Particle swarm optimization (PSO), an intelligent algorithm inspired by the flocking behavior of birds, has been shown to perform well and widely used solve continuous problem. But traditional PSO most its variants are developed for problems in space, which not able binary combinational To tackle this problem, Kennedy extended proposed a discrete PSO. performance is ideal just few further works were conducted based on it. In paper, we propose novel probability particle (PBPSO) problems....

This paper aims to improve the rapidity and accuracy of State Health (SOH) assessment for lithium-ion battery. By integrating Unscented Kalman Filter (UKF) Improved Particle (IUPF) algorithm, SOH can be effectively evaluated. The UKF algorithm is used estimate state charge (SOC), IUPF employed identify ohmic internal resistance. novelty proposed strategy relies on 4-dimensional filter that split into a 3-dimensional 1-dimensional filter. Experimental results demonstrate more faster rate...

Anomaly detection is an important challenge in wireless sensor networks for some applications, which require efficient, accurate, and timely data analysis to facilitate critical decision making situation awareness. Support vector description well applied anomaly using a very attractive kernel method. However, it has high computational complexity since the standard version of support needs solve quadratic programming problem. In this article, improved method on basis proposed, reduces used...

In recent years, a large number of wind power has been applied in the micro-grid (MG). Influenced by randomness characteristics speed, uncertainty output turbines imposes some safety and stability problems on optimal energy management MG. To address this problem, an expert system (EEMS) considering probability is developed study for dispatching typical grid-connected The EEMS composes probabilistic forecasting module, multi-objective optimization module storage (ESS) module. based...

Indoor location-based service is emerging as the crucial application of Internet Things, which promotes advance relevant technology in indoor scenario. Several positioning algorithms are proposed for different configurations recent years. The fingerprint-based algorithm has drawn much attention because good performance without additional hardware. However, false fingerprint matching frequently incurs due to complexity environment and affects accuracy. In this article, a principal component...

In order to handle the problem of frequency fluctuations caused by load disturbances in multi-area interconnected power systems, a sliding mode control strategy for hybrid energy storage system has been designed combining interval observer and disturbance reconstruction technology. The composed battery super capacitor used improve performance systems. Using model system, observers are each area get information about bounds state online. Then, is reconstructed online using estimation state,...

Dynamic principal component analysis (DPCA) is generally employed in monitoring dynamic processes and typically incorporates all measured variables. However, for a large-scale process, the inclusion of variables without fault-relevant information may cause redundancy degrade performance. In this paper, influence variable time-lagged selection on DPCA performance analyzed. Then, performance-driven distributed scheme proposed to achieve efficient fault detection diagnosis. First, process...

Aimed at the problem of false alarm and missing caused by information uncertainty existing in fire system, Bayesian network (BN) is proposed to analyze system. The paper elaborates internal logic relationship between physical-chemical characteristics generated process burning analyzing mechanism. Based on defining node variables BN, multi-sensor model for system established Netica. Probabilistic inference sensitivity analysis finding verified that probability through feasible effective.

Influenced by various environmental and meteorological factors, wind speed presents stochastic unstable characteristics, which makes it difficult to forecast. To enhance the forecasting accuracy, this study contributes short-term multi-step hybrid (WSF) models using wavelet packet decomposition (WPD), feature selection (FS) an extreme learning machine (ELM) with parameter optimization. In model, WPD technique is applied decompose empirical data into different, relatively stable components...

The integration of multi-energy systems increases renewable penetration and efficiency energy use, reduces costs. This is further reinforced by new technologies, such as cross-vector demand response power-to-gas bringing big flexibility to system operation. paper studies the optimal operation multi-vector systems, considering with technology using robust optimization. An hub (EHS) considered realization a system, which consists (a) two-way converters between electricity gas, (b) an storage...

Generally, the existing methods for constructing a knowledge graph used in question answering system adopted two different models respectively, one is identifying entities, and other extracting relationships between entities. However, this method may reduce quality of because it very difficult to keep contextual information consistent with same entities models. To address issue, paper proposes model called GPB (GlobalPointer + BiLSTM) which integrates BiLSTM into GlobalPointer through...

This paper is concerned with the indoor target tracking system based on received signal strength (RSS) and angle of arrival (AOA) combined measurements. Aiming at nonlinear state estimation multi-sensor fusion problem under correlation local error, a high-order modified extended Kalman particle filter (HM-EKPF) improved proposal distribution proposed. The effect truncation errors accuracy reduced by updating compensating covariance prediction measurement error. A method cross-covariance...

Given the large-scale exploitation and utilization of wind power, problems caused by high stochastic random characteristics speed make researchers develop more reliable precise power forecasting (WPF) models. To obtain better predicting accuracy, this study proposes a novel compound WPF strategy optimal integration four base engines. In process, density-based spatial clustering applications with noise (DBSCAN) is firstly employed to identify meaningful information discard abnormal data....

In order to achieve zero voltage switch (ZVS) and current (ZCS) of half-bridge LLC resonant converter, an optimal design method the converter was presented. this work, a detailed optimization procedure is proposed optimize parameters. The main circuit steady state equivalent model established based on fundamental harmonic approximation (FHA). By means normalization DC gain, zero-voltage-switching condition theoretically analyzed, key parameters including quality factor, magnetic inductor,...

With the increasing demand for indoor location-based services, received signal strength fingerprinting-based localization algorithm has become a research focus due to its accuracy and low hardware requirements. However, how achieve accurate location discovery relies solely on under sparse reference points condition, which is main contribution of this paper. First, Voronoi diagram adopted regionalize positioning area form distributed propagation description, can reduce influence environment...