{
  "fetched_at": "2026-10-19T15:02:35Z",
  "source_url": "https://www.kaggle.com/competitions/gem-predictive-maintenance-2022/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The dataset consists of different multivariate time-series. These different time-series refers to different engine ('engine_no' in the dataset). The sampling of the time series is 1 point per engine cycle ('time_in_cycles' in the dataset).\n\nThe time-series contain some operational features and some sensor features (explicitly mentionned in the header).\n\n\nREADME:\n\n\nData Set: FD001\nTrain trajectories: 100\nTest trajectories: 100\nConditions: ONE (Sea Level)\nFault Modes: ONE (HPC Degradation)\n\nData Set: FD002\nTrain trajectories: 260\nTest trajectories: 259\nConditions: SIX \nFault Modes: ONE (HPC Degradation)\n\nData Set: FD003\nTrain trajectories: 100\nTest trajectories: 100\nConditions: ONE (Sea Level)\nFault Modes: TWO (HPC Degradation, Fan Degradation)\n\nData Set: FD004\nTrain trajectories: 248\nTest trajectories: 249\nConditions: SIX \nFault Modes: TWO (HPC Degradation, Fan Degradation)\n\n\n\nExperimental Scenario\n\nData sets consists of multiple multivariate time series. Each data set is further divided into training and test subsets. Each time series is from a different engine � i.e., the data can be considered to be from a fleet of engines of the same type. Each engine starts with different degrees of initial wear and manufacturing variation which is unknown to the user. This wear and variation is considered normal, i.e., it is not considered a fault condition. There are three operational settings that have a substantial effect on engine performance. These settings are also included in the data. The data is contaminated with sensor noise.\n\nThe engine is operating normally at the start of each time series, and develops a fault at some point during the series. In the training set, the fault grows in magnitude until system failure. In the test set, the time series ends some time prior to system failure. The objective of the competition is to predict the number of remaining operational cycles before failure in the test set, i.e., the number of operational cycles after the last cycle that the engine will continue to operate. Also provided a vector of true Remaining Useful Life (RUL) values for the test data.\n\n The columns correspond to:\n1)\tunit number\n2)\ttime, in cycles\n3)\toperational setting 1\n4)\toperational setting 2\n5)\toperational setting 3\n6)\tsensor measurement  1\n7)\tsensor measurement  2\n...\n26)\tsensor measurement  26\n\n\nReference: A. Saxena, K. Goebel, D. Simon, and N. Eklund, �Damage Propagation Modeling for Aircraft Engine Run-to-Failure Simulation�, in the Proceedings of the Ist International Conference on Prognostics and Health Management (PHM08), Denver CO, Oct 2008.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## Aim of the challenge\n\nThe goal of this challenge is to predict the RUL (Remaining Useful Life) of turbofan engines.\n\nThe dataset consists of different multivariate time-series. These different time-series refer to different engines ( engineno in the dataset). The sampling of the time series is 1 point per engine cycle  timein_cycles in the dataset).\n\nThe dataset is split into train data and test data to evaluate your model.\n\nIn the train dataset: the engine runs until failure. It means that for each data point we can associate the RUL (Remaining Useful Life in cycles). This column is present in the train dataset (RUL).\n\nIn the test dataset: The engine runs until a certain point. What you need to predict is the RUL at the last point of the dataset.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "You will give a submission file containing one column:\n\nresult : containing the RUL of engine #i (where i is the line number)\n\nThe evaluation will be based on the RMSE. https://en.wikipedia.org/wiki/Root-mean-square_deviation",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}