A. JUDITSKY, H. HJALMARSSON, A. BENVENISTE, B. DELYON, L. LJUNG, J. SJ OBERG, AND Q. ZHANG, Nonlinear black box models in system identification: Mathematical foundations, Automatica, 31 (1995), pp. 1725--1751. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
A Qualitative-Fuzzy Framework for Nonlinear Black-Box.. - Bellazzi.. (1999) (2 citations) (Correct)
....the dynamics of thiamine (vitamin B1 ) and its phosphoesters in the cells of the intestine tissue. Introduction System Identification (si) deals with the development and analysis of methods which infer a quantitative model of the system dynamics from observed data (Haber Unbehauen 1990; Juditsky et al. 1995; Ljung 1987; Soderstrom Stoica 1989) si is applied to perform both grey and black box modeling tasks; we refer to grey models when the available knowledge of the underlying physics is such that the structural model equation may be explicitely formulated but the numeric values of some ....
Juditsky, A.; Hjalmarsson, H.; Benveniste, A.; Deylon, B.; Ljung, L.; Sjoberg, J.; and Zhang, Q. 1995. Nonlinear black-box models in system identification: Mathematical foundations. Automatica 31:1725--1750.
A Scheme for Nonlinear Modeling - van Gorp, al. (1999) (Correct)
....output. This mapping is a mathematical representation dependent on static or time dependent model parameters. Usually a White Box representation of a plant is favoured whenever precise knowledge on the plant is available. Sometimes it is impossible to extract detailed information and Black Box [22] [55] or Grey Box modeling [12] 41] is used. The basic choice here is the selection of the model. There have been many fierce discussions in favour or against different models. Yet, for any given continuous function that operates on it is possible to prove universal approximation properties [6] ....
.... triangular nonlinear structures [37] or saturating linear systems [18] The very general definitions for NN and FL makes them appropriate for mixed models, such as Neurofuzzy systems [20] 26] 58] or mixed with PI and PD controllers [31] 61] 63] Overviews of nonlinear systems are given in [16] [22] [28] 42] 45] and [48] All of these models are based on the same principle: how to provide a mathematical relationship between a given input and a given output. The remaining task is the choice of the model parameters that should be optimized or learned. IV. THE COST FUNCTION The proper ....
Juditsky A., Hjalmarsson H., Benveniste A., Delyon B., Ljung L., Sjberg J., Zhang Q., "Nonlinear Black-box Models in System Identification: Mathematical Foundations", Automatica, Vol. 31, No. 12, 1995, pp. 1725 - 1750.
Parametrization And Conditioning Of Hinging Hyperplane Models - Pucar, Sjöberg (1996) (Correct)
....Hinging Hyperplanes hinge function function hinge (a) 2 Dimensional (b) 3 Dimensional Fig. 1. Hinge, hinging hyperplane and hinge function atively simple building blocks, the basis functions h i , a broad class of nonlinear functions can be well approximated. In (Sjoberg et al. 1995) and (Juditsky et al. 1995) a general framework for nonlinear black box models is further developed. When the specific form of the basic expansion (1) has been decided upon, it remains to estimate the parameters by using collected data from the unknown system. This is typically performed by computing the parameter value ....
Juditsky, A., H. Hjalmarsson, A. Benveniste, B. Deylon, L. Ljung, J. Sjoberg and Q. Zhang (1995). "Nonlinear Black-Box Models in System Identification: Mathematical Foundations". Automatica.
Robust Full Bayesian Learning for Neural Networks - Andrieu, de Freitas, Doucet (1999) (4 citations) (Correct)
.... artificial neural network paradigms such as functional link networks (Pao 1989) multi layer perceptrons (MLPs) Rosenblatt 1959, Rumelhart et al. 1986) radial basis function networks (Lowe 1989, Moody and Darken 1988, Poggio and Girosi 1990) wavelet networks (Bakshi and Stephanopoulos 1993, Juditsky, Hjalmarsson, Benveniste, Delyon, Ljung and Sjoberg 1995) and hinging hyper planes (Breiman 1993) For an introduction to neural networks, the reader may consult any of the following books (Bishop 1995, Haykin 1994, Hecht Nielsen 1990, Ripley 1996) For the purposes of this paper, we adopt the approximation scheme of Holmes and Mallick (1998) ....
Juditsky, A., Hjalmarsson, H., Benveniste, A., Delyon, B., Ljung and Sjoberg, J. (1995). Nonlinear black-box models in system identification: Mathematical foundations, Technical report, Linkoping University, Sweden.
Neural Networks For Pneumatic Actuator Fault Detection - de Freitas, MacLeod, Maltz (Correct)
....generated at random, o] Normal valve [ Friction increased from 5 to 10 are likely to excite all system modes. Several attempts have been made to solve the nonlinear identification problem using an extension of the theory of linear autoregressive (ARX) models combined with neural networks [14 20]. In these attempts, however, the basis or activation functions used in each network layer are identical and their relation to the physical system has not been studied. A two step procedure is therefore used to model the control valve [21] The analysis step involves using a network with different ....
A Juditsky et al., "Non-linear black-box models in system identification: Mathematical foundations," tech. rep., Linkoping University, Sweden, 1995.
Fault Detection and Isolation in Nonlinear Dynamic.. - Zhang, Basseville.. (1998) (4 citations) Self-citation (Benveniste Zhang) (Correct)
....are physically meaningful and their changes correspond to faults to be detected and isolated. The system model, in particular its parameterization, should be suitably chosen so 2 Black box models are identified from measured data without physical knowledge. See for example (Sjoberg et al. 1995; Juditsky et al. 1995). PI n1074 6 Q. Zhang, M. Basseville and A. Benveniste that the faults to be detected and isolated can be modeled in this manner. More specifically, each faulty mode should correspond to changes in a sub vector of . Otherwise, the model should be modified (e.g. by changing its ....
Juditsky, A., Hjalmarsson, H., Benveniste, A., Deylon, B., Ljung, L., Sjoberg, J., and Zhang, Q. (1995). Nonlinear black-box models in system identification : Mathematical foundations.
Asymptotic properties of Least--Squares Estimates of - Hammerstein-Wiener Models.. (Correct)
No context found.
A. JUDITSKY, H. HJALMARSSON, A. BENVENISTE, B. DELYON, L. LJUNG, J. SJ OBERG, AND Q. ZHANG, Nonlinear black box models in system identification: Mathematical foundations, Automatica, 31 (1995), pp. 1725--1751.
Fourier Models For Non-Linear Signal Processing - Alba Pags-Zamora Miguel (1999) (Correct)
No context found.
A. Juditsky et al., Non-linear Black-Box Models in System Identification: Mathematical Foundations, Automatica, Vol. 31, No. 12, 1995, pp. 1725-1750.
Nonlinear Adaptive Control Using Neural Networks and Multiple.. - Chen, Narendra (2001) (Correct)
No context found.
A. Juditsky, H. Hjalmarsson, A. Benveniste, B. Delyon, L. Ljung, et al. Nonlinear black-box models in system identification: mathematical foundations. Automatica, 31(12):1725--1750, Dec 1995.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC