|
| 基于数字体积相关的应变先验损伤识别方法 |
| A prior-based strain identification method based on digital volume correlation |
| 投稿时间：2023-05-19 修订日期：2023-06-09 |
| DOI： |
| 中文关键词: CT图像 数字体积相关 应变；内部损伤识别 神经网络 |
| 英文关键词:CT image digital volume correlation strain internal damage identification neural network |
| 基金项目:国家自然科学基金项目 |
|
| 摘要点击次数: 486 |
| 全文下载次数: 0 |
| 中文摘要: |
| 研究材料内部的破坏失效过程，揭示内部损伤演化机制，是预防断裂失效的关键。计算机断层扫描技术（Computed tomography，CT）可以进行内部损伤演化过程的三维表征，为研究材料内部损伤演化机制提供支撑。然而CT图像中损伤演化的定量识别提取面临着损伤特征弱信号被图像中复杂结构信号湮没的难题。本文提出引入力学参量引导神经网络的思路，将基于数字体积相关（Digital volume correlation，DVC）获得的三维应变场作为力学参量先验信息，引导并约束网络训练，从而实现裂纹的识别提取。通过实际CT实验数据定量评价并验证了该方法可以提高微小裂纹识别精确率，减少识别错误率。 |
| 英文摘要: |
| It is the key to prevent fracture failure to study the failure process and reveal the evolution mechanism of internal damage. Computed tomography (CT) can provide three-dimensional characterization of the internal damage evolution process, which supports the research of the internal damage evolution mechanism of materials. However, the quantitative recognition and extraction of damage evolution faces the challenge of weak damage feature signals being overshadowed by the complex structural signals of CT images. In this paper, the idea of introducing mechanical parameters to guide neural networks is proposed. Three-dimensional strain fields obtained based on Digital volume correlation (DVC) are used as priori information of mechanical parameters to guide and constrain network training, enabling crack identification and extraction. Through quantitative evaluation and verification of actual CT experimental data, the method can improve micro crack identification precision and reduce the identification error rate. |
| 下载PDF阅读器 |
| 关闭 |
