Graph neural network approach for anomaly detection

Data-driven methodologies are indispensable for early satellite anomaly detection. However, their effectiveness in capturing temporal dependencies within non-stationary telemetry data is still not ideal. In the field of satellite anomaly detection using reconstruction theory, this limitation can make it unclear whether the distribution shifts of reconstruction errors are caused by inadequate training or the actual emergence of real anomalies. To address these challenges, we propose the Seasonal Decomposition Cross Attention Transformer (SDCA-Former), a new Transformer architecture specifically designed to effectively extract temporal dependencies in non-stationary satellite telemetry data, thereby enabling more precise early warning of satellite anomalies. Firstly, building upon the foundational architecture of the Vanilla Transformer, the SDCA-Former integrates a series of enhancements, including the Temporal Convolutional Network-based Position Encoding (TCNPE), Encoder architecture refinements, and the Decoder utilizing SDCA modules. Secondly, we developed a comprehensive satellite anomaly detection framework centered on the SDCA-Former, including technical components such as telemetry data feature engineering, anomaly scoring, and determination of anomaly thresholds. Lastly, we verified the effectiveness and superiority of the proposed method on a dataset composed of telemetry data from a Geostationary Earth Orbit (GEO) satellite. Notably, our approach achieved an early warning for anomalies up to four months in advance. 

Satellite Early Anomaly Detection Using an Advanced Transformer Architecture for Non-Stationary Telemetry Data

Satellite telemetry data is important strategic resource. We can monitor and predict the status of the satellite through analyzing the telemetry data. However, due to interference on the satellite and sensor failure, the telemetry data will jump and generate outliers. Therefore, it is necessary to identify and remove the outliers. This paper proposes an outlier removal method based on deconvolutional reconstruction network. The deconvolutional reconstruction network is composed of multiple convolution and deconvolution which is used to learn the internal laws from massive telemetry data. The learned network can make accurate predictions for normal data except for outliers. Our method use this difference to set the threshold and perform outlier removal. The deconvolutional reconstruction network proposed in this paper uses a very few parameters for rapid learning. The network can converge within 20 epochs for multiple sets of telemetry datasets which contains more than 60k discontinuous points. Numerical experiments show that the proposed method can achieve perfect removal effects. 

Outlier Removal of Discontinuous Satellite Telemetry Data Based on Deconvolutional Reconstruction Network

The training of deep neural networks on satellite high-dimensional telemetry data can achieve high-resolution anomaly detection and fault diagnosis. However, there are hundreds of types of satellite telemetry data, some of which are highly correlated. Although more data will contain more coupled implicit information, this will affect the training progress of neural networks. Therefore, to ensure that the model’s effect will not be reduced significantly, we should select as few types of telemetry data as possible for network training. This paper proposes a hybrid heuristic algorithm named genetic particle swarm optimization (GPSO) for the feature selection of satellite telemetry data. We designed the continuous-discrete value conversion as the encoding and decoding rule and the fitness function based on mutual information. We normalized the particles in each generation of the population in GPSO. Moreover, to avoid the population falling into the local optimum prematurely, GPSO uses the precedence operation crossover in the genetic algorithm to perturb the particles’ positions. Four popular unsupervised network schemes, Deconvolution Reconstruction Network (DRN), Convolutional Autoencoder (CAE), Long Short-Term Memory (LSTM), and Time Domain Convolutional Network (TCN), are designed in detail to verify the effectiveness and superiority of GPSO. Numerical experiments show that GPSO can perform feature selection with higher accuracy in the training of the networks with the loss performance improvement by 332%, 1894%, 186%, and 612%, respectively.

Satellite telemetry data feature selection method based on genetic particle swarm optimization

Satellite telemetry data is important strategic resource. We can monitor and predict the status of the satellite through analyzing the telemetry data. However, due to interference on the satellite and sensor failure, the telemetry data will jump and generate outliers. Therefore, it is necessary to identify and remove the outliers. This paper proposes an outlier removal method based on deconvolutional reconstruction network. The deconvolutional reconstruction network is composed of multiple convolution and deconvolution which is used to learn the internal laws from massive telemetry data. The learned network can make accurate predictions for normal data except for outliers. Our method use this difference to set the threshold and perform outlier removal. The deconvolutional reconstruction network proposed in this paper uses a very few parameters for rapid learning. The network can converge within 20 epochs for multiple sets of telemetry datasets which contains more than 60k discontinuous points. Numerical experiments show that the proposed method can achieve perfect removal effects.

The military requirements of space security defense and space fast response are increasingly urgent. Accurate and effective micro anomaly detection of on-orbit satellites is an important technical way of satellites life cycle health management. Under this military background, the micro anomaly detection of the key components of the satellite is proposed and carried out. In order to solve the problems of low diagnostic accuracy of the traditional Voherra series model in satellite telemetry signal micro anomaly detection, o-Voherra series anomaly detection model for the feature extraction of telemetry data based on the optimized sequence model is proposed. Firstly, the feature of satellite telemetry data is extracted by using the constructed optimized sequence model. Secondly, phase space reconstruction of telemetry data after preprocessing and feature extraction. Finally, the telemetry data micro anomaly detection are realized by the proposed o-Voherra series model. Through the remote sensing data experiment of the key components of the satellite after desensitization, the proposed model can accurately realize the micro anomaly detection of the key components of the satellite.

Satellite Micro Anomaly Detection Based on Telemetry Data

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Shaojun Chen

Author Tools

Chat about Author

Papers

Satellite Micro Anomaly Detection Based on Telemetry Data