³í¹®¸í |
¸Å´ÏÆúµå µ¥ÀÌÅÍ Áõ°±â¹ý ±â¹ÝÀÇ µö·¯´× ¹æ¹ý·ÐÀ» Àû¿ëÇÑ Ãà¼Ò ¸ðµ¨ °³¹ß / Development of a Reduced Order Model using a Deep Learning-based Manifold-Augmented Approach |
ÀúÀÚ¸í |
õ¼º¿ì ; ±èÇýÁø ; ·ù¼®Èñ ; Á¶Çؼº ; ÀÌÇÐÁø |
¼ö·Ï»çÇ× |
Çѱ¹Àü»ê±¸Á¶°øÇÐȸ³í¹®Áý, Vol.37 No.5 (2024-10) |
ÆäÀÌÁö |
½ÃÀÛÆäÀÌÁö(337) ÃÑÆäÀÌÁö(8) |
ÁÖÁ¦¾î |
¸Å´ÏÆúµå ·¯´×; ¸ðµ¨ Â÷¼ö Ãà¼Ò; µö·¯´×; ¿¬»êÀ¯Ã¼¿ªÇÐ; µ¥ÀÌÅÍ Áõ° ; manifold learning; model-order reduction; deep learning; data augmentation |
¿ä¾à1 |
º» ³í¹®¿¡¼´Â Àú ·¹À̳îÁî ¼ö ¿µ¿ª¿¡¼ ¿¡¾îÆ÷ÀÏÀÇ °ø±â¿ªÇÐÀû ¼º´ÉÀ» ¿¹ÃøÇϱâ À§ÇÑ µö·¯´× ±â¹ÝÀÇ Ãà¼Ò ¸ðµ¨À» Á¦½ÃÇÏ¿´´Ù. µö·¯´× ±â¹Ý Ãà¼Ò ¸ðµ¨¿¡¼ CFD Çؼ® °á°úÀÇ ³ôÀº Â÷¿øÀÇ µ¥ÀÌÅ͸¦ È¿À²ÀûÀ¸·Î ´Ù·ç±â À§ÇØ º¯ÀÌÇü ¿ÀÅäÀÎÄÚ´õ¸¦ °áÇÕÇÑ ÇÕ¼º°ö ½Å°æ¸ÁÀ» Àû¿ëÇÏ¿´´Ù. ºÎÈ£È °Å¸® ÇÔ¼ö¸¦ ÅëÇØ ¿¡¾îÆ÷ÀÏÀÇ Çü»ó°ú À¯µ¿ Á¶°ÇÀ» À̹ÌÁö µ¥ÀÌÅÍÈ ÇÏ°í, ÀÌ¿¡ ´ëÇØ ÇÕ¼º°ö ½Å°æ¸ÁÀ» ¸Å°³º¯¼öÈ ÇÏ¿´´Ù. ¶ÇÇÑ, Àü»êÀ¯Ã¼¿ªÇÐ Çؼ®ÀÇ °è»ê ºñ¿ëÀ¸·Î ÀÎÇÑ ºÎÁ·ÇÑ ÈÆ·Ã µ¥ÀÌÅ͸¦ ±Øº¹Çϱâ À§ÇØ Åõ¿µ ±â¹ÝÀÇ ºñ¼±Çü ¸Å´ÏÆúµå µ¥ÀÌÅÍ Áõ°±â¹ýÀ» °³¹ßÇÏ¿´´Ù. NACA 4°è¿ ¿¡¾îÆ÷ÀÏÀº Çؼ® ¿¹Á¦·Î °í·ÁÇÏ¿© Á¦¾ÈÇÏ´Â ÇÁ·¹ÀÓ¿öÅ©ÀÇ ³»»ð°ú ¿Ü»ð Á¤È®µµ¸¦ Æò°¡ÇÏ¿´À¸¸ç ¸Å´ÏÆúµå µ¥ÀÌÅÍ Áõ°±â¹ýÀ» Àû¿ëÇÏ¿© ÇÁ·¹ÀÓ¿öÅ©ÀÇ Á¤È®µµ Çâ»óÀ» È®ÀÎÇÏ¿´´Ù. |
¿ä¾à2 |
This study presents a deep learning-based framework to predict the aerodynamic performance of low Reynolds number airfoils. The framework employs a convolutional neural network (CNN) combined with a variational autoencoder (VAE) to efficiently handle large datasets. Moreover, the signed distance function is used as the network input to represent the airfoil configuration in the image data and parameterize the CNN. A novel generative model based on projection-based manifold learning is proposed to overcome the data mining limitation of computational fluid dynamics which may incur significant computational costs. The interpolation and extrapolation accuracy of the proposed framework is evaluated using the NACA 4-digit airfoil configuration.The results show improved accuracy via data augmentation performed by the proposed generative model. |