Autonomous Underwater Vehicle Fault Diagnosis Dataset

The dataset contains 1225 data samples for 5 \textit{fault types} (labels). We divided the dataset into the training set and the test set through random stratified sampling. The test set accounted for $20\%$ of the total dataset. Our experimental subject is `Haizhe', which is a small quadrotor AUV developed in the laboratory. For each \textit{fault type}, `Haizhe' was tested several times. For each time, `Haizhe' ran the same program and sailed underwater for 10-20 seconds to ensure that \textit{state data} was long enough. The \textit{state data} recorded in each test were then used as a data sample, and the corresponding \textit{fault type} was the true label of the data sample. The dataset was used to validate a model-free fault diagnosis method proposed in our paper published in Ocean Engineering（Model-free fault diagnosis for autonomous underwater vehicles using sequence convolutional neural network, Ocean Engineering. 232(2021)108874. https://doi.org/10.1016/j.oceaneng.2021.108874）.

本数据集包含1225个数据样本，针对5种故障类型（标签）进行划分。通过随机分层抽样，将数据集分为训练集与测试集，其中测试集占总数据集的20%。本实验对象为实验室自主研发的小型四旋翼无人水下航行器‘Haizhe’。针对每种故障类型，对‘Haizhe’进行了多次测试。每次测试中，‘Haizhe’执行相同的程序，在水下航行10-20秒以确保状态数据足够长。随后，在每次测试中记录的状态数据被用作数据样本，相应的故障类型即为数据样本的真实标签。该数据集被用于验证我们在《海洋工程》杂志上发表的论文中提出的无模型故障诊断方法（《基于序列卷积神经网络的自主水下航行器无模型故障诊断》，Ocean Engineering，2021年第232卷，第108874号。https://doi.org/10.1016/j.oceaneng.2021.108874）。

搜集汇总

背景与挑战

背景概述

该数据集包含1225个样本，涵盖5种故障类型，用于自主水下航行器(AUV)的故障诊断研究。数据来源于实验室开发的'Haizhe'四旋翼AUV的多次实验，并已划分为训练集和测试集，支持无模型故障诊断方法的验证。