基于改进PF算法的ADS-B风场反演

将装载自动相关监视广播(ADS-B)机载端的民航飞机视作传感器,利用ADS-B下行数据实施风场反演是近年来新颖的风场探测手段之一。现有的反演算法在飞机小角度转弯情况下存在精度不高的问题,大面积空间风场重建也对风场探测提出了新的挑战。针对上述问题,利用数据的几何结构和Kullback-Leibler Divergence(KLD)采样对粒子滤波(Particle Filter,PF)算法进行改进,该算法通过结合ADS-B数据对航线上的固定位置不同高度层上风矢量进行反演,构造垂直风廓线,并与欧洲中期天气预报中心气象数据作对比,验证了算法的可行性与准确性;最后,利用气象粒子(Meteo-Particle,MP)模型对航线外大面积的风矢量进行估计。实验结果表明,该方法能够反映真实的风场。

Improved Particle Filter for Passive Target Tracking

As a new method for dealing with any nonlinear or non-Ganssian distributions, based on the Monte Carlo methods and Bayesian filtering, particle filters （PF） are favored by researchers and widely applied in many fields. Based on particle filtering, an improved extended Kalman filter （EKF） proposal distribution is presented. Evaluation of the weights is simplified and other improved techniques including the residual resampling step and Markov Chain Monte Carlo method are introduced for target tracking. Performances of the EKF, basic PF and the improved PF are compared in target tracking examples. The simulation results confirm that the improved particle filter outperforms the others.

An unscented particle filter for ground maneuvering target tracking

In this study, an unscented particle filtering method based on an interacting multiple model (IMM) frame for a Markovian switching system is presented. The method integrates the multiple model (MM) filter with an unscented particle filter (UPF) by an interaction step at the beginning. The framework (interaction/mixing, filtering, and combination) is similar to that in a standard IMM filter, but an UPF is adopted in each model. Therefore, the filtering performance and degeneracy phenomenon of particles are improved. The filtering method addresses nonlinear and/or non-Gaussian tracking problems. Simulation results show that the method has better tracking performance compared with the standard IMM-type filter and IMM particle filter.

Hybrid three-dimensional variation and particle filtering for nonlinear systems

This work addresses the problem of estimating the states of nonlinear dynamic systems with sparse observations.We present a hybrid three-dimensional variation（3DVar） and particle piltering（PF） method,which combines the advantages of 3DVar and particle-based filters.By minimizing the cost function,this approach will produce a better proposal distribution of the state.Afterwards the stochastic resampling step in standard PF can be avoided through a deterministic scheme.The simulation results show that the performance of the new method is superior to the traditional ensemble Kalman filtering（EnKF） and the standard PF,especially in highly nonlinear systems.

Improved particle filtering techniques based on generalized interactive genetic algorithm

This paper improves the resampling step of particle filtering（PF） based on a broad interactive genetic algorithm to resolve particle degeneration and particle shortage.For target tracking in image processing,this paper uses the information coming from the particles of the previous fame image and new observation data to self-adaptively determine the selecting range of particles in current fame image.The improved selecting operator with jam gene is used to ensure the diversity of particles in mathematics,and the absolute arithmetical crossing operator whose feasible solution space being close about crossing operation,and non-uniform mutation operator is used to capture all kinds of mutation in this paper.The result of simulating experiment shows that the algorithm of this paper has better iterative estimating capability than extended Kalman filtering（EKF）,PF,regularized partide filtering（RPF）,and genetic algorithm（GA）-PF.

A dual channel perturbation particle filter algorithm based on GPU acceleration

The particle filter（PF） algorithm is one of the most commonly used algorithms for maneuvering target tracking. The traditional PF maps from multi-dimensional information to onedimensional information during particle weight calculation, and the incorrect transmission of information leads to the fact that the particle prediction information does not match the weight information, and its essence is the reduction of the information entropy of the useful information. To solve this problem, a dual channel independent filtering method is proposed based on the idea of equalization mapping. Firstly, the particle prediction performance is described by particle manipulations of different dimensions, and the accuracy of particle prediction is improved. The improvement of particle degradation of this algorithm is analyzed in the aspects of particle weight and effective particle number. Secondly, according to the problem of lack of particle samples, the new particles are generated based on the filtering results, and the particle diversity is increased. Finally, the introduction of the graphics processing unit（GPU） parallel computing the platform, the “channel-level” and “particlelevel” parallel computing the program are designed to accelerate the algorithm. The simulation results show that the algorithm has the advantages of better filtering precision, higher particle efficiency and faster calculation speed compared with the traditional algorithm of the CPU platform.

Throughput-efficient wireless system and blind detection via improved particle filtering

This paper introduces throughput-efficient wireless system based on an extension to binary phasemodulations,named extended binary phase shift keying(EBPSK),and the corresponding analysis ofpower spectra,especially the extension to channel capacity are given.Importantly,a novel sequential es-timation and detection approach for this EBPSK system is proposed.The basic idea is to design a proba-bilistic approximation method for the computation of the maximum a posterior distribution via particle fil-tering method(PF).Subsequently,a new important function in PF is presented,so that the performanceof the detector has a great improvement.Finally,computer simulation illustrates that EBPSK system hasvery high transmission rate,and also the good performance of the proposed PF detector is demonstrated.

Dominant Correlogram Based Particle Filter Tracking

A novel dominant correlogram based particle filter was proposed for an object tracking in visual surveillance. Particle filter outperforms the Kalman filter in non-linear and non-Gaussian estimation problem. This paper proposed incorporating spatial information into visual feature, and yields a reliable likelihood description of the observation and prediction. A similarity-ratio is defined to evaluate the effectivity of different similarity measurements in weighing samples. The experimental results demonstrate the effective and robust performance compared with the histogram based tracking in traffic scenes.

AN ITERATIVE PARTICLE FILTER SIGNAL DETECTOR FOR MIMO FAST FADING CHANNELS

For flat fast fading Multiple-Input Multiple-Output(MIMO) channels,this paper presents a sampling based channel estimation and an iterative Particle Filter(PF) signal detection scheme. The channel estimation is comprised of two parts:the adaptive iterative update on the channel distribution mean and a regular update on the "adaptability" via pilot. In the detection procedure,the PF is employed to produce the optimal decision given the known received signal and the sequence of the channel samples,where an asymptotic optimal importance density is constructed,and in terms of the asymptotic update order,the Parallel Importance Update(PIU) and the Serial Importance Update(SIU) scheme are performed respectively. The simulation results show that for the given fading channel,if an appropriate pilot mode is selected,the proposed scheme is more robust than the conventional Kalman filter based superimposed detection scheme.

A novel SMC-PHD filter based on particle compensation

As a typical implementation of the probability hypothesis density(PHD) filter, sequential Monte Carlo PHD(SMC-PHD) is widely employed in highly nonlinear systems. However, the particle impoverishment problem introduced by the resampling step, together with the high computational burden problem, may lead to performance degradation and restrain the use of SMC-PHD filter in practical applications. In this work, a novel SMC-PHD filter based on particle compensation is proposed to solve above problems. Firstly, according to a comprehensive analysis on the particle impoverishment problem, a new particle generating mechanism is developed to compensate the particles. Then, all the particles are integrated into the SMC-PHD filter framework. Simulation results demonstrate that, in comparison with the SMC-PHD filter, proposed PC-SMC-PHD filter is capable of overcoming the particle impoverishment problem, as well as improving the processing rate for a certain tracking accuracy in different scenarios.

基于TRNN和FA-PF融合的锂离子电池RUL预测

预测锂电池剩余使用寿命RUL(remaining useful life)可以提高电池供电系统的稳定性和安全性,从而明确故障的发生并及时做出响应。在预测过程中粒子滤波PF(particle filter)常用于在线辨识模型参数,但当PF在线辨识参数时易出现粒子贫化问题,需要大量粒子才能完成状态估计,这将会导致预测结果不准确。为了提高RUL预测的准确性,提出一种基于时间递归神经网络TRNN(time recurrent neural network)和萤火虫算法FA(firefly algorithm)优化PF融合的锂电池RUL预测方法。首先,由于TRNN的泛化能力优于经验模型,并且易于捕捉容量退化的长距离依赖问题,因此选用其模拟各种条件下的电池退化模型;其次,基于FA优化的PF技术对TRNN模型参数进行递归更新,使粒子群移动到高似然区域,从而减少PF的贫化;最后,选择不同条件下不同电池的实验数据进行验证和比较。结果表明,与传统方法相比,该方法具有更高的RUL预测精度。

基于HMM和优化的PF的数控转台精度衰退模型

针对数控转台精度衰退状态缺乏有效的评估方法的问题,提出一种数控转台重复定位精度衰退趋势预测模型,该模型结合了隐马尔科夫(Hidden Markov Model,HMM)算法和粒子滤波(Particle Filtering,PF)算法,其中粒子滤波算法使用粒子群算法(Particle Swarm Optimization,PSO)优化了初始参数。选择了从数控转台精度衰退加速寿命试验中获得的振动信号作为研究数据。通过聚合经验模态与主成分分析(EEMD-PCA)算法对原始信号降噪,并提取含有故障特征的信号进行信号重构;使用统计特征量作为观察值训练获得HMM模型,对数控转台精度衰减做出早期诊断,并由此获得数控转台精度健康状态指标;使用粒子滤波算法建立数控转台精度衰退预测模型,并预测精度的剩余寿命。在以第50组数据为预测起始点时,预测的剩余寿命为21,实际测量的结果为17,相差4,比较接近。综合分析模型计算与试验测量的结果表明。

改进权值计算的EPF算法及在目标跟踪中的应用

扩展卡尔曼粒子滤波(EPF)在预测阶段通过EKF选取重要性函数而优化了粒子选取,但是传统EPF算法中粒子权值一般是通过正态分布的概率密度函数计算的。此方法没有突出不同噪声粒子的权值差别,在计算中引入了较大的相对误差。通过在更新阶段对权值计算所依赖的概率密度函数做出改进,得到改进的EPF算法。同时采用实际目标跟踪数据进行仿真对比实验,结果验证了此方法有效可行,并且减小了预测误差。

基于EKPF的GPS导航模型研究

通过模拟GPS卫星系统的运行以及接收机的运动轨迹,采用11状态PVA(Position-Velocity-Acceleration)导航模型进行导航定位分析,并分别采用扩展卡尔曼粒子滤波和扩展卡尔曼滤波计算导航解,结果表明两种滤波均能得出较好导航解,并且前者削弱了多路径效应的影响,进一步提高了导航定位精度,尤其在高程方向精度提高更为明显。

IMM-UPF算法在机动目标跟踪中的研究

为解决机动目标跟踪的非线性和噪声不确定等问题,提出了一种新的滤波算法:融合了交互式多模型(IMM)、粒子滤波(PF)和无迹卡尔曼滤波(UKF)的IMM-UPF算法。该算法采用多模型结构以跟踪目标的任意机动,粒子滤波能处理非线性、非高斯问题,而采用UKF产生粒子,由于考虑了当前观测值,使得粒子的分布更接近后验概率密度分布,克服粒子的退化现象,从而提高估计精度。系统的模型集根据实际的目标系统设计了三个非线性模型。通过实例仿真,结果证明了IMM-UPF算法的有效性,且其性能优于PF、UPF算法。

修正的EKPF算法在固定单站被动目标跟踪中的应用

基于以角度、角度变化率、多普勒频率变化率信息为观测量的固定单站被动目标跟踪系统,引入扩展卡尔曼粒子滤波(EKPF)算法对定位结果进行滤波处理。理论分析和仿真实验证明了其滤波性能在该系统中的优越性。针对EKPF算法运算量大、实时性差的问题,通过对部分粒子进行间隔EKF采样,将EKPF算法进行修正。修正的EKPF算法既有效降低了运算量,又增加了粒子的多样性,使粒子集更加逼近真实的后验概率密度函数。计算机仿真表明,与传统的EKPF算法相比,修正算法在保证滤波性能基本不变的前提下,算法实时性得到了有效提高。

改进的SRCDKF-PF算法及在BOT系统中的应用

针对纯方位目标跟踪(Bearing-Only Tracking,BOT)系统强非线性特点,提出一种新的解决方案:采用平方根中心差分卡尔曼滤波器(Square-RootCDKF,SRCDKF)产生粒子滤波提议分布,融入最新的观测数据影响;增加改进措施以提高滤波性能,如采用系统重抽样算法减少方差、应用马尔可夫链模特卡罗(Markovchain Monte Carlo,MCMC)方法消除粒子贫乏等。仿真表明该算法是有效的,针对当前BOT系统,比传统EKF、PF算法可靠性更好,跟踪精度更高。

EKF、UKF、PF目标跟踪性能的比较

雷达系统的非线性目标跟踪已被人们广泛重视。扩展卡尔曼滤波器(EKF)是将卡尔曼滤波器(KF)局部线性化,其算法简单、计算量小,适用于弱非线性、高斯环境下。不敏卡尔曼滤波器(UKF)是用一系列确定样本来逼近状态的后验概率密度,在高斯环境中,对任何非线性系统都有较好的跟踪性能。粒子滤波器(PF)是用随机样本来近似状态后验概率密度函数,适用于任何非线性非高斯系统。文中通过仿真实验,对三者的性能进行了仿真比较,结果证明在复杂的非高斯非线性环境中,粒子滤波器的性能明显优于另外两种滤波器,但计算复杂,耗时长。

基于OOSM-PF的微弱目标检测前跟踪

由于量测数据预处理以及通信延迟等因素的影响,集中式融合跟踪系统面临着无序量测的问题。针对低信噪比和无序量测情况下的微弱目标检测与跟踪,提出了一种基于无序量测和粒子滤波的检测前跟踪方法,然后将该方法的性能与顺序量测滤波方法以及丢弃无序量测方法的性能进行分析对比。仿真结果表明,该算法可以有效处理无序量测问题,实现对微弱目标的有效检测和跟踪,其目标跟踪精度接近顺序量测滤波的跟踪精度。