كليدواژه :
اﺳﻼﻣﭗ ﺑﺘﻦ , ﻣﺤﺎﺳﺒﺎت ﻧﺮم , ﺳﯿﺴﺘﻢ ﻧﺮوﻓﺎزي ﺗﻄﺒﯿﻘﯽ , ﺷﺒﮑﻪ ﻋﺼﺒﯽ ﻣﺼﻨﻮﻋﯽ , اﻟﮕﻮرﯾﺘﻢﻫﺎي ﯾﺎدﮔﯿﺮي
چكيده فارسي :
ﮐﺎراﯾﯽ ﺑﺘﻦ از اﻫﻤﯿﺖ ﺑﺴﯿﺎر ﺑﺎﻻﯾﯽ در ﭘﺮوژهﻫﺎي ﻋﻤﺮاﻧﯽ ﺑﺮﺧﻮردار اﺳﺖ. ﯾﮑﯽ از ﻣﺘﺪاولﺗﺮﯾﻦ روشﻫﺎ ﺟﻬﺖ اﻧﺪازه ﮔﯿﺮي ﮐﺎراﯾﯽ ﺑﺘﻦ، آزﻣﺎﯾﺶ اﺳﻼﻣﭗ اﺳﺖ. ﺟﻬﺖ ﺻﺮﻓﻪﺟﻮﯾﯽ در زﻣﺎن، ﻫﺰﯾﻨﻪ و ﻣﺼﺎﻟﺢ، ﺑﻬﺘﺮ اﺳﺖ از روشﻫﺎي ﻫﻮﺷﻤﻨﺪي ﺟﻬﺖ ﭘﯿﺶﺑﯿﻨﯽ اﺳﻼﻣﭗ ﺑﺘﻦ اﺳﺘﻔﺎده ﺷﻮد. در اﯾﻦ ﺗﺤﻘﯿﻖ ﯾﮑﯽ از روشﻫﺎي ﻣﺒﺘﻨﯽ ﺑﺮ ﻣﺤﺎﺳﺒﺎت ﻧﺮم ﺑﮑﺎر ﮔﺮﻓﺘﻪ ﻣﯽﺷﻮد ﺗﺎ ﺑﺎ ﻃﺮاﺣﯽ ﺷﺒﮑﻪاي، ﺑﺪون ﻧﯿﺎز ﺑﻪ اﻧﺠﺎم آزﻣﺎﯾﺶﻫﺎي ﻓﯿﺰﯾﮑﯽ ﭘﺮزﺣﻤﺖ، ﺑﺘﻮان ﺗﺨﻤﯿﻨﯽ از اﺳﻼﻣﭗ ﺑﺘﻦ ﺑﺪﺳﺖ آورد. ﺑﺪﯾﻦ ﻣﻨﻈﻮر ﯾﮏ ﻣﺪل ﻧﺮوﻓﺎزي ﺗﻄﺒﯿﻘﯽ ﮐﻪ ﻣﺰاﯾﺎي ﺷﺒﮑﻪ ﻋﺼﺒﯽ و اﺳﺘﻨﺘﺎج ﻓﺎزي را ﺑﺎ ﻫﻢ دارا ﻣﯽﺑﺎﺷﺪ، ﺑﻪ ﻣﻨﻈﻮر ﭘﯿﺶﺑﯿﻨﯽ اﺳﻼﻣﭗ ﺑﺘﻦ ﭘﯿﺸﻨﻬﺎد ﻣﯽﺷﻮد. ﺑﻪ ﻣﻨﻈﻮر آﻣﻮزش ﻣﺪل ﭘﯿﺸﻨﻬﺎدي ﺟﻬﺖ ﭘﯿﺶﺑﯿﻨﯽﻫﺎي آﺗﯽ ﺑﺎ ﺟﻤﻊآوري دادهﻫﺎي ﻣﺮﺑﻮط ﺑﻪ 44 ﺗﺴﺖ آزﻣﺎﯾﺸﮕﺎﻫﯽ اﺳﻼﻣﭗ ﺑﺘﻦ، ﻣﺘﻐﯿﺮﻫﺎﯾﯽ ﻣﺎﻧﻨﺪ ﻧﺴﺒﺖ آب ﺑﻪ ﺳﯿﻤﺎن، ﻣﺎﺳﻪ، ﺷﻦ، ﻣﯿﮑﺮوﺳﯿﻠﯿﺲ و ﻓﻮق روان ﮐﻨﻨﺪه ﮐﻪ از اﺟﺰاي اﺻﻠﯽ ﺳﺎزﻧﺪه ﺑﺘﻦ ﻣﯽﺑﺎﺷﻨﺪ، ﺑﻪ ﻋﻨﻮان ﻣﺘﻐﯿﺮﻫﺎي ورودي و ﻣﻘﺪار اﺳﻼﻣﭗ ﻧﯿﺰ ﺑﻪ ﻋﻨﻮان ﻣﺘﻐﯿﺮ ﺧﺮوﺟﯽ در ﻧﻈﺮ ﮔﺮﻓﺘﻪ ﺷﺪه اﺳﺖ. در ﻧﻬﺎﯾﺖ دﻗﺖ ﻧﺘﺎﯾﺞ و ﮐﺎراﯾﯽ ﻣﺪل ﻧﺮوﻓﺎزي ﺗﻄﺒﯿﻘﯽ ﭘﯿﺸﻨﻬﺎدي ﺑﺎ اﺳﺘﻔﺎده از ﺷﺎﺧﺺﻫﺎي آﻣﺎري ﺿﺮﯾﺐ ﻫﻤﺒﺴﺘﮕﯽ و ﺟﺬر ﻣﯿﺎﻧﮕﯿﻦ ﻣﺮﺑﻌﺎت ﺧﻄﺎ ﺑﺎ ﯾﮏ ﻣﺪل ﺷﺒﮑﻪ ﻋﺼﺒﯽ ﻣﺼﻨﻮﻋﯽ ﻣﻘﺎﯾﺴﻪ ﺷﺪه اﺳﺖ. ﻧﺘﺎﯾﺞ ﻧﺸﺎن داد ﮐﻪ از ﻣﯿﺎﻧﮕﯿﻦ ﻧﺘﺎﯾﺞ ده دﺳﺘﻪﺑﻨﺪي ﻣﺘﻔﺎوت از دادهﻫﺎي آزﻣﺎﯾﺸﮕﺎﻫﯽ ورودي، ﺿﺮﯾﺐ ﻫﻤﺒﺴﺘﮕﯽ ﺑﯿﻦ اﺳﻼﻣﭗﻫﺎي ﭘﯿﺶﺑﯿﻨﯽ ﺷﺪه ﺑﻪ روش ﭘﯿﺸﻨﻬﺎدي و ﺷﺒﮑﻪ ﻋﺼﺒﯽ ﻣﺼﻨﻮﻋﯽ ﺗﻘﺮﯾﺒﺎ ﺑﺮاﺑﺮ اﺳﺖ. در ﺣﺎﻟﯽﮐﻪ ﻣﻘﺪار ﺟﺬر ﻣﯿﺎﻧﮕﯿﻦ ﻣﺮﺑﻌﺎت ﺧﻄﺎي اﺳﻼﻣﭗﻫﺎي روش ﻧﺮوﻓﺎزي ﭘﯿﺸﻨﻬﺎدي 0/4477 ﺗﻌﯿﯿﻦ ﺷﺪ ﮐﻪ ﮐﻤﺘﺮ از ﻣﻘﺪار 0/6964 ﻣﺮﺑﻮط ﺑﻪ ﺧﺮوﺟﯽ ﺷﺒﮑﻪ ﻋﺼﺒﯽ اﺳﺖ. از دﻻﯾﻞ ﺗﻔﺎوت در ﺧﻄﺎي ﺧﺮوﺟﯽ دو ﻣﺪل ﻣﯽﺗﻮان ﺑﻪ اﻟﮕﻮرﯾﺘﻢﻫﺎي ﯾﺎدﮔﯿﺮي ﻣﺘﻔﺎوت ﺑﮑﺎر رﻓﺘﻪ در دو ﻣﺪل و ﻋﺪم ﻣﺪﻟﺴﺎزي ﻋﺪم ﻗﻄﻌﯿﺖ، اﺑﻬﺎم در اﻧﺘﺨﺎب ﺑﻬﺘﺮﯾﻦ ﺗﻌﺪاد ﻻﯾﻪﻫﺎي ﻣﺨﻔﯽ و ﻧﺮونﻫﺎي اﯾﻦ ﻻﯾﻪﻫﺎ در ﻣﺪل ﺷﺒﮑﻪ ﻋﺼﺒﯽ ﻣﺼﻨﻮﻋﯽ اﺷﺎره ﮐﺮد.
چكيده لاتين :
Concrete performance is of very high importance in civil engineering projects. One of the most common ways to measure the performance of concrete, is the slump test. To save time, money and materials, it is better to use intelligent methods in predicting the slump. Therefore, in this study a method based on soft computing is used, so without the need to perform arduous physical experiments, one can obtain an estimate of the slump. In this study, an adaptive neuro-fuzzy model which has the benefits of both neural network and fuzzy inference system, is used to predict the concrete slump. In order to train the algorithm for future use, comprehensive experimental data is essential .So by collecting data related to 44 concrete slump experimental tests, variables such as water-cement ratio, sand, gravel, silica fume and super plasticizer which are the principal components of concrete, are considered as input variables and the amount of slump is considered as the output variable in the proposed model. In order to evaluate the performance of the proposed model and accuracy of the results, the results of the adaptive neuro-fuzzy model is compared to that of artificial neural network model, which is obtained in a parallel research done by author, by statistical parameters such as correlation coefficient and root mean square error. By averaging the results of ten different classifications of experimental input data, the correlation coefficient is approximately equal between adaptive neuro-fuzzy and neural network slump. While the root mean square error obtained by using adaptive neuro-fuzzy model is 0/4477 which is less than 0/6964 by neural network model. The difference in the output error of the two models are due to different learning algorithms used in two models and unknown number of hidden layers and neurons in the desirable artificial neural network model.
