Due to the frequent occurrence of spacecraft failures and accidents, it will cause personal injury and economic loss, and will have a huge impact on the aerospace industry. Therefore, it is necessary to enrich the research on satellite constellation fault diagnosis and detection technology. In order to solve the shortcomings of existing research on fault diagnosis and detection of satellite swarms, this paper discusses the neural network fault diagnosis technology, satellite swarm fault diagnosis method and the functional equation of satellite swarm execution fault types. The fault samples and parameter settings of the group fault diagnosis detection application are briefly introduced. In addition, the work design and calculation process of satellite swarm fault diagnosis and detection relying on neural network are discussed. Finally, the application of neural network in satellite swarm fault diagnosis and detection is subjected to experimental comparison and analysis of the correct rate of fault diagnosis. The experimental data show that the algorithm proposed in this paper and Although the correct rate of fault diagnosis of the other two types shows a downward trend after the failure rate of 10%, the correct rate of the neural network algorithm proposed in this paper is significantly better than the other two algorithms, and the algorithm in this paper is in 50% to 200% of the satellites. In the group failure rate, the correct rate of diagnosis is stable at about 96%, while the correct rate of the other two algorithms is gradually lower than 90%. Therefore, it is verified that the satellite group fault diagnosis and detection relying on neural network has high use value.

Rajit Kautish. Satellite Cluster Fault Diagnosis and Detection Analysis Based on Neural Network. International Journal of Neural Network (2021), Vol. 2, Issue 3: 37-44. https://doi.org/10.38007/NN.2021.020305.

[1] Hajipour P, Shahzadi A, S Ghazi‐Maghrebi. Interference Management for Spectral Coexistence in a Heterogeneous Satellite Network. International Journal of Satellite Communications and Networking. (2020) 38(3):229-253. https://doi.org/10.1002/sat.1321

[2] Akyildiz I F, Jornet J M, Nie S. A New Cubesat Design with Reconfigurable Multi-Band Radios For Dynamic Spectrum Satellite Communication Networks. Ad Hoc Networks. (2019) 86(APR.):166-178. https://doi.org/10.1016/j.adhoc.2018.12.004

[3] Asvm A, Ajm A, Ak A, et al. Optimal Satellite Rod Constructs to Mitigate Rod Failure Following Pedicle Subtraction Osteotomy (PSO): A Finite Element Study. The Spine Journal. (2019) 19(5):931-941. https://doi.org/10.1016/j.spinee.2018.11.003

[4] Dawson J, Lyon B, Murakami N. Risk Factors for Pyroshock Qualification Failure of Satellite Hardware. Journal of the IEST. (2018) 61(1):31-50. https://doi.org/10.17764/1098-4321.61.1.31

[5] Kim B, Yang H. Reliability Optimization of Real-Time Satellite Embedded System under Temperature Variations. IEEE Access. (2020) 8(99):1-1. https://doi.org/10.1109/ACCESS.2020.3044044

[6] Mostacciuolo E, Vasca F, Baccari S, et al. Fault analysis to improve reliability of a LEO satellite EPS. IFAC-PapersOnLine. (2019) 52(12):200-205. https://doi.org/10.1016/j.ifacol.2019.11.243

[7] Lucas A, Iliadis M, Molina R, et al. Using Deep Neural Networks for Inverse Problems in Imaging: Beyond Analytical Methods. IEEE Signal Processing Magazine. (2018) 35(1):20-36. https://doi.org/10.1109/MSP.2017.2760358

[8] Aljarah I, Faris H, Mirjalili S. Optimizing connection weights in neural networks using the whale optimization algorithm. Soft Computing. (2018) 22(1):1-15. https://doi.org/10.1007/s00500-016-2442-1

[9] Venieris S I, Alexandros K, Christos-Savvas B. Toolflows for Mapping Convolutional Neural Networks on FPGAs: A Survey and Future Directions. Acm Computing Surveys. (2018) 51(3):1-39. https://doi.org/10.1145/3186332

[10] Harris A D. 10 Troubleshooting, Diagnostic Tips for HVAC Technicians in the Field. Air Conditioning, Heating & Refrigeration News. (2019) 266(4):10-11.

[11] Kella D, Stambler B. Subcutaneous Implantable Cardioverter Defibrillator (S-ICD) Electrode Fracture: Follow-up, Troubleshooting and Evaluation. Journal of cardiovascular electrophysiology. (2021) 32(5):1452-1457. https://doi.org/10.1111/jce.14994

[12] Dabiri S, Heaslip K. Inferring transportation modes from GPS trajectories using a convolutional neural network. Transportation Research Part C Emerging Technologies. (2018) 86(JAN.): 360-371. https://doi.org/10.1016/j.trc.2017.11.021

[13] Rezaei V, Stefanovic M. Distributed Stabilization of Interconnected Multiagent Systems using Structurally Nonsymmetric Control Layers. IFAC-PapersOnLine. (2020) 53(2):3223-3229. https://doi.org/10.1016/j.ifacol.2020.12.1094

[14] Kirchhoffer H, Haase P, Samek W, et al. Overview of the Neural Network Compression and Representation (NNR) Standard. IEEE Transactions on Circuits and Systems for Video Technology. (2021) (99):1-1.

[15] Seki H, Yamamoto K, Akiba T, et al. Discriminative Learning of Filterbank Layer within Deep Neural Network Based Speech Recognition for Speaker Adaptation. IEICE Transactions on Information and Systems. (2019) E102.D(2):364-374. https://doi.org/10.1587/transinf.2018EDP7252

[16] Andrew, Bate. Bayesian confidence propagation neural network. Drug safety. (2018) 30(7):623-625. https://doi.org/10.2165/00002018-200730070-00011

[17] Ern M, Trinh Q T, Preusse P, et al. GRACILE: A comprehensive climatology of atmospheric gravity wave parameters based on satellite limb soundings. Earth System Science Data Discussions. (2018) 10(2):1-57. https://doi.org/10.5194/essd-10-857-2018

[18] Palmer D M, Holmes R M. Extremely Low Resource Optical Identifier: A License Plate for Your Satellite. Journal of Spacecraft and Rockets. (2018) 55(4):1-10. https://doi.org/10.2514/1.A34106