|
|
|
Çѱ¹Áö¹Ý°øÇÐȸ / v.18, no.5, 2002³â, pp.123-132
|
µ¿Àû½Å°æ¸ÁÀ» ÀÌ¿ëÇÑ À̾ÏdzÈÅäÀÇ Àü´Ü°Åµ¿¿¹Ãø
( A Prediction of Shear Behavior of the Weathered Mudstone Soil Using Dynamic Neural Network ) |
| ±è¿µ¼ö;Á¤¼º°ü;±è±â¿µ;±èº´Å¹;ÀÌ»ó¿õ;Á¤´ë¿õ; °æºÏ´ëÇб³ °ø°ú´ëÇÐ Åä¸ñ°øÇаú;°æºÏ´ëÇб³ ³ó°ú´ëÇÐ Á¶°æ°øÇаú;°æºÏ´ëÇб³ °ø°ú´ëÇÐ Åä¸ñ°øÇаú;Çѱ¹Çؾ翬±¸¿ø;°æºÏ´ëÇб³ °ø°ú´ëÇÐ Åä¸ñ°øÇаú;°æºÏ´ëÇб³ °ø°ú´ëÇÐ Åä¸ñ°øÇаú;
|
|
|
 |
|
| |
| ÃÊ ·Ï |
| º» ¿¬±¸¿¡¼´Â Àΰ£ÀÇ »ç°í°úÁ¤À» ±Ù°Å·Î °³¹ßµÈ µ¿Àû Àΰø½Å°æ¸ÁÀ» ÀÌ¿ëÇÏ¿© À̾ÏdzÈÅäÀÇ Àü´Ü°Åµ¿À» ¿¹ÃøÇÏ¿´´Ù. ÈëÀÇ ºñ¼±Çü°Åµ¿À» ¿¹ÃøÇÔ¿¡ ÀÖ¾î Çǵå¹é °úÁ¤¿¡ ÀÇÇØ ½Ã°£°æ°ú¿¡ µû¸¥ ÆÐÅÏÀÇ Æ¯¼ºº¯È¸¦ ¿¬¼ÓÀûÀ¸·Î ¿¹ÃøÇÒ ¼ö ÀÖ´Â µ¿Àû½Å°æ¸ÁÀÇ Á¾·ùÀÎ SNN¸ðµ¨°ú RNN¸ðµ¨À» ÀÌ¿ëÇÏ¿´´Ù. Àΰø½Å°æ¸ÁÀÇ ÇнÀ´É·Â°ú ¿¹Ãø´É·Â¿¡ ¿µÇâÀ» ¹ÌÄ¡´Â ¿©·¯ º¯¼öµîÀ» ºÐ¼®ÈÄ SNN¸ðµ¨¿¡¼´Â ÇнÀÀ², ¸ð¸àÅÒ »ó¼ö, ½Å°æ¸Á±¸Á¶°¡ 0.5, 0.7, 8$ imes$18$ imes$2, RNN¸ðµ¨ÀÎ °æ¿ì´Â °¢°¢ 0.3,0.9,8$ imes$24$ imes$2ÀÇ ±¸Á¶°¡ ÀûÇÕÇÑ °ÍÀ¸·Î ³ªÅ¸³µ´Ù ¿¹Ãø°á°ú´Â µÎ ³×Æ®¿öÅ© ¸ðµÎ Á¤±Ô¾Ð¹Ð »óÅÂÀÇ Àü´Ü°Åµ¿À» Àß ¿¹ÃøÇÏ¿´Áö¸¸, °ú¾Ð¹Ð »óÅÂÀÇ Àü´Ü°Åµ¿ ¿¹Ãø¿¡¼´Â ºÒ±ÔÄ¢ÀûÀÎ ÀÔ·ÂÆÐÅÏ¿¡ È¿°úÀûÀÎ RNN¸ðµ¨ÀÇ ¿¹Ãø´É·ÂÀÌ ´õ¿í ¿ì¼öÇÏ¿´´Ù. |
|
| The purpose of this study is to predict the shear behavior of the weathered mudstone soil using dynamic neural network which mimics the biological system of human brain. SNN and RNN, which are kinds of the dynamic neural network realizing continuously a pattern recognition as time goes by, are used to predict a nonlinear behavior of soil. After analysis, parameters which have an effect on learning and predicting of neural network, the teaming rate, momentum constant and the optimum neural network model are decided to be 0.5, 0.7, 8$ imes$18$ imes$2 in SU model and 0.3, 0.9, 8$ imes$24$ imes$2 in R model. The results of appling both networks showed that both networks predicted the shear behavior of soil in normally consolidated state well, but RNN model which is effective fir input data of irregular patterns predicted more efficiently than SNN model in case of the prediction in overconsolidated state. |
| |
| Ű¿öµå |
| Dynamic neural network;learning rate;Momentum constant;RNN;SNN; |
| |
|
|
 |
|
Çѱ¹Áö¹Ý°øÇÐȸ³í¹®Áý / v.18, no.5, 2002³â, pp.123-132
Çѱ¹Áö¹Ý°øÇÐȸ
ISSN : 1229-2427
UCI : G100:I100-KOI(KISTI1.1003/JNL.JAKO200211921407810)
¾ð¾î : Çѱ¹¾î |
|
| ³í¹® Á¦°ø : KISTI Çѱ¹°úÇбâ¼úÁ¤º¸¿¬±¸¿ø |
|
|
|
|
|
|