An Informatic Approach to Predict the Mechanical Properties of Aluminum Alloys using Machine Learning Techniques
| Autor: | C.P.S. Prakash, M Aruna Devi, Venugopal Prasanna Joshi, Rahul Pandappa Chinnannavar, Ravut Dixit, Rohit Shankar Palada |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Artificial neural network
business.industry Computer science chemistry.chemical_element Machine learning computer.software_genre GeneralLiterature_MISCELLANEOUS k-nearest neighbors algorithm Condensed Matter::Materials Science chemistry Aluminium Ultimate tensile strength Linear regression Artificial intelligence business computer Energy (signal processing) |
| Zdroj: | 2020 International Conference on Smart Electronics and Communication (ICOSEC). |
| DOI: | 10.1109/icosec49089.2020.9215277 |
| Popis: | One of the major problems faced by the industries during the manufacturing of aluminum components is by achieving the required properties of aluminum alloys. Lot of time and energy is involved in the expeimentation and testing of properties of new aluminum alloys. It leads to wastage of many resources and even sometimes ends up with no results. This paper presents an algorithm for prediction of mechanical properties of aluminum alloys using different machine learning techniques such as linear regression (LR), artificial neural network (ANN), and k-nearest neighbor (KNN) algoithm. In this paper, KNN algorithm gives a better prediction of tensile strength and hardness values. In yield strength predictions, ANN gives the better and accurate results compared to other two algorithms. More amount of energy and time is saved using machine learning techniques. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|