<![CDATA[The analysis of mechanical properties based on data is a method used to analyze the mechanical properties of a material using data, typically obtained from a material database. This process encounters several challenges, such as large volume of data, complexity in data processing, as well as difficulties in data visualization and interpretation. In this study, Pandas Profiling, a Python library designed specifically for automated dataset analysis, was employed. The dataset used consisted of tensile test results for various austenitic stainless steel types such as SUS 304, SUS 316, SUS 321, SUS 347, and NCF 800H. This dataset comprised 1916 samples with attributes related to mechanical properties and factors influencing them. The analysis results using Pandas Profiling indicated a strong negative correlation between heat treatment temperature and Yield Strength (YS) and Ultimate Tensile Strength (UTS). Additionally, a positive correlation was found between chemical elements such as Copper (Cu) and Nickel (Ni) with Elongation (EL). Furthermore, the analysis results revealed that stainless steel treated with water cooling exhibited a higher average UTS value, measuring at 493 MPa, compared to air cooling, which only reached 403 MPa. Pandas Profiling offers an effective solution to overcome common challenges in data-based mechanical property analysis, including dealing with large data volumes, complex data processing, as well as challenges in data visualization and interpretation. By utilizing Pandas Profiling, researchers can easily comprehend the dataset comprehensively, identify patterns, trends, and relationships among variables, and optimize the analysis process of data-based material mechanical properties.]]>
Copyrights © 2024
