Issues in nonlinear stochastic grey box identification

Grey box identification refers to the practice of identifying dynamical systems in model structures exploiting partial prior information. This contribution reviews a method for stochastic grey box identification and surveys experiences and lessons of applying it to a number of industrial processes. Issues to be addressed include advantages and costs of introducing stochastics into the model, the question of what contribution must be expected from the model designer as opposed to what can be formalized in computer algorithms, and an outlook on future plans to resolve present shortcomings.     

Approximate channel identification via δ‐signed correlation

A method of approximate channel identification is proposed that is based on a simplification of the correlation estimator. Despite the numerical simplification (no multiplications or additions are required, only comparisons and an accumulator), the performance of the proposed estimator is not significantly worse than that of the standard correlation estimator. A free (user selectable) parameter moves ‘smoothly’ from a situation with small sum‐squared channel estimation error but hard‐to‐identify channel peaks, to one with a larger sum‐squared estimation error but easy‐to‐identify channel peaks. The proposed estimator is shown to be biased and its behaviour is analysed in a number of situations. Applications of the proposed estimator to sparsity detection, symbol timing recovery and to the initialization of blind equalizers are suggested. Copyright © 2002 John Wiley & Sons, Ltd.     

储层识别模式的研究

用数学方法建立气测井油气储层识别模式,以解决录井中实时软件在判别依据少的条件下,及时识别油气显示假异常的难题。该判别式经实用,正到率达90％。     

TRANSFER FUNCTION MODEL ORDER AND PARAMETER ESTIMATION

Abstract. A distributed lag model with a rational transfer function is considered. We have demonstrated that the C -table can be used to determine the orders of the rational transfer function and the Padé table can be used to estimate the parameters of an identifiable transfer function. In case the model is not uniquely identified, the C -table reduces possible competing models to only a few for further examination. Padé approximant gives consistent initial values for possibly more efficient iterative procedures to estimate the coefficients of the identified model. Some asymptotic results on the estimation of the C -table and the Padé table are given. A few examples are presented to demonstrate the effectiveness of the method.     

Sensorless control of synchronous reluctance motors using on‐line parameter identification method not affected by position estimation accuracy

This paper presents a novel on‐line parameter identification method for sensorless control of Synchronous Reluctance Motors (SynRMs). Although conventional sensorless control methods based on mathematical models usually need some complex measurements of motor parameters in advance, the proposed identification method does not require them and can be realized on‐line. The proposed method identifies motor parameters under sensorless control, so rotor position and velocity cannot be used to identify these parameters. However, the proposed method does not need rotor position and velocity, and identified parameters are not affected by these estimation errors. The sensorless control using identified motor parameters is realized, and the effectiveness of the proposed method is verified by experimental results. © 2006 Wiley Periodicals, Inc. Electr Eng Jpn, 155(3): 62–69, 2006; Published online in Wiley InterScience ( www.interscience.wiley.com ). DOI 10.1002/eej.20258     

Predicting Youth Access to Tobacco: The Role of Youth Versus Store-Clerk Behavior and Issues of Ecological Validity.

Twenty-one 15- to 17-year-olds attempted to purchase cigarettes in 232 stores in the manner that confederates typically do in access studies, as well as in the manipulative ways (e.g., lying about their ages) that youth smokers do, thereby modeling youth access to tobacco within versus outside of studies, respectively. Youth typical-research versus manipulative behavior was contrasted with clerk behavior (requests for youth ID cards) to examine the relative contributions of both to youth access to tobacco for the 1st time. Results revealed that clerk behavior was the strongest predictor of cigarette sales to youth and hence underscore the need for interventions with merchants. Sales nonetheless were higher under youth-manipulative conditions and thereby highlight the low ecological validity of access research. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

测井相识别模型及其在东海油气勘探中的应用

文章提出一种测井相识别模型,该模型用常规测井信息,定量地确定测井相在钻遇地层中的空间位置,建立测井相。配合东海油气勘探工作,用该识别模型对苏堤构造带的钻遇地层进行了测井相分析。     

Performance analysis of the forgetting factor RLS algorithm

An analysis is given of the performance of the standard forgetting factor recursive least squares (RLS) algorithm when used for tracking time-varying linear regression models. Three basic results are obtained: (1) the ‘P-matrix’ in the algorithm remains bounded if and only if the (time-varying) covariance matrix of the regressors is uniformly non-singular; (2) if so, the parameter tracking error covariance matrix is of the order O(μ + γ²/μ), where μ = 1 - λ, λ is the forgetting factor and γ is a quantity reflecting the speed of the parameter variations; (3) this covariance matrix can be arbitrarily well approximated (for small enough μ) by an expression that is easy to compute.     

Citations do not solve problems.

D. T. Cambell and D. W. Fiske (1959) made the now-obvious statement that measures of the same variable made by different methods should agree (converge) and certainly should agree better than measures of different variables made by those several methods. Almost everyone accepted that statement, yet the multitrait–multimethod matrices published today show little or no improvement over the published examples cited in 1959. The article raised the conceptual problem of how a variable and its measurement should be linked and the methodological problem of clarifying the nature of methods and their effects. Given these unresolved problems, it is perhaps not surprising that the question of the appropriate statistical analysis of these matrices has also no consensual answer. Perhaps methods and traits or contents are so thoroughly intertwined that their interaction cannot be adequately analyzed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

基于模块化模型的自适应预失真技术

系统地比较和分析了OFDM传输系统里高功率放大器（HPA）预失真方法的优缺点,提出一种基于模块化模型的有记忆高功率放大器自适应数字预失真方法,该方法分别基于Wiener、Hammerstein和Wiener-Hammerstein模型各自构成一个有记忆HPA的自适应预失真器。从而避免了因分别估计Wiener-Hammerstein模型各个环节特性参数所带来的复杂性。使得有记忆高功率放大器的预失真设计变得简单了。