查看更多>>摘要：Motion planning and control of autonomous mobile robots(AMRs)have attracted widespread attention in recent years.As the problem of aging intensifies,it is significant to develop AMRs for the wellbeing of old people.In this paper,a novel long short-term memory(LSTM)-recurrent deep neural network(RDNN)based motion planning and control strategy with data aggregation mechanism is developed for autonomous wheelchairs(AWC)to send the seniors to the exit of the nursing home in a timely manner when emergencies happen.The proposed scheme is ver-ified to be feasible,efficient and robust.
查看更多>>摘要：In today's world where everything is interconnected,air-space-ground integrated net-works have become a current research hotspot due to their characteristics of high,long and wide area coverage.Given the constantly changing and dynamic characteristics of air and space net-works,along with the sheer number and complexity of access nodes involved,the process of rapid networking presents substantial challenges.In order to achieve rapid and dynamic networking of air-space-ground integrated networks,this paper focuses on the study of methods for large-scale nodes to randomly access satellites.This paper utilizes a cross-layer design methodology to enhance the access success probability by jointly optimizing the physical layer and medium access control(MAC)layer aspects.Load statistics priority random access(LSPRA)technology is proposed.Experiments show that when the number of nodes is greater than 1 000,this method can also ensure stable access performance,providing ideas for the design of air-space-ground integrated network access systems.
查看更多>>摘要：The novel aircraft engine-off taxi towing system featuring aircraft power integration has demonstrated significant advantages,including reduced energy consumption,diminished emissions,and enhanced efficiency.However,the aircraft engine-off taxi towing system lacks the consideration of attendant constraints in the trajectory generation process,which can potentially lead to ground accidents and constrain the improvement of traction speed.Addressing this challenge,the present work investigates the optimal control problem of trajectory generation for the taxiing traction sys-tem in the complex stochastic environment in the airport flight area.For the stochastic constraints,a strategy of deterministic processing is proposed to describe the stochastic constraints using ran-dom constraints.Furthermore,an adaptive pseudo-spectral method is introduced to transform the optimal control problem into a nonlinear programming problem,enabling its effective resolution.Simulation results substantiate that the generated trajectory can efficiently handle the stochastic constraints and accomplish the given task towards the time-optimization objective,thereby effec-tively enhancing the stability and efficiency of the taxiing traction system,ensuring the safety of the aircraft system,and improving the ground access capacity and efficiency of the airport.
查看更多>>摘要：The paper proposes a wireless sensor network(WSN)localization algorithm based on adaptive whale neural network and extended Kalman filtering to address the problem of excessive reliance on environmental parameters A and signal constant n in traditional signal propagation path loss models.This algorithm utilizes the adaptive whale optimization algorithm to iteratively optimize the parameters of the backpropagation(BP)neural network,thereby enhancing its predic-tion performance.To address the issue of low accuracy and large errors in traditional received sig-nal strength indication(RSSI),the algorithm first uses the extended Kalman filtering model to smooth the RSSI signal values to suppress the influence of noise and outliers on the estimation results.The processed RSSI values are used as inputs to the neural network,with distance values as outputs,resulting in more accurate ranging results.Finally,the position of the node to be mea-sured is determined by combining the weighted centroid algorithm.Experimental simulation results show that compared to the standard centroid algorithm,weighted centroid algorithm,BP weighted centroid algorithm,and whale optimization algorithm(WOA)-BP weighted centroid algorithm,the proposed algorithm reduces the average localization error by 58.23%,42.71%,31.89%,and 17.57%,respectively,validating the effectiveness and superiority of the algorithm.
查看更多>>摘要：This paper proposes an adaptive predefined-time terminal sliding mode control(APTSMC)scheme for attitude tracking control of a quadrotor.To create this,an adaptive prede-fined-time stability controller based on a terminal sliding mode is constructed.The upper bound of convergence time in the proposed scheme can be adjusted by the explicit parameters during the design process of the controller.In addition,it is proved that the attitude tracking error will con-verge within two periods of the preset time.These two periods are set between two ranges:From the initial values to the sliding mode surface and from the sliding mode surface to the region near the origin.Furthermore,an adaptive law is adopted to eliminate unknown external disturbances and the effects of the uncertainties in the quadrotor model,so it is unnecessary to require the prior knowledge of the upper bound of the perturbations.Simulation results are produced and compara-tive case studies are carried out to demonstrate that the proposed scheme has faster convergence speed and smaller tracking errors.
查看更多>>摘要：This paper proposes a robust control scheme based on the sequential convex program-ming and learning-based model for nonlinear system subjected to additive uncertainties.For the problem of system nonlinearty and unknown uncertainties,we study the tube-based model predic-tive control scheme that makes use of feedforward neural network.Based on the characteristics of the bounded limit of the average cost function while time approaching infinity,a min-max opti-mization problem(referred to as min-max OP)is formulated to design the controller.The feasibil-ity of this optimization problem and the practical stability of the controlled system are ensured.To demonstrate the efficacy of the proposed approach,a numerical simulation on a double-tank sys-tem is conducted.The results of the simulation serve as verification of the effectualness of the pro-posed scheme.
查看更多>>摘要：In the field of remote sensing,the rapid and accurate acquisition of the category and location of airplanes has emerged as a prominent research.However,remote sensing fuzzy imaging and complex environmental interference affect airplane detection.Besides,the inconsistency in the size of remote sensing images and the low accuracy of small target detection are crucial challenges that need to be addressed.To tackle these issues,we propose a novel network SDaDCS(SAHI-data augmentation-dilation-channel and spatial attention)based on YOLOX model and the slicing aided hyper inference(SAHI)framework,a new data augmentation technique and dilation-channel and spatial(DCS)attention mechanism.Initially,we create a remote sensing dataset for airplane tar-gets and introduce a new data augmentation technique based on the Rotate-Mixup and mixed data augmentation to enhance data diversity.The DCS attention mechanism,which comprises the dilated convolution block,channel attention and spatial attention,is designed to bolster the feature extraction and discrimination of the network.To address the challenges arised by the difficulties of detecting small targets,we integrate the YOLOX model with the SAHI framework.Experiment results show that,when compared to the original YOLOX model,the proposed SDaDCS remote sensing target detection algorithm enhances overall accuracy by 13.6%.The experimental results validate the effectiveness of the proposed algorithm.
查看更多>>摘要：This paper discusses the design of resilient and event-triggered control for linear aperi-odic sampled-data systems.The stability and stabilization problem of the aperiodic sampled-data systems under a dynamic event-triggered scheme and against a stochastic deception attack is addressed in a novel looped-functional framework.A quadratic event-triggered scheme with a dis-crete-time dynamic variable is proposed in which the system states are only evaluated at aperiodic sampling instants so that the Zeno phenomenon can be avoided consequently.The system is assumed to be intruded by a deception attack signal which is determined by a Bernoulli random variable.Our objective in this paper is to derive the stability conditions firstly and then provide the resilient and event-triggered controller design for the aperiodic sampled-data system.With a cer-tain H∞ performance index,the closed-loop system is stochasticlly stable against the deception attack and the control updates can be obviously reduced by the proposed dynamic event-triggered scheme,which means the system performance,the limited communication resources,and the sys-tem security can be well balanced in our design.Finally,the validity and effectiveness of the pro-posed method is demonstrated by the simulations.
查看更多>>摘要：In order to reduce the temperature difference caused by condensed water in vulcanized tire capsules,the flow field and temperature field inside vulcanized tire capsules were numerically simulated by setting three different intake angles based onvolume of fluid(VOF)multiphase flow model.When the intake air is blown to the upper and lower tire sides of the vulcanized capsule at 18° from the horizontal direction,the distribution of condensed water at the bottom of the capsule changes obviously due to the effect of vorticity flow,and the distribution along the wall is more uniform.When the inlet air is blown down the tire side,the condensate is most evenly distributed along the wall,and the maximum temperature difference drops to 9.5℃.The results show that changing the distribution of condensed water by adjusting the proper intake angle can effectively reduce the temperature difference of condensed water in vulcanized capsules.
查看更多>>摘要：Buck-Boost converter in the total dose radiation environment will mainly bring the out-put voltage drift,linear adjustment rate and load adjustment rate decline and other effects,so that the output stability performance of the circuit deteriorates.Aiming at the problems of high cost,large layout area and poor universality caused by the traditional total ionizing dose effect harden-ing method based on process and layout,this paper proposes a total ionizing dose effect hardening design method with parallel monitoring and hardening,which can achieve total ionizing dose effect hardening at the circuit level without process.The anti-total dose capability of Buck-Boost con-verter is improved.The circuit design and physical implementation of the proposed method are ver-ified based on 0.18 μm bipolar complementary metal-oxide-semiconductor(CMOS)double-diffused metal-oxide-semiconductor(DMOS)(BCD)process.The results show that the system gain decrease rate can be compensated from 19.2%to 6.2%,and the output voltage shift rate can be improved from 2.00%to 0.15%at a dose of 200×103 rad(Si).Moreover,the load adjustment rate and linear adjustment rate are reduced.They are respectively decreased to 0.191%/A and 0.093%/V.This provides a new idea for the design of total ionizing dose effect hardening at circuit and system level.
万方数据
维普