Hongjiang Qian , Jiebin Shen , Zhiyong Huang , Jian Wang , Qingyun Zhu , Zeshuai Shen , Haidong FAN
{"title":"基于 PINN 的热循环载荷下 TSV-Cu 结构变形的储能密度解决方案","authors":"Hongjiang Qian , Jiebin Shen , Zhiyong Huang , Jian Wang , Qingyun Zhu , Zeshuai Shen , Haidong FAN","doi":"10.1016/j.ijplas.2024.104046","DOIUrl":null,"url":null,"abstract":"<div><p>TSV-Cu is widely used for chip interconnects, where high testing costs and complex crystal plasticity finite element (CPFE) limit the research of its deep microplastic evolution process. Considering the stored energy density (SED) based on dislocation density and plastic work as a fatigue indicator factor (FIP), this paper proposes for the first time a physics-informed neural network (PINN) framework based on SED, which aims to achieve the solution of SED distributions quickly and efficiently to save computational time and cost. The grain orientation, geometrical compatibility factor, back stress, and effective plastic strain are taken into account as inputs to the PINN model. The total dislocation density is used as an indirect solution variable to construct the associated loss boundary terms, which results in the solution of the SED. The results of the two real EBSD tests show that the PINN model is able to accurately and sensitively predict the SED concentration distribution for different thermal cycle loadings, and maintains a high degree of agreement with the CPFE calculation results. Moreover, The superiority of PINN over other machine learning algorithms in terms of physical model interpretation and prediction accuracy is verified. These make it a reality for PINN to solve for the FIP distribution for the first time, and to accurately and quickly predict the location of crack initiation.</p></div>","PeriodicalId":340,"journal":{"name":"International Journal of Plasticity","volume":null,"pages":null},"PeriodicalIF":9.4000,"publicationDate":"2024-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Stored energy density solution for TSV-Cu structure deformation under thermal cyclic loading based on PINN\",\"authors\":\"Hongjiang Qian , Jiebin Shen , Zhiyong Huang , Jian Wang , Qingyun Zhu , Zeshuai Shen , Haidong FAN\",\"doi\":\"10.1016/j.ijplas.2024.104046\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>TSV-Cu is widely used for chip interconnects, where high testing costs and complex crystal plasticity finite element (CPFE) limit the research of its deep microplastic evolution process. Considering the stored energy density (SED) based on dislocation density and plastic work as a fatigue indicator factor (FIP), this paper proposes for the first time a physics-informed neural network (PINN) framework based on SED, which aims to achieve the solution of SED distributions quickly and efficiently to save computational time and cost. The grain orientation, geometrical compatibility factor, back stress, and effective plastic strain are taken into account as inputs to the PINN model. The total dislocation density is used as an indirect solution variable to construct the associated loss boundary terms, which results in the solution of the SED. The results of the two real EBSD tests show that the PINN model is able to accurately and sensitively predict the SED concentration distribution for different thermal cycle loadings, and maintains a high degree of agreement with the CPFE calculation results. Moreover, The superiority of PINN over other machine learning algorithms in terms of physical model interpretation and prediction accuracy is verified. These make it a reality for PINN to solve for the FIP distribution for the first time, and to accurately and quickly predict the location of crack initiation.</p></div>\",\"PeriodicalId\":340,\"journal\":{\"name\":\"International Journal of Plasticity\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":9.4000,\"publicationDate\":\"2024-06-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Plasticity\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0749641924001736\",\"RegionNum\":1,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, MECHANICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Plasticity","FirstCategoryId":"88","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0749641924001736","RegionNum":1,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}
引用次数: 0
摘要
TSV-Cu 广泛用于芯片互连,但高昂的测试成本和复杂的晶体塑性有限元(CPFE)限制了对其深层微塑性演化过程的研究。考虑到基于位错密度和塑性功的储能密度(SED)作为疲劳指标因子(FIP),本文首次提出了基于 SED 的物理信息神经网络(PINN)框架,旨在快速高效地实现 SED 分布求解,节省计算时间和成本。PINN 模型的输入考虑了晶粒取向、几何相容性因子、背应力和有效塑性应变。总位错密度作为间接求解变量,用于构建相关的损耗边界项,从而求解 SED。两次实际 EBSD 试验的结果表明,PINN 模型能够准确、灵敏地预测不同热循环负载下的 SED 浓度分布,并与 CPFE 计算结果保持高度一致。此外,还验证了 PINN 在物理模型解释和预测准确性方面优于其他机器学习算法。这使得 PINN 首次求解 FIP 分布并准确快速地预测裂纹起始位置成为现实。
Stored energy density solution for TSV-Cu structure deformation under thermal cyclic loading based on PINN
TSV-Cu is widely used for chip interconnects, where high testing costs and complex crystal plasticity finite element (CPFE) limit the research of its deep microplastic evolution process. Considering the stored energy density (SED) based on dislocation density and plastic work as a fatigue indicator factor (FIP), this paper proposes for the first time a physics-informed neural network (PINN) framework based on SED, which aims to achieve the solution of SED distributions quickly and efficiently to save computational time and cost. The grain orientation, geometrical compatibility factor, back stress, and effective plastic strain are taken into account as inputs to the PINN model. The total dislocation density is used as an indirect solution variable to construct the associated loss boundary terms, which results in the solution of the SED. The results of the two real EBSD tests show that the PINN model is able to accurately and sensitively predict the SED concentration distribution for different thermal cycle loadings, and maintains a high degree of agreement with the CPFE calculation results. Moreover, The superiority of PINN over other machine learning algorithms in terms of physical model interpretation and prediction accuracy is verified. These make it a reality for PINN to solve for the FIP distribution for the first time, and to accurately and quickly predict the location of crack initiation.
期刊介绍:
International Journal of Plasticity aims to present original research encompassing all facets of plastic deformation, damage, and fracture behavior in both isotropic and anisotropic solids. This includes exploring the thermodynamics of plasticity and fracture, continuum theory, and macroscopic as well as microscopic phenomena.
Topics of interest span the plastic behavior of single crystals and polycrystalline metals, ceramics, rocks, soils, composites, nanocrystalline and microelectronics materials, shape memory alloys, ferroelectric ceramics, thin films, and polymers. Additionally, the journal covers plasticity aspects of failure and fracture mechanics. Contributions involving significant experimental, numerical, or theoretical advancements that enhance the understanding of the plastic behavior of solids are particularly valued. Papers addressing the modeling of finite nonlinear elastic deformation, bearing similarities to the modeling of plastic deformation, are also welcomed.