At present, under the background of the social development of the increasing popularity of 5G technology, the automatic inspection of power lines through 5G UAV has become an inevitable demand for the development of smart grid. 5G has brought advanced technical advantages to the power inspection UAV, overcoming the difficulties in flight environment, data transmission and image analysis. The use of 5G UAV realizes the intelligent panoramic operation of power inspection and is an important means to ensure the reliable operation of power grid. However, due to the constraints of relevant factors, the use of 5G inspection UAV is both challenging and imperative in the future. This paper mainly introduces the basic meaning and advantages of 5G technology and UAV, compares and analyzes the differences between manual inspection, traditional UAV and 5G UAV in power inspection, discusses the technical advantages of 5G UAV, and combines with application cases to prospect the development prospect and trend of 5G UAV inspection.

Understanding the influence of the main cutting force energy consumption of the milling cutter is the basis for prediction and control of energy and machining efficiency. The existing models of cutting force energy consumption lack variables related to milling vibration and cutter teeth errors. According to the instantaneous bias of the main profile of the milling cutter under vibration, the instantaneous cutting boundary of the cutter teeth was investigated. The energy consumption distribution of the instantaneous main cutting force of the cutter tooth was studied. The model for the energy consumption of the instantaneous main cutting force of the cutter tooth and the milling cutter were both developed. The formation of energy consumption of the dynamic main cutting force of a high energy efficiency milling cutter was researched. A method for identifying the time–frequency characteristics of the energy consumption of the main cutting force under vibration was proposed and verified by experiments.

No abstract

No abstract

Graph neural networks have been widely used to learn node representations for many real-world static graphs. In general, they learn node representations by recursively aggregating information from neighbors. However, graphs in many applications are dynamic, evolving with continuous graph events, such as node feature and graph structure updates. These events require the node representations to be updated accordingly. Currently, due to the real-time requirement, how to efficiently and reliably update node representations under continuous graph events is still an open problem. Recent studies propose two solutions to partially address this problem, but their performance is still limited. First, local-based GNNs only update the nodes directly involved in events, suffering from the quality-deficit issue, since they neglect the other nodes affected by these events. Second, neighbor-sampling GNNs propose to sample neighbors to accelerate neighbor aggregation computations, encountering the neighbor-redundant issue. These sampled neighbors may be similar and cannot reflect the distribution of all neighbors, leading that node representations aggregated on these redundant neighbors may differ from those aggregated on all neighbors. In this paper, we propose an efficient and reliable graph neural network, namely EARLY, to update node representations for dynamic graphs. We first identify the top-k influential nodes that are most affected by graph events. Then, to sample neighbors diversely, we propose a diversity-aware layer-wise sampling technique. We theoretically demonstrate that this technique can decrease the sampling expectation error and learn more reliable node representations. Therefore, the top-k nodes selection and diversity-aware sampling enable EARLY to efficiently update node representations in a reliable way. Extensive experiments on the five real-world graphs demonstrate the effectiveness and efficiency of our proposed EARLY.