Recurrent Neuro-fuzzy Network Research Articles

A Hybrid Neuro-Fuzzy Network Based on Differential Biogeography-Based Optimization for Online Population Classification in Earthquakes

Timely and accurate identification and classification of victims in earthquakes is crucial for improving rescue efficiency, but available information about victims and their surrounding environment is often vague and imprecise. Rescue wings is a web-based intelligent system that monitors and analyzes the statuses of identified victims to support decision making in earthquake rescue operations. A key component of the system is a Takagi–Sugeno (T–S)-type neuro-fuzzy network for disaster-stricken population classification, and one important input of the network is the output of another T–S-type recurrent neuro-fuzzy network for recognizing the movement patterns from the users’ temporal location data. A novel differential biogeography-based optimization (DBBO) algorithm is developed for parameter optimization of both the main network and the subnetwork. Experimental results have shown that the hybrid neuro-fuzzy network exhibits good classification performance in comparison with some other typical neuro-fuzzy networks, and the proposed DBBO outperforms some state-of-the-art evolutionary algorithms in network learning. The solution approach has also been successfully applied to the 2013 Ya’an Earthquake in Sichuan province, China.

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

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.

Identification of nonlinear discrete systems by a state-space recurrent neurofuzzy network with a convergent algorithm

Recurrent neurofuzzy networks have proven to be useful in identification of systems with unknown dynamics when only input–output information is available. However, training algorithms for these structures usually require also the measurement of the actual states of the system in order to obtain a convergent algorithm and then obtain a scheme to approximate its dynamic behavior. When states are not available and only input–output information can be obtained, the stability of the training algorithm of the recurrent networks is hard to establish, as the dynamics is driven by the internal recurrent dynamics of each connection. In this paper, we present a structure and an ultimately stable training algorithm inspired by adaptive observer for black-box identification based on state-space recurrent neural networks for a class of dynamic nonlinear systems in discrete-time. The network catches the dynamics of the unknown plant and jointly identifies its parameters using only output measurements, with ultimately bounded identification and parameter error. Numerical examples using simulated and experimental systems are included to illustrate the effectiveness of the proposed method.

Analyzing the dynamics of emotional scene sequence using recurrent neuro-fuzzy network

In this paper, we propose a new framework to analyze the temporal dynamics of the emotional stimuli. For this framework, both electroencephalography signal and visual information are of great importance. The fusion of visual information with brain signals allows us to capture the users' emotional state. Thus we adopt previously proposed fuzzy-GIST as emotional feature to summarize the emotional feedback. In order to model the dynamics of the emotional stimuli sequence, we develop a recurrent neuro-fuzzy network for modeling the dynamic events of emotional dimensions including valence and arousal. It can incorporate human expertise by IF-THEN fuzzy rule while recurrent connections allow the fuzzy rules of network to see its own previous output. The results show that such a framework can interact with human subjects and generate arbitrary emotional sequences after learning the dynamics of an emotional sequence with enough number of samples.

RECURRENT NEURO FUZZY AND FUZZY NEURAL HYBRID NETWORKS: A REVIEW

An attempt is made to provide a comprehensive survey of the current trends in hybrid recurrent structures of fuzzy logic (FL) and neural networks (NN) for solving temporal problems. Their applications extending to universal approximations are also discussed with available reported literature on recurrent neuro fuzzy networks (RNFN) and recurrent fuzzy neural networks (RFNN).

MODELING AND PREDICTIVE CONTROL USING HYBRID INTELLIGENT TECHNIQUES FOR A NONLINEAR MULTIVARIABLE PROCESS

A recurrent neuro fuzzy network (RNFN) model–based multistep ahead predictive control strategy is proposed in this article. The fuzzy logic (FL) and neural networks (NN) are intelligent system approaches, and they complement each other. Hybridization of FL and NN utilizes the concepts of human cognitive capabilities and biological systems, respectively. Dynamic processes necessitate past information about the process input/output variables. In order to store the information, a memory unit is introduced between the fuzzy inference layer and the fuzzification layer. This recurrent structure enhances the prediction capability; hence, this RNFN model can be used to develop the multistep ahead predictive controller. The objective function of model based controller (MPC) minimizes the future control moves. The gradient descent (GD) algorithm is used to the optimize control moves. The proposed RNFN model is used to develop a model predictive controller. The performance of the RNFN-MPC is compared with that of a neuro fuzzy network (NFN)–based MPC for a laboratory scale quadruple tank process.

Black-Box Identification of a Class of Nonlinear Systems by a Recurrent Neurofuzzy Network

This brief presents a structure for black-box identification based on continuous-time recurrent neurofuzzy networks for a class of dynamic nonlinear systems. The proposed network catches the dynamics of a system by generating its own states, using only input and output measurements of the system. The training algorithm is based on adaptive observer theory, the stability of the network, the convergence of the training algorithm, and the ultimate bound on the identification error as well as the parameter error are established. Experimental results are included to illustrate the effectiveness of the proposed method.

A Hammerstein Recurrent Neurofuzzy Network With an Online Minimal Realization Learning Algorithm

This paper presents a Hammerstein recurrent neurofuzzy network associated with an online minimal realization learning algorithm for dealing with nonlinear dynamic applications. We fuse the concept of states in linear systems into a neurofuzzy framework so that the whole structure can be expressed by a state-space representation. An online minimal realization learning algorithm has been developed to find a controllable and observable state-space model of minimal size from the input-output measurements of a given system. Such an idea can simultaneously resolve the problem of the determination of a minimal structure and the difficulty of network stability analysis. The advantages of our approach include: 1) our recurrent network is capable of translating the complicated dynamic behavior of a nonlinear system into a minimal set of linguistic fuzzy dynamical rules and into state-space representation as well and 2) an online minimal realization learning algorithm unifies an order determination algorithm, a hybrid parameter initialization method, and a recursive recurrent learning algorithm into a systematic procedure to identify a minimal structure with satisfactory performance. Performance evaluations on benchmark examples as well as real-world applications have successfully validated the effectiveness of our approach.

Modified recurrent neuro-fuzzy network for modeling ball-screw servomechanism by using Chebyshev polynomial

This paper proposes a Chebyshev functional recurrent neuro-fuzzy (CFRNF) network to identify a nonlinear system, which is composed of nine layers network and a six-layer Chebyshev recurrent neural network (CRNN) used to emulate nonlinear system is one of nine layers. Based on Takagi–Sugeno–Kang (TSK) fuzzy model, the nonlinear dynamics of this system can be addressed by enhancing the input dimensions of the consequent parts in the fuzzy rules due to functional expansion of a Chebyshev polynomial. The back propagation algorithm is used to adjust the parameters of the antecedent membership functions as well as those of consequent functions. For a real system of ball-screw servomechanism with nonlinearity of stick-slip motion, the analytical and experimental results indicate that the accuracy and convergence of the CFRNF are superior to those of the identification results by adaptive neural fuzzy inference system (ANFIS) and recurrent neural network (RNN).

Modeling Belt-Servomechanism by Chebyshev Functional Recurrent Neuro-Fuzzy Network

A novel Chebyshev functional recurrent neuro-fuzzy (CFRNF) network is developed from a combination of the Takagi-Sugeno-Kang (TSK) fuzzy model and the Chebyshev recurrent neural network (CRNN). The CFRNF network can emulate the nonlinear dynamics of a servomechanism system. The system nonlinearity is addressed by enhancing the input dimensions of the consequent parts in the fuzzy rules due to functional expansion of a Chebyshev polynomial. The back propagation algorithm is used to adjust the parameters of the antecedent membership functions as well as those of consequent functions. To verify the performance of the proposed CFRNF, the experiment of the belt servomechanism is presented in this paper. Both of identification methods of adaptive neural fuzzy inference system (ANFIS) and recurrent neural network (RNN) are also studied for modeling of the belt servomechanism. The analysis and comparison results indicate that CFRNF makes identification of complex nonlinear dynamic systems easier. It is verified that the accuracy and convergence of the CFRNF are superior to those of ANFIS and RNN by the identification results of a belt servomechanism.

Nonlinear System Identification and Control Using an Input-Output Recurrent Neurofuzzy Network

In this work we develop an input-output recurrent neurofuzzy network in discrete-time for identification and control of nonlinear systems. The structure is linear in the consequent parameters and nonlinear in the antecedent ones. The training of the antecedent parameters is achieved by linearizing them around a suboptimal value, assuming that the only known data are input-output signals obtained directly from measurements of the system, as well as some information about its structure (local stability and time delays). The training algorithm is based on a Kalman filter, stable under certain assumptions. It is also presented a theorem to check the stability of the resulting network in the Lyapunov sense, and a predictive control design. The performance of the network is shown by the identification and control of a nonlinear benchmark system.

Recurrent Neurofuzzy Network in Thermal Modeling of Power Transformers

This work suggests recurrent neurofuzzy networks as a means to model the thermal condition of power transformers. Experimental results with actual data reported in the literature show that neurofuzzy modeling requires less computational effort, and is more robust and efficient than multilayer feedforward networks, a radial basis function network, and classic deterministic modeling approaches

A new recurrent neurofuzzy network for identification of dynamic systems

In this paper a new structure of a recurrent neurofuzzy network is proposed. The network is based on two interconnected Fuzzy Inference Systems (FISs), one recurrent and another static, that intend to model the behavior of an unknown dynamic system from input–output data. In the proposed structure each rule involves a linear system in a controllable canonical form in order to reduce the online computational load and facilitate the online checking of the stability of the resulted network. The training for the recurrent FIS is made by a gradient-based Real-Time Recurrent Learning Algorithm (RTRLA), while the training for the static FIS is based on a simple gradient method. The initial parameter conditions prior to training are obtained by extracting information from a static FIS trained with delayed input–output signals. To demonstrate the effectiveness of the proposed structure, two nonlinear systems are identified.

Modelling and multi-objective optimal control of batch processes using recurrent neuro-fuzzy networks

In this paper, the modelling and multi-objective optimal control of batch processes, using a recurrent neuro-fuzzy network, are presented. The recurrent neuro-fuzzy network, forms a "global" nonlinear long-range prediction model through the fuzzy conjunction of a number of "local" linear dynamic models. Network output is fed back to network input through one or more time delay units, which ensure that predictions from the recurrent neuro-fuzzy network are long-range. In building a recurrent neural network model, process knowledge is used initially to partition the processes non-linear characteristics into several local operating regions, and to aid in the initialisation of corresponding network weights. Process operational data is then used to train the network. Membership functions of the local regimes are identified, and local models are discovered via network training. Based on a recurrent neuro-fuzzy network model, a multi-objective optimal control policy can be obtained. The proposed technique is applied to a fed-batch reactor.

Modeling and optimal control of batch processes using recurrent neuro-fuzzy networks

A recurrent neuro-fuzzy network based strategy for batch process modeling and optimal control is presented in this paper. The recurrent neuro-fuzzy network allows the construction of a "global" nonlinear long-range prediction model from the fuzzy conjunction of a number of "local" linear dynamic models. In this recurrent neuro-fuzzy network, the network output is fed back to the network input through one or more time delay units. This particular structure ensures that predictions from a recurrent neuro-fuzzy network are long-range or multi-step-ahead predictions. Long-range predictions are particularly important for batch processes where the interest lies in the product quality and quantity at the end of a batch. To enhance batch process control and monitoring, a model capable of predicting accurately the product quality/quantity at the end of a batch is required. Process knowledge is used to initially partition the process nonlinear characteristics into several local operating regions and to aid in the initialization of the corresponding network weights. Process input output data is then used to train the network. Membership functions of the local regimes are identified and local models are discovered through network training. An advantage of this recurrent neuro-fuzzy network model is that it is easy to interpret. This helps process operators in understanding the process characteristics. The proposed technique is applied to the modeling and optimal control of a fed-batch reactor.

Long Range Predictive Control of Nonlinear Processes Based on Recurrent Neuro-Fuzzy Network Models

A recurrent neuro-fuzzy network-based nonlinear long range model predictive control strategy is proposed in this paper. The process operation is partitioned into several fuzzy operating regions. Within each region, a local linear model is used to model the process. The global model output is obtained through the centre of gravity defuzzification. Based upon a neuro-fuzzy network model, a nonlinear model-based predictive controller can be developed by combining several local linear model-based predictive controllers which usually have analytical solutions. This strategy avoids the time consuming numerical optimisation procedure, and the uncertainty in convergence to the global optimum which are typically seen in conventional nonlinear modelbased predictive control strategies, Furthermore, control actions obtained based on local incremental models contain integration actions which can naturally eliminate static control offsets. The technique is demonstrated by an application to the modelling and control of liquid level in a water tank.

Recurrent neuro-fuzzy networks for nonlinear process modeling

A type of recurrent neuro-fuzzy network is proposed in this paper to build long-term prediction models for nonlinear processes. The process operation is partitioned into several fuzzy operating regions. Within each region, a local linear model is used to model the process. The global model output is obtained through the centre of gravity defuzzification which is essentially the interpolation of local model outputs. This modeling strategy utilizes both process knowledge and process input output data. Process knowledge is used to initially divide the process operation into several fuzzy operating regions and to set up the initial fuzzification layer weights. Process input output data are used to train the network. Network weights are such trained so that the long-term prediction errors are minimized. Through training, membership functions of fuzzy operating regions are refined and local models are learn. Based on the recurrent neuro-fuzzy network model, a novel type of nonlinear model-based long range predictive controller can be developed and it consists of several local linear model-based predictive controllers. Local controllers are constructed based on the corresponding local linear models and their outputs are combined to form a global control action by using their membership functions. This control strategy has the advantage that control actions can be calculated analytically avoiding the time consuming nonlinear programming procedures required in conventional nonlinear model-based predictive control. The techniques have been successfully applied to the modeling and control of a neutralization process.

Linearization and state estimation of unknown discrete-time nonlinear dynamic systems using recurrent neurofuzzy networks

Model-based methods for the state estimation and control of linear systems have been well developed and widely applied. In practice, the underlying systems are often unknown and nonlinear. Therefore, data based model identification and associated linearization techniques are very important. Local linearization and feedback linearization have drawn considerable attention in recent years. In this paper, linearization techniques using neural networks are reviewed, together with theoretical difficulties associated with the application of feedback linearization. A recurrent neurofuzzy network with an analysis of variance (ANOVA) decomposition structure and its learning algorithm are proposed for linearizing unknown discrete-time nonlinear dynamic systems. It can be viewed as a method for approximate feedback linearization, as such it enlarges the class of nonlinear systems that can be feedback linearized using neural networks. Applications of this new method to state estimation are investigated with realistic simulation examples, which shows that the new method has useful practical properties such as model parametric parsimony and learning convergence, and is effective in dealing with complex unknown nonlinear systems.