Object detection, as a fundamental task in computer vision, has been developed enormously, but is still challenging work, especially for Unmanned Aerial Vehicle (UAV) perspective due to small scale of the target. In this study, authors develop special detection method objects UAV perspective. Based on YOLOv3, Resblock darknet first optimized by concatenating two ResNet units that have same width and height. Then, entire structure improved increasing convolution operation at an early layer...

Text-driven 3D stylization is a complex and crucial task in the fields of computer vision (CV) graphics (CG), aimed at transforming bare mesh to fit tar-get text. Prior methods adopt text-independent multilayer perceptrons (MLPs) predict attributes target with supervision CLIP loss. However, such architecture lacks textual guidance during predicting attributes, thus leading unsatisfactory slow convergence. To address these limitations, we present X-Mesh, an innovative text-driven framework...

This paper proposes an optimal sizing and control strategy for islanded microgrid, consisting of renewable energy sources such as wind turbine generators (WT) solar photovoltaic (PV), diesel (DE) battery storage system (BS). The problem is formulated to minimize the annualized cost (ASC) based on a with two modes. In mode 1, BS main power source DE backup power, but in 2, master unit assists improve reliability economic operation benefit. Combination strategy, particle swarm optimization...

Frequency control is a big challenge to an islanded microgrid, resulting from load and those intermittent microsources such as solar photovoltaic (PV) wind turbine (WT). A novel frequency scheme proposed enhances the anti interference ability for microgrid. The hierarchical structure designed according different net fluctuation range characteristics of battery storage system (BS) diesel generator (DE). primary regulation inverter based on droop strategy improve transient response, error...

Abstract Peak‐valley period partition of load curve is a key aspect time‐of‐use (ToU) tariff to improve power characteristics, such as shifting peak loads towards valley time periods. Fuzzy clustering algorithm an effective and popular method commonly used solve the peak‐valley curves, but it still encounters difficulty dividing some data within boundary regions different Therefore, this paper presents abnormal correction scheme for ToU tariffs under typical daily curves based on improved...

An optimal economic operation method is presented to attain a joint-optimization of cost reduction and strategy for islanded microgrid, which includes renewable energy source, the diesel generator, battery storage system. The optimization objective minimize overall generating involving depreciation cost, emission subsidy available while satisfying various equality inequality constraints. A novel dynamic process proposed based on two different control modes where generator or acts as master...

To overcome the limitations of digital simulation (numerical oscillation, limited computing capability processors, etc.), a converter-based hardware test-bed was developed at CURENT for real-time power grid emulation. However, distribution systems especially microgrids cannot be emulated and tested on existing test-bed. This paper develops microgrid based to enable controller testing with dynamic boundary. The design realization are introduced. experimental results tests also provided.

A triple-objective optimal sizing method based on a dynamic strategy is presented for an islanded hybrid energy microgrid, consisting of wind turbine, solar photovoltaic, battery storage system and diesel generator. The given complementary coordination between two different master-slave control modes maximum renewable utilization. Combined with the proposed strategy, NSGA-II-based optimization program applied to problem triple objectives including minimization annualized cost, loss power...

In order to achieve a prospective economic effect of renewable energy generations and vehicle grid (V2G), this paper proposes an optimal dispatch method wind-PV-battery microgrid considering V2G under time-of-use (TOU) tariffs for those isolated communities in remote islands mountainous areas. A cooperative strategy model are both presented the total operation cost minimization higher utilization generation. Finally, simulation results show that proposed is effective feasible.

Microgrids (MGs) with dynamic boundaries and multiple source locations have been proposed as a future MG concept, which requires sophisticated control coordination. Testing of controllers in realistic environment becomes essential for the efficient reliable deployment such MGs. A converter-based testing platform has controller evaluation, well-modeled emulators. However, core component, existing battery energy storage system (BESS) emulators literature cannot meet needs M G locations. In...

In the Vehicle-to-Grid (V2G) network, electric vehicles (EVs) transmit vehicle identity, battery details, state of charge, and current location to charging piles. Due wireless communication, a malicious adversary can eavesdrop on, modify, interrupt transmitted messages between Therefore, privacy concerns for EVs arise. To address challenge leakage, privacy-preserving authentication mechanism is essential Currently, numerous studies have explored anonymous preservation charging. But existing...

Abstract To predict the health status of lithium-ion batteries, long and short-term memory (LSTM) recurrent neural networks are used to build two types battery SOH evaluation models. The discharge capacity is as input a single feature model. While, charge capacity, time, average temperature, voltage, voltage multiple data samples separated training test dataset. results show that maximum absolute error LSTM-based model less than 2%, which satisfies industry standard (less 5%). Meanwhile,...

Differential geometric guidance command (DGGC) is widely acknowledged as a better method of endoatmospheric interception than three-dimensional (3D) pure proportional navigation (PPN).DGGC can be regarded an intelligent due to its sophisticated sense Lyapunov.However, traditional DGGC cannot guarantee line sight (LOS) finite time convergence (FTC) zero against maneuvering targets, particularly in regard stable, robust trajectory, which effectively lowers the overall intelligence method.This...

Accurate prediction of short-term photovoltaic output power is an important technical measure to improve the grid-connected capacity intermittent generation. A PV method proposed in this paper based on FCM-ISSA-LSTM as obvious problems low accuracy and poor applicability. Fuzzy-C-Means clustering (FCM) firstly used identify classify input data three types typical weather for all-weather historical data, then improved sparrow search algorithm (ISSA) presented optimize structure parameters...

Abstract During the storage and transportation of liquid hydrogen, damage pipeline or sealing failure valve may cause hydrogen leakage. The cryogenic combustible produced by leakage are dangerous. Because pressure is higher than atmospheric pressure, flash will occur in accident, resulting LH2 / H2 two-phase flow at port. In order to study effect evaporation on diffusion characteristics, CFD method used simulate leaking diffusing process different mass fractions evaporation. results show...

<title>Abstract</title> In modern hot strip mill control systems, tension is the core function, and its performance will be directly reflected in product quality. A prediction model based on Back Propagation (BP) neural network proposed. To ensure that true value obtained, this paper proposes a four-dimensional judgment mode for contact time between looper steel establishes data set of parameters rolled steel. The traditional BP network, genetic algorithm optimized (GA-BP), whale (WOA-BP)...

In response to the low level of agricultural production automation and labor shortage, improve efficiency machinery utilization reliability automatic navigation, this paper designs an intelligent system based on OpenMV for multi-vehicle unmanned following operations. Firstly, kinematics vehicle is analyzed, path recognition location line extraction are carried out using vision module, steering control designed cascade PID closed-loop technology, which achieves accurate tracking straight...