物理学启发的神经网络揭示改变意识感知的回路机制。
- 批准号:
BB/X013243/1 - 财政年份:2023
- 资助金额:
-- - 项目类别:
Research Grant
CRII: RI: Immune-Inspired Learning Foundations of Neural Network General Robustness
CRII:RI:神经网络一般鲁棒性的免疫启发学习基础
- 批准号:
2246157 - 财政年份:2023
- 资助金额:
-- - 项目类别:
Standard Grant
Designing cancer-inspired scaffolds for neural repair
设计受癌症启发的神经修复支架
- 批准号:
10376778 - 财政年份:2021
- 资助金额:
-- - 项目类别:
Collaborative Research: SHF: Medium: Analog EDA-Inspired Methods for Efficient and Robust Neural Network Design
合作研究:SHF:媒介:用于高效、鲁棒神经网络设计的模拟 EDA 启发方法
- 批准号:
2107321 - 财政年份:2021
- 资助金额:
-- - 项目类别:
Continuing Grant
Collaborative Reserach: SHF:Medium: Analog EDA-Inspired Methods for Efficient and Robust Neural Network Designs
协作研究:SHF:Medium:用于高效、鲁棒神经网络设计的模拟 EDA 启发方法
- 批准号:
2107373 - 财政年份:2021
- 资助金额:
-- - 项目类别:
Continuing Grant
Designing cancer-inspired scaffolds for neural repair
设计受癌症启发的神经修复支架
- 批准号:
10552595 - 财政年份:2021
- 资助金额:
-- - 项目类别:
Designing cancer-inspired scaffolds for neural repair
设计受癌症启发的神经修复支架
- 批准号:
10195737 - 财政年份:2021
- 资助金额:
-- - 项目类别:
Biologically inspired adaptive mechanisms for artificial neural networks
人工神经网络的受生物学启发的自适应机制
- 批准号:
2504973 - 财政年份:2021
- 资助金额:
-- - 项目类别:
Studentship
Collaborative Research: SHF: Medium: Analog EDA-Inspired Methods for Efficient and Robust Neural Network Design
合作研究:SHF:媒介:用于高效、鲁棒神经网络设计的模拟 EDA 启发方法
- 批准号:
2107189 - 财政年份:2021
- 资助金额:
-- - 项目类别:
Continuing Grant
A Novel Power Reduction Technique Using Error-resilient Deep Neural Networks for STT-MRAM Based Energy-efficient Brain-inspired Processor Design
一种新颖的功耗降低技术,使用容错深度神经网络进行基于 STT-MRAM 的节能类脑处理器设计
- 批准号:
21K17719 - 财政年份:2021
- 资助金额:
-- - 项目类别:
Grant-in-Aid for Early-Career Scientists