Abstract
Unmanned aeroplanes, or ‘drones’ for short, are unmanned aircraft that are maneuvered by radio remote-controlled equipment and self-contained programmed control devices or are operated autonomously, either completely or intermittently, by on-board computers. As a modern intelligent equipment, UAV has the characteristics of no casualties, less restriction of use, and high efficiency and cost ratio, and its status and role in modern national economic production and life are becoming more and more prominent. Currently, there are various methods for fault diagnosis and health management in the field of PHM in UAV power systems (engines). Single-parameter fault diagnosis has certain limitations, but the current research is still dominated by single-signal analysis. There are fewer studies on UAV engine condition monitoring and health management based on multi-source signal characteristics. Multi-source heterogeneous information through information fusion technology maximises the possibility of fusing useful information through efficient algorithms, which in turn gives accurate results.
References
[1] Liu YZ, Qu Q, Cao D. Improved multi-sensor information fusion algorithm and its application. Sensors and Microsystems. 2024;43(07):161-4.
[2] Wang RH, Wen X, Xiang ZR. Research progress of human-machine fusion system collaboration and optimisation method. Command Control and Simulation. 2024;46(05):103-13.
[3] Tang SJ, Wang TY, Zhao GL, et al. A review of multi-sensor data fusion research for target tracking. Air and Space Defence. 2024;7(04):18-29.
[4] Zhang HC, Li LX, Liu DJ. A review of multimodal data fusion research. Computer Science and Exploration. 2024;18(10):2501-20.
[5] Jiang CS, Zeng Z, Wan J. A review on the progress of multi-source information fusion research. Modern Computer. 2023;29(18):1-9+29.
[6] Xu WH, Huang XD, Cai K. A review of multi-source information fusion methods based on granular computing. Data Acquisition and Processing. 2023;38(02):245-61.
[7] Li HL, Meng JX, Zhu WW, et al. Delay-Informed Intelligent Formation Control for UAV-Assisted IoT Application. Sensors (Basel, Switzerland). 2023;23(13):6190.
[8] Zhang XD, Li SB, Li CJ, et al. An overview of UAV clustering: technology, challenges and future. Radio Engineering. 2023;53(07):1487-1501.
[9] Shi XD, Yang SK. A review of multi-sensor information fusion research. Communication and Information Technology. 2022;(06):34-41.
[10] Zhang KH, Dong XW, Yu JL, et al. A review of multi-sensor fusion state estimation methods. Navigation Positioning and Timing. 2022;9(05):28-37.
[11] Li H, Sun DM, Shen YC. Application of improved weighted fusion algorithm and bispectral technology in wind power bearing fault diagnosis. Electronic Devices. 2018;41(04):898-904.
[12] Li R, Chen S, Xia J, et al. Predictive modeling of deep vein thrombosis risk in hospitalized patients: A Q-learning enhanced feature selection model. Computers in Biology and Medicine. 2024;175:108447.
[13] Liu Q, Ting J, Ye YG, et al. Research on fault discrimination of transverse instability in high-speed trains based on D-S evidence theory. China Test. 2017;43(07):103-7.
[14] Palash D, Sonom S. A new belief entropy measure in the weighted combination rule under DST with faulty diagnosis and real-life medical application. International Journal of Machine Learning and Cybernetics. 2022;14(4):1179-203.
[15] Han F, Yang WH, Yuan XG. A fuzzy set-based information fusion method for evidence theory. Control and Decision Making. 2010;25(03):449-52.
[16] Zhang YQ, Ma XM, Liang L. Fuzzy integral multi-sensor data fusion based on RBF for scraper conveyor motor fault diagnosis. Journal of Xi'an University of Science and Technology. 2016;36(02):271-4.