Neural networks for control systems—A survey

Hunt, Kenneth J.; Sbárbaro, Daniel; Żbikowski, Rafał; Gawthrop, P.J.

doi:10.1016/0005-1098(92)90053-i

Cited by 1,700 publications

(564 citation statements)

References 69 publications

Supporting

Mentioning

508

Contrasting

Unclassified

Order By: Relevance

“…This method is also named identification technique. There are two system identification approaches: forward system identification and inverse system identification The procedure of training a neural network to represent the forward dynamics of a system is often referred to as the forward system identification approach [28] . A schematic diagram of this process is shown in Fig.…”

Section: Intelligent Controllers: This Category Of Controllers Includmentioning

confidence: 99%

See 1 more Smart Citation

Control Techniques in Heating, Ventilating and Air Conditioning (HVAC) Systems

Mirinejad¹,

Sadati²,

Ghasemian³

et al. 2008

J. of Computer Science

View full text Add to dashboard Cite

Problem statement: Heating, Ventilating and Air Conditioning (HVAC) systems are among the main installations in residential, commercial and industrial buildings. The purpose of the HVAC systems is normally to provide a comfortable environment in terms of temperature, humidity and other environmental parameters for the occupants as well as to save energy. Achieving these objectives requires a suitable control system design. Approach: In this overview, thermal comfort level and ISO comfort field is introduced, followed by a review and comparison of the main existing control techniques used in HVAC systems to date. Results: The present overview shows that intelligent controllers which are based on the human sensation of thermal comfort have a better performance in providing thermal comfort as well as energy saving than the traditional controllers and those based on a model of the HVAC system. Conclusion: Such an overview provides an insight into current control methods in HVAC systems and can help scholars and HVAC learners to have the comprehensive information about a variety of control techniques in the field of HVAC and therefore to better design a proper controller for their work.

show abstract

Section: Intelligent Controllers: This Category Of Controllers Includmentioning

confidence: 99%

“…In an inverse system identification approach, a network is trained in an effort to model the inverse of the plant mapping [28] . One of the simplest approaches, known as direct inverse system identification, is shown schematically in Fig.…”

Section: Intelligent Controllers: This Category Of Controllers Includmentioning

confidence: 99%

Control Techniques in Heating, Ventilating and Air Conditioning (HVAC) Systems

Mirinejad¹,

Sadati²,

Ghasemian³

et al. 2008

J. of Computer Science

View full text Add to dashboard Cite

show abstract

“…Hunt et al (1992) reviewed various neural network architectures for use in the modelling, identification and control of non-linear systems.…”

Section: Development Of a Neural Network Controller For The Pilot Plamentioning

confidence: 99%

Advanced Control of a Rotary Dryer

Yliniemi¹,

Koskinen²,

Leiviskä³

1998

IFAC Proceedings Volumes

View full text Add to dashboard Cite

Real knowledge is based on experience.(Chinese saying) AbstractDrying, especially rotary drying, is without doubt one of the oldest and most common unit operations in the process industries. Rotary dryers are workhorses which are easy and reliable to operate, but neither energy-efficient nor environmentally friendly. In order to conform better to the requirements of modern society concerning working conditions, safety practices and environmental aspects, the development of control systems can provide opportunities for improving dryer operation and efficiency. Our in depth understanding of rotary drying is poor, because it is a very complex process that includes the movement of solids in addition to thermal drying. Thus even today rotary dryers are controlled partly manually, based on the operator's "eye" and experience, and partly relying on conventional control methods. The control of a rotary dryer is difficult due to the long time delay, which means that accidental variations in the input variables can disturb the process for long periods of time before they are reflected in the output variables. To eliminate such disturbances at an early stage, increasing interest has been shown in more sophisticated control systems such as model-based constructs, fuzzy logic and neural nets in recent years. Although it has proved difficult and time-consuming to develop model-based control systems, due to the complexity of the process, intelligent control methods based on fuzzy logic and neural nets offer attractive solutions for improving dryer control. These methods make it possible to utilise experience, knowledge and historical data, large amounts of which are readily available.The aim of this research was to improve dryer control by developing new hybrid control systems, one consisting of a fuzzy logic controller (FLC) and PI controller and the other of a three-layer neural network (NN) and PI controller. The FLC and NN act as supervisory controllers giving set points for the PI controllers. The performance of each was examined both with simulations and in pilot plant experiments. The pilot plant dryer at the University of Oulu closely resembles a real industrial situation, so that the results are relevant. Evaluation of these results showed that the intelligent hybrid controllers are well suited for the control of a rotary dryer, giving a performance in which disturbances can be eliminated rapidly and operation of the dryer can thereby be improved, with the aim of enhancing its efficiency and environmental friendliness.

show abstract

“…Se as perturbações são pequenas podem-se despreciar os termos de ordem superior, obtendo-se a equação linear, eq. (3). …”

Section: Introductionunclassified

An�lise Qualitativa de Processos Atrav�s dos Fatores de Sensibilidade Via Redes Neurais e Sua Aplica��o na Lamina��o em Tandem

Zrate¹,

Bittencout²

2016

Anais Do 5. Congresso Brasileiro De Redes Neurais

View full text Add to dashboard Cite

IntroduçãoO entendimento de um processo físico, químico, econômico, etc. pode ser obtido através do estudo das variáveis envolvidas no processo. A relação das variáveis pode ser expressa por meio de equações analíticas que compõem o modelo e que permitem analizar as relações causa-efeito entre as variáveis. A modelagem física é sempre uma atividade que demanda um grande tempo de análise e entendimento do processo. A dificuldade de obter um modelo é diretamente proporcional à complexidade do fenómeno em estudo. A modelagem é um trabalho árduo e pode levar, dependendo do processo, anos para sua conclusão. Por outro lado durante o desenvolvimento de um modelo matemático existem complexidades que não possuem fácil solução analítica. Isto pode levar a soluções numéricas que demandem grande esforço computacional [1].Na maioria das vezes modelos físicos de processos apresentam características não lineares que dificultam a aplicação em sistemas de controle e de supervisão "online". A primeira porque a aplicação da teoria de controle clássico exige modelos lineares, e a segunda, porque modelos complexos que proporcionam valores de simulação para supervisionar um processo podem requerer de solução numérica com grande esforço computacional.Frequentemente não é possivel obter uma relação direta entre um parâmetro A (causa) e uma função B (efeito). No entanto pode-se as vezes correlacionar experimentalmente o parâmetro A com valores das derivadas da função B (efeito).Considere uma função não linear dado pela eq. (1). Para obter um modelo matemático linear supõe-se que as variáveis variam muito pouco dentro de uma condição de operação.

show abstract

Neural networks for control systems—A survey

Cited by 1,700 publications

References 69 publications

Control Techniques in Heating, Ventilating and Air Conditioning (HVAC) Systems

Control Techniques in Heating, Ventilating and Air Conditioning (HVAC) Systems

Advanced Control of a Rotary Dryer

An�lise Qualitativa de Processos Atrav�s dos Fatores de Sensibilidade Via Redes Neurais e Sua Aplica��o na Lamina��o em Tandem

Contact Info

Product

Resources

About