Fault isolation of reaction wheels onboard three-axis controlled in-orbit satellite using ensemble machine learning

Abstract

The primary objective of this study is to explore novel applications of data-driven machine learning methods for isolation of nonlinear systems with a case study for an in-orbit closed-loop controlled satellite with reaction wheels as actuators. Highfidelity models of the three-axis controlled satellite are developed to provide an abundance of data for both healthy and various faulty conditions of the satellite. These data are then used as input for the proposed data-driven fault isolation method. Once a fault is detected, the fault isolation module is activated, where it employs a machine learning technique that incorporates ensemble methods involving random forests, decision trees, and nearest neighbors. Results of the classified faulty condition are then cross-validated using k-fold and leave-one-out methods. Performance comparison among different combinations for the ensemble architecture shows promising fault isolation of the non-linear systems using ensemble methods.

A Reliable Deep Learning Approach for Time-Varying Faults Identification: Spacecraft Reaction Wheel Case Study

“…However, to reach a high accuracy using these approaches at different inception times, the network designer has to use a huge dataset and a complex network design. The proposed methodology is compared also with a machine learning approach that is introduced in [29]. The former technique can classify reaction wheel faults with an accuracy of only ~59% which isn't accepted for space applications.…”

“…In recent years, many studies were proposed for spacecraft Reaction Wheel (RW) fault diagnosis [11]- [29]. For instance, in [11] E. Sobhani et al utilized a group of neural parameter estimators for nonlinear fault detection, isolation, and identification with application to spacecraft reaction wheel.…”

A high accuracy modeling scheme for dynamic systems: spacecraft reaction wheel model

“…In spacecraft missions that need a high pointing accuracy, Attitude Control Subsystem (ACS) with specific actuators shall be used. The reaction wheel (RW) is a vital actuator for the spacecraft ACS [1]. The accurate modeling of the spacecraft reaction wheel is recommended for the design, simulation, analysis, and fault identification applications.…”