In today's increasingly serious world energy crisis, Renewable such as wind has gradually penetrated into life. Aiming at the uncertainty of power and need a mass sample data in nonparametric kernel density estimation, interval prediction method based on hybrid semi-cloud model estimation is proposed. Firstly, aiming asymmetrical distribution error, qualitative description error concept using And conceptual produced by are filtered through "3En rule". Secondly, according to fitting...

The state of lithium-ion battery is a key indicator for the management system (BMS) electric vehicles (EVs). State charge (SOC) and health (SOH) power cell are main parameters BMS during operation. In this paper, an adaptive unscented Kalman filter algorithm (AUKF) presented joint estimation SOC SOH batteries. Firstly, paper develops 2-RC equivalent circuit model identifies using recursive least squares with forgetting factor. Then, estimated simultaneously by AUKF. Finally, accuracy...

Because of its clean and green, wind power is broadly used all over the world. Wind random unstable, so integration will inevitably bring great impact to system. Accurate prediction can effectively alleviate caused by uncertainty. In order increase accuracy prediction, this article uses paper swarm optimization algorithm (PSO) improve traditional Kalman filter, PSO-Kalman point model established. The proposed solves problem low filter observation noise process noise. Finally, based on error,...

The development of accurate data-driven models is great significance for online monitoring and control industrial processes. In this study, a nonlinear dynamic soft-sensing algorithm measuring predicting the nitrogen oxides (NOx) emissions denitration system power plant was developed. First, processes principles were studied. Second, based on long short-term memory (LSTM) least absolute shrinkage selection operator (LASSO) proposed. dynamics process captured by LSTM, influential input...

Most of the current wind power interval forecast methods are based on assumption point error is subject to a known distribution (such as normal distribution, beta etc.). The obtained after solving confidence distribution. However, this does not reflect truth because random and necessary obey any Moreover, method for calculating only good Therefore, those cannot be applied generally, quality good. In paper, general proposed determine optimal power. Firstly, found by using non-parametric...

In the study, we propose an adaptive variable selection algorithm for multi-layer perceptron (MLP)-based soft sensors. The proposed employs nonnegative garrote (NNG) to shrink input weights of trained MLP. To improve shrinkage efficiency NNG, operators are designed using mean impact value estimate. Moreover, data dependent, and introduced into constraints NNG make more efficient effective. Cross-validation Bayesian information criterion used determine optimal parameter NNG. performance is...

To better track the planned output (forecast output), energy storage systems (ESS) are used by wind farms to compensate forecast error of power and reduce uncertainty output. When compensation degree is same, interval not unique, different intervals need ESS sizing. This paper focused on finding optimal only satisfied but also obtained max profit farm. First, a mathematical model was proposed as well corresponding optimization method aiming at maximizing Second, effect influencing factors...

Industrial processes are often nonlinear and multivariate suffer from non-Gaussian noise outliers in the process data, which cause significant challenges data-driven modelling. To address these issues, a robust soft-sensing algorithm that integrates Huber’s M-estimation adaptive regularisations with multilayer perceptron (MLP) is proposed this paper. The algorithm, called RAdLASSO-MLP, starts an initially well-trained MLP for Subsequently, residuals of model robustified to improve resistance...

In recent years power quality (PQ) has become a major concern to both utilities and customers. How extract features of disturbances from large number signals how recognize them automatically are important for further understanding improving quality. The paper presents an identification scheme online monitoring system caused by nonlinear loads. wide proliferation distributed renewable energy green sources, rapid changes in utility load types require affordable robust on-line data acquisition...

By grafting with ethylene diamine tetraacetic acid (EDTA), novel multi-walled carbon nanotube nano-composites (EDTA-MWCNTs) have been successfully prepared. The integration of gold nanoparticles (AuNPs) and functionalized matrix shows very promising applications in the fabrication biosensors for sensitive detection dopamine presence ascorbic uric combination chargerepelling property carboxylic anion electrocatalytic effect EDTA. AuNPs EDTA-MWCNTs modified film excellent sensitivity...

Harmonic voltages at PCC of a power grid are the combinations voltage contributions each harmonic source located in same grid. In particular, quantifying customers and utility system is highly important for quality management. This paper presents new method identification problems: how to quantify levels observed network location. The first defines problem. It then statistical correlation based estimate index. characteristics proposed investigated through case studies. Finally, improvements...

In order to overcome the high volatility caused by single-phase voltage curve and improve accuracy of judging whether two substation areas belong same 10 kV line. The reduction method outlet transformer with unbalanced three-phase load is proposed in this paper. Simulation models have also been built calculate transformer. results simulation compared. Results show that are consistent results. Although there exist differences between method, but tolerable. It can be concluded paper has good...

The uncertain and stochastic output of the wind farm results in a lot problems when it is connected to power grid. In order improve power's friendship grid, should has certain self-discipline level. this paper, studied from perspective interval. First, concept interval proposed, followed by comprehensive index which used evaluate level comprehensively considering width accuracy. Second, an optimization method discussed obtain optimal This general applicability, not only suitable for normal...

Wind power point prediction can only give the exact predicted value at a certain time point, and fluctuation range of cannot be obtained, which brings lot problems troubles to wind grid connection. In this paper, short-term interval method based on Kalman filter non-parametric kernel density estimation is proposed. First, points obtained by method; Second, error statistically analyzed, probability function Finally, under given confidence degree. Simulation analysis data farm in Oklahoma show...

<title>Abstract</title> LiDAR has become a prominent technology in 3D sensing due to its reliable distance detection. However, the sparse point cloud data it produces, particularly during long-range scanning, poses challenges for processing. To overcome this, we developed novel system with focusing functionality improve density when scanning objects. The system, which comprises MEMS mirror-based and CMOS camera, leverages adjustable light beam steering of mirror dynamically alter laser angle...

In order to analyze the temperature rise of transformer body under AC-DC conditions, this paper investigates losses DC bias magnetism based on finite element method. The electric-magnetic-thermal coupling model three-phase three-column is established, and transient electromagnetic field calculated by using COMSOL software, calculation results are coupled cell according grid obtain distribution core winding three-dimensional different magnetization. show that leads increase losses, in area...

Due to the strong volatility of wind power generation, it will have an impact on safe operation system, while accurate prediction helps stable grid. In order improve accuracy prediction, this paper proposes a hybrid model based Variational Mode Decomposition (VMD) and using Grey Wolf Optimization (GWO) optimize hyperparameters Long Shor-Term Memory (LSTM) network. Firstly, initial sequence is decomposed into multiple modal components by VMD sample entropy value each calculated, sequences...