Recently wireless power transfer technology (WPT) attracts considerable attention, its incurred electromagnetic radiation (EMR), however, is largely overlooked by most existing literatures. In this paper, we first propose and study the radiation constrained fair wireless charging problem, i.e., maximizing the minimum utility of devices by adjusting the power of wireless chargers with no EMR intensity at any location in the field exceeding a given threshold . To address this problem, we first adopt an area discretization method to transform it from nonlinear to linear. Then, we propose two algorithms to deal with the reformulated problem. One is called Primal-Dual algorithm, which is semi-distributed and uses lagrangian dual and subgradient methods to solve the problem iteratively. The other is called area division algorithm. It is not only fully distributed and scalable with network size, but also provably achieves an approximation ratio of (1- ϵ). We conducted extensive simulations and built a field test-bed to verify our theoretical findings. Our simulations show that the approximation ratio of the area division algorithm holds; the Primal-Dual and area division algorithms can have comparable and over 90.9% performance of the optimal results, respectively; and both of the algorithms outperform a baseline algorithm by more than 37%.

Recently, wireless power transfer technology (WPT) has attracted considerable attention and become a promising technology to prolong the lifetime of wireless sensor networks (WSNs) by providing perpetual energy to sensors. However, electromagnetic radiation (EMR) incurred by WPT is largely overlooked in most of the existing literature. In this article, we first propose and study the radiation constrained fair charging problem for WPT, i.e., maximizing the minimum utility of sensors by adjusting the power of wireless chargers with no EMR intensity at any location in the field exceeding a given threshold R _t . To address this problem, we first adopt an area discretization method to transform it from nonlinear to linear. Then, we propose four algorithms to deal with the reformulated problem, i.e., 1/3 and 1/4 Approximation Algorithms, Primal-Dual algorithm, and area division algorithm. In particular, the area division algorithm is not only fully distributed but also provably achieves an approximation ratio of (1 − ϵ). Further, we conduct extensive simulations and build a field testbed to verify our theoretical findings. Our simulation results show that the approximation ratios of the proposed algorithms hold; the Primal-Dual and area division algorithms have comparable performance of the optimal results and outperform baseline algorithms obviously.

The development of wireless power transfer (WPT) facilitates wireless rechargeable sensor networks (WRSNs) receiving considerable attention in the sensor network research community. Most existing works mainly focus on general charging patterns and metrics while overlooking the precedence constraints among tasks, resulting in charging inefficiency. In this paper, we are the first to advance the issue of scheduling wireless charging tasks with precedence constraints (SCPC), with the optimization objective of minimizing the completion time of all the charging tasks under the precedence constraints while guaranteeing that the energy capacity of the mobile charger (MC) is not exhausted and the deadlines of charging tasks are not exceeded. In order to address this problem, we first propose a priority-based topological sort scheme to derive a unique feasible sequence on a directed acyclic graph (DAG). Then, we combine the proposed priority-based topological sort scheme with the procedure of a genetic algorithm to obtain the final solution through a series of genetic operators. Finally, we conduct extensive simulations to validate our proposed algorithm under the condition of three different network sizes. The results show that our proposed algorithm outperformed the other comparison algorithms by up to $11.59\%$ in terms of completion time.

A method of steel structure surface crack identification based on artificial intelligence technology is proposed to solve the problem that steel cracks can not be detected and forewarned in time when they appear in the railway industrial environment. The appearance of steel cracks greatly weakens the stability of steel structures, and will seriously endanger the safety of the railway industry if it is not detected and repaired in time. However, the common steel crack detection methods cannot achieve real-time monitoring of steel structures. In order to monitor the surface of steel structure in real-time and explore the recognition effect and model the advantages of common classification neural network models for surface cracks of railway industrial steel, this study evaluates the network model with multiple indicators and parameters under two experimental conditions. In this study, the steel surface cracks in the railway industrial environment are taken as samples, and the steel cracks are identified through the neural network model. For large-volume datasets, the recognition accuracy of the three network models has reached 97%, of which the YOLOv5 model has the best comprehensive recognition ability, and the C-Alex model has the best performance and convergence speed in small-volume datasets. This study explores the application prospects of models under different scenarios, proving that the three models can effectively detect steel surface cracks in real-time, and at the same time, it will pave the way for the development and application of artificial intelligence multi-model fusion technology in the field of the railway industry.