°ÇÃ൵½Ã°ø°£¿¬±¸¼Ò

Architecture & Urban Research Institute

pdf¿ø¹®º¸±â ¿¡·¯ ÇØ°á¹æ¹ý ¹Ù·Î°¡±â



¹®ÇåȨ > Àú³Î > »ó¼¼

[¿ø¹®º¸±â½Ã ¼ÒºñµÇ´Â Æ÷ÀÎÆ® : 50 Æ÷ÀÎÆ®] ¹Ì¸®º¸±â

Çѱ¹±¸Á¶¹°Áø´ÜÀ¯Áö°ü¸®°øÇÐȸ|³í¹®Áý 2024³â 10¿ù

±â»ç¸í ±â°èÇнÀ ±â¹Ý ÇØ¾ç ³ëÃâ ȯ°æÀÇ ÄÜÅ©¸®Æ® ±³·® µ¥ÀÌÅ͸¦ È°¿ëÇÑ ¿°È­¹° È®»ê°è¼ö ¿¹Ãø¸ðµ¨ °³¹ß / Development of a Machine Learning-Based Model for the Prediction of Chloride Diffusion Coefficient Using Concrete Bridge Data Exposed to Marine Environments
ÀúÀÚ¸í ³²¿ì¼® ; ÀÓÈ«Àç
¹ßÇà»ç Çѱ¹±¸Á¶¹°Áø´ÜÀ¯Áö°ü¸®°øÇÐȸ
¼ö·Ï»çÇ× Çѱ¹±¸Á¶¹°Áø´ÜÀ¯Áö°ü¸®°øÇÐȸ ³í¹®Áý , Vol.28 No.5(2024-10)
ÆäÀÌÁö ½ÃÀÛÆäÀÌÁö(20) ÃÑÆäÀÌÁö(10)
ISSN 2234-6937
ÁÖÁ¦ºÐ·ù
ÁÖÁ¦¾î ±â°èÇнÀ; ¿°È­¹° È®»ê°è¼ö; ÇØ¾ç ³ëÃâ ȯ°æ; ÄÜÅ©¸®Æ® ±³·®; Á¤¹Ð¾ÈÀüÁø´Ü µ¥ÀÌÅÍ ; Machine learning; Chloride diffusion coefficient; Marine exposure environment; Concrete bridge; Precision safety diagnosis data
¿ä¾à1 ¿°È­¹° È®»ê°è¼ö´Â Çؾçȯ°æ¿¡ À§Ä¡ÇÑ ÄÜÅ©¸®Æ® ±³·®ÀÇ ³»±¸¼º Æò°¡¸¦ À§ÇÑ Áß¿äÇÑ ÁöÇ¥ Áß ÇϳªÀÌ´Ù. º» ³í¹®¿¡¼­´Â ±âÁ¸ ¿¬±¸¿¡¼­ °í·ÁÇÏÁö ¾Ê¾Ò´ø ÇØ¾ç ³ëÃâ ȯ°æ(´ë±âÁß, ºñ¸»´ë, °£¸¸´ë)°ú °ø¿ë ÁßÀÎ ÄÜÅ©¸®Æ® ±³·®ÀÇ µ¥ÀÌÅ͸¦ È°¿ëÇØ ¿°È­¹° È®»ê°è¼ö ¿¹Ãø ¸ðµ¨À» °³¹ßÇÏ¿´´Ù. À̸¦ À§ÇØ ±³·® ÇϺα¸Á¶¿¡¼­ ÃëµæÇÑ ¿°È­¹° ÇÁ·ÎÆÄÀÏ µ¥ÀÌÅ͸¦ È°¿ëÇÏ¿´°í µ¥ÀÌÅÍ Àüó¸® ÈÄ ±â°èÇнÀ ¸ðµ¨ÀÎ RF, GBM, KNNÀ» ÇÏÀÌÆÛÆĶó¹ÌÅÍ Æ©´×À» ÅëÇØ ÃÖÀûÈ­ ÇÏ¿´´Ù. ÄÜÅ©¸®Æ® ¹°¼ºÄ¡¸¦ Æ÷ÇÔÇÑ 6°³ º¯¼ö(W/B, ½Ã¸àÆ® Á¾·ù, ±½Àº°ñÀç ºÎÇÇ ºñÀ², °ø¿ë¿¬¼ö, °­µµ, ³ëÃâ ȯ°æ) ¸ðµ¨°ú ³ëÃâ ȯ°æÀ» °í·ÁÇÏÁö ¾ÊÀº 5°³ º¯¼ö ¸ðµ¨, Á¤¹Ð¾ÈÀüÁø´Ü¿¡¼­ Ãëµæ °¡´ÉÇÑ 3°³ º¯¼ö(°ø¿ë¿¬¼ö, °­µµ, ³ëÃâ ȯ°æ) ¸ðµ¨À» °³¹ßÇÏ¿© ¼º´ÉÀ» ºñ±³¡¤°ËÅä ÇÏ¿´´Ù. ±× °á°ú Çؾç ȯ°æ¿¡ À§Ä¡ÇÑ ÄÜÅ©¸®Æ® ±³·®ÀÇ °æ¿ì ³ëÃâ ȯ°æÀ» °í·ÁÇÔ¿¡ µû¶ó ¿°È­¹° È®»ê°è¼ö ¿¹Ãø ¸ðµ¨ÀÇ ¼º´ÉÀ» Çâ»ó½Ãų ¼ö ÀÖÀ½À» È®ÀÎÇÏ¿´À¸¸ç, ¶ÇÇÑ Á¤¹Ð¾ÈÀüÁø´Ü µ¥ÀÌÅ͸¸À¸·Îµµ ¿°È­¹° È®»ê°è¼ö¸¦ È¿°úÀûÀ¸·Î ¿¹ÃøÇÒ ¼ö ÀÖÀ½À» È®ÀÎÇÏ¿´´Ù.
¿ä¾à2 The chloride diffusion coefficient is a critical indicator for assessing the durability of concrete marine substructures. This study develops a prediction model for the chloride diffusion coefficient using data from concrete bridges located in marine exposure zones (atmospheric, splash, tidal), an aspect that has not been considered in previous studies. Chloride profile data obtained from these bridge substructures were utilized. After data preprocessing, machine learning models, including Random Forest (RF), Gradient Boosting Machine (GBM), and K-Nearest Neighbors (KNN), were optimized through hyperparameter tuning. The performance of these models was developed and compared under three different variable sets. The first model uses six variables: water-to-binder (W/B) ratio, cement type, coarse aggregate volume ratio, service life, strength, and exposure environment.
The second model excludes the exposure environment, using only the remaining five variables. The third model relies on just three variables: service life, strength, and exposure environment factors that can be obtained from precision safety diagnostics. The results indicate that including the exposure environment significantly enhances model performance for predicting the chloride diffusion coefficient in concrete bridges in marine environments.
Additionally, the three variable model demonstrates that effective predictions can be made using only data from precision safety diagnostics.
¼ÒÀåó Çѱ¹±¸Á¶¹°Áø´ÜÀ¯Áö°ü¸®°øÇÐȸ
¾ð¾î Çѱ¹¾î
DOI https://doi.org/10.11112/jksmi.2024.28.5.20