Dynamic output feedback control of a flexible air-breathing hypersonic vehicle via T–S fuzzy approach

By utilising Takagi–Sugeno (T–S) fuzzy set approach, this paper addresses the robust H_∞ dynamic output feedback control for the non-linear longitudinal model of flexible air-breathing hypersonic vehicles (FAHVs). The flight control of FAHVs is highly challenging due to the unique dynamic characteristics, and the intricate couplings between the engine and fight dynamics and external disturbance. Because of the dynamics’ enormous complexity, currently, only the longitudinal dynamics models of FAHVs have been used for controller design. In this work, T–S fuzzy modelling technique is utilised to approach the non-linear dynamics of FAHVs, then a fuzzy model is developed for the output tracking problem of FAHVs. The fuzzy model contains parameter uncertainties and disturbance, which can approach the non-linear dynamics of FAHVs more exactly. The flexible models of FAHVs are difficult to measure because of the complex dynamics and the strong couplings, thus a full-order dynamic output feedback controller is designed for the fuzzy model. A robust H_∞ controller is designed for the obtained closed-loop system. By utilising the Lyapunov functional approach, sufficient solvability conditions for such controllers are established in terms of linear matrix inequalities. Finally, the effectiveness of the proposed T–S fuzzy dynamic output feedback control method is demonstrated by numerical simulations.     

On Trajectory Tracking Model Predictive Control of an Unmanned Quadrotor Helicopter Subject to Aerodynamic Disturbances

In this article a model predictive control (MPC) strategy for the trajectory tracking of an unmanned quadrotor is presented. The quadrotor's dynamics are modeled using a hybrid systems approach and, specifically, a set of piecewise affine (PWA) systems around different operating points of the translational and rotational motions. The proposed control scheme is dual and consists of an integral MPC for the translational motions, followed by an MPC scheme for the tracking of the quadrotor's attitude motions. By the utilization of PWA representations, the controller is computed for a larger part of the quadrotor's flight envelope, which provides more control authority for aggressive maneuvering. The proposed dual control scheme is able to calculate optimal control actions with robustness against atmospheric disturbances (e.g. wind gusts) and with respect to the physical constraints of the quadrotor (e.g. maximum lifting forces or fixed thrust limitations in order to extend flight endurance). Extended simulation studies indicate the efficiency of the MPC scheme, both in trajectory tracking and aerodynamic disturbance attenuation.     

结构化道路车道线的鲁棒检测与跟踪

针对智能车在视觉导航过程中车道线检测的鲁棒性和实时性问题,提出一种适用于结构化道路的车道线鲁棒检测与跟踪方法。首先,简化的Sobel算子提取车道线边缘图像,将边缘图像与改进的Otsu方法得到的车道线分割图像进行融合,实现对车道线标记点的鲁棒检测;然后,采用迭代最小二乘方法拟合车道线标记点并去除干扰点,并根据拟合参数建立车道线模型;最后,引入尺度无迹卡尔曼滤波(SUKF)对车道线进行跟踪。通过对多段实地采集的视频进行了仿真实验,结果表明,该方法对于高速公路车道线的检测率可达到99%,并具有较好实时性能;对于受损和弄污的城市道路车道线也体现出较好的鲁棒性和时间性能。     

攻击型无人机鲁棒导引律研究

文章研究了攻击型无人机鲁棒导引系统,采用对干扰和摄动具有自适应能力的滑动模态变结构控制方法设计了攻击型无人机滑模导引规律.针对用于消除颤振的伪滑动模态不能实现精确跟踪的缺陷,对滑模导引规律中颤振消除进行了优化设计,引入系统运动状态轨迹接近角变量,使消除颤振的伪滑动模态边界层宽度随着系统状态到达滑动模态而逐渐减小为零,从而达到了既能消除颤振又能实现精确跟踪的设计目标.通过仿真验证了该导引规律具有攻击弹道平缓、抗目标机动扰动能力强、鲁棒性好、制导精度高的优点.     

运输部机车车辆检修库平面布置分析

随着我国国民经济的持续快速发展,各钢铁企业加快了钢铁工业战略性结构调整的力度.因此,本篇论文对运输部机车车辆检修库平面布置进行分析,为运输部机车车辆检修库的设计提供借鉴.     

Guaranteed transient performance based control with input saturation for near space vehicles

This paper describes the design of guaranteed transient performance based attitude control for the near space vehicle(NSV)with control input saturation using the backstepping method.To improve the robust controllability of the NSV,the parameter adaptive method is used to tackle the integrated effect of unknown time-varying disturbance and control input saturation.Based on the backstepping technique and parameter estimated outputs,a robust attitude control scheme is proposed for the NSV with input saturation.A novel robust attitude control scheme is then proposed based on a prescribed performance bound(PPB)which characterizes the convergence rate and maximum overshoot of the attitude tracking error.The closed-loop system stability under both the developed robust attitude control schemes is proved using Lyapunov’s method and uniformly asymptotical convergence of all closed-loop signals is guaranteed.Finally,simulation results are given to show the effectiveness of both the proposed robust constrained attitude control schemes.     

基于ViLBERT与BiLSTM的图像描述算法

传统图像描述算法存在提取图像特征利用不足、缺少上下文信息学习和训练参数过多的问题,提出基于ViLBERT和双层长短期记忆网络(BiLSTM)结合的图像描述算法.使用ViLBERT作为编码器,ViLBERT模型能将图片特征和描述文本信息通过联合注意力的方式进行结合,输出图像和文本的联合特征向量.解码器使用结合注意力机制的BiLSTM来生成图像描述.该算法在MSCOCO2014数据集进行训练和测试,实验评价标准BLEU-4和BLEU得分分别达到36.9和125.2,优于基于传统图像特征提取结合注意力机制图像描述算法.通过生成文本描述对比可看出,该算法生成的图像描述能够更细致地表述图片信息.     

结合Bi-2DPCA与CNN的美式手语识别

针对现有美式手语（ASL）识别算法准确率低和模型训练时间长的问题,提出一种结合双向二维主成分分析（Bi-2DPCA）与卷积神经网络（CNN）并基于贝叶斯优化的识别算法。利用Bi-2DPCA算法对原始图像做数据降维处理,提取行、列方向的特征图,使用卷积神经网络对特征图进行训练分类,同时采用贝叶斯优化算法对模型超参数进行自动调参。在24分类ASL数据集上的实验结果表明,该算法的识别准确率达到99.15%,训练时间相比传统CNN算法减少90.3%。     

基于矢量传感器的无人驾驶车辆信号远程监测系统

传统无人驾驶车辆远程检测系统,由于信号传输距离的影响,在信号波传输过程中在电路耦合率衰减下出现监测信号清晰度降低,信号整体监测效果无法满足实际检测系统应用要求的问题;对此设计系统通过采用矢量传感器对系统变量、模量与定量数据进行矢量统一计算,提出基于矢量传感器的无人驾驶车辆信号远程监测系统;首先完成基于矢量传感器的系统总体框架设计;然后根据设计框架建立无人驾驶车辆监控信号交互硬件单元,通过不同矢量传感器构成监控信号数据矢量转换计算平台;最后通过对硬件平台的矢量化软件适配,完成硬件与软件监控信号统一,提升信号传输强度,增强信号清晰度,从而满足无人驾驶车辆信号远程监测要求,完成系统的设计;通过对比实验数据表明,设计的基于矢量传感器的无人驾驶车辆信号远程监测系统,能够在50～100 km范围内稳定监测车辆状态,车辆状态数据监测实时性与连续性明显优于传统检测系统.     

Long-term economic sensitivity analysis of light duty underground mining vehicles by power source

LHD's are expensive vehicles; therefore, it is important to accurately define the financial consequences associated with the investment of purchasing the mining equipment. This study concentrates on longterm incremental and sensitivity analysis to determine whether it is feasible to incorporate current battery technology into these machines. When revenue was taken into account, decreasing the amount of haulage in battery operated equipment by 5% or 200 kg per h amounts to a $4.0 × 10~4 loss of profit per year. On average it was found that using battery operated equipment generated $9.5 × 10~4 more in income annually, reducing the payback period from seven to two years to pay back the additional $1.0 × 10~5 investment of buying battery powered equipment over cheaper diesel equipment. Due to the estimated 5% increase in capital, it was observed that electric vehicles must possess a lifetime that is a minimum of one year longer than that of diesel equipment.