DATASET FOR FAULT CLASSIFICATION IN ROCK DRILLS (PHM2022 Data)

The training data consists of data from various faults from five individual configurations, while the testing data is blind and is from one individual configuration of the rock drill. A final validation data set will be from two individual configurations from the rock drill and the labels are blind. The training data set contains data from 11 different fault classification categories, in which 10 are different failure modes and one class is from the healthy/no fault condition. Each file follows the naming convention of data_{sensor}{individual impact cycle number}.csv.For each CSV file that is provided, the first column is the label for that cycle, in which a label of 1 represents the no-fault condition, a label of 2-11 correspond to different fault types. A label of 0, which is present for the testing data for the online leaderboard and the final validation data set, indicate an unknown/blind label, in which the objective is to predict the label for each cycle. The columns of data after the label represent the pressure signal data for that cycle.

该训练数据集由五个独立配置的多种故障数据构成，而测试数据则完全盲测，源自岩石钻探的单个配置。最终的验证数据集将来源于岩石钻探的两个独立配置，且标签同样处于盲测状态。训练数据集包含11个不同的故障分类类别，其中10个代表不同的故障模式，剩下一个类别则代表健康/无故障状态。每个文件均遵循数据_{传感器}{单个冲击循环编号}.csv的命名规范。对于每个提供的CSV文件，第一列是该循环的标签，其中标签1表示无故障状态，标签2至11对应不同的故障类型。标签0，存在于在线排行榜的测试数据和最终验证数据集中，表示未知/盲标签，其目标是预测每个循环的标签。标签之后的数据列代表该循环的压力信号数据。