RflyMAD: A Dataset for Multicopter Fault Detection and Health Assessment

TL;DR

RflyMAD addresses the scarcity of multicopter fault data by delivering a comprehensive, open-source collection that combines SIL/HIL simulation data from the RflySim platform with real-flight recordings. It spans 11 simulated fault types across 6 flight statuses and 7 real-flight faults across 5 statuses, totaling 5629 flight cases (~114.6 GB) with rich per-flight data streams (TestInfo, ULog, Telemetry, GTData/BAG). The authors validate sim-to-real relationships via transfer learning and domain adaptation, demonstrating that high-quality simulation data can substantially support fault diagnosis when complemented with limited real data. The dataset is designed for extensibility through OpenHA and RflySim, enabling ongoing addition of faults, scenarios, and data modalities to advance multicopter FDI and health assessment research.

Abstract

This paper presents an open-source dataset RflyMAD, a Multicopter Abnomal Dataset developed by Reliable Flight Control (Rfly) Group aiming to promote the development of research fields like fault detection and isolation (FDI) or health assessment (HA). The entire 114 GB dataset includes 11 types of faults under 6 flight statuses which are adapted from ADS-33 file to cover more occasions in which the multicopters have different mobility levels when faults occur. In the total 5629 flight cases, the fault time is up to 3283 minutes, and there are 2566 cases for software-in-the-loop (SIL) simulation, 2566 cases for hardware-in-the-loop (HIL) simulation and 497 cases for real flight. As it contains simulation data based on RflySim and real flight data, it is possible to improve the quantity while increasing the data quality. In each case, there are ULog, Telemetry log, Flight information and processed files for researchers to use and check. The RflyMAD dataset could be used as a benchmark for fault diagnosis methods and the support relationship between simulation data and real flight is verified through transfer learning methods. More methods as a baseline will be presented in the future, and RflyMAD will be updated with more data and types. In addition, the dataset and related toolkit can be accessed through https://rfly-openha.github.io/documents/4_resources/dataset.html.

Figures (6)

• Figure 1: RflyMAD hierarchy.
• Figure 2: Methods to collect simulation data.
• Figure 3: Quadcopters used in real flight.
• Figure 4: Trajectory of one flight in experiments
• Figure 5: Methods to collect real flight data.