Crack Catcher AI – Enabling smart fracture mechanics approaches for damage control of thin silicon cells or wafers
Source abstract
Abstract
Silicon has been one among a few key technologically important materials especially in our modern world. Silicon, especially in its current most useful forms (thin layers), is a brittle material by nature. Thin silicon cells crack easily during manufacturing assembly. Every crack is a defect in any PV manufacturing lines, and if let to grow/propagate it will lead to reliability and quality issues with time. Nevertheless, the global silicon solar PV industry is aggressively reducing the cost of solar PV systems through cutting down the thickness of silicon solar cells. Cell cracks immediately lower PV module efficiency and can lead to premature aging of the entire module. The “Crack Catcher AI” was our research joint collaboration`s entry in the Department of Energy (DOE)`s American-Made Solar Innovation competition in 2022 (Round 6) which later was selected as the national semifinalists and won an award announced by DOE in December 2022. It uses smart stress sensing and smart fracture prediction approaches utilizing fundamental fracture mechanics and big data analytics to reduce crack defects and enhance long-term durability/reliability of PV products/devices. Smart Stress Sensing uses a novel laser-based curvature methodology for fast in-line stress metrology in manufacturing lines. Smart Fracture Prediction uses Artificial Intelligence (AI) for defect control metrology and yield enhancement in PV production lines. It is based on monocrystalline silicon used in solar PV industries, but all scientific principles utilized and technological innovations developed in this article would be applicable as well for single crystal silicon semiconductor wafers.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Silicon and Solar Cell Technologies · Advanced Surface Polishing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (71)
Show source-provided references
1. Characterization of PV modules by combining results of mechanical and electrical analysis methods
2. Enabling thin silicon technologies for next generation c-Si solar PV renewable energy systems using synchrotron X-ray microdiffraction as stress and crack mechanism probe10.1016/j.solmat.2014.07.029 ↗
3. Probing stress and fracture mechanism in encapsulated thin silicon solar cells by synchrotron X-ray microdiffraction10.1016/j.solmat.2016.12.028 ↗
4. From cells to laminate: probing and modeling residual stress evolution in thin silicon photovoltaic modules using synchrotron X-ray micro-diffraction experiments and finite element simulations10.1002/pip.2891 ↗
5. Numerical simulation of the evolution of stress in solar cells during the entire manufacturing cycle of a conventional silicon wafer based photovoltaic laminate10.1109/JPHOTOV.2017.2775158 ↗
6. Probing phase transformations and microstructural evolutions at the small scales: synchrotron X-ray microdiffraction for advanced applications in 3D IC (integrated circuits) and solar PV (photovoltaic) devices10.1007/s11664-016-5012-5 ↗
7. Budiman · 2013
8. Thermomechanical residual stress evaluation in multi-crystalline silicon solar cells of photovoltaic modules with different encapsulation polymers using synchrotron X-ray microdiffraction10.1016/j.solmat.2019.01.016 ↗
9. The effect of cell thickness on module reliability
10. The risk of power loss in crystalline silicon based photovoltaic modules due to micro-cracks10.1016/j.solmat.2010.10.034 ↗
11. Interdependency of mechanical failure rate of encapsulated solar cells and module design parameters
12. Systematic investigation of cracks in encapsulated solar cells after mechanical loading10.1016/j.solmat.2012.12.031 ↗
13. J. Wendt, M. Träger, M. Mette, A. Pfennig, and B. Jaeckel, “The link between mechanical stress induced by soldering and micro damages in silicon solar cells,” Proc. of 24th EUPVSEC, pp. 3420–3423.
14. Soldering induced damage to thin Si solar cells and detection of cracked cells in modules
15. Advantages of microelectronic packaging for low temperature lead free soldering of thin solar cells
16. Electroluminescence observation of microcrack growth behavior of crystalline silicon solar modules fabricated by hot-air soldering technology10.1142/S2010194512002917 ↗
17. Analysis of luminescence images applying pattern recognition techniques
18. Quality control of as-cut multicrystalline silicon wafers using photoluminescence imaging for solar cell production10.1016/j.solmat.2010.06.003 ↗
19. In-line monitoring of electrical wafer quality using photoluminescence imaging
20. Mechanical stability of solar cells within solar panels
21. Spatial and orientational distribution of cracks in crystalline photovoltaic modules generated by mechanical load tests10.1016/j.solmat.2011.06.032 ↗
22. Investigations on cracks in encapsulated solar cells after thermal and mechanical loading
23. The 7th edition of the International Technology Roadmap for Photovoltaics (ITRPV) Current trends and future challenges in c-Si PV
24. Slow crack growth in single-crystal silicon10.1126/science.256.5063.1537 ↗
25. A reaction-layer mechanism for the delayed failure of micron-scale polycrystalline silicon structural films subjected to high-cycle fatigue loading10.1016/S1359-6454(02)00158-1 ↗
26. R. Ballarini, H. Kahn, N. Tayebi, and A. H. Heuer, “Effects of microstructure on the strength and fracture toughness of polysilicon: a wafer level testing approach,” in Mechanical Properties of Structural Films, ASTM International, pp. 37–51. doi: 10.1520/STP10979S.10.1520/STP10979S ↗
27. Mechanical stability in crystalline silicon solar cells
28. Mechanical strength of silicon wafers depending on wafer thickness and surface treatment
29. High precision thermal stress study on flip chips by synchrotron polychromatic x-ray microdiffraction10.1063/1.3309750 ↗
30. Timoshenko · 1959 · 2
31. A comparison of X-ray microdiffraction and coherent gradient sensing in measuring discontinuous curvatures in thin film: substrate systems10.1115/1.2150500 ↗
32. Mechanical investigations on metallization layouts of solar cells with respect to module reliability10.1016/j.egypro.2013.07.308 ↗
33. A novel setup for wafer curvature measurement at very high heating rates10.1063/1.4975378 ↗
34. Service innovation and smart analytics for industry 4.0 and big data environment10.1016/j.procir.2014.02.001 ↗
35. Synchrotron X-ray Topography for encapsulation stress/strain and crack detection in crystalline silicon modules10.1109/JPHOTOV.2016.2585022 ↗
36. Gölzer · 2015 · 1
37. Data-driven smart manufacturing10.1016/j.jmsy.2018.01.006 ↗
38. A vision of industry 4.0 from an artificial intelligence point of view
39. Industrie 4.0 und Big Data–wirklich ein neuer Technologieschub?
40. Bischoff
41. Detection and analysis of micro-cracks in multi-crystalline silicon wafers during solar cell production
42. Vapnik · 2013
43. The self-organizing map10.1109/5.58325 ↗
44. Nearest neighbor pattern classification10.1109/TIT.1967.1053964 ↗
45. Duda · 1995
46. Decision trees and diagrams10.1145/356893.356898 ↗
47. Breiman · 2017
48. Haykin · 1998
49. On discriminative vs. generative classifiers: a comparison of logistic regression and naive bayes
50. Sparse bayesian learning and the relevance vector machine
51. [51] E. Alpaydin, “Introduction to Machine Learning,” MIT Press. pp. 597-642. https://mitpress.mit.edu/9780262043793/introduction-to-machine-learning/ (accessed Aug. 03, 2023).
52. Parameter expansion for data augmentation10.1080/01621459.1999.10473879 ↗
53. Effect of encapsulants on the thermomechanical residual stress in the back-contact silicon solar cells of photovoltaic modules – a constrained local curvature model10.1016/j.solener.2019.02.028 ↗
54. Fracture mechanics and testing of interface adhesion strength in multilayered structures – application in advanced solar PV materials and technology10.1016/j.proeng.2015.09.232 ↗
55. Effect of interconnect geometry on the evolution of stresses in a solar photovoltaic laminate during and after lamination10.1016/j.solmat.2018.07.026 ↗
56. A simulation study of the stresses in crystalline silicon photovoltaic laminates during the soldering and lamination processes along the longitudinal direction10.1002/adem.201800986 ↗
57. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
58. Attention is all you need
59. Towards end-to-end speech recognition with recurrent neural networks
60. Deep learning with long short-term memory networks for financial market predictions10.1016/j.ejor.2017.11.054 ↗
61. Modeling missing data in clinical time series with rnns
62. Scalable and accurate deep learning with electronic health records10.1038/s41746-018-0029-1 ↗
63. Bojarski · 2016 · 1
64. Long-term recurrent convolutional networks for visual recognition and description
65. Smart Dome 4.0: Low-Cost, Independent, Automated Energy System for Agricultural Purposes enabled by Machine Learning10.1088/1742-6596/2224/1/012118 ↗
66. Cenggoro · 2022
67. Stress and Curvature Measurements of Thin Films with the kSA MOS Ultra-Scan from k-Space Associates.” https://www.azonano.com/article.aspx?ArticleID=1499.
68. A data-driven approach based on long short-term memory and hidden Markov model for crack propagation prediction10.1016/j.engfracmech.2020.107085 ↗
69. Influence of cracks on fracture strength and electric power losses in Silicon solar cells at high temperatures: deep machine learning and molecular dynamics approach
70. Braid · 2022
71. Cooper · 2024