Neural network modeling and control of cement mills using a variable structure systems theory based on-line learning mechanism

Topalov, Andon V.; Kaynak, Okyay

doi:10.1016/j.jprocont.2003.10.005

Cited by 38 publications

(20 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is noted that when there is a change of setpoint for (y f ) or (z) there is only a small deviation in the other loop compared to the other control strategy reported in the literature (Nonlinear robust controller [20], Nonlinear receding horizon (NRH) control [30], linear quadratic control [30], Nonlinear learning control [7], Neural Network based control [21]), also the effect of hardness change does not destabilize the cement mill.…”

Section: Resultsmentioning

confidence: 92%

“…The proposed approach shows a good performance in building the fuzzy logic controllers for a complex Cement mill process. The performance of our fuzzy controller is tested with cement mill circuit via simulation, and the results are compared with other control techiniques proposed in [7], [20], [21] and [30].…”

Section: Resultsmentioning

confidence: 99%

“…The tailings are recycled at a rate y r [tons /h] to the mill while the finished product exits the plant at a rate y f [tons /h]. The plant is described by a simple dynamical model with three state variables (y f , y r , z) [3], [19], [20], [21].…”

Section: Mathematical Modelingmentioning

confidence: 99%

See 2 more Smart Citations

Evolutionary Design of Intelligent Controller for a Cement Mill Process

Subbaraj¹,

Anand²

2010

IJCA

View full text Add to dashboard Cite

The Knowledge Base of a Fuzzy Logic Controller (FLC) encapsulates expert knowledge and consists of the Data Base (membership functions) and Rule-Base of the controller. Optimization of these Knowledge Base components is critical to the performance of the controller and has traditionally been achieved through a process of trial and error. Such an approach is convenient for FLCs having low numbers of input variables however for greater number of inputs, more formal methods of Knowledge Base optimization are required. Genetic Algorithms (GAs) provide such a method to optimize the FLC parameters. An intelligent multi input multi output (MIMO) control for the cement milling circuit is presented. The FLC is optimized by GA for varying nonlinearity in the plant. The proposed control algorithm was tested on the cement mill simulation model within MATLABTM SimulinkTM environment. Parameters of the simulation model were set up based on the actual cement mill characteristics. The performances of the proposed control technique are compared with various control technique. The results of the control study indicate that the proposed algorithm can prevent the mill from plugging and control the cement mill circuit effectively compared to the other control technique.

show abstract

Section: Resultsmentioning

confidence: 92%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Evolutionary Design of Intelligent Controller for a Cement Mill Process

Subbaraj¹,

Anand²

2010

IJCA

View full text Add to dashboard Cite

show abstract

“…Modelling and control of closed circuit cement mills is described by Topalov and Kaynak (2004). Still, these models do not adequately account for the non-linear nature of the ball milling process, and do not perform well enough to achieve the required quality level for metal powder ball milling.…”

Section: Powder Ball Millingmentioning

confidence: 99%

Agent-based control of manufacturing processes

Albadawi

Boulet

DiRaddo

et al. 2006

IJMR

View full text Add to dashboard Cite

“…As the dataset, data from the production of clinker was used. Researchers have explored some stages of the cement and clinker production with usage of ANN (Svinning et al 2010, Stanisic et al 2014, Topalov 2004) but they do not solve the prediction of the chemical composition of raw material. Firstly, introduction into the clinker production is given, than a description of artificial neural network (ANN) follows.…”

Section: Introductionmentioning

confidence: 99%

Prediction Of Raw Material Batches For The Production Of Clinker By Means Of Artificial Neural Networks -Analysis Of Behaviour

Oplatková¹,

Šenkeřík

2015

ECMS 2015 Proceedings Edited By: Valeri M. Mladenov, Petia Georgieva, Grisha Spasov, Galidiya Petrova

View full text Add to dashboard Cite

This research deals with the analysis of the behaviour of artificial neural nets for prediction of raw material batches for the production of clinker. During the production several oxides that are present in raw materials in quarries have to be extracted for homogenization of the mixture suitable for clinker production. There is some delay between the measurement of the mixture and the material which is send from quarry. It is necessary to "send" precise chemical composition to ensure a good quality of clinker and resulting product -cement. Artificial neural networks (ANN) are suitable for such kind of timeindependent prediction. The results show that not all oxides are necessary to use for the prediction of one oxide. The ANN were designed into several nets with one input similarly as pseudo neural networks are able to work. The results will be used for the purpose of further research of pseudo neural nets which currently serve only as classifiers.

show abstract

Neural network modeling and control of cement mills using a variable structure systems theory based on-line learning mechanism

Cited by 38 publications

References 15 publications

Evolutionary Design of Intelligent Controller for a Cement Mill Process

Evolutionary Design of Intelligent Controller for a Cement Mill Process

Agent-based control of manufacturing processes

Prediction Of Raw Material Batches For The Production Of Clinker By Means Of Artificial Neural Networks -Analysis Of Behaviour

Contact Info

Product

Resources

About