A Study on Structural Health Monitoring of a Large Space Antenna via Distributed Sensors and Deep Learning

Abstract

Most modern Earth and Universe observation spacecraft are now equipped with large lightweight and flexible structures, such as antennas, telescopes, and extendable elements. The trend of hosting more complex and bigger appendages, essential for high-precision scientific applications, made orbiting satellites more susceptible to performance loss or degradation due to structural damages. In this scenario, Structural Health Monitoring strategies can be used to evaluate the health status of satellite substructures. However, in particular when analysing large appendages, traditional approaches may not be sufficient to identify local damages, as they will generally induce less observable changes in the system dynamics yet cause a relevant loss of payload data and information. This paper proposes a deep neural network to detect failures and investigate sensor sensitivity to damage classification for an orbiting satellite hosting a distributed network of accelerometers on a large mesh reflector antenna. The sensors-acquired time series are generated by using a fully coupled 3D simulator of the in-orbit attitude behaviour of a flexible satellite, whose appendages are modelled by using finite element techniques. The machine learning architecture is then trained and tested by using the sensors’ responses gathered in a composite scenario, including not only the complete failure of a structural element (structural break) but also an intermediate level of structural damage. The proposed deep learning framework and sensors configuration proved to accurately detect failures in the most critical area or the structure while opening new investigation possibilities regarding geometrical properties and sensor distribution.

Continuum Modeling and Boundary Control of a Satellite with a Large Space Truss Structure

“…(2) Transverse deformation in the truss structure is negligible, enabling the dismissal of geometric and material nonlinearity. (3) The nonlinear coupling effect between attitude motion and structural vibration is deemed insignificant and thus disregarded. Truss structures, prevalent in space applications, exhibit a repetitive pattern and consist of numerous elemental components, as depicted in Figure 1.…”

“…(2) Transverse deformation in the truss structure is negligible, enabling the dismissal of geometric and material nonlinearity. (3) The nonlinear coupling effect between attitude motion and structural vibration is deemed insignificant and thus disregarded.…”

“…Large space truss structures have found extensive applications in modern space missions, including Earth observation [1][2][3], deep space exploration [4,5], and astronomy observation [6], owing to their attributes of easy deployment and high stiffness-to-mass ratios. However, due to launch capacity limitations, these structures tend to be highly flexible with low and dense natural frequencies, presenting significant challenges in control system design.…”

Multi-Damage Detection in Composite Space Structures via Deep Learning

“…The current work builds on the approach developed by the authors [31,32], with the aim to further structure the method, not only by testing the DL framework on a new case study, but also challenging its classification capabilities. Indeed, based on the knowledge and experience gained in previous work, the present study aims to introduce a general and detailed end-to-end architecture and guidelines to be followed for performing the SHM of space structured based on LSTM-NNs.…”

Data-driven deep neural network for structural damage detection in composite solar arrays on flexible spacecraft

“…As far as current state-of-the-art solutions for damage identification are concerned, there are mostly two adopted philosophies: physics-based and data-driven methods [1][2][3]. The purpose of this study is to propose a Deep Learning methodology with multi-classification damage capabilities, with respect to the research proposed by the authors' previous work [4][5]. Indeed, the present study aims at proposing an architecture and guidelines for performing SHM of space structured based on LSTM-NNs.…”