Gradient based iterative parameter identification for Wiener nonlinear systems

This paper focuses on the identification problem of Wiener nonlinear output error systems. The application of the key-term decomposition technique provides a special form of the Wiener model with polynomials, where all the model parameters to be estimated are separated. To solve the identification problem of Wiener nonlinear output error systems with the unmeasurable variables in the information vector, an auxiliary model-based gradient iterative algorithm is presented by replacing the unmeasurable variables with their corresponding iterative estimates. The performances of the proposed algorithm are analyzed and compared by using numerical examples.     

Multi-innovation stochastic gradient algorithm for multiple-input single-output systems using the auxiliary model

In order to reduce computational burden and improve the convergence rate of identification algorithms, an auxiliary model based multi-innovation stochastic gradient (AM-MISG) algorithm is derived for the multiple-input single-output systems by means of the auxiliary model identification idea and multi-innovation identification theory. The basic idea is to replace the unknown outputs of the fictitious subsystems in the information vector with the outputs of the auxiliary models and to present an auxiliary model based stochastic gradient algorithm, and then to derive the AM-MISG algorithm by expanding the scalar innovation to innovation vector and introducing the innovation length. The simulation example shows that the proposed algorithms work quite well.     

Convergence of HLS estimation algorithms for multivariable ARX-like systems

A hierarchical least squares (HLS) algorithm is derived in details for identifying MIMO ARX-like systems based on the hierarchical identification principle. It is shown that the parameter estimation errors by the HLS algorithm consistently converge to zero for bounded noise variances by using the stochastic martingale theory. A numerical example is given.     

Least squares based iterative parameter estimation algorithm for multivariable controlled ARMA system modelling with finite measurement data

Difficulties of identification for multivariable controlled autoregressive moving average (ARMA) systems lie in that there exist unknown noise terms in the information vector, and the iterative identification can be used for the system with unknown terms in the information vector. By means of the hierarchical identification principle, those noise terms in the information vector are replaced with the estimated residuals and a least squares based iterative algorithm is proposed for multivariable controlled ARMA systems. The simulation results indicate that the proposed algorithm is effective.     

Performance analysis of the AM-SG parameter estimation for multivariable systems

The auxiliary model based stochastic gradient (AM-SG) parameter estimation method is an important identification one. This paper analyzes the performances of the AM-SG estimation algorithm for multiple-input single-output systems (i.e., multivariable systems) under the strong persistent excitation condition. The analysis and simulation results indicate that the parameter estimation errors converge to zero.     

Hierarchical multi-innovation stochastic gradient algorithm for Hammerstein nonlinear system modeling

This paper decomposes a Hammerstein nonlinear system into two subsystems, one containing the parameters of the linear dynamical block and the other containing the parameters of the nonlinear static block, and presents a hierarchical multi-innovation stochastic gradient identification algorithm for Hammerstein systems based on the hierarchical identification principle. The proposed algorithm is simple in principle and easy to implement on-line. A simulation example is provided to test the effectiveness of the proposed algorithm.     

Parameter and state estimation algorithm for single-input single-output linear systems using the canonical state space models

This paper presents a new parameter and state estimation algorithm for single-input single-output systems based on canonical state space models from the given input–output data. Difficulties of identification for state space models lie in that there exist unknown noise terms in the formation vector and unknown state variables. By means of the hierarchical identification principle, those noise terms in the information vector are replaced with the estimated residuals and a new least squares algorithm is proposed for parameter estimation and the system states are computed by using the estimated parameters. Finally, an example is provided.     

Computation algorithms for disturbance rejection in multivariable systems

In this paper, one way of solving an important problem in linear time-invariant multivariable systems control for synthesizing feedback controllers to make the outputs of a physical system respond in a desirable manner to reference inputs and external disturbances is presented. The proposed algorithms can be regarded as a logical extension of the pole assignment problem in that, measurable or unmeasurable multiple disturbance acting on multivariable systems described by the 4-tuples (A,B,C,E) or the 6-tuples (A,B,C,D,E,F) can be rejected at the outputs in steady state. This is done by assignment of the `disturbance blocking zeros' at specified locations using the concept of pole assignment for computing the state feedback controllers. The performance of the algorithms is illustrated by a numerical example.     

Model Selection of Dnamical Systems via Entropic Regression and Bayesian Information Criteria

Recovering system model from noisy data is a key challenge in the analysis of dynamical systems. Based on a data-driven identification approach, we develop a model selection algorithm called Entropy Regression Bayesian Information Criterion (ER-BIC). First, the entropy regression identification algorithm (ER) is used to obtain candidate models that are close to the Pareto optimum and combine as a library of candidate models. Second, BIC score in the candidate models library is calculated using the Bayesian information criterion (BIC) and ranked from smallest to largest. Third, the model with the smallest BIC score is selected as the one we need to optimize. Finally, the ER-BIC algorithm is applied to several classical dynamical systems, including one-dimensional polynomial and RC circuit systems, two-dimensional Duffing and classical ODE systems, three-dimensional Lorenz 63 and Lorenz 84 systems. The results show that the new algorithm accurately identifies the system model under noise and time variable $t$, laying the foundation for nonlinear analysis.     

Auxiliary model based parameter estimation for dual-rate output error systems with colored noise

The dual-rate sampled-data systems can offer better quality of control than the systems with single sampling rate in practice. However, the conventional identification methods run in the single-rate scheme. This paper focuses on the parameter estimation problems of the dual-rate output error systems with colored noises. Based on the dual-rate sampled and noise-contaminated data, two direct estimation algorithms are addressed: the auxiliary model based recursive extended least squares algorithm and the recursive prediction error method. The auxiliary model is employed to estimate the noise-free system output. An example is given to test and illustrate the proposed algorithms.     

An online identification algorithm of unknown time-varying delay and internal multimodel control for discrete non-linear systems

In this paper, an online algorithm is proposed for the identification of unknown time-varying input delay in the case of discrete non-linear systems described by decoupled multimodel. This method relies on the minimization of a performance index based on the error between the real system and the partial internal models outputs. In addition, a decoupled internal multimodel control is proposed for the compensation of discrete non-linear systems with time-varying delay. This control scheme incorporates partial internal model controls. Each partial controller is associated to a specified operating zone of the non-linear system. The switching between these controllers is ensured by a supervisor that contains a set of local predictors. A simulation example is carried out to illustrate the significance of the proposed time-varying delay identification algorithm and the proposed internal multimodel control scheme.     

Model recovery for Hammerstein systems using the auxiliary model based orthogonal matching pursuit method

This article investigates parameter and order identification of a block-oriented Hammerstein system by using the orthogonal matching pursuit method in the compressive sensing theory which deals with how to recover a sparse signal in a known basis with a linear measurement model and a small set of linear measurements. The idea is to parameterize the Hammerstein system into the linear measurement model containing a measurement matrix with some unknown variables and a sparse parameter vector by using the key variable separation principle, then an auxiliary model based orthogonal matching pursuit algorithm is presented to recover the sparse vector.The standard orthogonal matching pursuit algorithm with a known measurement matrix is a popular recovery strategy by picking the supporting basis and the corresponding non-zero element of a sparse signal in a greedy fashion. In contrast to this, the auxiliary model based orthogonal matching pursuit algorithm has unknown variables in the measurement matrix. For a K-sparse signal, the standard orthogonal matching pursuit algorithm takes a fixed number of K stages to pick K columns (atoms) in the measurement matrix, while the auxiliary model based orthogonal matching pursuit algorithm takes steps larger than K to pick K atoms in the measurement matrix with the process of picking and deleting atoms, due to the gradually accurate estimates of the unknown variables step by step.The auxiliary model based orthogonal matching pursuit algorithm can simultaneously identify parameters and orders of the Hammerstein system, and has a high efficient identification performance.     

AR模型辨识的稀疏结构迭代算法

模型估计是机器学习领域一个重要的研究内容,动态数据的模型估计是系统辨识和系统控制的基础.针对AR时间序列模型辨识问题,证明了在给定阶数下AR模型参数的最小二乘估计本质上也是一种矩估计.根据结构风险最小化原理,通过对模型拟合度和模型复杂度的折衷,提出了基于稀疏结构迭代的AR序列模型估计算法,并讨论了基于广义岭估计的最优正则化参数选取规则.数值结果表明,方法能以节省参数的方式有效地实现AR模型的辨识,比矩估计法结果有明显改善.     

Bias compensation methods for stochastic systems with colored noise

For ARX-like systems, this paper derives a bias compensation based recursive least squares identification algorithm by means of the prefilter idea and bias compensation principle. The proposed algorithm can give the unbiased estimates of the system model parameters in the presence of colored noises, and can be on-line implemented. Finally, the advantages of the proposed bias compensation recursive least squares algorithm are shown by simulation tests.     

Recursive parameter identification for fermentation processes with the multiple model technique

This paper considers parameter identification problems for a fermentation process. Since the fermentation process is nonlinear, it is difficult to use a single-model for describing such a process and thus we use the multiple model technique to study the identification methods. The basic idea is to establish the model of the fermentation process at each operation point by means of the least squares principle, to obtain multiple models with different points, and then use the weighting functions or interpolation methods to compute the total model or the global model. Finally, a numerical example is provided to test the effectiveness of the proposed algorithm.     

Data-driven recursive least squares methods for non-affined nonlinear discrete-time systems

Aiming at identifying nonlinear systems, one of the most challenging problems in system identification, a class of data-driven recursive least squares algorithms are presented in this work. First, a full form dynamic linearization based linear data model for nonlinear systems is derived. Consequently, a full form dynamic linearization-based data-driven recursive least squares identification method for estimating the unknown parameter of the obtained linear data model is proposed along with convergence analysis and prediction of the outputs subject to stochastic noises. Furthermore, a partial form dynamic linearization-based data-driven recursive least squares identification algorithm is also developed as a special case of the full form dynamic linearization based algorithm. The proposed two identification algorithms for the nonlinear nonaffine discrete-time systems are flexible in applications without relying on any explicit mechanism model information of the systems. Additionally, the number of the parameters in the obtained linear data model can be tuned flexibly to reduce computation complexity. The validity of the two identification algorithms is verified by rigorous theoretical analysis and simulation studies.     

卖空限制下知情交易的测度及识别研究

经典的测量知情交易概率的模型默认交易者可以无限制的按照私有信息进行卖空交易,而目前我国股票市场存在卖空限制,直接将经典模型应用到我国股票市场时会使测量结果出现偏差。考虑到我国股票市场现状,本文在经典的知情交易概率模型中引入两个卖空限制参数,构建了本文的SC-TPIN模型。通过对融券标的中发生利空消息的股票样本进行实证分析,证实了本文构建的SC-TPIN模型估计出的结果与实际情况相符合。本文还以SC-TPIN模型估计出的SCTPIN值为参照,基于样本股票的低频数据构建了知情交易识别指标组,并使用数据挖掘中的支持向量机算法、KNN算法及Logit模型对黑白样本的知情交易高低情况进行识别比较,构建知情交易识别体系,发现使用支持向量机算法识别全样本的正确率达到了89%,识别效果较理想。     

Introduction to the Special Issue on Discrete Event Models of Continuous Systems

Automatic control systems rely on models to predict the near future and identification algorithms to adapt the models to changing process behaviour. The traditionally highly complex models of the activated sludge process developed for scientific purposes cannot be identified from on-line measurements and are not suited for process control purposes in their present form. Model decoupling based on the different time scales of the dynamic processes is one possible way of attacking this problem. It allows the implementation of more simple and realistically applicable controllers in combination with predictions based on simplified models in hierarchical control structure. This paper discusses these concepts and presents a reduced order model describing carbonaceous removal, nitrification, and denitrification in a medium time scale (several hours/days). The model parameters are identifiable from available on-line measurements and the dynamic behaviour is verified against computer simulations of the IAWQ activated sludge model no. 1.     

Auxiliary model identification method for multirate multi-input systems based on least squares

This paper derives state-space models for multirate multi-input sampled-data systems. Based on the corresponding transfer function models, an auxiliary model based recursive least squares algorithm is presented to identify the parameters of the multirate systems from the multirate input–output data. Further, convergence properties of the proposed algorithm are analyzed. Finally, an illustrative example is given.     

Gradient based estimation algorithm for Hammerstein systems with saturation and dead-zone nonlinearities

This paper focuses on identification problems for Hammerstein systems with saturation and dead-zone nonlinearities. An appropriate switching function is introduced to derive an identification model with fewer parameters and all the unknown parameters can be estimated by using an iterative method. A numerical simulation is carried out to show the effectiveness of the proposed method.