TY - JOUR
T1 - Deep-learning-based data loss reconstruction for spatiotemporal temperature in piloti structures
T2 - Enhancing applicability with limited datasets
AU - Kim, Sunjoong
AU - Park, Soyeon
AU - Shin, Jinwon
AU - Choi, In Rak
AU - Choi, Sungmo
N1 - Publisher Copyright:
© 2023 Elsevier Ltd
PY - 2023/10
Y1 - 2023/10
N2 - A time-temperature curve, representing the fire characteristics of structures, can be obtained by real fire experiments. However, these experiments are inherently susceptible to data loss, which can compromise the accuracy of results. To address this challenge, this study proposed the framework utilizing a long-short-term memory (LSTM) with Bayesian optimization to reconstruct temperature histories by learning the spatiotemporal correlation of the data. The proposed framework is first validated using simulated datasets from computational fluid dynamics analyses. The field applicability of the model is further demonstrated through real fire test results, affirming its reliability in practical scenarios. The study also introduces a novel data processing technique to mitigate overfitting issues in LSTM applications with limited data, enhancing the robustness and reliability of temperature history reconstruction. Overall, the results highlight the potential of deep learning in accurately and practically reconstructing temperature histories in fire experiments.
AB - A time-temperature curve, representing the fire characteristics of structures, can be obtained by real fire experiments. However, these experiments are inherently susceptible to data loss, which can compromise the accuracy of results. To address this challenge, this study proposed the framework utilizing a long-short-term memory (LSTM) with Bayesian optimization to reconstruct temperature histories by learning the spatiotemporal correlation of the data. The proposed framework is first validated using simulated datasets from computational fluid dynamics analyses. The field applicability of the model is further demonstrated through real fire test results, affirming its reliability in practical scenarios. The study also introduces a novel data processing technique to mitigate overfitting issues in LSTM applications with limited data, enhancing the robustness and reliability of temperature history reconstruction. Overall, the results highlight the potential of deep learning in accurately and practically reconstructing temperature histories in fire experiments.
UR - http://www.scopus.com/inward/record.url?scp=85166072198&partnerID=8YFLogxK
U2 - 10.1016/j.firesaf.2023.103887
DO - 10.1016/j.firesaf.2023.103887
M3 - Article
AN - SCOPUS:85166072198
SN - 0379-7112
VL - 140
JO - Fire Safety Journal
JF - Fire Safety Journal
M1 - 103887
ER -