A Novel Framework for Anomaly Detection for Satellite Momentum Wheel Based on Optimized SVM and Huffman-Multi-Scale Entropy

Abstract

The health status of the momentum wheel is vital for a satellite. Recently, research on anomaly detection for satellites has become more and more extensive. Previous research mostly required simulation models for key components. However, the physical models are difficult to construct, and the simulation data does not match the telemetry data in engineering applications. To overcome the above problem, this paper proposes a new anomaly detection framework based on real telemetry data. First, the time-domain and frequency-domain features of the preprocessed telemetry signal are calculated, and the effective features are selected through evaluation. Second, a new Huffman-multi-scale entropy (HMSE) system is proposed, which can effectively improve the discrimination between different data types. Third, this paper adopts a multi-class SVM model based on the directed acyclic graph (DAG) principle and proposes an improved adaptive particle swarm optimization (APSO) method to train the SVM model. The proposed method is applied to anomaly detection for satellite momentum wheel voltage telemetry data. The recognition accuracy and detection rate of the method proposed in this paper can reach 99.60% and 99.87%. Compared with other methods, the proposed method can effectively improve the recognition accuracy and detection rate, and it can also effectively reduce the false alarm rate and the missed alarm rate.

Improved time-variable transformer-based fault diagnosis method for satellite attitude control system

“…For example, Bingqing et al 12 used principal-component analysis (PCA) to detect faults in a satellite ACS. Li et al 13 proposed a support vector machine (SVM) model based on a directed acyclic graph to detect anomalies in satellite momentum-wheel voltage telemetry data. Folami 14 applied a random forest (RF) algorithm to realise the fault isolation of a three-axis reaction wheel.…”

A novel method for local anomaly detection of time series based on multi entropy fusion

“…Fractional fourier entropy is used to detect hyperspectral anomalies by Ran Tao et al [13], and Joshua Garland et al [14] apply permutation entropy to identify abnormal data records of paleoclimate. Huffman-multi-scale entropy is utilized to detect satellite momentum wheel anomalies [15], and Valentina et al [16] take advantage of machine learning enhanced entropy and effectively detect network anomalies. Different entropy shows excellent results within a certain range of their application [17,18].…”

Information Theory and Its Application in Machine Condition Monitoring

“…Li et al proposed a novel anomaly detection framework for a satellite momentum wheel [ 9 ]. Aimed at the lack of research on simulation data, and the scarcity of research on real telemetry data, the proposed framework was able to detect anomalies in a satellite momentum wheel, based on the features extracted by a newly proposed Huffman-multi-scale entropy method.…”