Automated Design of Fault Diagnosis CNN Network for Satellite Attitude Control Systems.

Despite the dominance of unsupervised and self-supervised anomaly detection methods in the current satellite fault diagnosis domain, supervised anomaly detection offers a superior alternative for high-sensitivity detection and lightweight deployment requirements specific to subsystems or components, such as attitude control systems (ACSs). This article addresses the issues of over-design and insufficient accuracy in the CNN network design for satellite ACS fault diagnosis by introducing the modified particle swarm optimization-advanced convolution blocks-based CNN (MPSO-ACBCNN) method. First, we present the ACBCNN, a lightweight, flexible-layer CNN architecture. This architecture leverages advanced convolution blocks (ACBs), which incorporate numerous efficient design elements to enhance feature extraction capabilities within power spectral density (PSD) graphs of various fault samples, and employs classical dense connection methods to prevent the issue of gradient vanishing. Second, we devise the MPSO-ACBCNN algorithm to optimize the ACBCNN fault diagnosis architecture for specified ACS using MPSO. In MPSO-ACBCNN, several optimizations to the canonical PSO are implemented, including the fitness design that balances the tradeoff between total parameter quantity and the training effectiveness, and methods to ensure feasible solutions, etc. Finally, numerical experimental results demonstrate the effectiveness and superiority of MPSO-ACBCNN in fault diagnosis for ACS.

A Hybrid Data Preprocessing-Based Hierarchical Attention BiLSTM Network for Remaining Useful Life Prediction of Spacecraft Lithium-Ion Batteries.

As a crucial energy storage for the spacecraft power system, lithium-ion batteries degradation mechanisms are complex and involved with external environmental perturbations. Hence, effective remaining useful life (RUL) prediction and model reliability assessment confronts considerable obstacles. This article develops a new RUL prediction method for spacecraft lithium-ion batteries, where a hybrid data preprocessing-based deep learning model is proposed. First, to improve the correlation between battery capacity and features, the empirically selected high-dimensional features are linearized by using the Box-Cox transformation and then denoised via the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method. Second, the principal component analysis (PCA) algorithm is employed to perform feature dimensionality reduction, and the output of PCA is further processed by the sliding window technique. Third, a multiscale hierarchical attention bi-directional long short-term memory (MHA-BiLSTM) model is constructed to estimate the capacity in future cycles. Specifically, the MHA-BiLSTM model can predict the RUL of lithium-ion batteries by considering the correlation and significance of each cycle's information during the degradation process on different scales. Finally, the proposed method is validated based on multiple types of experiments under two lithium-ion battery datasets, demonstrating its superior performance in terms of feature extraction and multidimensional time series prediction.

Attitude-orbit coupled sliding mode tracking control for spacecraft formation with event-triggered transmission.

In this paper, the event-triggered integrated attitude and orbit control problem is studied for the distributed spacecraft formation system. First, the operation rules of dual numbers and dual quaternion are presented, and the attitude-orbit coupling error dynamics models for single spacecraft and spacecraft formation are established based on the dual quaternion. An event-triggered attitude-orbit coupled sliding mode tracking control law is proposed to stabilize the attitude-orbit control system, which can reduce the communication burden among spacecraft at the same time. Under the developed control scheme, the state trajectory of attitude-orbit control systems can arrive on the designed sliding surface in finite time, and the asymptotic stability of the overall formation control system can be ensured. Considering the fact that the inertia and mass parameters in practice may not be measured exactly, an adaptive sliding mode control law is further proposed. Finally, a simulation example is given to verify the validity and feasibility of the proposed spacecraft event-triggered control method.

Design and flight results of the VHF/UHF communication system of Longjiang lunar microsatellites.

As a part of China's Chang'e-4 lunar far side mission, two lunar microsatellites for low frequency radio astronomy, amateur radio and education, Longjiang-1 and Longjiang-2, were launched as secondary payloads on 20 May 2018 together with the Queqiao L2 relay satellite. On 25 May 2018, Longjiang-2 successfully inserted itself into a lunar elliptical orbit of 357 km × 13,704 km, and became the smallest spacecraft which entered lunar orbit with its own propulsion system. The satellite carried the first amateur radio communication system operating in lunar orbit, which is a VHF/UHF software defined radio (SDR) designed for operation with small ground stations. This article describes and evaluates the design of the VHF/UHF radio and the waveforms used. Flight results of the VHF/UHF radio are also presented, including operation of the radio, performance analysis of downlink signals and the first lunar orbit UHF very-long-baseline interferometry (VLBI) experiment.

Neural-Network-Based Adaptive Backstepping Control With Application to Spacecraft Attitude Regulation.

This paper investigates the neural-network-based adaptive control problem for a class of continuous-time nonlinear systems with actuator faults and external disturbances. The model uncertainties in the system are not required to satisfy the norm-bounded assumption, and the exact information for components faults and external disturbance is totally unknown, which represents more general cases in practical systems. An indirect adaptive backstepping control strategy is proposed to cope with the stabilization problem, where the unknown nonlinearity is approximated by the adaptive neural-network scheme, and the loss of effectiveness of actuators faults and the norm bounds of exogenous disturbances are estimated via designed online adaptive updating laws. The developed adaptive backstepping control law can ensure the asymptotic stability of the fault closed-loop system despite of unknown nonlinear function, actuator faults, and disturbances. Finally, an application example based on spacecraft attitude regulation is provided to demonstrate the effectiveness and the potential of the developed new neural adaptive control approach.

Transcriptome analysis of the variations between autotetraploid Paulownia tomentosa and its diploid using high-throughput sequencing.

Timber properties of autotetraploid Paulownia tomentosa are heritable with whole genome duplication, but the molecular mechanisms for the predominant characteristics remain unclear. To illuminate the genetic basis, high-throughput sequencing technology was used to identify the related unigenes. 2677 unigenes were found to be significantly differentially expressed in autotetraploid P. tomentosa. In total, 30 photosynthesis-related, 21 transcription factor-related, and 22 lignin-related differentially expressed unigenes were detected, and the roles of the peroxidase in lignin biosynthesis, MYB DNA-binding proteins, and WRKY proteins associated with the regulation of relevant hormones are extensively discussed. The results provide transcriptome data that may bring a new perspective to explain the polyploidy mechanism in the long growth cycle of plants and offer some help to the future Paulownia breeding.