几种非线性滤波算法的性能比较与分析

在非线性状态估计中,传统的扩展卡尔曼滤波通过线性化来实现高斯近似,由于截断误差的存在很难保证估计精度;而基本粒子滤波容易出现粒子退化,导致滤波发散。针对粒子滤波的两个基本假设:蒙特卡罗假设和重要采样假设,采用蒙特卡罗随机链的方法来提高粒子的多样性,并利用无味卡尔曼滤波来产生更高精度的替代分布,发展了无味粒子滤波。通过仿真实验证明,相比较扩展卡尔曼滤波和基本粒子滤波,改进后的无味粒子滤波算法性能更优越,对含有非线性非高斯的状态估计问题有更好的滤波效果。

Conditional autoregressive negative binomial model for analysis of crash count using Bayesian methods

In order to improve crash occurrence models to account for the influence of various contributing factors, a conditional autoregressive negative binomial （CAR-NB） model is employed to allow for overdispersion （tackled by the NB component）, unobserved heterogeneity and spatial autocorrelation （captured by the CAR process）, using Markov chain Monte Carlo methods and the Gibbs sampler. Statistical tests suggest that the CAR-NB model is preferred over the CAR-Poisson, NB, zero-inflated Poisson, zero-inflated NB models, due to its lower prediction errors and more robust parameter inference. The study results show that crash frequency and fatalities are positively associated with the number of lanes, curve length, annual average daily traffic （AADT） per lane, as well as rainfall. Speed limit and the distances to the nearest hospitals have negative associations with segment-based crash counts but positive associations with fatality counts, presumably as a result of worsened collision impacts at higher speed and time loss during transporting crash victims.

一种辨别目标与拖曳式诱饵的融合贝叶斯模型

在当今电子战中,有源拖曳式诱饵能够在跟踪雷达的半功率波束内捕获其跟踪分辨单元,并将跟踪门从目标转移到诱饵上来。针对这一问题,雷达抗干扰中迫切需要一种在诱饵干扰下仍能正确识别目标的技术。在此状态下正确识别目标的前提是先要将目标与有源拖曳式诱饵分离。考虑到逻辑回归是基于线性回归的二分类器,因此利用逻辑回归概率模型,并以蒙特卡罗马尔可夫链(MCMC)为载体形成一种融合贝叶斯模型,能够达到很好的目标与诱饵分离效果。

Nash Model Parameter Uncertainty Analysis by AM-MCMC Based on BFS and Probabilistic Flood Forecasting

A hydrologic model consists of several parameters which are usually calibrated based on observed hy-drologic processes. Due to the uncertainty of the hydrologic processes, model parameters are also uncertain, which further leads to the uncertainty of forecast results of a hydrologic model. Working with the Bayesian Forecasting System (BFS), Markov Chain Monte Carlo simulation based Adaptive Metropolis method (AM-MCMC) was used to study parameter uncertainty of Nash model, while the probabilistic flood forecasting was made with the simu-lated samples of parameters of Nash model. The results of a case study shows that the AM-MCMC based on BFS proposed in this paper is suitable to obtain the posterior distribution of the parameters of Nash model according to the known information of the parameters. The use of Nash model and AM-MCMC based on BFS was able to make the probabilistic flood forecast as well as to find the mean and variance of flood discharge, which may be useful to estimate the risk of flood control decision.

One-step random-walk process of nanoparticles in cement-based materials

Efficient modelling approaches capable of predicting the behavior and effects of nanoparticles in cement-based materials are required for conducting relevant experiments.From the microstructural characterization of a cement-nanoparticle system,this paper investigates the potential of cell-based weighted random-walk method to establish statistically significant relationships between chemical bonding and diffusion processes of nanoparticles within cement matrix.LaSr_(0.5)C_(0.5)O_(3)(LSCO)nanoparticles were employed to develop a discrete event system that accounts for the behavior of individual cells where nanoparticles and cement components were expected to interact.The stochastic model is based on annihilation(loss)and creation(gain)of a bond in the cell.The model considers both chemical reactions and transport mechanism of nanoparticles from cementitious cells,along with cement hydration process.This approach may be useful for simulating nanoparticle transport in complex 2D cement-based materials systems.

Potential-Decomposition Strategy in Markov Chain Monte Carlo Sampling Algorithms

We introduce the potential-decomposition strategy （PDS）, which can be used in Markov chain Monte Carlo sampling algorithms. PDS can be designed to make particles move in a modified potential that favors diffusion in phase space, then, by rejecting some trial samples, the target distributions can be sampled in an unbiased manner. Furthermore, if the accepted trial samples are insumcient, they can be recycled as initial states to form more unbiased samples. This strategy can greatly improve efficiency when the original potential has multiple metastable states separated by large barriers. We apply PDS to the 2d Ising model and a double-well potential model with a large barrier, demonstrating in these two representative examples that convergence is accelerated by orders of magnitude.

Robustness analysis of underground powerhouse construction simulation based on Markov Chain Monte Carlo method

Scheduling is a major concern in construction planning and management, and current construction simulation research typically targets the shortest total duration. However, uncertainties are inevitable in actual construction, which may lead to discrepancies between the actual and planned schedules and increase the risk of total duration delay. Therefore, developing a robust construction scheduling technique is of vital importance for mitigating disturbance and improving completion probability. In the present study, the authors propose a robustness analysis method that involves underground powerhouse construction simulation based on the Markov Chain Monte Carlo(MCMC) method. Specifically, the MCMC method samples construction disturbances by considering the interrelationship between the states of parameters through a Markov state transition probability matrix, which is more robust and efficient than traditional sampling methods such as the Monte Carlo(MC) method. Additionally, a hierarchical simulation model coupling critical path method(CPM) and a cycle operation network(CYCLONE) is built, using which construction duration and robustness criteria can be calculated. Furthermore, a detailed measurement method is presented to quantize the robustness of underground powerhouse construction, and the setting model of the time buffer is proposed based on the MCMC method. The application of this methodology not only considers duration but also robustness, providing scientific guidance for engineering decision making. We analyzed a case study project to demonstrate the effectiveness and superiority of the proposed methodology.

Comparing the VGCG model as the unification of dark sectors with observations

Current observations indicate that 95% of the energy density in the universe is the unknown dark component.The dark component is considered composed of two fluids:dark matter and dark energy.Or it is a mixture of these two dark components,i.e.,one can consider it an exotic unknown dark fluid.With this consideration,the variable generalized Chaplygin gas(VGCG)model is studied with not dividing the unknown fluid into dark matter and dark energy parts in this paper.By using the Markov Chain Monte Carlo method,the VGCG model as the unification of dark sectors is constrained,and the constraint results on the VGCG model parameters are,n=0.00057+0.0001+0.0009-0.0006-0.0006,α=0.0015+0.0003+0.0017-0.0015-0.0015and B s=0.778+0.016+0.030-0.016-0.035,obtained by the cosmic microwave background data from the 7-year WMAP full data points,the baryon acoustic oscillation data from Sloan Digital Sky Survey(SDSS)and 2-degree Field Galaxy Redshift(2dFGRS)survey,and the Union2 type Ia supernova data with systematic errors.At last,according to the evolution of deceleration parameter it is shown that an expanded universe from deceleration to acceleration can be obtained in VGCG cosmology.