Design of Intelligent Self‐Tuning GA ANFIS Temperature Controller for Plastic Extrusion System

Ravi, S.; Sudha, M.; Balakrishnan, P.

doi:10.1155/2011/101437

Cited by 41 publications

(21 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This merged technique of the learning power of the ANNs with the knowledge representation of FL has created a new hybrid technique, called neuro fuzzy networks or adaptive neuro fuzzy inference system (ANFIS) [14]. ANFIS, as a hybrid intelligent system that enhances the ability to automatically learn and adapt, was used by researchers for modeling [15,16], predictions [17][18][19] and control [20,21] in various engineering systems. The basic idea behind these neuro-adaptive learning techniques is to provide a method for the fuzzy modeling procedure to learn information about data [22,23].…”

Section: Introductionmentioning

confidence: 99%

RETRACTED ARTICLE: Input Displacement Neuro-fuzzy Control and Object Recognition by Compliant Multi-fingered Passively Adaptive Robotic Gripper

Petković

Shamshirband

Anuar

et al. 2015

J Intell Robot Syst

View full text Add to dashboard Cite

The requirement for new flexible adaptive grippers is the ability to detect and recognize objects in their environments. It is known that robotic manipulators are highly nonlinear systems, and an accurate mathematical model is difficult to obtain, thus making it difficult make decision strategies using conventional techniques. Here, an adaptive neuro fuzzy inference system (ANFIS) for controlling input displacement and object recognition of a new adaptive compliant gripper is presented. The grasping function of the proposed adaptive multi-fingered gripper relies on the physical contact of the finger with an object. This design of the each finger has embedded sensors as part of its structure. The use of embedded sensors in a robot gripper gives the control system the ability to control input displacement of the gripper and to recognize particular shapes of the grasping objects. Fuzzy based controllers develop a control signal according to grasping object shape which yields on the firing of the rule base. The selection of the proper rule base depending on the situation can be achieved by using an ANFIS strategy, which becomes an integrated method of approach for the control purposes. In the designed ANFIS scheme, neural network techniques are used to select a proper rule base, which is achieved using the back propagation algorithm. The simulation results presented in this paper show the effectiveness of the developed method.

show abstract

Section: Introductionmentioning

confidence: 99%

RETRACTED ARTICLE: Input Displacement Neuro-fuzzy Control and Object Recognition by Compliant Multi-fingered Passively Adaptive Robotic Gripper

Petković

Shamshirband

Anuar

et al. 2015

J Intell Robot Syst

View full text Add to dashboard Cite

show abstract

“…The three most significant variables were selected and applied to develop an ANFIS model. ANFIS is a robust tool favored by researchers for modeling (Al-Ghandoor and Samhouri 2009;Petković et al 2012a, b;Petković and Ćojbašić 2012), making predictions (Hosoz et al 2011;Gocić et al 2015b;Sivakumar and Balu 2010) and control in engineering systems (Kurnaz et al 2010;Ravi et al 2011;Khoshnevisan et al 2015;Petković et al 2012a, b;Tian and Collins 2005). ANFIS facilitates a fuzzy modeling procedure to gather data (Aldair and Wang 2011) and it can also be used to organize fuzzy inference systems using input/output data pairs.…”

Section: Introductionmentioning

confidence: 99%

Comparative Study of Soft Computing Methodologies for Energy Input–Output Analysis to Predict Potato Production

et al. 2015

View full text Add to dashboard Cite

In this study, an adaptive neuro-fuzzy inference system (ANFIS) was developed to predict potato production in Iran. Data related to potato yield from 2010 to 2011 was collected from 50 potato producers in Hamedan, Iran. The resulting ANFIS network has an input layer with eight neurons and an output layer with a single neuron (potato yield). The energy inputs were manual labor, diesel, chemical fertilizers, and manure from farm animals, chemicals, machinery, water, and seed. The most significant and influential inputs were selected from the eight initial inputs and the ANFIS network was used to choose the parameters that have the most influence on potato yield. A new ANFIS model was created after the three most influential parameters were selected. The new ANFIS model was then utilized to estimate yield using the three energy inputs. Next, the ANFIS model results were compared with the results from the support vector regression (SVR) technique. The end results revealed that ANFIS provided more accurate predictions and had the capacity to generalize. The Pearson correlation coefficient (r) for ANFIS potato yield prediction was 0.9999 in the training and testing phases, while the SVR model had a correlation coefficient of 0.8484 in training and 0.9984 in testing.Resumen En este estudio se desarrolló un sistema de inferencia adaptativa de lógica difusa (ANFIS) para predecir la producción de papa en Irán. Se colectaron datos relacionados con el rendimiento de papa de 2010 a 2011 de 50 productores en Hamedan, Irán. La red ANFIS resultante tiene una capa de insumos con ocho neuronas y una capa de salidas con una única neurona (rendimiento de papa). Los insumos de energía fueron mano de obra, diésel, fertilizantes químicos y estiércol de animales de granja, químicos, maquinaria, agua y semilla. Se seleccionaron los insumos más significativos y de influencia de los ocho insumos iniciales, y se usó la red ANFIS para escoger los parámetros que tienen la mayor influencia en el rendimiento de papa. Se creó un nuevo modelo ANFIS después que se seleccionaron los tres parámetros de mayor influencia. Entonces se utilizó el nuevo modelo ANFIS para estimar rendimiento usando los tres insumos de energía. Después, los resultados del modelo ANFIS se compararon con los resultados de la técnica de regresión de vector de respaldo (SVR). Los resultados finales revelaron que ANFIS suministró predicciones más precisas y tuvo la capacidad de generalizar. El coeficiente de correlación de Pearson (r) para la predicción del rendimiento de papa por ANFIS fue 0.9999 en las fases de formación y de prueba, e el modelo SVR tuvo un coeficiente de correlación de 0.8484 en formación y 0.9984 en prueba.

show abstract

“…Simulation results showed that the optimised controller gave a much faster settling time with no overshoot. Ravi and Balakrishnan [36,37] used AI techniques in extruder barrel temperature control. The results showed that a FLC can perform well with a lesser overshoot than a PI controller.…”

Section: B Control Schemes Based On Artificial Intelligence Techniquesmentioning

confidence: 99%

Single screw extrusion control: A comprehensive review and directions for improvements

Abeykoon

2016

Control Engineering Practice

View full text Add to dashboard Cite

Polymer extrusion is usually a complex process, particularly due to the coupled nature of process parameters, and hence highly prone to fluctuations. Although a number of different approaches have been attempted in research/industry over the last few decades for extrusion control, it is still experiencing some problems in achieving consistent product quality. Presently, most of the polymer processing extruders are equipped with PID controllers mainly for the control of the screw speed and barrel temperatures in their set limits. It seems that only both of these controllers are commonly used as the major aids of process control to achieve the required melt quality. Although, the quality of the melt output (i.e., a thermally homogeneous melt output which is constant in quantity and quality over the time) is the key variable in polymer extrusion, only a few control techniques are available which make control decisions by observing the actual melt flow quality. Therefore, the development of new control strategies which consider the actual melt quality, perhaps incorporating industrially popular nonlinear techniques such as artificial intelligence, should be highly valuable. In this work, a critical evaluation is made on the state-of-the-art of the previous control approaches in polymer extrusion in industry and research while identifying their limitations. Then, some of the possible directions for future research and also to develop an advanced process control strategy are presented by eliminating a few of the existing limitations.

show abstract

Design of Intelligent Self‐Tuning GA ANFIS Temperature Controller for Plastic Extrusion System

Cited by 41 publications

References 12 publications

RETRACTED ARTICLE: Input Displacement Neuro-fuzzy Control and Object Recognition by Compliant Multi-fingered Passively Adaptive Robotic Gripper

RETRACTED ARTICLE: Input Displacement Neuro-fuzzy Control and Object Recognition by Compliant Multi-fingered Passively Adaptive Robotic Gripper

Comparative Study of Soft Computing Methodologies for Energy Input–Output Analysis to Predict Potato Production

Single screw extrusion control: A comprehensive review and directions for improvements

Contact Info

Product

Resources

About