This record has versions v1, v2, v3. This is version v1.
×

Recommended by

Indexed by

A deep learning dataset for metal multiaxial fatigue life prediction

Shuonan Chen1*, Yongtao Bai*2*, Xuhong Zhou*2*, Ao Yang1

1 School of Civil Engineering, Chongqing University, Chongqing 400045, China

2 Research Center of Steel Structure Engineering, Chongqing University, Chongqing 400045, China

* Corresponding authors emails: 441014578@qq.com, bai.yongtao@cqu.edu.cn, zhouxuhong@126.com
DOI10.24435/materialscloud:wt-98 [version v1]

Publication date: Jul 05, 2024

How to cite this record

Shuonan Chen, Yongtao Bai*, Xuhong Zhou*, Ao Yang, A deep learning dataset for metal multiaxial fatigue life prediction, Materials Cloud Archive 2024.105 (2024), https://doi.org/10.24435/materialscloud:wt-98

Description

In this work, we present a comprehensive dataset designed to facilitate the prediction of metal fatigue life using deep learning techniques. The dataset includes detailed experimental data from 40 different metallic materials, comprising a total of 1195 data points under 48 distinct loading paths. Each data point is stored in a CSV file, capturing the loading path as a time-series with axial and tangential stress or strain values.The primary purpose of this dataset is to support the development and validation of deep learning models aimed at accurately predicting the fatigue life of metals under various loading conditions. This dataset includes stress-controlled and strain-controlled data, ensuring a broad representation of experimental scenarios. Additionally, an Excel file accompanies the dataset, providing detailed mechanical properties of each material, such as elastic modulus, tensile strength, yield strength, and Poisson's ratio, along with references to the original experimental sources.This dataset is intended for researchers in materials science and mechanical engineering, offering a robust foundation for training and testing deep learning algorithms in fatigue analysis. By making this dataset publicly available, we aim to foster collaboration and further advancements in the field of metal fatigue prediction. Researchers are encouraged to utilize and contribute to the dataset, thereby enhancing its scope and applicability.

Materials Cloud sections using this data

No Explore or Discover sections associated with this archive record.

Files

File name Size Description
A Deep Learning Dataset for Metal Multiaxial Fatigue Life Prediction-revised.zip
MD5md5:7ddb60ded6aa21eeef71cb2194146d7e
1.8 MiB The compressed file contains two folders, two CSV files and one Excel files. "Specific Information of the Materials" provides detailed information on the collected materials. Two CSV files are intended for use with deep learning algorithms, with one corresponding to stress-controlled loading experiment samples and the other to strain-controlled samples. The specific loading paths for each sample are stored as time-series data in CSV files.

License

Files and data are licensed under the terms of the following license: Creative Commons Attribution 4.0 International.
Metadata, except for email addresses, are licensed under the Creative Commons Attribution Share-Alike 4.0 International license.

External references

Journal reference (Paper where the data is discussed)
Chen, S., Bai, Y., Zhou, X., Yang, A., Scientific Data, in preparation
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Website (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Doquet, V., & Pineau, A. In Third International Conference on Biaxial/Multiaxial Fatigue (pp. 81-101). MEP (1991)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)
Journal reference (Source of the collected data)

Keywords

Metal fatigue Multiaxial fatigue Deep learning Fatigue life prediction