DSpace Community: KAIST College of EngineeringKAIST College of Engineeringhttp://hdl.handle.net/10203/72024-02-29T23:08:25Z2024-02-29T23:08:25Z반도체 FAB 내 Machine과 Vehicle의 상태를 고려한 투입량 관리 및 강화 학습을 사용한 고도화 알고리즘 개발연소의장영재http://hdl.handle.net/10203/3039572023-01-04T07:02:15Z2024-12-04T00:00:00ZTitle: 반도체 FAB 내 Machine과 Vehicle의 상태를 고려한 투입량 관리 및 강화 학습을 사용한 고도화 알고리즘 개발
Authors: 연소의; 장영재2024-12-04T00:00:00ZSingle domain generalizable and physically interpretable bearing fault diagnosis for unseen working conditionsKim, IljeokKim, Sung WookKim, JeongsanHuh, HyunsukJeong, IljooChoi, TaegyuKim, JeongchanLee, Seungchulhttp://hdl.handle.net/10203/3171742024-01-02T06:00:12Z2024-05-01T00:00:00ZTitle: Single domain generalizable and physically interpretable bearing fault diagnosis for unseen working conditions
Authors: Kim, Iljeok; Kim, Sung Wook; Kim, Jeongsan; Huh, Hyunsuk; Jeong, Iljoo; Choi, Taegyu; Kim, Jeongchan; Lee, Seungchul
Abstract: State-of-the-art deep learning methods have demonstrated impressive performance in the intelligent fault diagnosis of rolling element bearings. However, in previous studies, critical issues such as domain discrepancy and the inability to interpret a classification decision made it difficult to apply deep learning in real industrial scenarios. Although domain adaptation and domain generalization-based methods have been investigated to solve domain discrepancy, collecting labeled data for various domains (especially continuous and non-stationary working conditions) is extremely difficult in an engineering application. Furthermore, since the classification decision cannot be physically explained, serious reliability problems arise for unseen working conditions (i.e., target domain with domain discrepancy). This study proposes the single domain generalizable and physically interpretable (SDGPI) framework. The proposed model embeds prior knowledge into the neural network combined with signal-preprocessing, which simultaneously enables single source domain generalization and domain interpretation with physical guarantees. Comprehensive case studies demonstrate that domain generalizable representation leads to 1) superior performance and robustness compared with existing methods for various untrained working conditions, as well as 2) efficient data inference even with small data size. Finally, the diagnosis results could be physically understood by displaying the classification decision in terms of the theoretical characteristic fault frequency (i.e., the characteristic fault order), indicating that SDGPI is a versatile and reliable diagnostic tool for unseen working conditions.2024-05-01T00:00:00ZFe-based high-entropy alloy with excellent mechanical properties enabled by nanosized precipitates and heterogeneous grain distributionJung, HeechanLee, SangwonKang, TaehyeokZargaran, AlirezaChoi, Pyuck-PaSohn, Seok Suhttp://hdl.handle.net/10203/3171562024-01-19T20:00:24Z2024-05-01T00:00:00ZTitle: Fe-based high-entropy alloy with excellent mechanical properties enabled by nanosized precipitates and heterogeneous grain distribution
Authors: Jung, Heechan; Lee, Sangwon; Kang, Taehyeok; Zargaran, Alireza; Choi, Pyuck-Pa; Sohn, Seok Su
Abstract: High-entropy alloys (HEAs) consisting of CoCrFeNiAlTi systems, with a face-centered cubic (FCC) matrix reinforced by ordered L1 2 precipitates, have demonstrated exceptional strength-ductility combinations. However, the current compositional design of HEAs heavily relies on high Ni and Co contents, compromising the balance between properties and cost. Thus, it is crucial to optimize the cost-performance trade-off by fine-tuning the range of Fe, Co, and Ni, while maintaining excellent strength-ductility com-bination. In this study, we propose a novel Fe-based HEA with nanosized precipitates and a heteroge-neous grain distribution, achieving a strength-ductility combination comparable to state-of-the-art Ni -or Co-based HEAs. The alloy benefits from both precipitation hardening and hetero-deformation-induced strengthening attributed to the heterogeneous grain distribution, resulting in excellent yield strength of 1433 MPa, tensile strength of 1599 MPa, and ductility of 22%. The microstructural evolution and its in-fluence on mechanical properties are unraveled with respect to the observation of precipitate-dislocation interaction and hetero-deformation-induced stress (HDI stress) evaluation. This study suggests that the challenge of balancing properties and cost can be addressed through optimized compositional and microstructural design.2024-05-01T00:00:00ZCombined impacts of aluminum and silica ions on RO membrane fouling in full-scale ultrapure water production facilitiesPark, DaeseonYeo, In-HoLee, JiseonKim, HyojeonChoi, SeungjuKang, Seoktaehttp://hdl.handle.net/10203/3179992024-02-05T07:00:12Z2024-05-01T00:00:00ZTitle: Combined impacts of aluminum and silica ions on RO membrane fouling in full-scale ultrapure water production facilities
Authors: Park, Daeseon; Yeo, In-Ho; Lee, Jiseon; Kim, Hyojeon; Choi, Seungju; Kang, Seoktae2024-05-01T00:00:00Z