Application of Adaptive Controller Neural Network Based on RBF NN for Temperature Control Electrical Resistance Furnace

Kada, Benyekhlef

doi:10.15199/48.2020.06.06

Cited by 1 publication

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sensor and instrumentation amplifier set is supposed to be linear in the furnace temperature range. As reported in [1]- [3].…”

Section: Research Methods 21 Furnace System Modelssupporting

confidence: 64%

“…An effective temperature estimate for an electrical furnace thus minimizing the uncertainty in temperature prediction. The temperature measurement is tainted with white Gaussian noise and centered [1]- [3] in this case the state of the Electrical resistance furnace can be reconstructed using KSR. The Kalman function makes it possible to obtain the observer's gain vector from the process description of the variance of the noise of the process Q and the variance of the measurement noise R. We take for our application,…”

Section: Discussionmentioning

confidence: 99%

“…The mathematical modeling of electrical furnace and the model parameters of the furnace. According [1]- [3]. The electric furnace behaves like a first order process with a time constant close to 500 seconds.…”

Section: Research Methods 21 Furnace System Modelsmentioning

confidence: 99%

“…The mathematical model of electric resistance furnace is being represented in the state space as reported in [1]- [3]:…”

Section: Discrete State Representation Of the Electrical Furnace Resistancementioning

confidence: 99%

“…State modeling of the electrical furnace resistance takes into account two random variables Noise of process and measurement [1]- [3]. In this case, the temperature measurement is trained with centered Gaussian white noise.…”

Section: Algorithm 31 Development Of the Discrete Kalman Filter Algorithmmentioning

confidence: 99%

See 4 more Smart Citations

Study of designing regulator for temperature electrical resistance furnace using Kalman stochastic reconstructor

Kada

Kebir²,

Berka³

et al. 2021

IJEECS

Self Cite

View full text Add to dashboard Cite

<span>Electric <span>resistance furnaces are the most popular and widely used industrial electro thermal equipment which continues to be the subject of many improvements. The aim of this paper is to control the temperature of electrical furnace for noisy thermocouple sensors. It can be assessed by observing some variables, which are very difficult to observe. Due to limitations, mainly the location of thermal sensors and their noises. In this case, the temperature measurement is trained with centered Gaussian white noise. The problem of accurate temperatures estimation for such sensors is solved using Kalman filter, which is an optimized estimator that provides a computationally efficient way to estimate system state. Thus, variables that are not directly measurable can be reconstructed from the algorithm. Kalman stochastic reconstructor (KSR). We cannot use with fixed parameters to control the temperature. For this reason, this paper comes up with a KSR approach based pole placement (PL) hybrid controller to realize an algorithm for the temperature control electrical furnace. Results based on Matlab simulation show that the improved algorithm has well produced an optimal estimate of the temperature. Evolving over time from noisy measurements. Hybrid algorithm KSR approach based PL give good performance compared to PL controllers.</span></span>

show abstract

“…The sensor and instrumentation amplifier set is supposed to be linear in the furnace temperature range. As reported in [1]- [3].…”

Section: Research Methods 21 Furnace System Modelssupporting

confidence: 64%

Section: Discussionmentioning

confidence: 99%

Section: Research Methods 21 Furnace System Modelsmentioning

confidence: 99%

“…The mathematical model of electric resistance furnace is being represented in the state space as reported in [1]- [3]:…”

Section: Discrete State Representation Of the Electrical Furnace Resistancementioning

confidence: 99%

Section: Algorithm 31 Development Of the Discrete Kalman Filter Algorithmmentioning

confidence: 99%

See 3 more Smart Citations

Study of designing regulator for temperature electrical resistance furnace using Kalman stochastic reconstructor

Kada

Kebir²,

Berka³

et al. 2021

IJEECS

Self Cite

View full text Add to dashboard Cite

show abstract

Application of Adaptive Controller Neural Network Based on RBF NN for Temperature Control Electrical Resistance Furnace

Cited by 1 publication

References 0 publications

Study of designing regulator for temperature electrical resistance furnace using Kalman stochastic reconstructor

Study of designing regulator for temperature electrical resistance furnace using Kalman stochastic reconstructor

Contact Info

Product

Resources

About