ﺑﻪ ﻓﺮﻣﺎن آوري ﻗﺎب ﻫﺎي دوﺑﻌﺪي ﺑﺎ ﺷﺒﮑﻪ ي ﻋﺼﺒﯽ ﺳﺎزﮔﺎر ﺷﻮﻧﺪه

Active Control of Plane Frames by Compatible Neural Network

ﯾﮑﯽ از دﻏﺪﻏﻪﻫﺎي ﻫﻤﯿﺸﮕﯽ ﻣﻬﻨﺪﺳﺎن ﻋﻤﺮان، ﮐﻢ ﮐﺮدن ﭘﺎﺳﺦﻫﺎي ﺳﺎزه در ﺑﺮاﺑﺮ ﺑﺎرﻫﺎي ﭘﻮﯾﺎي ﻧﺎﺷﯽ از زﻣﯿﻦ ﻟﺮزه، ﺑﺮاي ﺟﻠﻮﮔﯿﺮي از ﻓﺎﺟﻌﻪﻫﺎي اﻧﺴﺎﻧﯽ ﯾﺎ زﯾﺎن ﻫﺎي اﻗﺘﺼﺎدي ﺳﻨﮕﯿﻦ ﺑﻮده اﺳﺖ. داﻧﺸﻤﻨﺪان در دو دﻫﻪي ﭘﯿﺸﯿﻦ، ﭘﮋوﻫﺶﻫﺎي ﻓﺮاواﻧﯽ در اﯾﻦ ﺑﺎره اﻧﺠﺎم داده اﻧﺪ. ﻧﮕﺮهﻫﺎي ﮐﻨﺘﺮل ﭘﯿﺸﺮﻓﺘﻪ ﺑﻪ ﻃﻮر ﮔﺴﺘﺮده و ﻣﻮﻓﻘﯿﺖ آﻣﯿﺰ در ﺳﺎﻣﺎﻧﻪﻫﺎي ﻣﻬﻨﺪﺳﯽ ﺑﺮق اﺟﺮا ﮔﺮدﯾﺪه اﻧﺪ. در اﯾﻦ ﺳﺎل ﻫﺎ، ﭘﮋوﻫﺶ ﻫﺎي ﻓﺮاواﻧﯽ درﺑﺎره ي ﮐﺎرﺑﺮد اﯾﻦ روش ﻫﺎ در ﻣﻬﻨﺪﺳﯽ ﻋﻤﺮان، اﻧﺠﺎم ﺷﺪه اﺳﺖ. در اﯾﻦ ﭘﮋوﻫﺶ ﻫﺎ، ﺑﺴﯿﺎري از اﺑﺰارﻫﺎ و ﻓﺮآﯾﻨﺪﻫﺎي ﮐﻨﺘﺮﻟﯽ ﺑﺮاي ﮐﺎﻫﺶ ﭘﺎﺳﺦﻫﺎي ﭘﻮﯾﺎي ﺳﺎزه ﺑﻪ ﮐﺎر رﻓﺘﻪ اﺳﺖ. ﮐﻤﯿﻨﻪ ﮐﺮدن ﭘﺎﺳﺦ ﺳﺎزه در ﺑﺮاﺑﺮ ﻧﻮﺳﺎن زﻣﯿﻦ ﺑﺎ ﺑﻬﺮه ﺟﻮﯾﯽ از دو ﻣﺤﺮك، ﻫﺪف اﯾﻦ ﻣﻘﺎﻟﻪ اﺳﺖ. راﺑﻄﻪي ﻣﯿﺎن ﻧﯿﺮوي ﮐﻨﺘﺮﻟﯽ ﻣﺤﺮك ﻫﺎ را ﻧﻮﯾﺴﻨﺪﮔﺎن ﺑﻪ ﮔﻮﻧﻪاي ﺑﺮ ﻗﺮار ﻣﯽﮐﻨﻨﺪ ﮐﻪ ﻧﯿﺮوي وارد در ﻣﺪ ﯾﮑﻢ ﺳﺎزه ﺻﻔﺮ ﮔﺮدد. ﺳﭙﺲ، ﺑﺮاي ﮐﻤﯿﻨﻪ ﮐﺮدن ﭘﺎﺳﺦﻫﺎ از ﻓﻦ ﺑﻬﯿﻨﻪ ﺳﺎزي ارﺛﯽ ﺑﻬﺮه ﺟﻮﯾﯽ ﺧﻮاﻫﺪ ﺷﺪ. ﺳﺎﺧﺘﺎر ﮐﻨﺘﺮﻟﯽ ﮐﻪ در اﯾﻦ ﻣﻘﺎﻟﻪ ﺑﻪ ﮐﺎر ﻣﯽرود، از ﮔﻮﻧﻪي ﺣﻠﻘﻪي ﺑﺴﺘﻪ اﺳﺖ. ﻫﻤﭽﻨﯿﻦ، از ﺷﺒﮑﻪي ﻋﺼﺒﯽ ﺳﺎزﮔﺎر ﺷﻮﻧﺪه ﺑﺮاي ﭘﯿﺶ ﺑﯿﻨﯽ ﺷﺘﺎب زﻣﯿﻦ ﺑﻬﺮه ﺟﻮﯾﯽ ﻣﯽﮔﺮدد. ﻧﻮﯾﺴﻨﺪﮔﺎن، ﺷﺒﮑﻪي ﻋﺼﺒﯽ را ﺑﺮ ﻣﯽﮔﺰﯾﻨﻨﺪ ﮐﻪ ﺑﺎ ﺗﻐﯿﯿﺮ در ﺷﻤﺎر ﻧﺮونﻫﺎي ﻻﯾﻪﻫﺎ در ﻫﻨﮕﺎم زﻣﯿﻦ ﻟﺮزه ﺗﻮاﻧﺎﯾﯽ ﺳﺎزﮔﺎري ﺑﺎ ﺗﻐﯿﯿﺮ ﺷﺘﺎب زﻣﯿﻦ را دارا ﺑﺎﺷﺪ. ﺑﺮاي اﻓﺰاﯾﺶ ﺳﺮﻋﺖ ﻫﻤﮕﺮاﯾﯽ ﺷﺒﮑﻪي ﻋﺼﺒﯽ، وزنﻫﺎي ﮔﺎم ﭘﯿﺸﯿﻦ ﺑﺮاي آﻏﺎز آﻣﻮزش در ﮔﺎم ﺑﻌﺪ ﺑﻪ ﮐﺎر ﻣﯽروﻧﺪ. ﺗﺠﺮﺑﻪﻫﺎي ﻋﺪدي ﮔﺴﺘﺮده ﺑﺮ روي زﻣﯿﻦ ﻟﺮزهﻫﺎ و ﻧﯿﺰ ﺳﺎزهﻫﺎي ﻓﺮاوان، ﻧﺸﺎن ﻣﯽدﻫﺪ ﮐﻪ روش ﭘﯿﺸﻨﻬﺎدي ﺑﺴﯿﺎر ﻣﻮﺛﺮ اﺳﺖ. ﺑﺎ اﻓﺰاﯾﺶ ﺑﻠﻨﺪي ﺳﺎزه، ﺷﺘﺎب در ﺑﺮﺧﯽ ﻃﺒﻘﻪﻫﺎ اﻓﺰاﯾﺶ ﻣﯽ ﯾﺎﺑﺪ وﻟﯽ ﻫﻢ ﭼﻨﺎن اﯾﻦ ﻓﻦ ﺗﻮاﻧﺎﯾﯽ زﯾﺎدي در ﮐﺎﻫﺶ ﺗﻐﯿﯿﺮﻣﮑﺎنﻫﺎي ﻧﺴﺒﯽ ﺳﺎزه دارد. ﺑﻪ ﺳﺨﻦ دﯾﮕﺮ، ﮐﺎﺳﺘﯽ ﻓﻦ ﭘﯿﺸﻨﻬﺎدي در اﯾﻦ ﭘﮋوﻫﺶ را ﻣﯽﺗﻮان در ﺑﻪ ﻓﺮﻣﺎن آوري رﻓﺘﺎر ﺳﺎزه ﻫﺎي ﺑﻠﻨﺪ داﻧﺴﺖ. ﺑﻨﺎﺑﺮاﯾﻦ، ﮔﺴﺘﺮهي ﮐﺎرﺑﺮد اﯾﻦ روش، ﮐﻨﺘﺮل رﻓﺘﺎر ﺳﺎزهﻫﺎي ﮐﻮﺗﺎه و ﻣﯿﺎن ﻣﺮﺗﺒﻪ اﺳﺖ.

Controlling the behavior of frame building is very common these days. This goal is achieved by changing the structural behaviors through applying forces to the frames. Recently, extensive studies have been carried out in the field of structural control related to the earthquakes. All studies conducted in this area can be divided into two groups. The first category is devoted to the control devices. Since accuracy and sensitivity of required equipment play an important role, some industries are trying to build better and more robust instruments. The key subject of the second group of researchers is developing new control algorithms. These approaches need some innovations. The purpose of this study is to minimize the structural response against earthquake utilizing two actuators. The purpose of this study is to minimize the structural response against earthquake utilizing two actuators. The relationship between the control forces of the actuators was so arranged that the first mode force becomes zero. In order to minimize the structural responses, the genetic algorithm was used. The controlling system, which is exploited in this paper, is a closed circle. In addition, the neural network was employed to predict the earth acceleration. The authors selected a kind of the neural network to have compatibility with earthquake acceleration variation. To achieve this, the number of the neurons in layers should be varied. The comprehensive experimental numerical results for a variety of earthquakes and structures indicated that the suggested method is very effective. However, the present study drawback is in decreasing the responses of tall frames.