A Self-Constructing Neural Fuzzy Network with Dynamic-Form Symbiotic Evolution

An interval-valued fuzzy cerebellar model neural network (IV-FCMNN) is proposed for the identification and control of uncertain systems. It is a more general model that uses the framework of a cerebellar model neural network (CMNN) and Atanassov intuitionistic fuzzy sets (AIFSs), so that the mathematical representation of a fuzzy event is more complete and the fuzzy neural network is more general. In some special cases, this neural network can be reduced to an interval-valued fuzzy neural network (IV-FNN), a fuzzy neural network (FNN), a fuzzy cerebellar model neural network (FCMNN) or a CMNN. Since the interval-type input data are used to realize this algorithm, the IV-FCMNN copes better with uncertainty and allows greater freedom of design. Therefore, the ability to learn, the approximation precision and the fuzzy semantic description of this network are much better than those of other models. In the proposed IV-FCMNN, a training algorithm that uses a gradient descent method is proposed to adjust the parameters and convergence is proved using the Lyapunov stability theorem. The variable learning rates are analyzed and the optimal learning rates are also determined. For demonstrating the effectiveness of the proposed IV-FCMNN, three types of applications, including multiple functions approximation, multi-dimensional classification and nonlinear dynamic system feedback control, are performed and the comparison with other models are also provided.

This chapter provides a comprehensive review of fuzzy neural network models. Existing methods to combine fuzzy logic and neural networks are presented. Several classifications of fuzzy neural networks are provided. Those classifications are based on the type of application of the fuzzy neural network. Fuzzy neural network models with supervised learning features are also reviewed in detail. A review of various biomedical engineering applications that use fuzzy neural networks is also presented. Some future medical science applications of fuzzy neural networks are described. A complete bibliography is listed at the end of the chapter.

This paper investigates the warp let-off and take-up mechanism of rapier looms to solve the problem that the warp tension of rapier looms fluctuates greatly and the warp let-off is difficult to maintain constant. The design and hardware implementation of a let-off and take-up control system based on fuzzy neural network (FNN) and vector control (VC) are presented to improve the control level of warp tension and drive performance of the let-off and take-up system. Firstly, the spring-damper dynamic model of the warp is established according to the mechanical properties. The parametric expression of warp tension and the control strategy of fixed angle interval based on let-off and take-up motions are constructed according to the generation mechanism and fluctuation law of warp tension. Then, based on fuzzy reasoning mechanism and neural network model, the fusion theory of fuzzy neural network is introduced, and a tension controller based on T-S fuzzy neural network (FNN) is designed. FNN is trained by introducing genetic optimization and the backpropagation fusion algorithm (GA-BP). In addition, a specialized let-off and take-up hardware circuit is constructed through embedded technology, and the SVPWM algorithm is used as the driving scheme of the hardware circuit. Finally, simulation and actual weaving experiments test the proposed let-off and take-up control system and hardware circuit. The results show that, compared to PID and fuzzy PID, the proposed fuzzy neural network algorithm has higher tension control accuracy and can effectively restrain the rapier loom’s warp tension undulation. The designed hardware circuit and SVPWM algorithm have a fast and stable driving ability, which ensures the constant let-off amount.

It is well-known that any nonlinear complex system can be modeled by using a collection of "if źthen" fuzzy rules. In spite of a number of successful models reported in the literature, there are still two open issues: (1) one is not able to reflect the heterogeneous partition of the input space; (2) it becomes very difficult to deal effectively with high dimensionality of the problem (data). In this study, we present a parallel fuzzy polynomial neural networks (PFPNNs) with the aid of heterogeneous partition of the input space. Like fuzzy rules encountered in fuzzy models, the PFPNNs comprises a collection of premise and consequent parts. In the design of the premise part of the rule a weighted fuzzy clustering method is used not only to realize a nonuniform partition of the input space but to overcome a possible curse dimensionality. While in the design of consequent part, fuzzy polynomial neural networks are exploited to construct optimal local models (high order polynomials) that describe the relationship between the input variables and output variable within some local region of the input space. Two types of information granulation-based fuzzy polynomial neurons are developed for FPNNs. Particle swarm optimization (PSO) is employed to adjust the design parameters of parallel fuzzy polynomial neural networks. To evaluate the performance of PFPNNs a series of experiments based on several benchmarks are included. A comparative analysis demonstrates that the proposed model comes with higher accuracy and generalization capabilities in comparison with some previous models reported in the literature.

Provides an abstract of the presentation and a brief professional biography of the presenter. The complete presentation was not made available for publication as part of the conference proceedings.

Fuzzy neural network has been considered as an effective model to apply in many applications. However, due to the training mode based on minimizing the mean squared error, the typical fuzzy neural network suffers from poor robustness for disturbances. To overcome this problem, a robust fuzzy neural network with α-divergence is designed and analyzed in this paper. First, a cost function based on α-divergence is developed to describe the discrepancy between the real output and fuzzy neural network output. Then, a training mode, which minimizes the above function, can reduce the sensibility of disturbances to improve the robustness of fuzzy neural network. Second, an adaptive learning algorithm is employed to adjust the parameter of fuzzy neural network. Then, the proposed fuzzy neural network is able to obtain fast convergence in the learning process. Finally, some benchmarks are used to test the merits of fuzzy neural network. The simulation results illustrate that the proposed fuzzy neural network can achieve good robustness.

Knowledge extraction from trained artificial neural networks has been studied by many researchers. Modeling of nonlinear systems using fuzzy neural networks (FNNs) is a promising approach to the knowledge acquisition, and a FNN is specially designed for knowledge extraction. The authors have proposed a hierarchical fuzzy modeling method using FNNs and a genetic algorithm (GA). This method can identify fuzzy models of nonlinear objects with strong nonlinearity. The disadvantage of the method is that the training of the FNN is time consuming. This paper presents a quick method for a rough search for proper structures in the antecedent of fuzzy models. The fine tuning of the acquired rough model is done by the FNN. This modeling method is quite efficient to identify precise fuzzy models of systems with strong nonlinearities. A simulation is done to show the effectiveness of the proposed method.

The fuzzy logic and neural networks are combined in this paper, setting up the fuzzy neural network (FNN); meanwhile, the distinct differences and connections between the fuzzy logic and neural network are compared. Furthermore, the algorithm and structure of the FNN are introduced. In order to diagnose the faults of nuclear power plant, the FNN is applied to the nuclear power plant, and the intelligence fault diagnostic system of the nuclear power plant is built based on the FNN. The fault symptoms and the possibility of the inverted U-tube break accident of steam generator are discussed. In order to test the system’s validity, the inverted U-tube break accident of steam generator is used as an example and many simulation experiments are performed. The test result shows that the FNN can identify the fault.

A new optimal algorithm for fuzzy model is presented on chaos optimization. In the model, fuzzy inference rules are transformed to be fuzzy radial basis function(RBF) network model, which combines the chaos algorithm with the typical clustering algorithms such as fuzzy C means(FCM) clustering algorithm to study parameters of fuzzy neural network. At first, FCM clustering algorithm and partition effect entropy are used to obtain model structure. And then the initial parameters of clustering centers are gotten by synthetical chaos series and the most optimal clustering center is obtained by FCM. Last fuzzy neural network model is achieved. A example is presented to illustrate the performance and applicability of the proposed model and simulation results show excellent performance.

On the basis of previous research, This article studies the structure and working principle of recurrent fuzzy neural network. The traditional fuzzy controller is not precise enough, does not have simple algorithm but poor timely traceability. The use of the fuzzy neural network is good for fully integrating the fuzzy control feature and neural network control feature. And we can improve the fuzzy neural network into recurrent fuzzy neural network, and apply this in the power flow control of the power converter. Through simulating and contrasting, the experiments show that it can achieve the UPFC trend of dynamic real-time monitoring, it has better tracking control capability and robustness, and preferable effect of power control.

Path planning is one of the key technologies in the research of mobile robots. Based on the research of fuzzy theory and neural network, a new algorithm is proposed, namely fuzzy neural network. The fuzzy neural network can be processed in parallel and self-learning like a neural network, and can also process fuzzy information like fuzzy theory and complete the fuzzy inference function. The fuzzy neural network is used to plan the path of the mobile robot, and the respective advantages of the fuzzy theory and the neural network are fully utilized to obtain the optimal path from the starting point to the target point. The simulation experiment was carried out under the condition that the environmental information is completely unknown and static. The results show that: The algorithm has high efficiency and fast convergence speed and effectively improves the intelligent level of the mobile robot.

A new approach for multilevel image segmentation based on fuzzy cellular neural network(CNN) is proposed. Based on a novel fuzzy CNN, a new template is proposed for multilevel image segmentation. The result of computer simulation proves this approach is reasonable. The stability of the fuzzy neural network is also analyzed in this paper.

In response to the problems of large computational volume and tedious computational process of fuzzy integrated evaluation, and general neural network models without clear water quality training criteria, this paper organically combines fuzzy rules, affiliation function, and neural network, and proposes a comprehensive method for the evaluation of water quality based on a T-S fuzzy neural network. On the three water quality monitoring data of six national key monitoring stations in Taihu Lake Basin, three evaluation methods—the one-factor evaluation method, the fuzzy integrated evaluation method, and the T-S fuzzy neural network evaluation method—were used to comprehensively evaluate water environment quality, and the results showed that the T-S fuzzy neural network method has the advantages of convenient calculation, strong applicability, and scientific results.

In the induction motor speed control without sensors operated by the method Field Oriented Control (FOC) was required an observer to estimate the speed. Obsever methods have been developed, among others, was the method of Self-Constructing Fuzzy Neural Network (SCFNN) with some training algorithms such as backpropagasi (BP). Levenberg Marquard (LM) etc.. In the induction motor control techniques were also developed methods of Direct Torque Control (DTC) with observer Recurrent Neural Network (RNN). This paper compares the performance of the motor response to initial rotation between SCFNN observer method that uses the LM training algorithm with DTC control technique with RNN observer. From the observation performance of the motor response to initial rotation of the two methods shows that the LM method has better performances than the RNN. This can be seen on both the parameters : overshoot, rise time, settling time, peak and peak time. With the right method, can enhance better performance of the system. With the improvement of system performance, is expected to increase work efficiency in the industrial world, so overall, particularly for systems that require high precision, FNN methodcan be said to be better. Keywords: Motor Speed control without sensors, FOC, SCFNNO, DTC, Levenberg Marquardt and RNN. DOI: http://dx.doi.org/10.11591/ijpeds.v1i1.66

Ching-chang Wong et. al(1999) proposed a cluster method to make training sample data stepwise converge to cluster centers regardless of the predetermination of center number. This paper improves the cluster method, and proves its convergence by using Brouwer fixed point theorem. Based on the result of the cluster method, one first order TSK fuzzy neural network is established and a hybrid algorithm is implemented to tune network parameters. Finally, simulation results are given to demonstrate the effectiveness of this cluster method in fuzzy neural networks.