DDCNN: A Promising Tool for Simulation-To-Reality UAV Fault Diagnosis

TL;DR

This paper introduces DDCNN, a deep learning model combined with domain adaptation techniques, to improve the accuracy of UAV propeller fault diagnosis from simulated training data to real-world applications.

Contribution

The paper proposes a novel difference-based deep convolutional neural network with a new domain adaptation method to significantly enhance sim-to-real UAV fault diagnosis accuracy.

Findings

Accuracy increased from 52.9% to 99.1% in real-world fault detection

Difference features reduce the sim-to-real gap effectively

Domain adaptation improves classifier performance in real flights

Abstract

Identifying the fault in propellers is important to keep quadrotors operating safely and efficiently. The simulation-to-reality (sim-to-real) UAV fault diagnosis methods provide a cost-effective and safe approach to detecting propeller faults. However, due to the gap between simulation and reality, classifiers trained with simulated data usually underperform in real flights. In this work, a novel difference-based deep convolutional neural network (DDCNN) model is presented to address the above issue. It uses the difference features extracted by deep convolutional neural networks to reduce the sim-to-real gap. Moreover, a new domain adaptation (DA) method is presented to further bring the distribution of the real-flight data closer to that of the simulation data. The experimental results demonstrate that the DDCNN+DA model can increase the accuracy from 52.9% to 99.1% in real-world UAV fault detection.