Wyniki wyszukiwania - BazTech

1

Assessment of the GPC control quality using non-Gaussian statistical measures

Domański P. D., Ławryńczuk M.

International Journal of Applied Mathematics and Computer Science

|

2017

|

Vol. 27, no. 2

291--307

EN

This paper presents an alternative approach to the task of control performance assessment. Various statistical measures based on Gaussian and non-Gaussian distribution functions are evaluated. The analysis starts with the review of control error histograms followed by their statistical analysis using probability distribution functions. Simulation results obtained for a control system with the generalized predictive controller algorithm are considered. The proposed approach using Cauchy and Lévy α-stable distributions shows robustness against disturbances and enables effective control loop quality evaluation. Tests of the predictive algorithm prove its ability to detect the impact of the main controller parameters, such as the model gain, the dynamics or the prediction horizon.

2

Non-Gaussian statistical measures of control performance

Domański P. D.

Control and Cybernetics

|

2017

|

Vol. 46, no. 3

259--290

EN

Statistical approach to Control Performance Assessment (CPA) is of great practical importance. This is particularly visible in process industry, where there are many PID loops. They are often assessed with measures derived from the Gaussian probabilistic density function. Standard deviation, variance, skewness or kurtosis form the majority of applied indexes. The review of data originating from process industry shows, however, to the contrary, that these signals have rather non-Gaussian properties and are mostly characterized by fat-tailed distribution disable the ability. Investigations show that strong disturbances may signiﬁcantly disable the capacity of proper assessment. Standard measures often fail in such cases. It is shown that non-Gaussian measures can help with this problem. Various disturbances are tested and compared. Results show that fat-tailed distributions are an interesting alternative. They are less sensitive to disturbance shadowing and still make possible loop dynamic assessment.

3

Controller adaptation using dynamic evolutionary algorithm

Kaczyński P., Domański P.D.

Prace Naukowe Politechniki Warszawskiej. Elektronika

|

2006

|

z. 156

179-187

EN

In this paper we present an algorithmic solution to PID controller parameters tuning task. Firstly, the brief test model and a simple example on how to tune PID parameters using genetic algorithm are presented. This functionality is then tested in more complicated situation of a non-stationary linear object. Adaptivity of such a solution is considered along with some results.

4

Optymalizacja pracy młyna węglowego przy użyciu regulatora typu MPC

Jankowski R., Świrski K., Domański P. D.

Prace Naukowe Politechniki Warszawskiej. Konferencje

|

2003

|

z. 23

137--149

PL

Artykuł przedstawia zagadnienie optymalizacji pracy wentylatorowego młyna węglowego w oparciu o predykcyjny regulator optymalizujący z przesuwanym horyzontem, który jest rozwinięciem klasycznych regulatorów predykcyjnych z modelem typu MPC (Model Predictive Control). Na podstawie odpowiedniej procedury optymalizacyjnej regulator generuje korekty nastaw, które wprowadzane są do klasycznych struktur regulacji w rozproszonym systemie sterowania. Nieliniowy model procesu, zaimplementowany w regulatorze, zbudowany jest w oparciu o rozmyte sieci neuronowe. Zastosowanie sieci neuronowych zapewnia sprawną implementację oraz efektywne uczenie i strojenie. Istota regulacji polega na powtarzanej cyklicznie optymalizacji wskaźnika jakości, zdefiniowanego na podstawie założonych celów projektu. Celem pracy regulatora jest wyeliminowanie niekorzystnych zjawisk występujących podczas pracy młyna. Należą do nich: niestabilna wartość tepmeratury mieszanki pyłowo-powietrznej za młynem, nadmierne wahania temperatury powietrza przed młynem oraz położenie klap powietrza pierwotnego i wtórnego poza zakresem regulacyjnym. Cele te są realizowane poprzez odpowiednie sterowanie położeniem klapy powietrza pierwotnego i prędkością obrotową młyna. Wykonana została implementacja opisywanego regulatora w cyfrowym systemie automatyki na 8 młynach wentylatorowych kotła 360MW opalanego węglem brunatnym. W artykule przedstawiono uzyskane wyniki i przeprowadzono ich analizę.

EN

The article presents the question of optimization of a ventilation coal mill on the basis of a predictive optimizing controller with a receding horizon, which is an extension of the standard linear MPC (Model Predictive Control) type controllers. The controller has been realized in a digital version operating with a certain sampling period dependent upon the process dynamics. All calculations of the control rules are performed in one cycle which enables the controller to operate in the on-line mode. On the basis of a right optimization procedure the controller regulates the correction of settings, which are introduced to classic control structures in a fuzzy control system. The non-linear process model, implemented in the controller, is based on the basis of fuzzy neural networks. The use of neural networks ensures a fast and efficient implementation and effective learning and tuning. The problem of control is based in on a periodically performed optimization of the performance index, defined on the basis of the assumed project goals. The aim of the controller operation is to eliminate undesired events occurring during mill operation. Such events are: instability of temperature value of air-dust mix after the mill, excessive fluctuation of air temperature before the mill and positioning of primary and secondary air dampers outside the control range. These goals are realized through appropriate control of the primary air damper and revolving speed of the mill. The implementation carried out of the described controller in a digital automatic control system on 8 ventilation mills of a 360 MW brown coal fired boiler. This article presents the results obtained and a carried out analysis.

5

Global optimization based learning for recurrent neural networks

Strzelczyk M., Domański P. D.

Prace Naukowe Politechniki Warszawskiej. Elektronika

|

2002

|

z. 139

163--172

EN

This chapter describes the application of two different global optimization algorithms (CRS3 and the evolutionary strategy) to the problem of recurrent neural network learning. The performance has been compared with the standard multilayer perceptron with classical gradient learning strategy. The performance has been tested on different dynamic test models. The efficiency of the global optimization approach is shown.

6

Optymalizacj kotła pyłowego i obniżenia emisji NO x przy wykorzystaniu sieci neuronowych- metody soft computing

Arabas J., Białobrzeski L., Domański P.D., Świrski K., Chomiak T.

Energetyka

|

1998

|

nr 1

21-29