A Supervised Machine Learning Model for Dental Crowns Material Design for Manufacturing | ||
| The Egyptian International Journal of Engineering Sciences and Technology | ||
| Articles in Press, Accepted Manuscript, Available Online from 14 September 2024 | ||
| Document Type: Original Article | ||
| DOI: 10.21608/eijest.2024.308663.1284 | ||
| Authors | ||
| Adel Osama* ; Noha Fouda; mohamed eraky | ||
| faculty of engineering | ||
| Abstract | ||
| Dental crowns material design is an urgent matter for dental manufacturers. Therefore, evaluating the composition and properties for implementing a decision-making model in materials design is a topical problem in the field of the design for manufacturing. The article aims to develop a supervised machine learning model for dental crowns material design. The proposed model is a function of two phases. The first phase that is an integration of two methods: FUZZY-ENTROPY and FUZZY-TOPSIS filters the submitted dataset and determines the most appropriate dental crowns material, and the second phase is a supervised machine learning model in which a filtered dataset that is a function of the material composition of zirconia(ZrO2) with different stabilizers at different sintering temperatures as inputs, and physical and mechanical properties of the different types of stabilized zirconia as outputs is fed into the model, trained using regression analysis and validated using mean average percentage error and root mean square error. The model can predict the required physical and mechanical properties in case of feeding the model with material composition and required sintering temperature(direct problem), and the model also can predict the required material composition in case of feeding the model with available physical and mechanical properties(inverse problem). Our model provides support and help for dental manufacturers to optimize dental crowns material. | ||
| Keywords | ||
| stabilized zirconia; materials Design; supervised machine learning | ||
|
Statistics Article View: 74 |
||
