Data-driven fault diagnosis of satellite power system using fuzzy Bayes risk and SVM

Suo, Mingliang; Zhu, Baolong; An, Rong; Sun, Huimin; Xu, Shengzhong; Yu, Zhenhua

doi:10.1016/j.ast.2018.11.049

Cited by 54 publications

(20 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although it can achieve good results, the training of the DBN network and SVM is time-consuming. It is not applicable for the large-scale and multivariate time-series satellite power subsystem data [13][14][15]. The application scenario of PCA is to reduce the dimension of the data set, and the reduced dimension data can retain the characteristics of the original data to the greatest extent.…”

Section: Introductionmentioning

confidence: 99%

An Analytical Investigation of Anomaly Detection Methods Based on Sequence to Sequence Model in Satellite Power Subsystem

Jin

Zhang

Sun

et al. 2022

Sensors

View full text Add to dashboard Cite

The satellite power subsystem is responsible for all power supply in a satellite, and is an important component of it. The system’s performance has a direct impact on the operations of other systems as well as the satellite’s lifespan. Sequence to sequence (seq2seq) learning has recently advanced, gaining even more power in evaluating complicated and large-scale data. The potential of the seq2seq model in detecting anomalies in the satellite power subsystem is investigated in this work. A seq2seq-based scheme is given, with a thorough comparison of different neural-network cell types and levels of data smoothness. Three specific approaches were created to evaluate the seq2seq model performance, taking into account the unsupervised learning mechanism. The findings reveal that a CNN-based seq2seq with attention model under suitable data-smoothing conditions has a better ability to detect anomalies in the satellite power subsystem.

show abstract

Section: Introductionmentioning

confidence: 99%

An Analytical Investigation of Anomaly Detection Methods Based on Sequence to Sequence Model in Satellite Power Subsystem

Jin

Zhang

Sun

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Conversely, if the in-orbit data were classified as a fault class by the classifier, the in-orbit data would be deemed to be faulty in some way. Representative supervised fault detection methods are linear discriminant analysis (LDA) [22], support vector machine (SVM) [23], neural networks [24], random forest [25], and so on. However, due to the high reliability of satellites, most of the samples collected by satellite operation and maintenance systems are normal, and fault samples are exceedingly rare.…”

Section: Introductionmentioning

confidence: 99%

A Method for Detecting Incipient Faults in Satellites Based on Dynamic Linear Discriminant Analysis

Zhang

Yang

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

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.

show abstract

“…In the past few decades, some advanced signal processing methods [3] and machine learning algorithms [4,5] were employed for spacecraft fault diagnosis. Machine learning usually plays an essential role in exploring the mapping relationships between features extracted by the signal processing techniques and the health states of spacecraft [6,7].…”

Section: Introductionmentioning

confidence: 99%

Spacecraft Intelligent Fault Diagnosis under Variable Working Conditions via Wasserstein Distance-Based Deep Adversarial Transfer Learning

Xiang

Tian

2021

International Journal of Aerospace Engineering

View full text Add to dashboard Cite

In recent years, deep learning methods which promote the accuracy and efficiency of fault diagnosis task without any extra requirement of artificial feature extraction have elicited the attention of researchers in the field of manufacturing industry as well as aerospace. However, the problems that data in source and target domains usually have different probability distributions because of different working conditions and there are insufficient labeled or even unlabeled data in target domain significantly deteriorate the performance and generalization of deep fault diagnosis models. To address these problems, we propose a novel Wasserstein Generative Adversarial Network with Gradient Penalty- (WGAN-GP-) based deep adversarial transfer learning (WDATL) model in this study, which exploits a domain critic to learn domain invariant feature representations by minimizing the Wasserstein distance between the source and target feature distributions through adversarial training. Moreover, an improved one-dimensional convolutional neural network- (CNN-) based feature extractor which utilizes exponential linear units (ELU) as activation functions and wide kernels is designed to automatically extract the latent features of raw time-series input data. Then, the fault model classifier trained in one working condition (source domain) with sufficient labeled samples could be generalized to diagnose data in other working conditions (target domain) with insufficient labeled samples. Experiments on two open datasets demonstrate that our proposed WDATL model outperforms most of the state-of-the-art approaches on transfer diagnosis tasks under diverse working circumstances.

show abstract

Data-driven fault diagnosis of satellite power system using fuzzy Bayes risk and SVM

Cited by 54 publications

References 39 publications

An Analytical Investigation of Anomaly Detection Methods Based on Sequence to Sequence Model in Satellite Power Subsystem

An Analytical Investigation of Anomaly Detection Methods Based on Sequence to Sequence Model in Satellite Power Subsystem

A Method for Detecting Incipient Faults in Satellites Based on Dynamic Linear Discriminant Analysis

Spacecraft Intelligent Fault Diagnosis under Variable Working Conditions via Wasserstein Distance-Based Deep Adversarial Transfer Learning

Contact Info

Product

Resources

About