An optimization approach within supervisor architecture for boiler control

Ryashentseva, Daria; Lüder, Arndt; Rosendahl, Ronald; Finaev, Valerij

doi:10.1109/etfa.2015.7301584

Cited by 4 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The control tasks of the production facilities under uncertainty are solved successfully by the usage of the artificial intelligence methods [1][2][3][4][5][6]. The uncertainty is described by the lack of the adequate mathematical model of the control object and inauthenticity of the data concerning the control process.…”

Section: Introductionmentioning

confidence: 99%

Updating probabilistic method of the fuzzy control model's parameters of the production facilities

Finaev

Sinjavskaya

Lüder

et al. 2016

2016 IEEE 21st International Conference on Emerging Technologies and Factory Automation (ETFA)

Self Cite

View full text Add to dashboard Cite

The paper describes the controlmethod of the production facilities (baking chamber) under uncertainty. Due tothe impossibility to find the adequate analytical model for this object, to control this type of the object under uncertainty the Mamdani fuzzy model is applied. A distinctive feature of this paper is connected with following: the parameters of the fuzzy model can be determined inaccuracy by the experts and, therefore, the model can work insufficiently, in order to eliminate the possibility of inaccuracy, the problems of assessment of the fuzzy model adequacy and the updating of its parameters are discussed. The iterative algorithm for the updating of the parameters of the described model is designed. The base of the iterative algorithm is connected with probability theory and mathematical statistics. Justification of application of the probability theory criteria is fulfilled. The research of the fuzzy model's work with the application of the updating block of the model's parameters is fulfilled and assessment of the fuzzy model's work is carried out by the usage of the probabilistic criterion (mean square deviation of the fuel consumption in the baking chamber). The updating process consists in correction of the membership functions according to the fulfilled experiments. Keywords-Control system, uncertainty, expert knowledge, fuzzy inference, rule base, membership function, mean square deviation, probabilistic updating algorithm of the fuzzy model's parametersI.

show abstract

Section: Introductionmentioning

confidence: 99%