Abstract
Timely detection and treatment of possible incipient faults in satellites will effectively reduce the damage and harm they could cause. Although much work has been done concerning fault detection problems, the related questions about satellite incipient faults are little addressed. In this paper, a new satellite incipient fault detection method was proposed by combining the ideas of deviation in unsupervised fault detection methods and classification in supervised fault detection methods. First, the proposed method uses dynamic linear discriminant analysis (LDA) to find an optimal projection vector that separates the in-orbit data from the normal historical data as much as possible. Second, under the assumption that the parameters obey a multidimensional Gaussian distribution, it applies the normal historical data and the optimal projection vector to build a normal model. Finally, it employs the noncentral F-distribution to test whether a fault has occurred. The proposed method was validated using a numerical simulation case and a real satellite fault case. The results show that the method proposed in this paper is more effective at detecting incipient faults than traditional methods.
Highlights
With the reduction in the costs of launching rockets and manufacturing satellites, the number of satellites operating in orbit increases annually, bringing large economic benefits to society [1,2,3]
Based on the existing research, this paper proposes a new satellite incipient fault detection method that combines the ideas of deviation in unsupervised fault detection methods and classification in supervised fault detection methods. e main contributions of our work are summarized as follows: (1) is paper first uses the idea of classification to find an optimal projection vector separating the in-orbit data from the normal historical data
Erefore, this paper proposes a new method that treats the normal historical samples as normal samples and treats the in-orbit samples which need to be tested as fault samples. e traditional use of linear discriminant analysis (LDA) and the new use of LDA in this paper are shown in Figures 1(a) and 1(b), respectively
Summary
With the reduction in the costs of launching rockets and manufacturing satellites, the number of satellites operating in orbit increases annually, bringing large economic benefits to society [1,2,3]. Erefore, the detection of incipient faults in satellites is receiving an increasing amount of attention because it is one of the key technologies that ensures the normal operation of satellites [6, 7]. Is fault detection method is suitable for detecting abrupt and large faults. It may be less effective at detecting incipient faults because the telemetry parameters with an incipient fault may not change significantly from their normal condition [10]. As the production batches, processes, and operating environments of different satellites are not identical, different fault detection thresholds may need to be determined for different satellites, and it is inefficient to manually set the appropriate threshold for each telemetry parameter
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
