相关实验视频
Updated: Jul 12, 2025

Surrogate Model Development for Digital Experiments in Welding
Published on: March 28, 2025
基于动量不变数和通用回归神经网络的结构拓优化合规性预测
Yunmei Zhao1, Zhenyue Chen1, Yiqun Dong2
1School of Aerospace Engineering and Applied Mechanics, Tongji University, Shanghai 200092, China.
使用通用回归神经网络 (GRNN) 的新深度学习算法增强了结构拓优化. 这种人工智能方法准确地预测合规性,大大降低了设计先进纤维增强聚合物复合材料 (FRPC) 的计算成本.
科学领域:
- 机械工程 机械工程
- 材料科学 材料科学 材料科学
- 人工智能的人工智能
背景情况:
- 拓优化对于设计轻质,高强度结构,特别是纤维增强聚合物复合材料 (FRPC) 至关重要.
- 传统的方法,如有处罚的固体同位素材料 (SIMP) 方法,通常依赖于计算密集的有限元素分析 (FEA).
- 人工智能 (AI) 具有加速这些优化过程的潜力.
研究的目的:
- 提出一种新的深度学习算法,用于在结构拓优化中准确有效地预测合规性.
- 利用通用回归神经网络 (GRNN) 来提高与现有AI模型相比的性能.
- 为了减少SIMP方法中与FEA相关的计算负担.
主要方法:
- 开发了一种基于GRNN的深度学习算法,用于合规预测.
- 作为输入特征,利用了FEA结构拓中的第四阶动量不变数.
- 经过训练和验证,模型使用悬臂和简单支持的光束数据集.
- 将GRNN与卷积神经网络 (CNN) 和深度神经网络 (DNN) 的性能进行比较.
主要成果:
- 拟议的GRNN模型实现了高预测精度 (R2 > 0.97).
- GRNN显著降低了培训和预测计算成本.
- 对于旋转拓和各种材料体积分数的优秀概括能力.
- 在预测准确性和效率方面表现优于CNN和DNN模型.
结论:
- 在拓优化中,GRNN算法为FEA计算提供了一个有希望的替代方案.
- 这种人工智能驱动的方法可以为先进的FRPC结构设计实现实时优化.
- 该方法显示了在工程设计中更广泛的应用潜力,需要高效的结构分析.
更多相关视频
07:08Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues
Published on: July 14, 2015
07:09In situ Compressive Loading and Correlative Noninvasive Imaging of the Bone-periodontal Ligament-tooth Fibrous Joint
Published on: March 7, 2014
相关概念视频
Structural Classification of Joints
A fibrous joint is where the adjacent bones are united by fibrous connective...
Internal Loadings in Structural Members: Problem Solving
To illustrate this, let's consider a beam OC of 5 kN, inclined at an angle of 53.13° with the horizontal and supported at both ends. Determine the internal...
Shear and Bending Moment Diagram: Problem Solving
Draw a Free-Body Diagram: Start by drawing a free-body diagram of the entire beam, including the concentrated loads, distributed load, and reaction...
Functional Classification of Joints
The functional classification of joints is determined by the amount of mobility between the adjacent bones. Joints are functionally classified as a synarthrosis or immobile joint, an amphiarthrosis or slightly moveable joint, or as a diarthrosis, a freely moveable joint. Fibrous and cartilaginous joints can be functionally classified as either synarthroses or amphiarthroses, whereas all synovial joints are classified as diarthroses.
Synarthrosis
An...
Singularity Functions for Bending Moment
Plastic Deformations of Members with a Single Plane of Symmetry