Dynamic data rectification using particle filters
نویسندگان
چکیده
The basis of dynamic data rectification is a dynamic process model. The successful application of the model requires the fulfilling of a number of objectives that are as wide-ranging as the estimation of the process states, process signal denoising and outlier detection and removal. Current approaches to dynamic data rectification include the conjunction of the Extended Kalman filter (EKF) and the expectation-maximization algorithm. However, this approach is limited due to the EKF being less applicable where the state and measurement functions are highly non-linear or where the posterior distribution of the states is non-Gaussian. This paper proposes an alternative approach whereby particle filters, based on the sequential Monte Carlo method, are utilized for dynamic data rectification. By formulating the rectification problem within a probabilistic framework, the particle filters generate Monte Carlo samples from the posterior distribution of the system states, and thus provide the basis for rectifying the process measurements. Furthermore, the proposed technique is capable of detecting changes in process operation and thus complements the task of process fault diagnosis. The appropriateness of particle filters for dynamic data rectification is demonstrated through their application to an illustrative non-linear dynamic system, and a benchmark pH neutralization process.
منابع مشابه
Estimation of Dynamic Panel Data Models with Stochastic Volatility Using Particle Filters
Time-varying volatility is common in macroeconomic data and has been incorporated into macroeconomic models in recent work. Dynamic panel data models have become increasingly popular in macroeconomics to study common relationships across countries or regions. This paper estimates dynamic panel data models with stochastic volatility by maximizing an approximate likelihood obtained via Rao-Blackw...
متن کاملIntegrating robust likelihoods with Monte-Carlo filters for multi-target tracking
In this paper, a dynamic multi-modal fusion scheme for tracking multiple targets with Monte-Carlo filters is presented, with the goal of achieving robustness by combining complimentary likelihoods based on color and foreground segmentation. The generality of the proposed approach allows defining the measurements on different levels (pixel-, featureand object-space) through dynamic data fusion. ...
متن کاملBandwidth selection in pre-smoothed particle filters
This paper considers Pre-Smoothed Particle Filters (PSPF) as a regularized alternative to the Sampling Importance Resampling (SIR) lter for state space models with additive Gaussian observation noise. The PSPF adaptively bridges the unbiased, but variance-prone SIR lter and the biased, but less varianceprone Gaussian update lter. Our main contribution is the adaptive determination of the degree...
متن کاملUnsupervised Part of Speech Inference with Particle Filters
As linguistic models incorporate more subtle nuances of language and its structure, standard inference techniques can fall behind. Often, such models are tightly coupled such that they defy clever dynamic programming tricks. However, Sequential Monte Carlo (SMC) approaches, i.e. particle filters, are well suited to approximating such models, resolving their multi-modal nature at the cost of gen...
متن کاملEstimation of new ignited fires using particle filters in wildfire spread simulation
Assimilating real time data into wildfire spread simulations has the potential to improve simulation results of wildfires, which are complex and dynamic in nature. Our previous work developed a data assimilation method based on particle filters (PF) to estimate the state of a wildfire. This method, however, does not work effectively when there are significant events, such as new ignited fires, ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Computers & Chemical Engineering
دوره 32 شماره
صفحات -
تاریخ انتشار 2008