³í¹®¸í |
Novelty detectionÀ» ÀÌ¿ëÇÑ BIM°´Ã¼¿Í IFC Ŭ·¡½º °£ ¸ÅÇÎÀÇ ¹«°á¼º °ËÅä¿¡ °üÇÑ ¿¬±¸ / Applying Novelty Detection for Checking the Integrity of BIM Entity to IFC Class Associations |
¼ö·Ï»çÇ× |
Çѱ¹°Ç¼³°ü¸®ÇÐȸ ³í¹®Áý, Vol.18 No.6 (2017-11) |
ÆäÀÌÁö |
½ÃÀÛÆäÀÌÁö(78) ÃÑÆäÀÌÁö(11) |
ÁÖÁ¦¾î |
BIM ; IFC ; ÀÌ»óŽÁö ºÐ¼® ; Novelty detection ; one-class SVM ; BIM ; IFC ; Anomaly Detection ; Novelty Detection ; one-class SVM |
¿ä¾à1 |
°Ç¼³»ç¾÷ÀÇ »ý¾ÖÁֱ⠴ܰ躰·Î BIMÀÇ È°¿ëµµ°¡ ´Ù¾çÇØÁö¸é¼ À̸¦ À§ÇÑ Àü¹®ÈµÈ ¼ÒÇÁÆ®¿þ¾î°¡ Áõ°¡ÇÏ°í ÀÖ´Ù. ÀÌµé ¼ÒÇÁÆ®¿þ¾î °£ BIM Á¤º¸ ±³È¯ ½Ã »óȣȣȯ¼ºÀÌ Áß¿äÇϸç, À̶§ ±¹Á¦Ç¥ÁØ Æ÷¸ËÀÎ IFC µ¥ÀÌÅÍ ¸ðµ¨À» äÅÃÇÏ°í ÀÖ´Ù. ±×·¯³ª BIM µ¥ÀÌÅ͸¦ IFC·Î º¯È¯Çϱâ À§Çؼ´Â °³º° °´Ã¼¿¡ IFC Ŭ·¡½º¸¦ ¸ÅÇÎÇØ¾ß Çϴµ¥, ÇöÀç±îÁö º» ÀÛ¾÷Àº ¼öµ¿ ÀÛ¾÷À¸·Î ÀÌ·ïÁö°í ÀÖ¾î, ¸ÅÇÎ »óÀÇ ¿À·ù³ª ´©¶ôÀÌ ¹ß»ýÇÏ°Ô µÈ´Ù. º» ¿¬±¸¿¡¼´Â BIM °´Ã¼ ¹× IFC Ŭ·¡½º °£ ¸ÅÇÎÀÇ ¹«°á¼º °ËÁõÀ» À§ÇØ ÀÌ»óŽÁöºÐ¼® ±â¹ý Áß ÇϳªÀÎ Novelty detectionÀ» Àû¿ëÇÏ¿´´Ù. µ¿ÀÏÇÑ IFC Ŭ·¡½ºÀÇ °´Ã¼µéÀº ±âÇÏÇü»óÀÌ À¯»çÇÏ´Ù´Â ÀüÁ¦ÇÏ¿¡. ¸ÅÇÎÀÌ À߸øµÈ °´Ã¼¸¦ ÀÌ»óÄ¡·Î ÆǺ°ÇÏ°íÀÚ ÇÏ´Â °ÍÀÌ´Ù. 3°³ÀÇ BIM¸ðµ¨·ÎºÎÅÍ IFC Ŭ·¡½ºº°·Î °´Ã¼¸¦ ºÐ·ùÇÑ ÈÄ ÀÌ Áß 2°³ÀÇ IFC Ŭ·¡½º(º®Ã¼ ¹× ¹®)¿¡ ´ëÇØ one-class SVMÀ» ÇнÀ½ÃÅ°°í °ËÁõÇÏ¿´´Ù. ºÐ¼®ÇÑ °á°ú ÃÑ 160°³ÀÇ ÀÌ»óÄ¡ Áß 141°³¸¦ Á¤È®ÇÏ°Ô ºÐ·ùÇÏ¿© ÀÌ»óÄ¡ ÆǺ° ´É·ÂÀÌ ³ô°Ô ³ª¿Ô´Ù. Novelty detection ±â¹ýÀº ´ÙÁß °æ°è¸éÀ» Çü¼ºÇÏ°í »çÀüÀû ÇнÀÀÌ °¡´ÉÇÏ´Ù´Â Á¡¿¡¼ ³ôÀº ¿¹Ãø·ÂÀ» ¹ßÈÖÇÏ¿©, ±âÁ¸ ¹æ½ÄÀ̳ª Ÿ ¾Ë°í¸®Áòº¸´Ù ¸ÅÇÎ ¿À·ù¸¦ °ËÁõÇϴµ¥ ´õ ÀûÇÕÇÑ ¹æ¹ýÀÎ °ÍÀ¸·Î È®ÀεǾú´Ù. |
¿ä¾à2 |
With the growing use of BIM in the AEC industry, various new applications are being developed to meet these specific needs. Such developments have increased the importance of Industry Foundation Classes, which is the international standard for sharing BIM data and thus ensuring interoperability. However, mapping individual BIM objects to IFC entities is still a manual task, and is a main cause for errors or omissions during data transfers. This research focused on addressing this issue by applying novelty detection, which is a technique for detecting anomalies in data. By training the algorithm to learn the geometry of IFC entities, misclassifications (i.e., outliers) can be detected automatically. Two IFC classes (ifcWall, ifcDoor) were trained using objects from three BIM models. The results showed that the algorithm was able to correctly identify 141 of 160 outliers. Novelty detection is thus suggested as a competent solution to resolve the mapping issue, mainly due to its ability to create multiple inlier boundaries and ex ante training of element geometry. |