Gearbox bearings play an important role in wind power generation system. Their regular and stable operation will increase turbine improve the economic efficiency of farms. They often fail because they work under complex conditions. Therefore, it is necessary to find fault early. The vibration signal gearbox bearing has characteristics volatility continuity. Traditional diagnosis methods are based on analysis feature selection, process relatively complex. Deep learning can extract select...

Solar energy has intermittency and volatility, which poses a serious challenge to the stable safe operation of power grid. Accurate photovoltaic prediction is one key technologies solve this problem. Due larger volume data collected by systems, deep learning methods are more in-depth in field prediction. However, generation also diversity lower value density, brings severe challenges feature extraction ability models. Photovoltaic with mining capabilities urgently needed address these...

A large proportion of photovoltaic (PV) power generation is connected to the grid, and its volatility stochasticity have significant impacts on system. Accurate PV forecasting great significance in optimizing safe operation grid market transactions. In this paper, a novel dual-channel method based temporal convolutional network (TCN) proposed. The deeply integrates station feature data with model computing mechanism through architecture; utilizes combination multihead attention (MHA) TCN...

Accurate photovoltaic (PV) power forecasting allows for better integration and management of renewable energy sources, which can help to reduce our dependence on finite fossil fuels, drive transitions climate change mitigation, thus promote the sustainable development sources. A convolutional neural network (CNN) method with a two-input, two-scale parallel cascade structure is proposed ultra-short-term PV tasks. The dual-input pattern model constructed by integrating weather variables...

The bearing fault diagnosis of petrochemical rotating machinery faces the problems large data volume, weak feature signal strength and susceptibility to noise interference. To solve these problems, current research presents a combined ICEEMDAN-wavelet threshold joint reduction, mutual dimensionless metrics MPGA-SVM approach for diagnosis. Firstly, we propose an improved noise-reduction method Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) wavelet...

The vibration signals of hydropower units are nonstationary when serious vortex occurs in the draft tube hydraulic turbine. traditional signal analysis method based on Fourier transform is not suitable for signals. In face nonstationarity such and limitation empirical mode decomposition method, a new nonlinear analyzing variational (VMD) introduced into unit analysis. Firstly, VMD used to decompose an ensemble band-limited intrinsic functions components. Then, frequency spectrum these...

According to the non-stationary characteristic of rotating machinery vibration signals a rotor system with loose pedestal fault, variational mode decomposition was applied in looseness fault diagnosis for such system. Variational is used decompose signal into several stable components. This can achieve separation from background signals, and extract looseness. Experimental data were verify proposed method. The results showed that components obtained by have obvious amplitude modulation...

This paper presents a novel approach for optimizing wind farm control through the utilization of combined model predictive method. In contrast to conventional methods controlling active and reactive power in farms, suggested integrates prediction driven by neural network state-space turbines. combination facilitates more precise forecast power, thereby enabling dynamic range output from When with equation state space, it is possible accurately optimize farm. Furthermore, impact on voltage...

Accurate and reliable PV power probabilistic-forecasting results can help grid operators market participants better understand cope with energy volatility uncertainty improve the efficiency of dispatch operation, which plays an important role in application scenarios such as trading, risk management, scheduling. In this paper, innovative deep learning quantile regression ultra-short-term power-forecasting method is proposed. This employs a two-branch architecture to forecast conditional...

Abstract In recent years, China is actively developing wind power generation. Wind energy a natural factor with volatility, variability and uncontrollability, which will cause fluctuations in farm output. The accurate prediction of conducive to grid dispatchers deploying scheduling plans or doing ahead schedule Adjustments reduce losses certain extent are also improving grid-connected capacity. this paper, using the advantages empirical mode decomposition EMD algorithm nonlinear...

With a large proportion of wind farms connected to the power grid, it brings more pressure on stable operation systems in shorter time scales. Efficient and accurate scheduling, control decision making require high resolution forecasting algorithms with higher accuracy real-time performance. In this paper, we innovatively propose temporal method based light convolutional architecture—DC_LCNN. The starts from source data novelly designs dual-channel input mode provide different combinations...

Computer vision technology is being applied at an unprecedented speed in various fields such as 3D scene reconstruction, object detection and recognition, video content tracking, pose estimation, motion estimation. To address the issues of low accuracy high time complexity traditional image feature point matching, a fast image-matching algorithm based on nonlinear filtering proposed. By applying diffusion to images, details edge information can be effectively extracted. The descriptors...

Wind speed, wind direction, humidity, temperature, altitude, and other factors affect power generation, the uncertainty instability of above bring challenges to regulation control which requires flexible management scheduling strategies. Therefore, it is crucial improve accuracy ultra-short-term prediction. To solve this problem, paper proposes an prediction method with MIVNDN. Firstly, Spearman’s Kendall’s correlation coefficients are integrated select appropriate features. Secondly,...

In actual field testing environments of hydropower unit, unit vibration signals are often contaminated with noise. order to obtain the real signal, a signal de-noising method based on adaptive local iterative filtering (ALIF) and approximate entropy is presented. For proposed method, ALIF used decompose into several stable components. The each component calculated. According preset threshold value entropy, eligible components retained achieve noise cancellation unit’s signals. ALIF-based...

Virtual maintenance, which is widely used in aerospace, automobile, military equipment, etc., has been given abroad attention among equipment life-cycle including concept definition, system design, component production, daily operation, troubleshooting, and so on. maintenance many different definitions lot of technologies for implementation, but there no clear systematic conclusion on the both. Based review current achievements, elements virtual are extracted, systematically explored,...

A hybrid electric vehicle with battery pack and ultracapacitor is modeled because they are practicable to be energy storage units now. control strategy proposed regulate output power of units. Simulation model for the constructed in MATLAB/Simulink environment simulation performed. results show that effective performance satisfied.

In view of the problems that analytical inverse system decoupling method bearingless induction motor is sensitive to change parameters and greatly affected by unmodeled dynamics, traditional proportional–derivative controller lacking self-adaptive regulation ability, a neural network fuzzy self-tuning control strategy proposed for system. First, under conditions considering stator current dynamic torque winding, method, decoupled into four pseudo-linear integral subsystems. Second, improved,...

As for the inverse decoupling control system of a bearingless induction motor (BL-IM), in order to eliminate influence rotor resistance variation on its performance, basis reactive power calculation torque system, novel fuzzy model reference adaptive (MRAS) identification method is proposed. The and adjustable instantaneous are derived detail. In improve performance resistance, PI law based popov super stability theory constructed. On this basis, identifier constructed, it used on-line...

Ultra-short-term photovoltaic (PV) power forecasting is crucial in the scheduling and functioning of contemporary electrical systems, playing a key role promoting renewable energy integration sustainability. In this paper, novel hybrid model, termed AI_VMD-HS_CNN-BiLSTM-A, introduced to tackle challenges associated with volatility unpredictability inherent PV output. Firstly, Akaike information criterion variational mode decomposition (AI_VMD) integrates (VMD) reduces data complexity,...