Smart Fault Detection in Nanosatellite Electrical Power System

2026-01-01

arXiv.org

AI Summary

This study addresses the challenge of frequent failures in power systems of attitude determination and control system (ADCS)-free nanosatellites in low Earth orbit under environmental stress and launch loads. To this end, the authors propose an intelligent fault diagnosis method based on multimodal machine learning. A neural network baseline model is constructed with solar irradiance and solar panel temperature as inputs and current and load as outputs, integrated with algorithms including principal component analysis (PCA), decision trees, and k-nearest neighbors (KNN) to enable high-accuracy classification of typical faults—such as short circuits, open circuits, and IGBT failures—in photovoltaic subsystems, DC–DC converters, and battery regulators. This work presents the first end-to-end intelligent fault identification framework for nanosatellite power systems operating without ADCS, significantly enhancing diagnostic robustness and applicability.

Technology Category

• Intelligent Robots: State Estimation
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Multimodal Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

This paper presents a new detection method of faults at Nanosatellites'electrical power without an Attitude Determination Control Subsystem (ADCS) at the LEO orbit. Each part of this system is at risk of fault due to pressure tolerance, launcher pressure, and environmental circumstances. Common faults are line to line fault and open circuit for the photovoltaic subsystem, short circuit and open circuit IGBT at DC to DC converter, and regulator fault of the ground battery. The system is simulated without fault based on a neural network using solar radiation and solar panel's surface temperature as input data and current and load as outputs. Finally, using the neural network classifier, different faults are diagnosed by pattern and type of fault. For fault classification, other machine learning methods are also used, such as PCA classification, decision tree, and KNN.

Problem

• Fault Detection
• Nanosatellite
• Electrical Power System
• LEO
• ADCS

Innovation

• neural network
• fault detection
• nanosatellite
• machine learning
• electrical power system