Aiming at the challenge of balancing the optimization between coverage and energy consumption of wireless sensor networks in the railroad monitoring scenario of train attitude measurement system, an adaptive backbone particle swarm based algorithm was proposed. A three-dimensional optimisation model for railway line monitoring was established. By comprehensively considering regional coverage, total system energy consumption, and coverage requirements for critical monitoring points, a multi-objective optimisation model more closely aligned with engineering practice was constructed. A dynamic inertia weight and backbone particle number adjustment mechanism were incorporated to balance global exploration and local exploitation capabilities. An ε-elite dimension-wise backpropagation learning strategy was employed to enhance the probability of escaping local optima. Simulation results demonstrate that compared to traditional PSO, APSO, and BPSO algorithms, ABPSO achieves higher network coverage and superior energy balance with faster convergence and lower energy consumption. In complex scenarios, it effectively safeguards monitoring quality in critical areas, providing an efficient and reliable solution for WSN deployment along railway lines.
YuXiuwu, XiaoLin, LiuYong, et al. A WSN positioning algorithm integrating range measurement correction and spider-inspired optimisation[J]. Engineering Science and Technology, 2025, 57(5): 333-343.
YinZhenyu, LiShuo, ZhangFeiqing, et al. An optimisation method for coverage in shipboard wireless sensor networks based on the virtual force whale algorithm[J/OL]. [2025-10-24].Small and Micro Computer Systems. https://link.cnki.net/urlid/21.1106.TP.20250213.1801.022.
FanXinming. Research on three-dimensional WSN coverage optimisation using an improved grey wolf optimisation algorithm[J]. Sensors and Microsystems, 2025, 44(8): 148-153.
DingHonglin, ZhangLiwen. Analysis of frost damage on the lanzhou-xinjiang railway and study on the effectiveness of ballast cleaning and screening in mitigating frost damage[J]. Shanxi Architecture, 2025, 51(18): 114-118.
LeiLiting, JiangChangsheng, ShiGuangzhou. Application research of an innovative hybrid algorithm in train attitude measurement systems[J]. Internal Combustion Engines and Accessories, 2024(14): 22-24.
JiaRunliang, ZhangHaiyu. Improved population intelligence algorithm for wireless sensor network coverage optimisation[J]. Journal of Southwest University(Natural Science Edition), 2024, 46(1): 155-166.
[19]
FangH, ZhouA, ZhangH. Information fusion in offspring genera-tion: a case study in DE and EDA[J]. Swarm and Evolutionary Computation, 2018, 42: 99-108.
[20]
OuY, QinF, ZhouK Q, et al. An improved grey wolf optimizer with multi-strategies coverage in wireless sensor networks[J]. Symmetry, 2024, 16(3): 286-291.
[21]
HousseinE H, SaadM R, HashimF A, et al. Lévy flight distribution: a new metaheuristic algorithm for solving engineering optimization problems[J]. Engineering Applications of Artificial Intelligence, 2020, 94.DOI: 10.3390/sym16030286.
[22]
KennedyJ. Bare bones particle swarms[C]// Proceedings of the 2003 IEEE Swarm Intelligence Symposium (SIS'03). Indianapolis: IEEE, 2003.DOI: 10.1109/SIS.2003.1202251.
[23]
ClercM, KennedyJ. The particle swarm-explosion, stability, and convergence in a multidimensional complex space[J]. IEEE transactions on Evolutionary Computation, 2002, 6(1): 58-73.
[24]
ZhangY, GongD W, DingZ. A bare-bones multi-objective particle swarm optimization algorithm for environmental/economic dispatch[J]. Infor-mation sciences, 2012, 192: 213-227.