Low fault diagnosis accuracy in case of the insufficient and imbalanced samples is a major problem wind turbine diagnosis. The imbalance refers to large difference number different categories, or lack certain sample, which requires good learning characteristics small samples. Sample generation deep model can effectively solve this problem. In study, we proposed novel multi-class bearing strategy based on conditional variational generative adversarial network (CVAE-GAN) combining multi-source...

To study the impact of personal carbon trading (PCT) mechanism on economy and reliability power distribution system operation, this paper proposes an orderly charging discharging strategy for electric vehicles (EVs) that integrates a dynamic update tariff revenue, taking into account travel characteristics EVs users' willingness to respond. First, probability density time parameters is calculated based improved kernel estimation method. Second, emissions at each stage lifecycle are using...

Battery State of Health (SOH) estimation is crucial for providing valuable information optimizing battery usage and improving efficiency. Considering the uncertainties in charging behavior during practical usage, this paper proposes an ensemble model based on improved long short-term memory (LSTM) neural network. The takes random segments curves as input to estimate SOH lithium-ion batteries. In paper, a multi-layer LSTM network with attention mechanism proposed base learner. Then, multiple...

The graphdiyne (GD), a carbon allotrope with 2D structure comprising benzene rings and carbon–carbon triple bonds, can be synthesized through cross-coupling on the surface of copper foil. key problem is in understanding dependence layers number properties, however, controlled growth numbers GD film have not been demonstrated, its into large-area high ordered films different still an important challenge. Here, we show that new strategy for synthesizing nanostructures ZnO nanorod arrays...

The fault characteristics of the rolling bearings wind turbine gearboxes are unstable under actual operating conditions. Problems such as inadequate sample data, imbalanced data types, and noise labels (error labels) in historical occur. Consequently, accuracy gearbox bearing diagnosis conditions is insufficient. Hence, a new method for proposed. It uses an improved label-noise robust auxiliary classifier generative adversarial network (rAC-GAN) driven by limited data. rAC-GAN realizes batch...

Abstract Virtual synchronous generator technology can effectively improve the anti‐interference characteristics of system frequency and bus voltage in microgrid, solve problems insufficient damping low inertia system. However, an islanded microgrid with multiple distributed generation, difference line impedance will cause local deviations, which turn leads to a series problems, such as reducing power distribution accuracy increasing drop. Therefore, for island‐type multi‐inverter generation...

Abstract Inertial support for hybrid AC/DC microgrid systems is provided by the virtual synchronous generator (VSG). However, fast performance of system neglected while enhancing stability system. To address this problem, an adaptive inertia control strategy based on VSG technology proposed. This approach adaptively adjusts when operation deviates from nominal value, slowing down rate change AC frequency and DC voltage improving deviation voltage. Meanwhile, restore back to rated accelerated...

Abstract In the microgrid, virtual synchronous generator technology can significantly enhance anti‐interference characteristics of system frequency and bus voltage, as well solve problems insufficient damping low inertia. However, active power oscillation caused by fluctuations grid faults threaten stable operation seriously. Therefore, for an alternating current (AC) microgrid multi‐virtual (VSG) parallel system, improved control algorithm based on a fuzzy inference is proposed, which...

Purpose This paper aims to study the issues of adaptive fuzzy control for a category switched under-actuated systems with input nonlinearities and external disturbances. Design/methodology/approach A scheme based on sliding mode surface hierarchical structure is introduced enhance responsiveness robustness studied systems. An equivalent switching rules are co-designed in (HSMC) framework ensure that system state reaches given remains surface, finally stabilizing at equilibrium point....

Battery cell voltage is an important evaluation index for electric vehicle condition estimation and one of the main monitoring parameters battery management system, accurate prediction crucial failure warning. Therefore, this paper proposes a novel hybrid gated recurrent unit long short-term memory (GRU-LSTM) neural network to predict lithium-ion voltage. Firstly, Pearson coefficient correlation analysis carried out determine input by analyzing influence factors parameters, hyperparameters...

In this paper, the distributed model predictive load frequency control problem for virtual power plants (VPPs) under cloud-edge-terminal framework is addressed, where data packets are transmitted a novel dynamic event-triggered mechanism (DETM) with hybrid variables. The proposed DETM has ability to flexibly manage packet releases and reduce network congestion, thus decreasing communication delay of VPP. A method DETM-based (DMPC) proposed, which can shorten processing time further decrease...

Abstract In this study, a type of all‐degradable flame retardant wood/poly(lactic acid) (PLA) biocomposite (FPW) with low cost and excellent mechanical properties is prepared studied. A novel lignin‐based phosphorus‐containing (LMD) synthesized first. PLA, wood powder, poly(butyleneadipate‐ co ‐terephthalate), triglycidyl isocyanurate (TGIC), LMD are then melt‐blended to prepare FPW. The limiting oxygen index value PLAF25L15‐4T (25% L15MD 4% TGIC) reaches 28.6%. Furthermore, the residue at...

In an islanded microgrid with multiple distributed generations (DGs), the difference in line impedance may cause local voltage deviation, which leads to a series of problems such as lower power allocation accuracy and bus drop under traditional droop control. this respect, method for optimizing control using improved particle swarm optimization (IPSO) is proposed. Firstly, structure influence parameters on strategy analyzed. Then, Based basic (PSO) algorithm, fuzzy inference system (FIS)...

The optimal allocation of energy storage capacity is an important issue for integrated systems (IES). To reduce the impact volatility and intermittency renewable sources, needs to be smoothed out by rational storage. address above issues, this paper proposes a method source considering demand response(IDR). Firstly, basic mechanism IES based on hub(EH) constructed, model coupling relationship equipment components in system are introduced. IDR built optimize load curve according real-time...

The stress–strain curves for shale specimens under different fluids saturation.

A cooperative flame-retardant system based on natural intumescent-grafted bamboo charcoal (BC) and chitosan (CS) was developed for polylactic acid (PLA) with improved flame retardancy minimal decline in strength properties. Chitosan as an adhesion promoter the interfacial compatibility between graft-modified (BC-m) PLA leading to enhanced tensile properties by 11.11% 8.42%, respectively modulus. At 3 wt.% CS 30 BC-m, crystallinity of composite increased 38.92%, or 43 times that pure (0.9%)....

Abstract The finite-time tracking control issue for a class of nonlinear pure-feedback system with prescribed performance and unknown hysteresis is investigated in this work. To solve the Bouc-Wen parameters direction conditions, Nussbaum function auxiliary virtual are used. A applied performance, which can make error limited to pre-given boundary finite time. Moreover, mean-value theorem difficulty form. Combined backstepping technique, an adaptive scheme designed sure that all closed-loop...

Accidents involving electric vehicle fires have increased as the number of vehicles has grown recently. The issue charging safety is a key barrier to growth sector because these accidents resulted in large financial losses for car owners and facility operators. approach resolving through an warning system suggested this research. solution uses adaptive optimization long short-term memory neural network (A-LSTM) forecast voltage changes throughout whole process by using vehicle's daily...

Residents clustering in different periods of load fluctuation and aggregated forecasting can increase the prediction accuracy. But strength reflects difference electricity consumption behavior residents affects cluster results residents. This paper presents a new day-ahead load-forecasting method for distribution networks based on feature importance (FI) profile First, input features are determined, FI is clustered according to profile. Then, crow search algorithm used optimize initial...

Low carbon operation of power systems is a key way to achieve the goal energy peaking and neutrality. In order promote low transition coordinated optimized distributed sources in virtual plants (VPP), this paper proposes framework for collaborative utilization pumped storage–carbon capture–power-to-gas (P2G) technologies. It also constructs multi-time scale economic dispatch model VPP minimize internal resource cost each time period. During intraday scheduling stage, day-ahead results as...