ﺑﻪ ﮐﺎرﮔﯿﺮي روﯾﮑﺮد ﻫﺎي ﯾﺎدﮔﯿﺮي ﻣﺎﺷﯿﻦ ﺟﻬﺖ ﭘﯿﺶ ﺑﯿﻨﯽ اﻧﺤﺮاف اﺑﻌﺎد ﮐﺎﺷﯽ ﻫﺎي ﺳﺮاﻣﯿﮑﯽ

Predicting Dimensional Deviation of Ceramic Tiles using Machine Learning Methods

ﭼﮑﯿﺪه: اﻣﺮوزه، روﯾﮑﺮدﻫﺎي ﯾﺎدﮔﯿﺮي ﻣﺎﺷﯿﻦ ﻧﻘﺶ ﻣﻬﻤﯽ را در ﺷﻨﺎﺳﺎﯾﯽ ﻋﻮاﻣﻞ ﻣﺆﺛﺮ ﺑﺮ ﮐﯿﻔﯿﺖ ﻣﺤﺼﻮﻻت ﺗﻮﻟﯿﺪي از ﺟﻤﻠﻪ ﺗﻮﻟﯿـﺪ ﮐﺎﺷﯽ و ﺳﺮاﻣﯿﮏ اﯾﻔﺎ ﻣﯽ ﮐﻨﻨﺪ. ﯾﮑﯽ از ﭼﺎﻟﺶ ﻫﺎي ﻣﻮﺟﻮد در ﺗﻮﻟﯿﺪ ﮐﺎﺷﯽ و ﺳﺮاﻣﯿﮑﯽ، ﻣﻌﯿﻮب ﺷﺪن ﮐﺎﺷﯽﻫﺎ ﺑﺪﻟﯿﻞ اﯾﺠﺎد اﻧﺤﺮاف در اﺑﻌﺎد ﮐﺎﺷﯽ ﺗﻮﻟﯿﺪي اﺳﺖ. درﺻﻮرﺗﯿﮑﻪ ﺑﺘﻮان ﺑﺎ ﺗﻮﺟﻪ ﺑﻪ ﭘﺎراﻣﺘﺮﻫﺎي ﻓﺮآﯾﻨﺪ ﺗﻮﻟﯿﺪ، اﻣﮑﺎن اﯾﺠﺎد اﻧﺤﺮاف در اﺑﻌﺎد ﮐﺎﺷﯽ را ﻗﺒﻞ از ﺗﻮﻟﯿﺪ ﭘﯿﺶ ﺑﯿﻨﯽ ﻧﻤﻮد، ﻣﯽ ﺗﻮان از ﺗﻮﻟﯿﺪ ﮐﺎﺷﯽ ﻣﻌﯿﻮب ﺟﻠﻮﮔﯿﺮي و ﻧﺴﺒﺖ ﺑﻪ ﺗﻨﻈﯿﻢ ﻣﺠﺪد ﭘﺎراﻣﺘﺮﻫﺎي ﺗﻮﻟﯿﺪ اﻗﺪام ﻧﻤﻮد. در اﯾﻦ ﭘﮋوﻫﺶ، ﯾﮏ ﺳﯿﺴﺘﻢ ﺧﻮدﮐﺎر ﺟﻬﺖ ﭘﯿﺶ ﺑﯿﻨﯽ دﺳﺘﻪ ي اﻧﺤﺮاف ﮐﺎﺷﯽ و ﺷﻨﺎﺳﺎﯾﯽ ﻋﻮاﻣﻞ ﺗﺄﺛﯿﺮﮔﺬار ﺑﺮ آن، ﭘﯿﺸﻨﻬﺎد ﺷﺪه اﺳﺖ. ﺑﺪﯾﻦ ﻣﻨﻈـﻮر ﺳـ ﻪ ﻃﺒﻘﻪﺑﻨﺪ ﻣﺨﺘﻠﻒ ﺷﺎﻣﻞ رﮔﺮﺳﯿﻮن ﻣﻨﻄﻘﯽ، ﺟﻨﮕﻞ ﺗﺼﺎدﻓﯽ و ﻣﺎﺷﯿﻦ ﺑﺮدار ﭘﺸﺘﯿﺒﺎن ﺟﻬﺖ ﻣﺪل ﺳﺎزي ﭘﺎراﻣﺘﺮﻫﺎي ﻣﺮﺑﻮﻃﻪ ﻣﻮرد ﺑﺮرﺳﯽ ﻗﺮارﮔﺮﻓﺘﻪ و ﺑﺮﺗﺮﯾﻦ ﺳﺎﺧﺘﺎر ﻣﻌﺮﻓﯽ ﺷﺪه اﺳﺖ. ﻋﻼوهﺑﺮاﯾﻦ ﺑﺎ ﺑﺮرﺳﯽ ﭼﻨﺪ دﺳﺘﻪ وﯾﮋﮔﯽ و ﺑﻬﺮه ﮔﯿﺮي از روش اﻧﺘﺨﺎب وﯾﮋﮔﯽ ﭘـﯿﺶ رو، ﻣﺘﻐﯿﺮﻫﺎي ﻣﺆﺛﺮ در ﺗﺼﻤﯿﻢ ﮔﯿﺮي اﻧﺤﺮاف ﮐﺎﺷﯽ ﻧﯿﺰ ﺷﻨﺎﺳﺎﯾﯽ ﺷﺪه اﻧﺪ. ﻧﺘﺎﯾﺞ آزﻣﺎﯾﺶ ﻫﺎي اﻧﺠﺎم ﺷﺪه ﺑﺮ روي ﻧﻤﻮﻧﻪ ﻫﺎي واﻗﻌـﯽ، ﻧﺸـﺎن ﻣﯽ دﻫﺪ ﮐﻪ روﯾﮑﺮد ﺟﻨﮕﻞ ﺗﺼﺎدﻓﯽ ﮐﺎراﯾﯽ ﺑﻬﺘﺮي ﻧﺴﺒﺖ ﺑﻪ روﯾﮑﺮدﻫﺎي دﯾﮕﺮ داﺷﺘﻪ و ﺗﺄﺛﯿﺮﮔﺬارﺗﺮﯾﻦ ﭘﺎراﻣﺘﺮﻫـﺎ در ا ﯾﺠـﺎد اﻧﺤـﺮاف ﮐﺎﺷﯽ، ﻣﻘﺪار ﻧﺎﻣﻨﺎﺳﺐ دﻣﺎﻫﺎي ﮐﻮره ﺑﻮده اﺳﺖ.

In recent years, machine learning approaches play an important role in quality identification of manufactured products including tiles and ceramics. Deviation of tile dimensions is one the main challenge in ceramic and tile industry. Prediction of this deformation will be beneficial if it can be predicted before producing the tile. In this paper, an automatic system has been proposed to predict the deviation of the ceramic tiles. Besides, a machine learning approach is utilized to identify the most effective parameters that leads to tiles’ defect. In this way, three different classification approaches including logistic regression, random forest, and support vector machine have been studied and the best solution is determined for this purpose. Moreover, several feature sets and forward feature selection method have been employed to select more effective variables on our decision making. The experimental results conducted on real-world dataset show that, random forest approach achieves better performance than others, and the results illustrate that improper temperature parameters has more effect on tile deviation.