Design of Neural Based PID Controller For Nonlinear Process

Srivignesh, N.; Sowmya, P.; Ramkumar, K.; Balasubramanian, G.

doi:10.1016/j.proeng.2012.06.380

Cited by 13 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This step is uncomplicated, since the control action can be simply implemented using the identified NARMA-L2 plant model based on Eq. (8). As mentioned before, the functions ∧ f and ∧ g in Eq.…”

Section: The Wnn-based Narma-l2 Controller Design Stagementioning

confidence: 87%

“…As mentioned before, the functions ∧ f and ∧ g in Eq. (8) are defined in the NARMA-L2 plant identification stage. Moreover, in order to force the system output y p (k +1) to follow the desired reference signal y r (k +1), the following is done: y p (k + 1) = y r (k + 1).…”

Section: The Wnn-based Narma-l2 Controller Design Stagementioning

confidence: 99%

“…In this regard, the majority of researchers have applied MLP and RBF neural networks in the IMC structure. For instance, a MLP was used in [8] to find the optimal values for the gains of a PID controller acting as the main controller in the IMC structure. In [3], a MLP NN, with 22 nodes in its hidden layer, was utilized in an IMC structure to control a bearingless induction motor.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Wavelet Neural Network-Based NARMA-L2 Internal Model Control Utilizing Micro-artificial Immune Techniques to Control Nonlinear Systems

Lutfy

Selamat

2015

Arab J Sci Eng

View full text Add to dashboard Cite

This paper presents an intelligent control strategy based on internal model control (IMC) to control nonlinear systems. In particular, a wavelet neural network (WNN)-based nonlinear autoregressive moving average (NARMA-L2) network is used to acquire the forward dynamics of the controlled system. Subsequently, the control law can be directly derived. In this approach, a single NARMA-L2 with only one training phase is required. Hence, unlike other related works, this design approach does not require an additional training phase to find the model inversion. In the literature, gradient descent methods are the most widely applied training techniques for the neural network-based IMC. However, these methods are characterized by the slow convergence speed and the tendency to get trapped at local minima. To avoid these limitations, the newly developed modified micro-artificial immune system (modified Micro-AIS) is employed in this work to train the NARMA-L2. The simulation results have demonstrated the effectiveness of the proposed approach in terms of accurate control and robustness against external disturbances. In addition, a comparative study has shown the superiority of the WNN over the multilayer perceptron and the radial basis function based IMC. Moreover, compared with the genetic algorithm, the modified Micro-AIS has achieved better results as the training method in the IMC structure.

show abstract

Section: The Wnn-based Narma-l2 Controller Design Stagementioning

confidence: 87%

Section: The Wnn-based Narma-l2 Controller Design Stagementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Wavelet Neural Network-Based NARMA-L2 Internal Model Control Utilizing Micro-artificial Immune Techniques to Control Nonlinear Systems

Lutfy

Selamat

2015

Arab J Sci Eng

View full text Add to dashboard Cite

show abstract

“…Estos PBC son más simples que las técnicas citadas anteriormente en las referencias Gireesh y Sreenivasulu, 2014, Madhubala et al, 2004, Betancor-Martín et al, 2013, Arivalahan et al 2012, Ganesh Ram y Abraham Lincoln, 2013, Dhanalakshmi, R. y Vinodha, R., 2013, Srivignesh et al, 2012, Teena y Hepsiba, 2014, Beena et al, 2015; sin embargo, se basan en la cancelación exacta de términos entre el sistema no lineal y el controlador, por lo que no es robusto ante variaciones de los parámetros de la planta. Los controladores diseñados en Chandrasekar y Ponnusamy, 2013, Chandrasekar y Ponnusamy, 2014, se basan en una síntesis de conceptos y condiciones descritas en Byrnes et al, 1991, bajo las cuales un sistema no lineal con punto de equilibrio en el origen se puede convertir en Cr-pasivo y finalmente estabilizarse de manera simple mediante una técnica no adaptable de PBC.…”

Section: Introductionunclassified

Control Basado en Pasividad para una Clase de Sistemas no Lineales y su Aplicación a la Regulación de Nivel de un Estanque Cónico

Travieso-Torres

Duarte‐Mermoud

Gutiérrez-Osorio

et al. 2018

Rev. iberoam. autom. inform. ind.

View full text Add to dashboard Cite

ResumenEn este artículo científico se proponen dos estrategias de control basado en pasividad, una adaptable y la otra no adaptable para cierta clase de sistemas no lineales. A diferencia de la estrategia de control no adaptable, la adaptable no hace uso del conocimiento de los valores de los parámetros de la planta. Ambas estrategias son luego diseñadas y aplicadas para la regulación de nivel de un estanque cónico discutiéndose los resultados experimentalmente obtenidos luego de realizar un estudio comparativo experimental para verificar el comportamiento del sistema bajo control y evidenciar las ventajas y desventajas de los controladores. Los resultados muestran que el diseño del APBC es más simple que el diseño de los controladores PBC al no requerir el conocimiento de los parámetros de la planta controlada, también es más robusto frente a variaciones de un parámetro de la planta. Palabras Clave:Sistemas de control no-lineal, control adaptativo, pasividad. Passivity Based Control of a Class of Nonlinear Systems and its Application to the Level Regulation of a Conical Tank AbstractAn adaptive passivity-based controller (APBC) and a non-adaptive passivity-based controller (PBC) are proposed in this paper. In contrast to PBC, the APBC strategy does not make use of the knowledge of the values of the plant parameters. Both strategies are also designed and applied to the level regulation of a conical tank, discussing the experimental results obtained after performing an experimental comparative study to verify the behavior of the system under control and to demonstrate the advantages and disadvantages of the controllers. The results show that the design of the APBC is simpler than the design of PBC controllers by not requiring the knowledge of the plant parameters; it is also more robust in front of variations of a plant parameter.

show abstract

“…Conical tanks are nonlinear systems widely used in industrial applications for storage, with a shape that facilitates drainage. Several works on this subject have been reported in the technical literature [1][2][3][4][5][6][7][8][9][10] for level control of conical tanks. In [1][2][3][4] fuzzy techniques are used to adjust the PI settings depending on the level operating point.…”

Section: Introductionmentioning

confidence: 99%

Taylor polynomial Approximation and Adaptive Passivity‐Based Control Applied to the Level Regulation of a Conical Tank

Travieso-Torres

Duarte‐Mermoud

Beytía-Cancino

2017

Asian Journal of Control

View full text Add to dashboard Cite

The techniques of Taylor polynomial approximation (TPA) and adaptive passivity‐based controller (APBC) are combined in this study and applied to the level regulation of a conical tank. The design and comparative experimental results with a classical PI controller are presented. After combining these two approaches a robust adaptive controller named TPA–APBC, which is simpler than the classical APBC and PI controller, is obtained. This new TPA–APBC preserves the stability of the overall system after assuming that the nonlinear system is unknown and that it can be suitably represented by a first‐order linear model with unknown parameters.

show abstract

Design of Neural Based PID Controller For Nonlinear Process

Cited by 13 publications

References 10 publications

Wavelet Neural Network-Based NARMA-L2 Internal Model Control Utilizing Micro-artificial Immune Techniques to Control Nonlinear Systems

Wavelet Neural Network-Based NARMA-L2 Internal Model Control Utilizing Micro-artificial Immune Techniques to Control Nonlinear Systems

Control Basado en Pasividad para una Clase de Sistemas no Lineales y su Aplicación a la Regulación de Nivel de un Estanque Cónico

Taylor polynomial Approximation and Adaptive Passivity‐Based Control Applied to the Level Regulation of a Conical Tank

Contact Info

Product

Resources

About