Cu-Ni-Si Alloys Properties Dataset

This comprehensive dataset is specifically designed for the exploration of mechanical properties and electrical conductivity in Cu-Ni-Si alloys, offering detailed insights into chemical compositions, thermo-mechanical processing variables, and their impacts on alloy properties. The collection provides an extensive foundation for understanding and analyzing how various factors influence the performance and characteristics of Cu-Ni-Si alloys. The dataset was curated to facilitate the development and validation of a predictive Hybrid Deep Learning (DL) and Ensemble Learning (EL) model that aims to fill the research gaps in the current understanding of Cu-Ni-Si alloys. It includes data on alloy compositions, processing conditions, and the resultant electrical and mechanical characteristics. The unique combination of DL and EL techniques provides a robust framework for predicting alloy behavior, which is demonstrated through superior predictive performance, showcased by near-perfect R2 values for both training and test datasets. Moreover, for those looking to incorporate machine learning techniques into materials science, this dataset provides a unique opportunity to delve into the complex interplay between alloy composition, processing, and resultant properties. By offering a granular look at these relationships, the dataset opens up new avenues for innovation and research in material science and engineering. The file "Cu-Ni-Si-alloys.xlsx" contains a detailed dataset on various properties of copper-nickel-silicon (Cu-Ni-Si) alloys. It includes columns for the composition of these alloys in terms of percentages of copper (Cu), aluminum (Al), cobalt (Co), chromium (Cr), magnesium (Mg), nickel (Ni), silicon (Si), tin (Sn), and zinc (Zn). Additionally, it provides data on their solid solution strengthening temperature (Tss in K), aging temperature and time, as well as their mechanical and electrical properties such as hardness (HV), yield strength (MPa), ultimate tensile strength (MPa), and electrical conductivity (%IACS). Each entry also includes a DOI link to its source and references for further reading. The dataset presented herein is extracted from the comprehensive collection of data on the mechanical properties and electrical conductivity of copper-based alloys curated by Gorsse, Stephane; Gouné, Mohamed; LIN, Wei-Chih; Girard, Lionel (2023) titled "Dataset of mechanical properties and electrical conductivity of copper-based alloys" available on figshare (Collection, DOI: https://doi.org/10.6084/m9.figshare.c.6475600.v1).本综合数据集专为探究铜镍硅（Cu-Ni-Si）合金的力学性能与导电率而构建，可详细展现合金的化学成分、热机械加工参数及其对合金性能的影响。本数据集为理解与分析各类因素如何影响铜镍硅合金的性能与特征提供了扎实的研究基础。 本数据集经精心整理，旨在助力开发并验证一款混合深度学习（Hybrid Deep Learning, DL）与集成学习（Ensemble Learning, EL）预测模型，以填补当前对铜镍硅合金认知中的研究空白。数据集涵盖合金成分、加工条件以及由此产生的电学与力学性能相关数据。深度学习与集成学习的独特结合构建了一套鲁棒的合金行为预测框架，其优异的预测性能已通过训练集与测试集均接近完美的R²值得到验证。 此外，对于希望将机器学习技术融入材料科学领域的研究者而言，本数据集为深入探究合金成分、加工工艺与最终性能之间的复杂相互作用提供了绝佳契机。通过细致展现这些关联关系，本数据集为材料科学与工程领域的创新与研究开辟了全新路径。 文件"Cu-Ni-Si-alloys.xlsx"包含一套关于铜镍硅（Cu-Ni-Si）合金各项性能的详细数据集。数据集列有该类合金的化学成分占比，涵盖铜（Cu）、铝（Al）、钴（Co）、铬（Cr）、镁（Mg）、镍（Ni）、硅（Si）、锡（Sn）以及锌（Zn）。此外，数据集还包含其固溶强化温度（Tss，单位：开尔文）、时效温度与时效时间，以及硬度（HV）、屈服强度（MPa）、抗拉强度（MPa）和导电率（%IACS）等力学与电学性能数据。每条数据条目还附带来源的DOI链接与可供进一步研读的参考文献。 本文所呈现的数据集，源自Gorsse, Stephane、Gouné, Mohamed、LIN, Wei-Chih、Girard, Lionel（2023）整理的铜基合金力学性能与导电率综合数据集，该数据集题为"Dataset of mechanical properties and electrical conductivity of copper-based alloys"，可在figshare平台获取（数据集合集，DOI：https://doi.org/10.6084/m9.figshare.c.6475600.v1）。