• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) Áֱ⼺À» °®´Â ÀÔÃâ·Â µ¥ÀÌÅÍÀÇ ¿¬°ü¼º ºÐ¼®À» ÅëÇÑ È¸±Í ¸ðµ¨ ÇнÀ ¹æ¹ý
¿µ¹®Á¦¸ñ(English Title) Learning Method for Regression Model by Analysis of Relationship Between Input and Output Data with Periodicity
ÀúÀÚ(Author) ±èÇýÁø   ¹Ú¿¹½½   ÀÌÁ¤¿ø   Hye-Jin Kim   Ye-Seul Park   Jung-Won Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 11 NO. 07 PP. 0299 ~ 0306 (2022. 07)
Çѱ۳»¿ë
(Korean Abstract)
ÃÖ±Ù ·Îº¿À̳ª ¼³ºñ, ȸ·Î µî¿¡ ¼¾¼­ ³»ÀåÀÌ º¸ÆíÈ­ µÇ°í, ÃøÁ¤µÈ ¼¾¼­ µ¥ÀÌÅ͸¦ ÇнÀÇÏ¿© ±â±âÀÇ °íÀåÀ» Áø´ÜÇϱâ À§ÇÑ ¿¬±¸°¡ È°¹ßÇÏ°Ô ¼öÇàµÇ°í ÀÖ´Ù. ÀÌ·¯ÇÑ °íÀå Áø´Ü ¿¬±¸´Â °íÀå »óȲÀ̳ª Á¾·ù¸¦ ¿¹ÃøÇϱâ À§ÇÑ ºÐ·ù(Classification) ¸ðµ¨ °³¹ß°ú Á¤·®ÀûÀ¸·Î °íÀå »óȲÀ» ¿¹ÃøÇϱâ À§ÇÑ È¸±Í(Regression) ¸ðµ¨ °³¹ß·Î ±¸ºÐµÈ´Ù. ºÐ·ù ¸ðµ¨ÀÇ °æ¿ì, ´Ü¼øÈ÷ °íÀåÀ̳ª °áÇÔÀÇ À¯¹«(Class)¸¦ È®ÀÎÇÏ´Â ¹Ý¸é, ȸ±Í ¸ðµ¨Àº ¹«¼öÈ÷ ¸¹Àº ¼öÄ¡ Áß¿¡ ÇϳªÀÇ °ª(Value)À» ¿¹ÃøÇØ¾ß ÇϹǷΠÇнÀ ³­À̵µ°¡ ´õ ³ô´Ù. Áï, ÀԷ°ú Ãâ·ÂÀ» ´ëÀÀ½ÃÄÑ °íÀåÀ» ¿¹ÃøÀ» ÇÒ ¶§, À¯»çÇÑ ÀԷ°ªÀÌ µ¿ÀÏÇÑ Ãâ·ÂÀ» ³½´Ù°í °áÁ¤Çϱ⠾î·Á¿î ºÒ±ÔÄ¢ÇÑ »óȲÀÌ ´Ù¼ö Á¸ÀçÇϱ⠶§¹®ÀÌ´Ù. µû¶ó¼­ º» ³í¹®¿¡¼­´Â Áֱ⼺À» Áö´Ñ ÀÔÃâ·Â µ¥ÀÌÅÍ¿¡ ÃÊÁ¡À» ¸ÂÃß¾î, ÀÔÃâ·Â °ü°è¸¦ ºÐ¼®ÇÏ°í, ½½¶óÀ̵ù À©µµ¿ì ±â¹ÝÀ¸·Î ÀÔ·Â µ¥ÀÌÅ͸¦ ÆÐÅÏÈ­ ÇÏ¿© ÀÔÃâ·Â µ¥ÀÌÅÍ °£ÀÇ ±ÔÄ¢¼ºÀ» È®º¸Çϵµ·Ï ÇÑ´Ù. Á¦¾ÈÇÏ´Â ¹æ¹ýÀ» Àû¿ëÇϱâ À§ÇØ, º» ¿¬±¸¿¡¼­´Â MMC(Modular Multilevel Converter) ȸ·Î ½Ã½ºÅÛÀ¸·ÎºÎÅÍ Áֱ⼺À» Áö´Ñ Àü·ù, ¿Âµµ µ¥ÀÌÅ͸¦ ¼öÁýÇÏ¿© ANNÀ» ÀÌ¿ëÇÏ¿© ÇнÀÀ» ÁøÇàÇÏ¿´´Ù. ½ÇÇè °á°ú, ÇÑ ÁÖ±âÀÇ 2% ÀÌ»óÀÇ À©µµ¿ì¸¦ Àû¿ëÇÏ¿´À» ¶§, ÀûÇÕµµ 97% ÀÌ»óÀÇ ¼º´ÉÀÌ È®º¸µÉ ¼ö ÀÖÀ½À» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
In recent, sensors embedded in robots, equipment, and circuits have become common, and research for diagnosing device failures by learning measured sensor data is being actively conducted. This failure diagnosis study is divided into a classification model for predicting failure situations or types and a regression model for numerically predicting failure conditions. In the case of a classification model, it simply checks the presence or absence of a failure or defect (Class), whereas a regression model has a higher learning difficulty because it has to predict one value among countless numbers. So, the reason that regression modeling is more difficult is that there are many irregular situations in which it is difficult to determine one output from a similar input when predicting by matching input and output. Therefore, in this paper, we focus on input and output data with periodicity, analyze the input/output relationship, and secure regularity between input and output data by performing sliding window-based input data patterning. In order to apply the proposed method, in this study, current and temperature data with periodicity were collected from MMC(Modular Multilevel Converter) circuit system and learning was carried out using ANN. As a result of the experiment, it was confirmed that when a window of 2% or more of one cycle was applied, performance of 97% or more of fit could be secured.
Å°¿öµå(Keyword) eural Network   Fault Diagnosis   Sensor Data   Regression Model   Thermal Estimation   ½Å°æ¸Á   °íÀåÁø´Ü   ¼¾¼­ µ¥ÀÌÅÍ   ȸ±Í ¸ðµ¨   ¿Âµµ¿¹Ãø  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå