ﮐﺎرﺑﺮد روشﻫﺎي ﺗﺸﺨﯿﺺ آﻣﺎري اﻟﮕﻮ در ﺷﻨﺎﺳﺎﯾﯽ ﺧﺮاﺑﯽ ﺳﺎزهﻫﺎ در ﺷﺮاﯾﻂ ﭘﯿﺮاﻣﻮﻧﯽ ﻣﺘﻔﺎوت

Application of statistical pattern recognition methods for structural damage detection under various ambient conditions

ﭘﺎﯾﺶ ﺳﻼﻣﺖ ﺳﺎزه راﻫﮑﺎري اﻗﺘﺼﺎدي و ﻣﻄﻤﺌﻦ ﺑﻪ ﻣﻨﻈﻮر ارزﯾﺎﺑﯽ ﺷﺮاﯾﻂ ﺳﺎزهﻫﺎي زﯾﺮ ﺳﺎﺧﺘﯽ اﺳﺖ. در ﺳﺎلﻫﺎي اﺧﯿﺮ ﻣﺤﻘﻘﺎن ﺣﻮزه ﭘﺎﯾﺶ ﺳﻼﻣﺖ ﺳﺎزه ﮐﻮﺷﯿﺪهاﻧﺪ ﮐﻪ اﻟﮕﻮرﯾﺘﻢﻫﺎﯾﯽ ﺑﻪ ﻣﻨﻈﻮر ﺗﺸﺨﯿﺺ ﺧﺮاﺑﯽ ﺑﺮ ﭘﺎﯾﻪ روش ﺗﺸﺨﯿﺺ آﻣﺎري اﻟﮕﻮ1 اراﺋﻪ دﻫﻨﺪ. ﻣﻄﺎﻟﻌﺎت ﻧﺸﺎن ﻣﯽدﻫﺪ ﮐﻪ اﯾﻦ اﻟﮕﻮرﯾﺘﻢﻫﺎ ﻣﯽﺗﻮاﻧﻨﺪ ﺑﻪ ﻃﻮر ﻣﻮﻓﻘﯿﺖآﻣﯿﺰي در ﺷﻨﺎﺳﺎﯾﯽ ﺧﺮاﺑﯽ ﺳﺎزهﻫﺎ ﻣﻮرد اﺳﺘﻔﺎده ﻗﺮار ﮔﯿﺮﻧﺪ. ﯾﮑﯽ از ﻣﺴﺎﺋﻠﯽ ﮐﻪ ﺑﺎﯾﺪ ﺑﺮاي اﻋﻤﺎل روشﻫﺎي ﺗﺸﺨﯿﺺ آﻣﺎري اﻟﮕﻮ در ﮐﺎرﺑﺮدﻫﺎي ﻋﻤﻠﯽ در ﻧﻈﺮ ﮔﺮﻓﺖ ﻣﺘﻐﯿﺮ ﺑﻮدن ﺷﺮاﯾﻂ ﻣﺤﯿﻄﯽ و ﮐﺎرﺑﺮي در ﻫﻨﮕﺎم ﺛﺒﺖ دادهﻫﺎ اﺳﺖ. در ﻧﻈﺮ ﮔﺮﻓﺘﻦ اﯾﻦ ﻣﻮﺿﻮع ﺑﺮاي اﺟﺘﻨﺎب از ﺗﺸﺨﯿﺺ ﻧﺎدرﺳﺖ ﺧﺮاﺑﯽ اﻣﺮي ﺿﺮوري ﻣﯽﺑﺎﺷﺪ. اﯾﻦ ﻣﻘﺎﻟﻪ ﺑﻪ ﺑﺮرﺳﯽ ﮐﺎراﯾﯽ روشﻫﺎي ﺗﺸﺨﯿﺺ آﻣﺎري اﻟﮕﻮ ﺑﻪ ﮐﻤﮏ ﺗﺤﻠﯿﻞ ﺳﺮي زﻣﺎﻧﯽ در ﺷﺮاﯾﻂ ﭘﯿﺮاﻣﻮﻧﯽ ﻣﺘﻔﺎوت ﻣﯽﭘﺮدازد. دادهﻫﺎي ﺣﺎﺻﻞ از ﯾﮏ ﻣﻄﺎﻟﻌﻪ آزﻣﺎﯾﺸﮕﺎﻫﯽ ﺷﺎﻣﻞ ﺳﯿﺴﺘﻢ ﻫﺸﺖ درﺟﻪ آزادي ﺟﺮم و ﻓﻨﺮ ﻣﻮرد اﺳﺘﻔﺎده ﻗﺮار ﮔﺮﻓﺘﻪ اﺳﺖ. ﺑﺎ ﺗﻐﯿﯿﺮ وﻟﺘﺎژ ﺳﯿﮕﻨﺎل اﻋﻤﺎﻟﯽ، ﺗﻮاﻧﺎﯾﯽ اﯾﻦ روشﻫﺎ در ﺗﺸﺨﯿﺺ ﺧﺮاﺑﯽ در ﺷﺮاﯾﻂ ﭘﯿﺮاﻣﻮﻧﯽ ﻣﺘﻔﺎوت ﻣﻮرد ﺑﺤﺚ ﻗﺮار ﮔﺮﻓﺘﻪ اﺳﺖ. دو روﯾﮑﺮد ﭘﺮﮐﺎرﺑﺮد ﺗﺸﺨﯿﺺ آﻣﺎري اﻟﮕﻮ ﺷﺎﻣﻞ ﻣﺪل اﺗﻮرﮔﺮﺳﯿﻮ2 AR)( ﺑﻪ ﻫﻤﺮاه اﺳﺘﻔﺎده از ﻧﻤﻮدار ﮐﻨﺘﺮل3 و ﯾﺎ ﻓﺎﺻﻠﻪ ﻣﺎﻫﺎﻻﻧﻮﺑﯿﺲ4 در ﺗﺸﺨﯿﺺ دادهﻫﺎي ﭘﺮت ﺑﺮرﺳﯽ ﺷﺪه اﺳﺖ. ﻧﺘﺎﯾﺞ ﺣﺎﺻﻞ اﻫﻤﯿﺖ ﺑﺮرﺳﯽ ﺗﻮاﻧﺎﯾﯽ روشﻫﺎي ﺗﺸﺨﯿﺺ آﻣﺎري اﻟﮕﻮ در ﺗﺸﺨﯿﺺ درﺳﺖ ﺧﺮاﺑﯽ ﺳﺎزه در ﺷﺮاﯾﻂ ﻣﺤﯿﻄﯽ و ﮐﺎرﺑﺮي ﻣﺘﻔﺎوت در ﮐﺎرﺑﺮدﻫﺎي ﻋﻤﻠﯽ را ﻧﺸﺎن ﻣﯽدﻫﺪ.

Structural health monitoring is an economical and reliable strategy for infrastructure condition assessment. In recent years, researchers have tried to propose algorithms based on statistical pattern recognition techniques. Studies show these algorithms can be successfully used to detect structural damage. Variability of operational and ambient conditions during data acquisition should be considered as an important factor in applying statistical pattern recognition methods in practical applications. This paper studies the efficiency of statistical pattern recognition methods on the damage detection of structures under various operational and ambient conditions. The data is obtained from an experimental study on an eight degrees of freedom mass spring system. Ambient vibration is applied to the mass spring system using random excitation. In order to simulate various ambient conditions, the amplitude level of the input force has been varied. By applying the statistical pattern recognition methods, the ability of these methods to damage detection under various ambient conditions is discussed. Two common approaches of statistical pattern recognition are considered. These approaches are autoregressive model accompanied with using control chart and Mahalanobis distance for outlier analysis. Results show the importance of considering the statistical pattern recognition methods for structural damage detection under various operational and ambient conditions.