mdh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Adaptive Differential Evolution Supports Automatic Model Calibration in Furnace Optimized Control System
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems.ORCID iD: 0000-0002-3425-3837
Industrial Systems, Prevas, Västerås, Sweden.
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems.ORCID iD: 0000-0001-9857-4317
2017 (English)In: Computational Intelligence / [ed] Agostinho Rosa, Juan Julian Merelo, António Dourado, José M. Cadenas, Kurosh Madani, António Ruano and Joaquim Filipe, Germany: Springer, 2017, Vol. 669, 42-55 p.Chapter in book (Other academic)
Abstract [en]

Model calibration represents the task of estimating the parameters of a process model to obtain a good match between observed and simulated behaviours. This can be considered as an optimization problem to search for model parameters that minimize the discrepancy between the model outputs and the corresponding features from the historical empirical data. This chapter investigates the use of Differential Evolution (DE), a competitive class of evolutionary algorithms, to solve calibration problems for nonlinear process models. The merits of DE include simple and compact structure, easy implementation, as well as high convergence speed. However, the good performance of DE relies on proper setting of its running parameters such as scaling factor and crossover probability, which are problem dependent and which can even vary in the different stages of the search. To mitigate this issue, we propose a new adaptive DE algorithm that dynamically adjusts its running parameters during its execution. The core of this new algorithm is the incorporated greedy local search, which is conducted in successive learning periods to continuously locate better parameter assignments in the optimization process. In case studies, we have applied our proposed adaptive DE algorithm for model calibration in a Furnace Optimized Control System. The statistical analysis of experimental results demonstrate that the proposed DE algorithm can support the creation of process models that are more accurate than those produced by standard DE.

Place, publisher, year, edition, pages
Germany: Springer, 2017. Vol. 669, 42-55 p.
Series
Studies in Computational Intelligence, ISSN 1860-949X ; 669
Keyword [en]
Differential Evolution, Optimization, Model Identifi cation, Temperature estimation
National Category
Computer and Information Science
Identifiers
URN: urn:nbn:se:mdh:diva-33465DOI: 10.1007/978-3-319-48506-5_3ISI: 000407483200003Scopus ID: 2-s2.0-85005979528OAI: oai:DiVA.org:mdh-33465DiVA: diva2:1039929
Projects
EMOPAC - Evolutionary Multi-Objective Optimization and Its Applications in Analog Circuit Design
Available from: 2016-10-25 Created: 2016-10-25 Last updated: 2017-08-31Bibliographically approved
In thesis
1. Enhancing Differential Evolution Algorithm for Solving Continuous Optimization Problems
Open this publication in new window or tab >>Enhancing Differential Evolution Algorithm for Solving Continuous Optimization Problems
2016 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Differential Evolution (DE) has become one of the most important metaheuristics during the recent years, obtaining attractive results in solving many engineering optimization problems. However, the performance of DE is not always strong when seeking optimal solutions. It has two major problems in real world applications. First, it can easily get stuck in a local optimum or fail to generate better solutions before the population has converged. Secondly, its performance is significantly influenced by the control parameters, which are problem dependent and which vary in different regions of space under exploration.  It usually entails a time consuming trial-and-error procedure to set suitable parameters for DE in a specific problem, particularly for those practioners with limited knowledge and experience of using this technique.

 

This thesis aims to develop new DE algorithms to address the two aforementioned problems. To mitigate the first problem, we studied the hybridization of DE with local search techniques to enhance the efficiency of search. The main idea is to apply a local search mechanism to the best individual in each generation of DE to exploit the most promising regions during the evolutionary processs so as to speed up the convergence or increase the chance to scape from local optima. Four local search strategies have been integrated  and tested in the global DE framework, leading to variants of the memetic DE algorithms with different properties concerning diversification and intensification. For tackling the second problem, we propose a greedy adaptation method for dynamic adjustment of the control parameters in DE. It is implemented by conducting greedy search repeatedly during the run of DE to reach better parameter assignments in the neighborhood of a current candidate. The candidates are assessed by considering both, the success rate and also fitness improvement of trial solutions against the target ones. The incorporation of this greedy parameter adaptation method into standard DE has led to a new adaptive DE algorithm, referred to as Greedy Adaptive Differential Evolution (GADE).

 

The methods proposed in this thesis have been tested in different benchmark problems and compared with the state of the art algorithms, obtaining competitive results. Furthermore, the proposed GADE algorithm has been applied in an industrial scenario achieving more accurate results than those obtained by a standard DE algorithm. 

Abstract [sv]

Differential Evolution (DE) har blivit en av de viktigaste metaheuristikerna under de senaste åren och har uppnått attraktiva resultat för att lösa många optimeringsproblem inom teknik. Dock är prestationen hos DE inte alltid framgångsrik när man söker optimala lösningar. Det finns två huvudsakliga problem för applikationer i den verkliga världen. Det första är att den lätt kan fastna i lokala optimum eller misslyckas att generera bättre lösningar före det att populationen (en grupp av lösningar) har hunnit konvergera. Det andra är att prestandan påverkas märkvärdigt av kontrollparametrar, vilkas optimala värden beror på problem som ska lösas och varierar mellan regioner i sökrymden. Detta innebär oftast ett tidskrävande trial-and-error förfarande för att hitta lämpliga parametrar till ett specifikt DE-problem, framför allt för utövare med begränsad kunskap och erfarenhet av DE.

 

Syftet med denna licentiatavhandling är att utveckla nya DE-algoritmer för att behandla de ovannämnda problemen. För att möta det första problemet så studerades hybridisering av DE och lokala söktekniker för att effektivisera sökningen. Tanken är att använda en lokal sökmekanism på den bästa individen i varje generation i DE-algoritmen och utnyttja de mest lovande regionerna under evolutionsprocessen för att snabba på konvergensen eller öka chansen att undvika lokala optimum. Fyra lokala sökstrategier har integrerats och testats i det globala DE-ramverket vilket har lett till fyra varianter av DE-algoritmerna med olika egenskaper beträffande diversifiering och intensifiering. Till det andra problemet föreslås en greedy adaptation method för dynamisk justering av kontrollparametrarna i DE. Den implementeras genom att utföra greedy search upprepade gånger under körningen av DE för att hitta bättre värden till kontrollparametrarna. Utvärderingen av parameterval baseras på både success rate och fitness improvement av trial lösningar jämfört med target lösningar. Sammanslagningen av DE och denna greedy parameter adaptation har lett till en ny adaptiv DE-algoritm som kallas Greedy Adaptive Differential Evolution (GADE).

 

Den föreslagna metoden i denna licentiatavhandling har testats i olika prestandamätningar och jämförts med state-of-the-art-algoritmer, med goda resultat. Dessutom har den föreslagna GADE-algoritmen använts i ett industriellt scenario och uppnådde då mer exakta resultat än den med en standard DE-algoritm.

Place, publisher, year, edition, pages
Västerås: Mälardalen University, 2016
Series
Mälardalen University Press Licentiate Theses, ISSN 1651-9256 ; 246
National Category
Computer Science
Research subject
Computer Science
Identifiers
urn:nbn:se:mdh:diva-33466 (URN)978-91-7485-299-8 (ISBN)
Presentation
2016-12-15, Delta, Mälardalens högskola, Västerås, 13:15 (English)
Opponent
Supervisors
Available from: 2016-10-26 Created: 2016-10-25 Last updated: 2016-11-25Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Leon Ortiz, MiguelXiong, Ning
By organisation
Embedded Systems
Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 96 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf