Neural Network-based Fault Detection and Identification for Quadrotors using Dynamic Symmetry

TL;DR

This paper introduces a novel model-free neural network framework using LSTM for fault detection and isolation in quadrotors, leveraging symmetry to identify faults efficiently without system models.

Contribution

It develops a symmetry-based, model-free LSTM neural network approach for fault detection in quadrotors, capable of identifying partial and complete faults with high accuracy.

Findings

Over 90% fault prediction accuracy.

Performs comparably to model-based methods.

Robust to uncertainties and data shifts.

Abstract

Autonomous robotic systems, such as quadrotors, are susceptible to actuator faults, and for the safe operation of such systems, timely detection and isolation of these faults is essential. Neural networks can be used for verification of actuator performance via online actuator fault detection with high accuracy. In this paper, we develop a novel model-free fault detection and isolation (FDI) framework for quadrotor systems using long-short-term memory (LSTM) neural network architecture. The proposed framework only uses system output data and the commanded control input and requires no knowledge of the system model. Utilizing the symmetry in quadrotor dynamics, we train the FDI for fault in just one of the motors (e.g., motor $\# 2$), and the trained FDI can predict faults in any of the motors. This reduction in search space enables us to design an FDI for partial fault as well as complete fault scenarios. Numerical experiments illustrate that the proposed NN-FDI correctly verifies the actuator performance and identifies partial as well as complete faults with over $90\%$ prediction accuracy. We also illustrate that model-free NN-FDI performs at par with model-based FDI, and is robust to model uncertainties as well as distribution shifts in input data.