TF-C Pretrain FD-A

- Paper: Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency - Paper link: - Github repo: https://github.com/mims-harvard/TFC-pretraining - Project website: FD-A and FD-B are subsets taken from the FD dataset, which is gathered from an electromechanical drive system that monitors the condition of rolling bearings and detect damages in them. There are four subsets of data collected under various conditions, whose parameters include rotational speed, load torque, and radial force. Each rolling bearing can be undamaged, inner damaged, and outer damaged, which leads to three classes in total. We denote the subsets corresponding to condition A and condition B as Faulty Detection Condition A (FD-A) and Faulty Detection Condition B (FD-B) , respectively. Each original recording has a single channel with sampling frequency of 64k Hz and lasts 4 seconds. To deal with the long duration, we followe the procedure described by Eldele et al., that is, we use sliding window length of 5,120 observations and a shifting length of either 1,024 or 4,096 to make the final number of samples relatively balanced between classes.论文：《基于时频一致性的时间序列自监督对比预训练》，论文链接：无，GitHub仓库：https://github.com/mims-harvard/TFC-pretraining。FD-A与FD-B均为FD数据集的子集，该数据集采集自一套用于监测滚动轴承状态并检测其损伤的机电驱动系统。本次共采集了四种不同工况下的数据集，其采集参数包含转速、负载转矩与径向力。滚动轴承的健康状态可分为完好、内圈损伤与外圈损伤三类，总计三个类别。我们将工况A与工况B对应的子集分别记为故障检测工况A（Faulty Detection Condition A，FD-A）与故障检测工况B（Faulty Detection Condition B，FD-B）。每一段原始数据记录为单通道数据，采样频率为64 kHz，单段时长为4秒。为处理长时长数据，我们遵循Eldele等人提出的处理流程：采用长度为5120个观测值的滑动窗口，并将滑动步长设置为1024或4096，最终使各类别的样本数量相对均衡。