基于遥感影像的智能景像匹配适配区选择方法

飞行器景像匹配适配区选择是飞行器实现景像匹配视觉导航的前提。近年来，人们基于层次规则提出了许多适配区选择方法，也取得了良好的效果，但这些方法缺少对深度特征的提取能力，通用性较差，且存在一定的误选现象。针对这一问题，提出了一种基于深度特征的智能景像匹配适配区选择方法。所提方法利用深度学习ResNet-50网络结构实现对景像区高维特征的提取，通过深度特征匹配方法计算匹配误差与匹配概率，实现对适配区的选取。实验结果表明，所提方法与传统的适配区选择方法相比，适配成功率平均提高40%以上，鲁棒性更强。该方法避免了繁琐的适配性能指标选择流程，可应用于不同场景下的适配区选择，改善适配区域选择的有效性和泛化性。     

基于Fuzzy ARTMAP神经网络的景像匹配实时图选取方法

提出一种新的基于Fuzzy ARTMAP神经网络并利用图像直方图特征的快速景像匹配实时图选取方法。与已有的方法相比,该方法充分考虑了图像的边缘、亮度、对比度、信噪比等特征对影像实时图质量的影响,具有自适应聚类、收敛导速,实时性好,分类准确率高和通用性强等优点。将该方法应用于SMGS（景像匹配制导系统）进行实时图像的自动选取,可大大提高SMGS的智能性,可靠性和实时性。     

基于低成本组合导航定位系统的新融合滤波算法

设计了一种可用于地面交通工具或机器人的低成本组合导航定位系统，提出了基于该系统的新信息融合方法，将模糊卡尔曼滤波算法和地图匹配技术联合起来。仿真结果表明：模糊卡尔曼滤波算法相当于一数据平滑处理窗口，具有比常规卡尔曼滤波算法更高的精度。     

一种基于因子分析的重力适配区域选取方法

为了综合分析各类特征值对于适配区选取的影响,提出了一种通过因子分析,将多种特征值综合为少数几个因子,以此确定影响适配区选取参数的方法。首先将整个区域划分为15个子区域,计算每个子区域的各类特征值,利用因子分析的方法统计各区域得分。然后,根据得分情况确定适配区选择顺序。最后,对比验证基于因子分析选出的适配区匹配定位精度。仿真结果显示,基于因子分析选取的适配区总体定位精度为0.45 n mlie,优于传统的主成分分析法,表明利用因子分析来选取重力适配区是一种可行的方法。     

航行过程中实时校正的重力匹配算法

由于传统重力匹配定位通常受限于特定区域，无法对惯性导航系统（INS）实现连续校正，在应用重力匹配进行辅助导航时需要周期性前往重力特征适配区进行匹配校正。针对非适配区域内匹配精度无法判定的缺陷，提出一种航行过程中实时校正的重力匹配算法。计算载体实测重力序列与匹配输出位置在相对重力图上映射序列的差，取重力差序列的方差判断匹配输出的权重值，从而有效利用全航域的适配航段。根据重力差序列的方差与匹配精度的关系建立回归模型，将可信的重力匹配输出引入INS进行误差校正。利用实船数据进行了仿真验证，仿真结果表明所提算法在400 h的连续航行期间对INS位置误差的抑制达到30%以上，位置误差在全过程没有明显发散趋势，具有更好的适用性。     

基于局部连续场的重力匹配辅助导航

重力匹配辅助惯性导航是一种在惯性导航系统定位信息基础上利用地球重力场特征获取载体位置信息的组合导航技术。一般匹配辅助导航方法都是建立在格网化离散场的基础上,考虑到用局部连续场逼近离散散场的可行性,提出了利用连续场实现相关极值匹配算法,建立了基于局部连续场的相关极值匹配算法模型,采用随机初值迭代方式改进拟牛顿方法以实现在置信范围内全局寻优。最后在三组不同仿真条件下对该算法进行了仿真实验。从实验结果可以看出,在观测误差、初始定位误差较大的情况下,通过该算法获得的匹配航迹仍能以较高的精度跟踪真实航迹,从而验证了算法的有效性。     

基于分割嵌套三角剖分的重力场适配区选取算法

重力场适配区选取算法是水下重力定位系统的关键技术之一,直接影响重力匹配算法的定位精度和匹配率,为提高适配区选取算法的准确性,提出一种基于分割嵌套三角剖分的重力场适配区选取算法.首先利用墨卡托投影和重力异常空间校正,将传统重力场栅格信息变换为三维高程信息;再利用分割嵌套的思想,不断从重力场最小环形域中分割出最优三角形,从...     

重力垂直梯度数据地图特征及其辅助导航

从随机过程理论出发,研究了重力垂直梯度场的主要特征参数(标准差、粗糙度、信息熵),通过选定局部窗口的滑移,计算了西太平洋海域分辨率为2’×2’的重力垂直梯度特征参数。选取不同特征区域的3条航线进行辅助导航仿真定位,并对导航能力进行统计分析,给出了重力垂直梯度特征参数与匹配成功率、定位误差的关系;在统计准则下,匹配成功率大于90%、定位精度优于1nmile,表明重力垂直梯度特征参数可以作为匹配区域选择以及航线规划的数量性依据。     

重力辅助导航匹配区域选择准则

通过在重力场区域中移动局部计算窗口的方法,计算了实测重力场各个局部的多种统计特征并使用填色等值线图进行了对比和分析,以局部重力场的标准差和经纬度方向相关系数作为匹配区域选择的数量指标,给出了重力匹配区经验选择准则。采用均方误差和平均绝对差算法在实测重力图上对重力辅助惯性导航系统进行了仿真研究,计算结果表明,在满足重力匹配区选择准则下进行的重力辅助导航,其导航系统定位误差小于一个重力图网格,匹配率大于90%。     

基于重力场特征参数信息熵的适配区选择方法

针对当前重力统计特征参数类别繁多,选择标准复杂而导致错选有效匹配区域的问题,利用信息熵具有能够整合多种统计参数且算法计算量小的特点,提出了一种基于特征参数信息熵的重力辅助导航适配区的选择方法。首先,在DTU10模型下将该方法与传统单一特征参数的方法进行比较,确定了传统方法的确会错误选择可匹配区,从而也反映了所提出方法的优越性;其次,在该方法划分出的匹配区和非匹配区中分别设计了8条仿真航线,匹配区中仿真航线的匹配效果明显优于非匹配区中的匹配效果。仿真结果表明了该方法的有效性。     

Fuzzy knowledge-based model for prediction of soil loosening and draft efficiency in tillage

A knowledge-based system for assessing soil loosening and draft efficiency in tillage is presented. The knowledge-based system was built through expert opinion elicitation and available scientific data using fuzzy logic. It is expected that such a non-linear relationship includes some uncertainties. A fuzzy inference system employing fuzzy If-Then rules has an ability to deal with ill-defined and uncertain systems. Compared with traditional approaches, fuzzy logic is more efficient in linking the multiple inputs to a single output in a non-linear domain. The main purpose of this study is to investigate the relationship between cultivator shares working parameters to soil loosening and draft efficiency, and to illustrate how fuzzy expert system might play an important role in prediction of these. Experimental values were taken in soil bin. The trials were conducted in different working depths and forward velocities of cultivator shares. In this paper, a sophisticated intelligent model, based on Mamdani approach fuzzy modeling principles, was developed to predict the changes in soil loosening and draft efficiency of tool. The fuzzy model consists of 25 rules. In this research, a Mamdani max-min inference for inference mechanism and the center of gravity (Centroid) defuzzifier formula method for defuzzification were used as these operators assure a linear interpolation of the output between the rules. The verification of the proposed model is achieved via various numerical error criterias. For all parameters, the relative error of predicted values was found to be less than the acceptable limits (10%).     

RANDOM VARIABLE WITH FUZZY PROBABILITY

IntroductionThematteroffuzzyrandomisusuallyclassifiedintothreeparts:fuzzyevent_exactitudeprobabilitymodel,crispevent_fuzzyprobabilitymodel,fuzzyevent_fuzzyprobabilitymodel.Uptonow ,themajorityofresearchesandachievementsareaboutthefirstmodel,buttherearefewresearchesandachievementsaboutthesecondmodel[1- 4].Whenresearchingthesecondmodel,thefuzzyprobabilityaboutcertainbasiceventsmustbegivenfirst,andthefuzzinessofvariablesiscausedbythefuzzyprobabilityaboutthesebasicevents.Theabove_mentionedrelation…     

Observer-based adaptive fuzzy backstepping control of MIMO stochastic nonlinear strict-feedback systems

In this paper, an adaptive fuzzy output feedback control approach is proposed for a class of multiinput and multioutput (MIMO) uncertain stochastic nonlinear strict-feedback systems without the measurements of the states. The fuzzy logic systems are used to approximate the unknown nonlinear functions, and a fuzzy state observer is designed for estimating the unmeasured states. Utilizing the designed the fuzzy state observer and by combining the adaptive backstepping control design, an adaptive fuzzy output feedback control approach is developed. It is proved that the proposed control approach can guarantee that all the signals of the closed-loop system are semiglobally uniformly ultimately bounded (SUUB) in probability, and the observer errors and the output of the system converge to a small neighborhood of the origin by appropriate choice of the design parameters. A simulation example is provided to show the effectiveness of the proposed approach.     

Fuzzy evaluation for an intelligent air-cushion tracked vehicle performance investigation

This paper presents the fuzzy logic expert system (FLES) for an intelligent air-cushion tracked vehicle performance investigation operating on swamp peat terrain. Compared with traditional logic model, fuzzy logic is more efficient in linking the multiple units to a single output and is invaluable supplements to classical hard computing techniques. Therefore, the main purpose of this study is to investigate the relationship between vehicle working parameters and performance characteristics, and to evaluate how fuzzy logic expert system plays an important role in prediction of vehicle performance. Experimental values are taken in the swamp peat terrain for vehicle performance investigation. In this paper, a fuzzy logic expert system model, based on Mamdani approach, is developed to predict the tractive efficiency and power consumption. Verification of the developed fuzzy logic model is carried out through various numerical error criteria. For all parameters, the relative error of predicted values are found to be less than the acceptable limits (10%) and goodness of fit of the predicted values are found to be close to 1.0 as expected and hence shows the good performance of the developed system.     

Fuzzy logic adaptive Kalman filtering in the control of irrigation canals

A fuzzy logic adaptive Kalman filtering methodology was developed for the automatic control of an irrigation canal system under unknown disturbances (water withdrawals) acting in the canal. Using a linearized finite difference model of open channel flow, the canal operation problem was formulated as an optimal control problem and an algorithm for gate opening in the presence of arbitrary external disturbances (changes in flow rates) was derived. Based on the linear optimal control theory, the linear quadratic regulator (LQR), assuming all the state variables (flow depths and flow rates) were available, was designed to generate control input (optimal gate opening). As it was expensive to measure all the state variables (flow rates and flow depths) in a canal system, a fuzzy logic adaptive Kalman filter and traditional Kalman filter were designed to estimate the values for the state variables that were not measured but were needed in the feedback loop. The performances of the state estimators designed using the fuzzy logic adaptive Kalman filter methodology and the traditional Kalman filtering technique were compared with the results obtained using the LQR (target loop function). The results of the present study indicated that the performance of the fuzzy logic adaptive Kalman filter was far superior to the performance of the observer design based upon the traditional Kalman filter approach. The obvious advantages of the fuzzy logic adaptive Kalman filter were the prevention of filter divergence and ease of implementation. As the fuzzy logic adaptive Kalman filter requires smaller number of state variables for the acceptable accuracy therefore, it would need less computational effort in the control of irrigation canals. Copyright © 2009 John Wiley & Sons, Ltd.     

A new two-frame particle tracking algorithm using match probability

A new particle tracking algorithm using the concept of match probability between two consequent image frames has been developed to obtain an instantaneous 2-dimensional velocity field. Our proposed algorithm for correctly tracking particle paths from only two image frames is based on iterative estimation of match probability and no-match probability as a measure of the matching degree. A computer simulation has been carried out to study the performance of the developed algorithm by comparing with the conventional 4-frame Particle Tracking Velocimetry (PTV) method. The effect of various thresholds used in the developed algorithm on the recovery ratio and the error ratio were also investigated. Although the new algorithm relies on the iterative updating process of match probability which is time consuming, computation time is relatively short compared to that of the 4-frame PTV method. Additionally, the new 2-frame PTV algorithm recovers more velocity vectors and has a higher dynamic range and a lower error ratio.This work was supported in part by non-directed research fund, Korea Research Foundation, 1993 and Hyundai Maritime Research Institute.     

General failure probability simulation and application for multi-mode

ＩｎｔｒｏｄｕｃｔｉｏｎＴｈｅｆｕｚｚｉｎｅｓｓｉｓａｄｉｆｆｅｒｅｎｔｕｎｄｅｔｅｒｍｉｎｅｄｆａｃｔｏｒｆｒｏｍｔｈｅｒａｎｄｏｍｎｅｓｓ.Ｉｔｒｅｆｌｅｃｔｓｔｈａｔｔｈｅｄｉｓｔｉｎｃｔｉｏｎｏｆｔｈｅｔｗｏｉｓｖａｇｕｅｆｏｒｔｈｅｄｅｆｅｃｔｏｆｔｈｅｅｘｃｌｕｄｅｄｍｉｄｄｌｅｌａｗ .Ｔｈｅｓａｆｅｔｙｓｅｔａｎｄｔｈｅｆａｉｌｕｒｅｓｅｔａｒｅｆｕｚｚｙｉｎｍａｎｙｅｎｇｉｎｅｅｒｉｎｇｐｒｏｂｌｅｍｓ.Ｅｘｐｅｃｔａｌｉｔｔｌｅａｍｏｕｎｔａｂｒｕｐｔｆａｉｌｕｒｅ,ｔｈｅｆａｉ…     

Self-tuning fuzzy logic control of a non-linear structural system with ATMD against earthquake

Self-tuning fuzzy logic controllers (STFLC) for the active control of Marmara Kocaeli earthquake excited building structures are studied in this paper. Vibration control using intelligent controllers, such as fuzzy logic has attracted the attention of structural control engineers during the last few years, because fuzzy logic can handle nonlinearities, uncertainties, and heuristic knowledge effectively and easily. The improved seismic control performance can be achieved by converting a simply designed static gain into a real time variable dynamic gain through a self-tuning mechanism. Self-tuning fuzzy logic controller is designed to reduce the story-drift of each floor. The simulated system has a nine-degree-of-freedom, which is modeled using nonlinear behavior of the base-structure interaction. Modeled system was simulated against the ground motion of the Marmara Kocaeli earthquake (M _w=7.4) in Turkey on 17 August, 1999. At the end of the study, the time history of the story displacements, accelerations, ATMD displacements, control voltage, and frequency responses of the both uncontrolled and controlled cases are presented. The robustness of the controller has been checked through the uncertainty in stiffness of the structure. Performance of the designed STFLC has been demonstrated for the different disturbance using ground motion of the Kobe earthquake. Simulations of an earthquake excited nine story structure are performed to prove the validity of proposed control strategy.