2002
DOI: 10.1016/s0967-0661(02)00031-x
|View full text |Cite
|
Sign up to set email alerts
|

Grey-box model identification via evolutionary computing

Abstract: This paper presents an evolutionary grey-box model identification methodology that makes the best use of a-priori knowledge on a clear-box model with a global structural representation of the physical system under study, whilst incorporating accurate black-box models for immeasurable and local nonlinearities of a practical system. The evolutionary technique is applied to building dominant structural identification with local parametric tuning without the need of a differentiable performance index in the presen… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
27
0
1

Year Published

2004
2004
2016
2016

Publication Types

Select...
5
3
1

Relationship

0
9

Authors

Journals

citations
Cited by 50 publications
(28 citation statements)
references
References 26 publications
0
27
0
1
Order By: Relevance
“…Grey-box was developed in [5], where 'grey' means the combination of black box and clear box. Take (2) for instance, the model is in a clear linear form, and differences in estimation method will only alter the value of parameters but do not change the model to be black box.…”
Section: Methodolioges and Modelsmentioning
confidence: 99%
See 1 more Smart Citation
“…Grey-box was developed in [5], where 'grey' means the combination of black box and clear box. Take (2) for instance, the model is in a clear linear form, and differences in estimation method will only alter the value of parameters but do not change the model to be black box.…”
Section: Methodolioges and Modelsmentioning
confidence: 99%
“…There have been previously developed prediction models to predict cash flows in accountancy and finance. This paper applies the grey-box model developed in [5] and investigates the potential dynamic and nonlinear features of the model to cash flows that have been overlooked in previous modelling procedures.…”
Section: Introductionmentioning
confidence: 99%
“…A number of methods have been previously proposed for symbolic regression of nonlinear systems, but were limited to producing linear models (4) or were applied to systems composed of one or a few interacting variables (8)(9)(10)(11)(12)(13)(14)(15)(16). Here we introduce a scalable approach for automated symbolic regression, made possible by three advances introduced here: partitioning, in which equations describing each variable of the system can be synthesized separately, thereby significantly reducing the search space; automated probing, which automates experimentation in addition to modeling, leading to an automated ''scientific process'' (17)(18)(19)(20); and snipping, an ''Occam's Razor'' process that automatically simplifies and restructures models as they are synthesized to increase their accuracy, to accelerate their evaluation, and to render them more parsimonious and human-comprehensible.…”
Section: Partitioning Automated Probing and Snippingmentioning
confidence: 99%
“…tems design Multi-objective evolutionary algorithms have been successfully applied to many problems in the field of control systems engineering, from the offline design of robust controllers for a coal-fired gasification plant (Griffin et al, 2000) to model identification of nonlinear systems (Tan and Li, 2002). Whilst the majority of the applications of evolutionary multi-objective optimisation in control systems engineering have been in offline applications due to the iterative nature of the evolutionary design process, they have also been used in online applications applications such as hardware-in-the-loop tuning of a fuzzy logic based DC motor controller (Stewart et al, 2004).…”
Section: Multi-objective Evolutionary Algorithms In Control Sys-mentioning
confidence: 99%