Machine Fault Diagnosis

The dataset consists of sensor readings from bearing machines under four different operating conditions. Each of these conditions has three classes: healthy, inner-bearing damage, and outer-bearing damage. The operating conditions refer to different values for rotational speed, load torque, and radial force. In our experiments, each operating condition is treated as a separate domain. This allows us to perform 12 cross-condition scenarios for domain adaptation. To create the data samples for each domain, we used a sliding window technique to divide the data into smaller segments. The window size was set to 5120, with a shift of 4096本数据集包含四种不同运行工况下轴承设备的传感器读数。每种工况下设三个类别：健康状态、轴承内圈损伤以及轴承外圈损伤。所述运行工况指转速、负载转矩与径向载荷的不同参数组合。在本实验中，每种运行工况均被视作独立的域。这使得我们可以开展12种跨工况域自适应实验场景。为生成各域的数据样本，我们采用滑动窗口技术将原始数据划分为若干短片段，窗口大小设为5120，步长设为4096。

搜集汇总

背景与挑战

背景概述

Machine Fault Diagnosis数据集是一个用于机器故障诊断的公开数据集，发布于2022年。它包含轴承机器在四种不同运行条件下的传感器读数，每种条件分为健康、内轴承损坏和外轴承损坏三个类别，适用于领域适应研究，支持12种跨条件场景。数据通过滑动窗口技术预处理，窗口大小为5120，偏移为4096，旨在促进时间序列数据上的深度学习模型开发和评估。