Motor fault diagnosis based on multisensor-driven visual information fusion.

To need of accurate motor fault diagnosis in industrial system, we propose a fault diagnosis framework that utilizes motor current and electromagnetic signals, combining them with a self-attention-enhanced capsule network for enhanced signal analysis and accuracy. Firstly, the original signal extracted by multiple sensors is constructed into a symmetric point mode (SDP) image, and the visual fault information of different sensors and fusion signals of different motion health states are obtained by the proposed multi-channel image fusion method. Then, the capsule network, combined with self-attention, extracts spatial features from the high-dimensional tensor of the multi-channel fused image for adaptive recognition and extraction.

A Robot Hybrid Hierarchical Network for Sensing Environmental Variables of a Smart Grid.

With the rapid development of the social economy, high-voltage transmission lines as power supply infrastructure are increasing, subsequently presenting a new challenge to the effective monitoring of transmission lines. The dynamic sensor network integrated with robots can effectively solve the elastic monitoring of transmission lines, but the problems of real-time performance, energy consumption and economy of the network need to be solved. To solve this problem, a dynamic network deployment method based on the hybrid hierarchical network (HHN) is proposed to realize a low-cost, energy-saving and real-time dynamic sensing system for overhead high-voltage transmission lines.

Obstacle distance measurement based on binocular vision for high-voltage transmission lines using a cable inspection robot.

Obstacle distance measurement is one of the key technologies for cable inspection robots on high-voltage transmission lines. This article develops a novel method based on binocular vision for extracting the feature points of images and reconstructing 3D scenes. The proposed method seamlessly incorporates camera calibration, dense stereo matching, and 3D reconstruction.

Dynamic Barrier Coverage in a Wireless Sensor Network for Smart Grids.

The development of engineering technology such as inspection robots (IR) for transmission lines and wireless sensor networks (WSN) are widely used in the field of smart grid monitoring. However, how to integrate inspection robots into wireless sensor networks is still a great challenge to form an efficient dynamic monitoring network for transmission lines. To address this problem, a dynamic barrier coverage (DBC) method combining inspection robot and wireless sensor network (WSN) is proposed to realize a low-cost, energy-saving and dynamic smart grid-oriented sensing system based on mobile wireless sensor network.

Multi-Robot Cyber Physical System for Sensing Environmental Variables of Transmission Line.

The normal operation of a power grid largely depends on the effective monitoring and maintenance of transmission lines, which is a process that has many challenges. The traditional method of the manual or remote inspection of transmission lines is time-consuming, laborious, and inefficient. To address this problem, a novel method has been proposed for the Multi-Robot Cyber Physical System (MRCPS) of a power grid based on inspection robots, a wireless sensor network (WSN), and multi-agent theory to achieve a low-cost, efficient, fault-tolerant, and remote monitoring of power grids.

Detecting Inspection Objects of Power Line from Cable Inspection Robot LiDAR Data.

Power lines are extending to complex environments (e.g., lakes and forests), and the distribution of power lines in a tower is becoming complicated (e.

A Novel Method of Autonomous Inspection for Transmission Line based on Cable Inspection Robot LiDAR Data.

With the growth of the national economy, there is increasing demand for electricity, which forces transmission line corridors to become structurally complicated and extend to complex environments (e.g., mountains, forests).

[Weighted TOPSIS method and weighted RSR method in the construction of drug supervision and supply networks in rural areas of Hunan].

Objective: To evaluate the rationality and validity of weighted TOPSIS method and weighted RSR method to evaluate drug supervision and supply networks construction in rural areas of Hunan .

Methods: Data of drug network construction in rural Hunan in 2010 were used to establish a comprehensive evaluation model, and weighted TOPSIS and RSR method were applied to this model and the results of which were compared to that of synthetical scored method to examine the validity.

Results: A comprehensive evaluation model was established, comprising of 3 primary indices, 8 secondary indices and 56 tertiary ones.

GC-MS-based metabolic profiling reveals metabolic changes in anaphylaxis animal models.

Clinical definition and appropriate management of anaphylaxis is a clinical challenge because there is large variability in presenting clinical signs and symptoms. Monitoring of the metabolic status of anaphylaxis may be helpful in understanding its pathophysiological processes and diagnosis. The purpose of this study was to conduct GC-MS serum metabolic profiling of anaphylaxis animal models and search for potential biomarkers of anaphylaxis.

Occurrence, fatality and time distribution of food poisoning in Hunan Province.

Objective: To explore the incidence, mortality, trends and time distribution of food poisoning in Hunan Province.

Methods: The data on food poisoning was derived from the Information Office of Hunan Provincial Health Department. Using the trend-test and circular distribution methods, we have described the current situation of food poisoning and tested the central tendency of the peak time points and the peak time zone of food poisoning in Hunan from 2000 to 2009.