On-board Health-state Awareness to Detect Degradation in Multirotor Systems

This paper presents the development and demonstration of an on-board health-state awareness technology that can predict degradation over the dynamic operational life of the vehicle. We established the feasibility of replacing the standard electronic speed control on a small UAV with an Intelligent Electronic Speed Control (IESC) that uses the telemetry data from sensors to develop an intelligent rule set extracted from a trained artificial neural network to detect propulsion system degradation, predict specific types of failures by analyzing sensor data collected from the motor and ESC, and access life cycle characteristics for a UAV propulsion system. The IESC will improve performance and reliability, increase safety and decrease maintenance costs by detecting issues prior to flight. The long term goal of the project is to be able to predict failures across families of small UAV based upon historic performance data that can be shared among users.

[1]  Cezary Kownacki,et al.  Optimization approach to adapt Kalman filters for the real-time application of accelerometer and gyroscope signals' filtering , 2011, Digit. Signal Process..

[2]  Y. Ueno,et al.  Prediction of spalling on a ball bearing by applying the discrete wavelet transform to vibration signals , 1996 .

[3]  Brian J. Taylor,et al.  Rule Extraction From Dynamic Cell Structure Neural Network Used in a Safety Critical Application , 2004, FLAIRS.

[4]  Luis Eduardo Mujica,et al.  Damage classification in structural health monitoring using principal component analysis and self‐organizing maps , 2013 .

[5]  Bernd Fritzke,et al.  Growing cell structures--A self-organizing network for unsupervised and supervised learning , 1994, Neural Networks.

[6]  Tao Han,et al.  ART–KOHONEN neural network for fault diagnosis of rotating machinery , 2004 .

[7]  K. I. Ramachandran,et al.  Incipient gear box fault diagnosis using discrete wavelet transform (DWT) for feature extraction and classification using artificial neural network (ANN) , 2010, Expert Syst. Appl..

[8]  B. Samanta,et al.  ARTIFICIAL NEURAL NETWORK BASED FAULT DIAGNOSTICS OF ROLLING ELEMENT BEARINGS USING TIME-DOMAIN FEATURES , 2003 .

[9]  Gerald Sommer,et al.  Dynamic Cell Structures , 1994, NIPS.

[10]  Laura L. Pullum,et al.  Guidance for the Verification and Validation of Neural Networks: Pullum/Guidance for the Verification and Validation of Neural Networks , 2015 .

[11]  Thomas I. Strasser,et al.  Artificial neural networks for fault detection in large-scale data acquisition systems , 2004, Eng. Appl. Artif. Intell..

[12]  Ian Postlethwaite,et al.  Sensor fault detection and accommodation using neural networks with application to a non-linear unmanned air vehicle model , 2010 .

[13]  Brian J. Taylor,et al.  Rule Extraction as a Formal Method , 2006 .

[14]  Brian J. Taylor,et al.  Methods and Procedures for the Verification and Validation of Artificial Neural Networks , 2005 .

[15]  T. Martínez,et al.  Competitive Hebbian Learning Rule Forms Perfectly Topology Preserving Maps , 1993 .