Neural network based model predictive control for a steel pickling process

Kittisupakorn, Paisan; Thitiyasook, Piyanuch; Hussain, Mohd Azlan; Daosud, Wachira

doi:10.1016/j.jprocont.2008.09.003

Cited by 117 publications

(59 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, the manipulated variable (the set point of the jacket temperature) is adjusted as step changes and random changes in ranges of 270-400 K. The operational time is kept constant at 30 minutes and the sampling time of data is 0.1minutes.In the normalization step, all data are scaled in the range of the minimum and maximum value. Details of the procedure for obtaining the feedforward neural network models are explained in research [9].…”

Section: Neural Network Modeling For Optimal Purposementioning

confidence: 99%

“…The optimal NN structure is obtained by finding the number of nodes in the hidden layer where the NN1 has been developed based on the Lenvenberg-Marquardt training algorithm [9]. The sigmoid function is used as the activation functions of the nodes in the hidden layer and the linear transfer function used for its output layer.…”

Section: Neural Network Modeling For Optimal Purposementioning

confidence: 99%

“…The NN in this algorithm, NN2, is obtained by the procedure for developing neural network models as defined in research [9]. The training and validation data sets are obtained by selecting appropriate signals from the simulation of the purified terephthalic acid batch crystallizer by solving Eqs.…”

Section: Nn-based Model Predictive Control (Nnmpc)mentioning

confidence: 99%

“…Daosud et al improved the purity of acetone using neural network model for model based control algorithm [8]. Kittisupakorn et al applied neural network model for the prediction of the concentration profile of a hydrochloric acid for hydrochloric acid recovery process and used neural network as a model in control algorithm for a steel pickling process [9].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Improving of Crystal Size Distribution Control Based on Neural Network-Based Hybrid Model for Purified Terephthalic Acid Batch Crystallizer

Kittisupakorn¹,

Somsong²,

Hussain³

et al. 2017

Self Cite

View full text Add to dashboard Cite

Abstract. A main difficult task in batch crystallization is to control the size distribution of crystal products. Complexity and highly nonlinear dynamic behavior directly affect to model-based control strategies which heavily depend on the rigorous knowledge of crystallization. In this work, neural network-based model predictive control and inverse neural network control strategies are proposed and integrated with an optimization based on neural network-based hybrid model to control temperatures of a purified terephthalic acid batch crystallizer. A neural network-based hybrid model of the batch crystallizer is developed to provide nonlinear dynamic responses used in optimization algorithm for finding an optimal temperature profile related to the quality of a crystal product. Then, the obtained optimal profile is used as set points of the proposed control strategies for improving the crystal product quality. The performances and robustness of the proposed controllers are evaluated in several cases such as for set point tracking and plant/model mismatches. Simulation results show that the neural network-based model predictive control gives the best control performance among the inverse neural network control and a conventional PID controller in all cases.

show abstract

Section: Neural Network Modeling For Optimal Purposementioning

confidence: 99%

Section: Neural Network Modeling For Optimal Purposementioning

confidence: 99%

Section: Nn-based Model Predictive Control (Nnmpc)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving of Crystal Size Distribution Control Based on Neural Network-Based Hybrid Model for Purified Terephthalic Acid Batch Crystallizer

Kittisupakorn¹,

Somsong²,

Hussain³

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ultrasonic velocity changes due to acid concentration. 0.0000000e+000 a 5 -4.7305890e+000 a 6 0.0000000e+000 a 7 0.0000000e+000 a 8 2.0413212e+000 a 9 0.0000000e+000 a 10 2.0413212e+000 a 11 4.9006009e-002 a 12 7.1304870e-003 a 13 -1.7665033e-003 Accuracy +-0.7 g/l…”

Section: Concentration (%)mentioning

confidence: 99%

Development of a Concentration Measurement System for Pickling Line Control

Park¹,

Lee²,

Noh³

2013

Journal of Institute of Control, Robotics and Systems

View full text Add to dashboard Cite

This paper proposes the development of a new method for online analysis which measured acid concentration in a pickling line. Pickling is the most important step to remove surface scale layers and is strongly depending on the exactly controlled pickling liquor composition. Today, there is no feasible system available for the online control of pickling lines. Within this paper, new methods for online analysis of pickling liquors have been tested and implemented into an overall pickling process control tool. This method measured simultaneously the hydrochloric acid and iron ion concentration in a solution of hydrochloric acid by measuring the ultrasonic speed, the solution temperature, and the electrical conductivity. Experimental results showed excellent precision and the measurement error was ± 2 g / l compared with the neutralization titration measurement.

show abstract

Efficient Residential Indoor Thermal Environment Control

Deng

2015

Handbook of Clean Energy Systems

View full text Add to dashboard Cite

In this article, recent developments on the efficient control of residential indoor thermal environment are reported. Firstly, fundamental issues for indoor environmental control in residences are discussed. This is followed by presenting an analysis of a number of current control issues for direct expansion ( DX ) air‐conditioning (A/C) systems, including the capacity control, humidity control, and the inherent operating characteristics of a DX A/C system. A number of studied efficient control strategies for simultaneous controlling indoor air temperature and humidity using a DX A/C system, including direct digital control ( DDC )‐based control, multi‐input multi‐output ( MIMO ) control, and artificial neural network ( ANN )‐based control, are reported subsequently. Finally, some other related issues on residential indoor thermal environmental control using DX A/C systems, including a novel indoor humidity control algorithm (H–L (high–low) control algorithm), capacity control of multi‐evaporator air‐conditioning ( MEAC ) systems, and A/C for sleeping environments in the tropics and subtropics are discussed. It is expected that with the improvement on indoor thermal environmental control in residences, occupants' thermal comfort can be improved and more importantly, the energy use for A/C residential buildings reduced. This would in turn help reduce energy consumption in buildings, and thus carbon emission, contributing to sustainable development.

show abstract

Neural network based model predictive control for a steel pickling process

Cited by 117 publications

References 18 publications

Improving of Crystal Size Distribution Control Based on Neural Network-Based Hybrid Model for Purified Terephthalic Acid Batch Crystallizer

Improving of Crystal Size Distribution Control Based on Neural Network-Based Hybrid Model for Purified Terephthalic Acid Batch Crystallizer

Development of a Concentration Measurement System for Pickling Line Control

Efficient Residential Indoor Thermal Environment Control

Contact Info

Product

Resources

About