The emergence of smart grids has posed great challenges to traditional power system control given the multitude new risk factors. This paper proposes an online supplementary learning controller (OSLC) design method compensate controllers for coping with dynamic grid. proposed OSLC is a based on approximate programming, which works alongside existing controller. By introducing action-dependent cost function as optimization objective, nonidentifier-based provide optimal adaptively measurement...

An analysis of the relationship between rheumatoid arthritis (RA) and copper death-related genes (CRG) was explored based on GEO dataset.Based differential gene expression profiles in GSE93272 dataset, their to CRG immune signature were analysed. Using 232 RA samples, molecular clusters with delineated analysed for infiltration. Genes specific CRGcluster identified by WGCNA algorithm. Four machine learning models then built validated after selecting optimal model obtain significant predicted...

Policy iteration approximate dynamic programming (DP) is an important algorithm for solving optimal decision and control problems. In this paper, we focus on the problem associated with policy approximation in DP discrete-time nonlinear systems using infinite-horizon undiscounted value functions. Taking error into account, demonstrate asymptotic stability of under our setting, show boundedness function during each step, introduce a new sufficient condition to converge bounded neighborhood...

In order to solve the AGV vehicle path planning problem, this paper uses improved genetic algorithm makes improvements in each step on basis of traditional algorithm. First, real number coding and heuristic population initialization are performed. The fitness function adds obstacle avoidance smoothness modules enhance reliability. When selecting operators, elite strategy with three-stage selection roulette wheel gambling adopted, adaptive cross mutation factors used for evolutionary...

Doubly fed induction generators (DFIGs) are widely used in wind power generation. For controlling DFIGs to maintain network frequency within a safety range, the proportional-derivative (PD) type virtual inertia controllers (VIC) active control of DFIGs. However, as is well known, generation conditions change directly with nature. Such changes create great challenge for VIC design and actually force designs go beyond traditional problem formulation using explicit objective functions...

In this study, we investigated the prevalence of

Intermittent electricity generation from renewable sources is characterized by a wide range of fluctuations in frequency spectrum. The medium-frequency component 0.01 Hz-1 Hz cannot be filtered out system inertia and automatic control (AGC) thus it results deterioration quality. In this paper, an approximate dynamic programming (ADP) based supplementary controller for thermal generators developed to attenuate fluctuation range. A policy iteration training algorithm employed online model-free...

Dynamic reactive power control of doubly fed induction generators (DFIGs) plays a crucially important role in maintaining transient stability systems with high penetration DFIG based wind generation. Based on approximate dynamic programming (ADP), this paper proposes an optimal adaptive supplementary controller for DFIGs. By augmenting corrective regulation signal to the command rotor-side converter (RSC) DFIG, is designed reduce voltage sag at point common connection (PCC) during fault, and...

The coupling cavity theory is used to analyze the impact of high side mode suppression ratio (SMSR) on fiber grating external semiconductor lasers (FGECSL). SMSR and stable frequency FGECSLs were obtained by experiment. center wavelength 974 nm, 45 dB, change rate reaches 3.08 ppm/°C in temperature range −20 80 °C.

There is an extensive literature on value function approximation for approximate dynamic programming (ADP). Multilayer perceptrons (MLPs) and radial basis functions (RBFs), among others, are typical approximators in ADP. Similar approaches have been taken policy approximation. In this paper, we propose a new Volterra series based structure actor The approx-imator linear parameters with global optima attainable. Given the proposed approximator structures, further develop iteration framework...

This study presents a novel fault diagnosis model for urban rail transit systems based on Wavelet Transform Residual Neural Network (WT-ResNet). The integrates the advantages of wavelet transform feature extraction and ResNet pattern recognition, offering enhanced diagnostic accuracy robustness. Experimental results demonstrate effectiveness proposed in identifying faults trains, paving way improved maintenance strategies reduced downtime.

Extensive approximate dynamic programming (ADP) algorithms have been developed based on policy iteration. For iteration ADP of deterministic discrete-time nonlinear systems, existing literature has proved its convergence in the formulation undiscounted value function under assumption exact approximation. Furthermore, error bound analyzed a discounted with consideration approximation errors. However, there not any analysis In this paper, we intend to fill theoretical gap. We provide...

An approximate dynamic programming (ADP) based supplementary learning control method is developed to online improve the performance of existing controllers. The proposed structure can make full use prior knowledge pre-designed controller and endow with ability. Moreover, by introducing action dependent value function for policy evaluation, work in a model-free manner. iteration algorithm employed train actor-critic ADP controller. Simulation studies are carried out on cart-pole system...

A non-dominated sorting differential evolution algorithm with improved directional convergence and spread (NSDE-IDCS) is developed. Taking advantage of evolution, searching direction for a dominated solution determined by its nearest neighbor, while other two solutions. simplex local search operator an adaptive probability embedded to further exploit the neighborhood

Controller parameter tuning is an integral part of control engineering practice. Existing methods usually start with accurate mathematical model the controlled system, which may pose some challenges for practicing engineers dealing real systems. As such, optimization and adaptation are treated as two independent steps during tuning. To address these issues, we propose a new, online parameterized controller method general nonlinear dynamic system. This based on direct heuristic programming...

In order to improve the working efficiency and motion stability of robot, a time-pulsation optimal trajec-tory planning method based on improved firefly algorithm B-spline interpolation was proposed in joint space. First, series desired path points manipulator were set according task requirements, corresponding angles obtained by inverse kinematics, quintic non-uniform curve functions constructed ensure continuity C4. Under premise considering constraints, weight coefficient optimization...