The finite/fixed-time stabilization and tracking control is currently a hot field in various systems since the faster convergence can be obtained. By contrast to asymptotic stability, finite-time stability possesses better performance disturbance rejection property. Different from fixed-time has speed upper bound of settling time estimated. Moreover, convergent does not rely on initial information. This work aims at presenting an overview its applications engineering systems. Firstly,...

Electricity is fundamental to the development of national economies and societies, reliant on accurate power load forecasting for its stable supply. Ultra-short-term analyzes historical data predict changes within next hour. This crucial achieving efficient dispatching, improving emergency management, ensuring operation system. However, with increasingly widespread application renewable energy, inherent intermittency exacerbates complexity randomness loads, posing a challenge models...

Detecting anomalies in temporal data has gained significant attention across various real-world applications, aiming to identify unusual events and mitigate potential hazards. In practice, situations often involve a mix of segment-level labels (detected abnormal with segments time points) unlabeled (undetected events), while the ideal algorithmic outcome should be point-level predictions. Therefore, huge label information gap between training targets makes task challenging. this study, we...

Abstract In order to solve the related problems of detection and tracking shallow marine organisms, this paper designs a YOLO v5 multi‐target algorithm with attention mechanism. When working underwater, authors usually encounter many difficulties. Different luminosity complex coral background affect organisms. At same time, unrestricted movement ability hide behind rocks algae, their mutual occlusion while swimming pose additional challenges task. Considering characteristics organisms...

A fixed evolutionary mechanism is usually adopted in the multiobjective algorithms and their operators are static during process, which causes algorithm not to fully exploit search space easy trap local optima. In this paper, a SPEA2 based on adaptive selection evolution (AOSPEA) proposed. The proposed can adaptively select simulated binary crossover, polynomial mutation, differential operator process according contribution external archive. Meanwhile, convergence performance of analyzed...

Sustainable digital cultural heritage is now an essential aspect of our lives. The rapid development 3D technology in the historic preservation industry provides means documenting, recovering, and presenting items. However, transformation sculpture often led by without effective evaluation indicators as a guide. This study compares assessment methods for forms with traditional art. Our approach uses semantic differential scales machine learning regression models to assess importance fifteen...

Matching the detection speed and accuracy in practical applications is considered to improve of video object front trains. Lightweight convolutional neural network MobileNet clustering ideas are combined algorithm, MYOLO-lite model algorithm designed. The self-made dataset a forward-moving train with K-means idea. transcendental frame redesigned enhance scale adaptability. nonmaximum suppression loss function improvement methods proposed for occluded tracks train, obstruction trains, low...

A sliding mode control law of formation for multiple underactuated surface vessels is proposed. The three degrees freedom dynamics model considered. Since the sway axis not directly actuated, are underactuated. obtained based on leader-following approach. controller designed by using Lyapunov's direct method and technique. In design, first-order in terms surge motion tracking errors second-order introduced. stability analysis taken Lyapunov theory. Numerical simulations provided to validate...

SUMMARY A novel 6-degree-of-freedom (DoF) parallel manipulator with three planar mechanism limbs is proposed and its kinematics statics are analyzed systematically. First, the characteristics of degree freedom calculated. Second, formulae for solving displacement, velocity, acceleration derived. Third, an analytic example given this manipulator, solved results verified by simulation mechanism. Finally, a workspace constructed based on comparison between another 6-DoF manipulator.

In this paper, a robust control strategy is developed for unmanned helicopter prototype to simultaneously deal with random wind disturbances and remote communication delays. First, in the system modeling, gust not only treated as bounded external load disturbance, but propeller force-thrust coefficient variation that caused by disturbance also considered. Then, equivalently treating delays input delays, attitude controller energy-to-energy performance system. Lyapunov-Krasovskii functions...

An adaptive neural network (NN) control scheme is proposed for path following of underactuated surface vessels with only the surge and yaw moment available, despite presence uncertain parameters unstructured uncertainties including exogenous disturbances measurement noise, etc. The developed by integrating an NN approach implementation global sliding mode control. A to provide a framework ensuring existence throughout entire response, can force system state be within region in which used...

Purpose The purpose of this paper is to present the design and implementation a new manipulator with six joints driven by single DC motor. Design/methodology/approach consists several modules, each which has twisting pivoting degrees freedom. Two clutches one brake are mounted control joint. A clutch model based on PWM built compute average velocity clutch. parameters involved in model: frequency duty ratio. limited natural frequencies structure all postures. theoretical ratio should be...

Aiming at the multi-objective optimization of punctuality, precise parking, comfort and energy consumption in train operation, an ATO control strategy based on genetic algorithm is proposed. Because operation process multi-objective, complex non-linear, there are internal contradictions evaluation index, no optimal for all indicators. This paper establishes index model performance system automatic curve. Design velocity-displacement curve (V-S curve) algorithm. The enables to automatically...

The dynamic model of high-speed trains (HSTs) is nonlinear and uncertain; hence, with the decrease in running interval HSTs, an accurate safe train operation control algorithm required. In this study, adaptive output feedback trajectory tracking method for HSTs proposed on basis neural network observers. aims to solve problems, such as immeasurable speed, parameter disturbance, unknown external disturbance HSTs. method, a observer designed estimate velocity HST. Another used approximate...

Circuit breakers on the filter bank branches in converter stations are vulnerable to contact wear and mechanical deterioration caused by frequent operations, which can lead circuit breaker breakdowns explosions. It is imperative conduct research early detection of abnormal states breakers. Existing electrical quantity-based methods constrained a priori assumptions, their measurement susceptible interference, leading misjudgments. To address this issue, paper examines influence changes...

This paper proposes a cascaded sliding-mode observer for systems with high relative degree and studies its applications in output feedback controller design. In part I, the working principle parameter design of proposed are discussed detail. It is proved that, within sufficiently short period time, states will reach intersection all sliding surfaces. On surfaces, observation error converge to small values. Compared traditional high-gain observers, has smaller gain coefficients. addition,...

Based on diffeomorphism equivalent transformation and backstepping technology, a feedback control law is proposed for three-DOF underactuated surface vessel with nonholonomic acceleration constraints. With the aids of Lyapunov redesign high gain techniques, system under disturbances displays robust characteristics. All signals in closed-loop are proved uniformly ultimately bounded by means direct method. Numerical simulation results given to illustrate effectiveness approach.

Rail transit plays an important role in alleviating urban traffic pressure and improving capacity. The traditional train automatic driving (ATO) system control strategy accurately controls the switching of working conditions by tracking accuracy target speed. This method consumes a large amount energy cannot be globally optimized. In order to better solve defects strategies, this paper proposes based on particle swarm optimization optimize multi-objective strategy. Under premise ensuring...