Mengoptimalkan Analisis Sifat Mekanik Material Berbasis Data Dengan Pandas Profiling

Mengoptimalkan Analisis Sifat Mekanik Material Berbasis Data Dengan Pandas Profiling

Penulis

Desmarita Leni - Universita Muhammadiyah Sumatera Barat

Femi Earnestly - Universitas Muhammadiyah Sumatera Barat

Nike Angelia - Politeknik Negeri Padang

Elsa Nofriyanti - Politeknik Negeri Padang

Adriansyah Adriansyah - Politeknik Negeri Padang

DOI

doi

Kata Kunci

pandas profiling, sifat mekanik, visualisasi, data

Abstrak

Analisis sifat mekanik berbasis data adalah metode yang digunakan untuk menganalisis sifat mekanik suatu material menggunakan data, yang biasanya diperoleh dari basis data material. Proses ini menghadapi beberapa tantangan, seperti volume data yang besar, kompleksitas dalam pemrosesan data, serta kesulitan dalam visualisasi dan interpretasi data. Dalam penelitian ini, Pandas Profiling, sebuah pustaka Python yang dirancang khusus untuk analisis dataset secara otomatis, digunakan. Dataset yang digunakan terdiri dari hasil uji tarik untuk berbagai jenis baja tahan karat austenitik seperti SUS 304, SUS 316, SUS 321, SUS 347, dan NCF 800H. Dataset ini terdiri dari 1916 sampel dengan atribut yang berkaitan dengan sifat mekanik dan faktor-faktor yang memengaruhinya. Hasil analisis menggunakan Pandas Profiling menunjukkan korelasi negatif yang kuat antara suhu perlakuan panas dengan Kekuatan Luluh (YS) dan Kekuatan Tarik Maksimum (UTS). Selain itu, ditemukan korelasi positif antara unsur kimia seperti Tembaga (Cu) dan Nikel (Ni) dengan Elongasi (EL). Lebih lanjut, hasil analisis mengungkapkan bahwa baja tahan karat yang diberi perlakuan pendinginan air menunjukkan nilai UTS rata-rata yang lebih tinggi, yaitu 493 MPa, dibandingkan dengan pendinginan udara yang hanya mencapai 403 MPa. Pandas Profiling menawarkan solusi efektif untuk mengatasi tantangan umum dalam analisis sifat mekanik berbasis data, termasuk menangani volume data yang besar, pemrosesan data yang kompleks, serta tantangan dalam visualisasi dan interpretasi data. Dengan memanfaatkan Pandas Profiling, peneliti dapat dengan mudah memahami dataset secara komprehensif, mengidentifikasi pola, tren, dan hubungan antar variabel, serta mengoptimalkan proses analisis sifat mekanik material berbasis data.

Referensi

• J. Jung et al., “Super-resolving material microstructure image via deep learning for microstructure characterization and mechanical behavior analysis,” Npj Comput. Mater., vol. 7, no. 1, p. 96, Jun. 2021, doi: 10.1038/s41524-021-00568-8.
• F. Chen, J Z., “An intelligent online detection approach based on big data for mechanical properties of hot-rolled strip,” Int. J. Model. Identif. Control, vol. 37, no. 2, pp. 106–112.
• A. Agrawal and A. Choudhary, “Perspective: Materials informatics and big data: Realization of the ‘fourth paradigm’ of science in materials science,” APL Mater., vol. 4, no. 5, p. 053208, May 2016, doi: 10.1063/1.4946894.
• D. Merayo, A. Rodriguez-Prieto, and A. M. Camacho, “Prediction of Physical and Mechanical Properties for Metallic Materials Selection Using Big Data and Artificial Neural Networks,” IEEE Access, vol. 8, pp. 13444–13456, 2020, doi: 10.1109/ACCESS.2020.2965769.
• D. Leni, F. Earnestly, R. Sumiati, A. Adriansyah, and Y. P. Kusuma, “Evaluasi sifat mekanik baja paduan rendah bedasarkan komposisi kimia dan suhu perlakuan panas menggunakan teknik exploratory data analysis (EDA),” Din. Tek. Mesin, vol. 13, no. 1, p. 74, Apr. 2023, doi: 10.29303/dtm.v13i1.624.
• F. Khodabakhshi, F M. H., Nosko, M Gerlich, A. P., Trembošová, V, and Khajepour, A., “Effects of laser additive manufacturing on microstructure and crystallographic texture of austenitic and martensitic stainless steels.,” Addit. Manuf., vol. 31, p. 100915.
• E. A. Trillo and L. E. Murr, “Effects of carbon content, deformation, and interfacial energetics on carbide precipitation and corrosion sensitization in 304 stainless steel,” Acta Mater., vol. 47, no. 1, pp. 235–245, Dec. 1998, doi: 10.1016/S1359-6454(98)00322-X.
• H. Jirková, L. Kučerová, and B. Mašek, “The Effect of Chromium on Microstructure Development During Q-P Process,” Mater. Today Proc., vol. 2, pp. S627–S630, 2015, doi: 10.1016/j.2015.07.362.
• S. Dean, M. Martins, and L. Casteletti, “Effect of Heat Treatment on the Mechanical Properties of ASTM A 890 Gr6A Super Duplex Stainless Steel,” J. ASTM Int., vol. 2, no. 1, p. 13037, 2005, doi: 10.1520/JAI13037.
• Yang, H., “Data preprocessing,” 3rd edlvania State University:Citeseer.
• P. Mishra, A. Biancolillo, J. M. Roger, F. Marini, and D. N. Rutledge, “New data preprocessing trends based on ensemble of multiple preprocessing techniques,” TrAC Trends Anal. Chem., vol. 132, p. 116045, Nov. 2020, doi: 10.1016/j.2020.116045.
• D. Leni, “Pemilihan Algoritma Machine Learning Yang Optimal Untuk Prediksi Sifat Mekanik Aluminium.,” J. Engine Energi Manufaktur Dan Mater., vol. 7, no. 1, pp. 35–44, 2023.
• J. D. Romano et al., “PMLB v1.0: an open-source dataset collection for benchmarking machine learning methods,” Bioinformatics, vol. 38, no. 3, pp. 878–880, Jan. 2022, doi: 10.1093/bioinformatics/btab727.
• B. Gordon et al., “Evaluation of freely available data profiling tools for health data research application: a functional evaluation review,” BMJ Open, vol. 12, no. 5, p. e054186, May 2022, doi: 10.1136/bmjopen-2021-054186.
• D. Leni, Y. P. Kusuma, M. Muchlisinalahuddin, R. Sumiati, and H. C. Mayana, “THE IMPLEMENTATION OF PANDAS PROFILING AS A TOOL FOR ANALYZING MECHANICAL PROPERTIES DATA OF NICKEL-BASED SUPERALLOYS BASED ON ALLOY CHEMICAL COMPOSITION,” Int. J. Innov. Mech. Eng. Adv. Mater., vol. 4, no. 3, p. 86, May 2023, doi: 10.22441/ijimeam.v4i3.19439.
• A. F. G. Cabral, Data Profiling in Cloud Migration: Data Quality Measures While Migrating Data from a Data Warehouse to the Google Cloud Platform (Doctoral dissertation. Universidade Nova de Lisboa, 2021.
• M. Elansary, “Data wrangling & preparation automation. Why should you lose 80% of your time in one task?,” 2021, doi: 10.13140/RG.2.2.13981.03047.
• Swedberg, R. (2020), Exploratory research. The production of knowledge, Enhancing progress in social science. Cambridge University.
• S. L. Siedlecki, “Understanding Descriptive Research Designs and Methods,” Clin. Nurse Spec., vol. 34, no. 1, pp. 8–12, Jan. 2020, doi: 10.1097/NUR.0000000000000493.
• British Steelmakers Creep Committee, BSCC High Temperature Data: British Long Term Creep Rupture and Elevated Temperature Tensile Data on Steels for High Temperature Service, vol. 56. Iron and Steel Institute for the British Steelmakers Creep Committee, 1974.
• “Materials Algorithms Project Materials Data Library.”
• D. Leni and R. Sumiati, “Perbandingan Alogaritma Machine Learning Untuk Prediksi Sifat Mekanik Pada Baja Paduan Rendah.,” J. Rekayasa Mater. Manufaktur Dan Energi, vol. 5, no. 2, pp. 167–174.
• J. Adler and I. Parmryd, “Quantifying colocalization by correlation: The Pearson correlation coefficient is superior to the Mander’s overlap coefficient,” Cytometry A, vol. 77A, no. 8, pp. 733–742, Mar. 2010, doi: 10.1002/cyto.a.20896.
• S. Zhang et al., “Precipitation behavior and phase transformation mechanism of super austenitic stainless steel S32654 during isothermal aging,” Mater. Charact., vol. 137, pp. 244–255, Mar. 2018, doi: 10.1016/jr.2018.01.040.
• F. M. Moniruzzaman et al., “Study of direct aging heat treatment of additively manufactured PH13–8Mo stainless steel: role of the manufacturing process, phase transformation kinetics, and microstructure evolution,” J. Mater. Res. Technol., vol. 24, pp. 3772–3787, May 2023, doi: 10.1016/j.2023.04.023.
• M. C. Niu, K. Yang, J. H. Luan, W. Wang, and Z. B. Jiao, “Cu-assisted austenite reversion and enhanced TRIP effect in maraging stainless steels,” J. Mater. Sci. Technol., vol. 104, pp. 52–58, Mar. 2022, doi: 10.1016/j.2021.06.055.
• W. Bleck, X. Guo, and Y. Ma, “The TRIP Effect and Its Application in Cold Formable Sheet Steels: The TRIP Effect and Its Application in Cold Formable,” Steel Res. Int., vol. 88, no. 10, p. 1700218, Oct. 2017, doi: 10.1002/srin.201700218.
• M. Bayerlein, H.-J. Christ, and H. Mughrabi, “Plasticity-induced martensitic transformation during cyclic deformation of AISI 304L stainless steel,” Mater. Sci. Eng. A, vol. 114, pp. L11–L16, Jul. 1989, doi: 10.1016/0921-5093(89)90871-X.
• D. Kong et al., “About metastable cellular structure in additively manufactured austenitic stainless steels,” Addit. Manuf., vol. 38, p. 101804, Feb. 2021, doi: 10.1016/j.2020.101804.
• M. E. R. Cronemberger et al., “Study of Cooling Rate Influence on SAF 2205 Duplex Stainless Steel Solution Annealed,” Mater. Sci. Forum, vol. 802, pp. 398–403, Dec. 2014, doi: 10.4028/scientific