Insulator is an important part of transmission line. Defective insulators will cause potential safety hazard to transmission lines. Image detection technology can improve the efficiency of insulator defect detection and greatly reduce the maintenance cost. However, the existing insulator defect detection technology has the disadvantages of low accuracy and long detection time. An insulator defect detection method based on improved ResNeSt and Region Proposal Network (RPN) was proposed. First, this method builds a new network based on ResNeSt. Secondly, we added the improved RPN to the improved ResNeSt for feature extraction, to better detect minor defects on insulators. Finally, we enhanced the data processing and labeled the open insulator data set. On this data set, the proposed model is tested and a large number of controlled experiments are done. The results show that the proposed network is more accurate and faster than the control group. Moreover, the proposed network has an accuracy rate of 98.38% for insulator defect detection, which can detect 12.8 pictures per second. The proposed method has good efficiency and practicability in aerial photo insulator defect detection.
This paper develops an improved distributed finite-time control algorithm for multiagent-based ac microgrids with battery energy storage systems (BESSs) utilizing a low-width communication network. The proposed control algorithm can simultaneously coordinate BESSs to eliminate any deviation from the nominal frequency as well as solving state of charge (SoC) balancing problem. The stability of the proposed control algorithm is established using Lyapunov method and homogeneous approximation theory, which guarantees an accelerated convergence within a settling time that does not dependent on initial conditions. Based on this, to significantly reduce the communication burdens, an event-triggered communication mechanism is designed which can also avoid Zeno behavior. Then sufficient conditions on the event-triggered boundary are derived to guarantee the stability and reliability of the whole systems. Practical local constraints are imposed to implement the control protocol, and the theoretical results are applied to a test system consisting of five DGs and five BESSs, which verifies the effectiveness of the proposed strategy.
Index TermsFrequency restoration, SoC balancing, finite-time control, event-triggered, multi-agent systems.
I. INTRODUCTION
IN islanded microgrids (MGs), the intermittent characteristics of most DERs may cause load perturbations and significantly affect the system frequency in relatively small ac microgrids. Thus, the control of a microgrid is essential to improve the frequency synchronization performance. However, the primary droop controllers, locally implemented at each distributed DG unit, may lead to a steady-state deviation from the nominal frequency value due to the power mismatch [1]. To accommodate this, BESSs in an islanded ac MG can enhance the system stability and reliability through being charged by DERs or discharged for peak shaving or supporting local loads during grid failures and electrical shortages [2]. The BESSs are therefore indispensable modules that can buffer short-term power imbalances among DERs and loads [3]. At the same time, the state of charge (SoC) balancing problem which may result in the overcharging and overdischarging actions of BESSs arises [4]-[6]. However, a few works focus on solving the frequency restoration and SoC balancing problems at once. Coordination of BESSs in the microgrid can be regarded as a multi agent system (MAS), then the distributed control structure that only requires information exchange among neighboring components through a local communication network is
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.