Skip to main content
Government

NASA C-MAPSS Turbofan Engine Degradation — 4 Sub-datasets, 21 Sensors [Run-to-Failure]

Industrial IoT
1 views
2 min read

Abstract

"NASA Prognostics Center run-to-failure simulation dataset for turbofan engines. Four operational sub-datasets with 21 sensor channels and 3 operational settings. TXT/CSV format. Primary benchmark for Remaining Useful Life (RUL) estimation."

Description

Overview

The C-MAPSS (Commercial Modular Aero-Propulsion System Simulation) Turbofan Engine Degradation Simulation Dataset is one of the most widely used public benchmarks in industrial predictive maintenance. Released by the NASA Ames Prognostics Center of Excellence (PCoE), it simulates run-to-failure degradation trajectories for fleets of turbofan jet engines under varying operational conditions and fault modes.

The dataset is divided into four sub-challenges (FD001–FD004) of increasing complexity, reflecting one or two fault modes and one or six operational conditions per challenge. In the training set, engines run from normal operation to failure. In the test set, the time series ends at some point before failure, and the goal is to predict the Remaining Useful Life (RUL) for each engine unit.

Each record captures 21 sensor readings including fan inlet temperature, LPC outlet temperature, HPC outlet temperature, LPC outlet pressure, physical fan speed, corrected fan speed, bypass ratio, and bleed enthalpy, among others. C-MAPSS remains the standard RUL benchmark in industrial IoT, deep learning, and prognostics research.

Column Schema

ColumnDescription
unit_idEngine unit number identifier.
time_cyclesOperational time in engine cycles.
op_setting_1Operational setting 1 (one of 3 settings).
op_setting_2Operational setting 2.
op_setting_3Operational setting 3.
sensor_1 … sensor_2121 sensor measurement channels (temperature, pressure, speed, etc.).
RULRemaining Useful Life label (provided in separate RUL file for test set).

Key Statistics

  • Sub-datasets: FD001, FD002, FD003, FD004
  • Features: 26 columns (unit ID, time, 3 op settings, 21 sensors)
  • Fault Modes: 1 or 2 per sub-dataset
  • Operational Conditions: 1 or 6 per sub-dataset
  • File Format: TXT (space-delimited, CSV-compatible)
  • Time Period: Released 2008

Use Cases

  • Remaining Useful Life (RUL) estimation and prognostics modelling
  • Deep learning benchmarking with LSTM, CNN, Transformer architectures
  • Anomaly detection and fault mode classification in industrial engines
  • Transfer learning across operational conditions for IIoT systems

Source & Attribution

Created by Abhinav Saxena and Kai Goebel at the NASA Ames Prognostics Center of Excellence. The dataset is hosted on NASA's Open Data Portal and also mirrored on Zenodo. It is cited in thousands of prognostics and health management publications worldwide.

View Data Structure

To explore column names, data types, and sample rows, visit the official dataset page on Government.

Preview on Government

Cite This Dataset

Saxena, Abhinav, & Goebel, Kai (2008). NASA C-MAPSS Turbofan Engine Degradation — 4 Sub-datasets, 21 Sensors [Run-to-Failure]. [Dataset]. NASA Ames Prognostics Center of Excellence / NASA Open Data Portal. https://data.nasa.gov/dataset/cmapss-jet-engine-simulated-data

Source: NASA Ames Prognostics Center of Excellence / NASA Open Data Portal (2008)

Indexed by IoTDataset.com on Apr 10, 2026

Ready to Start Your Research?

Download this dataset directly from the official repository and start building your next breakthrough project.

Download Dataset

Related Topics & Keywords

Share This Research

More in Industrial IoT

View All
Industrial IoT University

CWRU Bearing Fault Dataset — 2HP Motor Vibration, 4 Fault Diameters [12k & 48k Hz]

Benchmark bearing vibration dataset from Case Western Reserve University with drive-end and fan-end faults at 4 severity levels. Sampled at 12 kHz and 48 kHz. MATLAB MAT and CSV formats. Used for fault diagnosis and vibration-based condition monitoring.

Apr 10, 2026
Industrial IoT UCI

AI4I 2020 Predictive Maintenance — Milling Machine Sensor Failures [10,000 Records]

Synthetic IIoT dataset reflecting real milling machine predictive maintenance scenarios. 10,000 records with 14 features including air temperature, process temperature, rotational speed, torque, and 5 labeled failure types. CSV format. Ideal for multi-label fault classification.

Apr 10, 2026
Industrial IoT Kaggle

Bosch Production Line Performance — Assembly Line Fault Detection [1.18M Parts]

One of Kaggle's largest IIoT manufacturing datasets with 1.18 million parts measured across Bosch's assembly lines. Thousands of anonymized sensor features split across numeric, categorical, and date files. CSV format. Used for quality control and failure prediction.

Apr 10, 2026
Industrial IoT Research Paper

IIoT Metalworking Fluid Degradation — Real-World Physicochemical Sensor Monitoring [Multi-Month]

Real-world IIoT multivariate time series dataset tracking physicochemical degradation of metalworking fluid over several months. Includes imputed benchmark variants for 5 methods. CSV format. Designed for predictive maintenance and anomaly detection research in manufacturing.

Apr 10, 2026