This paper deals with the simultaneous states and parameters estimation of an ozonation reactor using a dynamic neural network and the least squares method. We use a dynamic model derived from mass balance considerations. We propose a continuous time algorithm which includes two parallel procedures: state estimation using a Dynamic Neural Network (DNN) and parameters identification based on Lea...

1. What Is System Identification? 1.1. The Need of Mathematical Models 1.2. Classification of Models 1.3. Mathematical Modeling 1.4. Applying System Identification 2. The Setup 2.1. Some Basic Concepts 2.2. Identifiability 3. Identification Methods 3.1. Least Squares Method 3.2. Instrumental Variable Methods 3.2.1. The Basic Case 3.2.2. Extended IV Methods 3.2.3. Consistency Analysis 3.2.4. Asy...

Dependency of explicit costs index of mining opening on its parameters is modeled. In addition, the problem of structural identification is solved. Models enumeration is realized with the help of group methods of data handling (GMDH). Least-squares and least-modules methods are used for evaluating model parameters. The quality of resulting models is evaluated by the following criteria: (a) rema...

Abstrart-Many practical applications of control system design based on input-output measurements permit the repeated application of a system identification procedure operating on closed-loop data together with successive refinements of the designed controller. Here we develop a paradigm for such an iterative design. The key to the procedure is to account for evaluated modelling error in the con...

This paper derives a least squares-based and a gradient-based iterative identification algorithms for Wiener nonlinear systems. These methods separate one bilinear cost function into two linear cost functions, estimating directly the parameters of Wiener systems without re-parameterization to generate redundant estimates. The simulation results confirm that the proposed two algorithms are valid...

The aim of this paper is to extend our previous work on a novel and recent class of nonlinear filters called Spline Adaptive Filters (SAFs), implementing the linear part of the Wiener architecture with an IIR filter instead of an FIR one. The new learning algorithm is derived by an LMS approach and a bound on the choice of the learning rate is also proposed. Some experimental results show the e...

The Volterra series have been successfully and widely applied as a nonlinear system modeling technique. Considered as a prototype, the second order Volterra filter (FV2) has an increased complexity in comparison with a linear filter. The filter based on the multi memory decomposition (MMD) structure represents a good approximation of the FV2 and significantly reduces the number of the filter op...

One of today’s most frequently discussed topics in the business world is how to escape from the intense Red Ocean and how to create an uncontested Blue Ocean. However, because there are few practical guidelines available on this topic, we will introduce a case study of a third-party logistics (3PL) provider, CJ-Global Logistics Service (CJ-GLS), to show how it aspires to be a leader in the newl...

Nonlinear adaptive filtering techniques are widely used for the nonlinearities identification in many applications. This paper proposes a new implementation of the third order RLS Volterra filter based on the decomposition of the input vector. Its performances are evaluated in a typical nonlinear system identification application. Different degrees of nonlinearity for the nonlinear system are c...

A new unified modelling framework based on the superposition of additive submodels, functional components, and wavelet decompositions is proposed for nonlinear system identification. A nonlinear model, which is often represented using a multivariate nonlinear function, is initially decomposed into a number of functional components via the well known analysis of variance (ANOVA) expression, whic...