Recurrent Neuro Fuzzy and Fuzzy Neural Hybrid Networks: A Review

Subathra, B.; Radhakrishnan, T. K.

doi:10.1080/10739149.2011.633144

Cited by 7 publications

(5 citation statements)

References 88 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FNN is a hybrid system combining the theories of fuzzy theory and ANN, which can make use of easy interpretability of fuzzy theory as well as superior learning ability and selfadaptive capability of ANN. It has a broad application in areas of intelligent control, signal processing, prediction and forecasting, nonlinear system identification, intelligent optimization, pattern recognition, etc 15, 29. To get an intuitional understanding of FNN, Figure 1 shows a highly simplified schematic diagram of the structure of a four‐layer FNN 29…”

Section: Theory and Architecturementioning

confidence: 99%

“…The predictability of the model was evaluated by calculating average relative deviation (ARD), standard deviation (SD), and squared correlation coefficient ( R 2 ) 4, 15. The ARD and SD are defined as where N is the number of data points; Pre( i ) is the predicted value of model and Exp( i ) is the experimental data; the $\mathop x\nolimits_{_0 }$ is the average of the N data points.…”

Section: Theory and Architecturementioning

confidence: 99%

“…With the popularization of artificial neural networks (ANN), the determination of ANN structure, parameters and bias becomes the most crucial factors because the training process of ANN could be considered as a classical optimization problem 12. Recently, researchers discovered that many intelligent algorithms such as genetic algorithm,13 simulated annealing algorithm,14 fuzzy logic theory,15 gravitational search algorithm,16 wavelet analysis,17 ant colony optimization algorithm,18 particle swarm optimization algorithm (PSO),12, 19–21 chaos theory,22 and so on, can all be used for this determination. Therefore, ANN combined with intelligent optimization algorithms namely hybrid neural network has become one of the most active subject.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Solubility prediction of gases in polymers using fuzzy neural network based on particle swarm optimization algorithm and clustering method

Huang

Liu

et al. 2013

J of Applied Polymer Sci

View full text Add to dashboard Cite

A four-layer fuzzy neural network (FNN) model combining particle swarm optimization (PSO) algorithm and clustering method is proposed to predict the solubility of gases in polymers, hereafter called the CPSO-FNN, which combined fuzzy theory's better adaptive ability, neural network's capability of nonlinear and PSO algorithm's global search ability. In this article, the CPSO-FNN model has been employed to investigate solubility of CO 2 in polystyrene, N 2 in polystyrene, and CO 2 in polypropylene, respectively. Results obtained in this work indicate that the proposed CPSO-FNN is an effective method for the prediction of gases solubility in polymers. Meanwhile, compared with traditional FNN, this method shows a better performance on predicting gases solubility in polymers. The values of average relative deviation, squared correlation coefficient (R 2 ) and standard deviation are 0.135, 0.9936, and 0.0302, respectively. The statistical data demonstrate that the CPSO-FNN has an outstanding prediction accuracy and an excellent correlation between prediction values and experimental data.Recent years, the interdiscipline of information science and intelligent technology has a broad application perspective. 4,12,13 With the popularization of artificial neural networks (ANN), the determination of ANN structure, parameters and bias becomes the most crucial factors because the training process of ANN could be considered as a classical optimization problem. 12 Recently, researchers discovered that many intelligent algorithms such as genetic algorithm, 13 simulated annealing algorithm, 14 fuzzy logic theory, 15 gravitational search algorithm, 16 wavelet analysis, 17 ant colony optimization algorithm, 18 particle swarm optimization algorithm (PSO), 12,19-21 chaos theory, 22 and so on, can all be used for this determination. Therefore, ANN combined with intelligent optimization algorithms namely hybrid neural network has become one of the most active subject.So far as solubility of gases in polymers is concerned, it is affected by temperature, pressure, and sometimes it can also be affected by the interactions with the groups of the macromolecular chains. 23 As a result of the nonlinear relationship of these

show abstract

Section: Theory and Architecturementioning

confidence: 99%

Section: Theory and Architecturementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Solubility prediction of gases in polymers using fuzzy neural network based on particle swarm optimization algorithm and clustering method

Huang

Liu

et al. 2013

J of Applied Polymer Sci

View full text Add to dashboard Cite

show abstract

“…Thirty-three papers about fault diagnosis based on ANFIS, while two hundred and twelve papers about FNN could be found in the Web of Science database up to December 2016. Moreover, the two methods of hybrid fuzzy theory and neural network are different [ 11 ]. In this study, fault tree analysis is used to infer the fault rules between faults and fault symptoms, which may has function conflicts with the ANFIS.…”

Section: Introductionmentioning

confidence: 99%

Application of Fault Tree Analysis and Fuzzy Neural Networks to Fault Diagnosis in the Internet of Things (IoT) for Aquaculture

Chen

Zhen

et al. 2017

Sensors

View full text Add to dashboard Cite

In the Internet of Things (IoT) equipment used for aquaculture is often deployed in outdoor ponds located in remote areas. Faults occur frequently in these tough environments and the staff generally lack professional knowledge and pay a low degree of attention in these areas. Once faults happen, expert personnel must carry out maintenance outdoors. Therefore, this study presents an intelligent method for fault diagnosis based on fault tree analysis and a fuzzy neural network. In the proposed method, first, the fault tree presents a logic structure of fault symptoms and faults. Second, rules extracted from the fault trees avoid duplicate and redundancy. Third, the fuzzy neural network is applied to train the relationship mapping between fault symptoms and faults. In the aquaculture IoT, one fault can cause various fault symptoms, and one symptom can be caused by a variety of faults. Four fault relationships are obtained. Results show that one symptom-to-one fault, two symptoms-to-two faults, and two symptoms-to-one fault relationships can be rapidly diagnosed with high precision, while one symptom-to-two faults patterns perform not so well, but are still worth researching. This model implements diagnosis for most kinds of faults in the aquaculture IoT.

show abstract

“…Hence, only one output can be obtained at the end of training of the network and it is therefore not suitable for modelling multivariable processes. Review of the literature reveals that the use of RNFN for modelling real-time multivariable processes with interactions and design of predictive controllers has not been explored (Subathra & Radhakrishnan, 2011b). Motivated by this research gap, this investigation aims to model a nonlinear multivariable process with interactions using RNFN and then propose an MPC design methodology for the model.…”

Section: Introductionmentioning

confidence: 99%

A comparative study of neuro fuzzy and recurrent neuro fuzzy model-based controllers for real-time industrial processes

Subathra

Seshadhri

Radhakrishnan

2015

Systems Science & Control Engineering

Self Cite

View full text Add to dashboard Cite

Nonlinearities in system dynamics and the multivariable nature of processes offer a stiff challenge in designing predictive controllers that improve process performance in industries. This investigation presents a recurrent neuro fuzzy network (RNFN) model for a nonlinear multivariable system in process industries and a methodology to design model-predictive controllers (MPCs) using the proposed model. The RNFN model combines the learning features of artificial neural networks with human cognition capabilities of fuzzy systems. Therefore, RNFN leads to a modelling framework that has the ability not only to learn the model parameters, but also makes decision on operating region of the nonlinear model depending on the input-output data. Furthermore, the recurrent structure and the introduction of a memory unit between the fuzzy inference and fuzzification layer enhance the prediction capability due to the use of past input-output data, making the model more suitable for designing predictive controllers. Next, the MPC design methodology that exploits the advantages of the RNFN model to optimize the control moves is presented. The proposed MPC uses the gradient descent algorithm to minimize the control moves as against the traditional state-space approaches that require complex computations and solvers. Therefore, implementing the proposed MPC in embedded hardware becomes easier. The proposed modelling framework and the MPC design methodology are illustrated using experiments on a laboratory-scale quadruple tank. Our experiments show that the proposed RNFN-based MPC performs better than the neuro fuzzy network-based MPC for both servo and regulatory responses.

show abstract

Recurrent Neuro Fuzzy and Fuzzy Neural Hybrid Networks: A Review

Cited by 7 publications

References 88 publications

Solubility prediction of gases in polymers using fuzzy neural network based on particle swarm optimization algorithm and clustering method

Solubility prediction of gases in polymers using fuzzy neural network based on particle swarm optimization algorithm and clustering method

Application of Fault Tree Analysis and Fuzzy Neural Networks to Fault Diagnosis in the Internet of Things (IoT) for Aquaculture

A comparative study of neuro fuzzy and recurrent neuro fuzzy model-based controllers for real-time industrial processes

Contact Info

Product

Resources

About