非线性动态系统神经模糊建模与内模/PID双重控制系统设计

非线性动态系统的内模控制要求建立精确的对象正模型和逆模型,这对于大多数实际对象是难以做到.提出了基于一类神经模糊模型的非线性动态系统建模方法,并在此基础上研究了基于神经模糊模型的非线性系统的内模控制设计.基于输入输出数据辨识的对象正模型和逆模型存在着模型失配问题,导致神经模糊内模控制范围变窄和控制鲁棒性降低,为了改善系统的性能,提出了神经模糊内模控制与PID控制结合的双重控制策略.对CSTR的反应物浓度控制研究表明,双重控制策略能有效地拓宽系统可控范围,改善系统性能.仿真结果证明该控制策略简单而有效.     

An intelligent online fault diagnostic scheme for nonlinear systems

An online fault diagnostic scheme for nonlinear systems based on neurofuzzy networks is proposed in this paper. The scheme involves two stages. In the first stage, the nonlinear system is approximated by a neurofuzzy network, which is trained offline from data obtained during the normal operation of the system. In the second stage, residual is generated online from this network and is modelled by another neurofuzzy network trained online. Fuzzy rules are extracted from this network, and are compared with those in the fault database obtained under different faulty operations, from which faults are diagnosed. The performance of the proposed intelligent fault scheme is illustrated using a two-tank water level control system under different faulty conditions .     

Flow regimes identification and liquid-holdup prediction in horizontal multiphase flow based on neuro-fuzzy inference systems

Numerous techniques have been used to identify flow regimes and liquid holdup in horizontal multiphase flow, but often neither perform well nor very accurate. Recently, neuro-fuzzy inference systems learning scheme have been gaining popularity in its capability for solving both prediction and classification problems. It is a hybrid intelligent systems scheme that is able to forecast an output in the uncertainty situations. This paper investigates the capabilities of neuro-fuzzy TypeI in identifying flow regimes and forecasting liquid holdup in horizontal multiphase flow. The performance of neuro-fuzzy modeling scheme is implemented using different real-world industry databases. Comparative studies were carried out to compare neuro-fuzzy systems performance with the most popular existing approaches in identifying flow regimes and predict liquid holdup in horizontal multiphase flow. Results show that neuro-fuzzy is flexible, reliable, outperforms the existing techniques and show bright future capabilities in solving different oil and gas industry problems, namely, rock mechanics properties, water saturation, faceis classification, and distinct bioinformatics applications.     

Neurofuzzy Inverse Jacobian Mapping for Multi-Finger Robot Hand Control

Fuzzy systems and models are useful for describing processes where the underlying physical mechanisms are not completely known and where a system behavior is understood in qualitative terms. Neurofuzzy systems have been employed in large number of intelligent based control systems and robotics, that is due to the ability to deal with large number of inputs and with the ability to learn and remember specific learned patterns. This paper investigates the employment of a neurofuzzy system for a multi-finger robot hand control and manipulation tasks. The approach followed here is to let a defined neurofuzzy system to learn the nonlinear functional relation that maps the entire hand joint positions and displacements to object displacement. This is done by avoiding the use of the Inverse Hand Jacobian, while observing the interaction between hand fingers and the object being grasped and manipulated. The developed neurofuzzy system approach has been trained for several object training patterns and hand postures within a cartesian based palm dimension. The paper demonstrates the proposed algorithm for a four fingered robot hand motion, where inverse hand Jacobian plays an important role in the hand dynamics and control.     

A modified decoupling scheme for receiving antenna arrays with application to DOA estimation

Mutual coupling in antenna arrays can critically degrade the performance of subsystems, such as those aiming at the estimation of the direction of arrival (DOA) of incident signals. In this article, an accurate form of mutual impedance matrix (MIM) and decoupling methodology is introduced. The methodology for computing the MIM is presented. In the modified MIM and decoupling method, extreme care has been taken to account for all self‐impedance and mutual impedance terms, relating to the mutual coupling effects. It is shown that the new method results in an essential improvement in DOA estimation applications. The resolution and accuracy, achieved using the modified MIM and decoupling methodology, are unmatched with those of the previous techniques. © 2012 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2013.     

Neurofuzzy network modelling and control of steam pressure in 300 MW steam-boiler system

In boiler-generation system, steam pressure is an important factor affecting the total combustion system. A properly boiler system must maintain a desired steam pressure at the outlet of the drum. Modelling and control of 300 MW steam-boiler combustion system using neurofuzzy methodology is discussed in this paper. Associate memory network (AMN) is chosen to represent the nonlinear model of steam pressure system based on local mechanism model and dynamic experiments. With the established neurofuzzy model, a relative fuzzy PI controller is constituted. The performance of the control system has been verified by the simulation process and then tested on real-time process in distributed control system (DCS) under the setpoint tracking and load disturbance.     

Neurofuzzy model based predictive control for thermal batch processes

In many cases, it is difficult to derive a precise mathematical model, based on first principles, for a given process. Besides, the computation of the solution of models obtained through this methodology may require a large computational effort making them useless for real time tasks like control or optimization. Neurofuzzy modelling, which permits an easy way to derive successful models, is a good alternative which can be employed to overcome such limitations.In this paper, together with the neurofuzzy modelling, several strategies based on non-linear predictive control are presented. The low computational cost associated with neurofuzzy models and controllers makes them suitable candidates to be implemented into industrial Programmable Logic Controllers (PLC). Both the model and controllers are validated and implemented in a pilot plant for the thermal sterilization of solid canned food in steam retorts and based on the results, a comparison between the different predictive control strategies is presented.     

Self-organizing neurofuzzy networks based on evolutionary fuzzy granulation

Experimental software datasets describing software projects in terms of their complexity and development time have been a subject of intensive modeling. A number of various modeling methodologies and modeling designs have been proposed including such development frameworks as neural networks, fuzzy and neurofuzzy models. In this study, we introduce a concept of self-organizing neurofuzzy networks (SONFN), a hybrid modeling architecture combining neurofuzzy networks (NFN) and polynomial neural networks (PNN). For these networks we develop a comprehensive design methodology. The construction of SONFNs takes advantage of the well-established technologies of computational intelligence (CI), namely fuzzy sets, neural networks and genetic algorithms. The architecture of the SONFN results from a synergistic usage of NFNs and PNNs. NFN contributes to the formation of the premise part of the rule-based structure of the SONFN. The consequence part of the SONFN is designed using PNNs. We discuss two types of SONFN architectures whose taxonomy is based on the NFN scheme being applied to the premise part of SONFN. We introduce a comprehensive learning algorithm. It is shown that this network exhibits a dynamic structure as the number of its layers as well as the number of nodes in each layer of the SONFN are not predetermined (as this is the case in a popular topology of a multilayer perceptron). The experimental results include a well-known NASA dataset concerning software cost estimation.     

The ANFIS approach applied to AUV autopilot design

This paper describes the application of neurofuzzy techniques in the design of autopilots for controlling the yaw dynamics of an autonomous underwater vehicle. Autopilots are designed using an Adaptive-Network-based Fuzzy Inference System (ANFIS), a chemotaxis tuning methodology and a fixed fuzzy rule-based approach. To describe the yaw dynamic characteristics of an autonomous underwater vehicle, a realistic simulation model is employed. Results are presented which demonstrate the superiority of the ANFIS approach. It is concluded that the approach offers a viable alternative method for designing such autopilots.     

自适应模糊神经网络控制器在电阻加热炉中的应用

提出一种自适应模糊神经网络控制器,着重讨论了自适应模糊神经网络的混合学习算法和自适应动量解耦的最速下降法。给出了适于非线性时滞、基于径向基函数网络和自适应模糊神经网络控制器的控制方案,并把它用在电阻加热炉中。实际应用表明,模糊神经网络控制器具有良好的控制效果。     

Fuzzy Polynomial Neuron-Based Self-Organizing Neural Networks

We propose a new category of neurofuzzy networks—self-organizing neural networks (SONN) with fuzzy polynomial neurons (FPNs) and discuss a comprehensive design methodology supporting their development. Two kinds of SONN architectures, namely a basic SONN and a modified SONN architecture are discussed. Each of them comes with two topologies such as a generic and advanced type. Especially in the advanced type, the number of nodes in each layer of the SONN architecture can be modified with new nodes added, if necessary. SONN dwells on the ideas of fuzzy rule-based computing and neural networks. The architecture of the SONN is not fixed in advance as it usually takes place in the case of conventional neural networks, but becomes organized dynamically through a growth process. Simulation involves a series of synthetic as well as real-world data used across various neurofuzzy systems. A comparative analysis shows that the proposed SONN are models exhibiting higher accuracy than some other fuzzy models.     

Variable selection algorithm for the construction of MIMO operatingpoint dependent neurofuzzy networks

An input variable selection procedure is introduced for the identification and construction of multi-input multi-output (MIMO) neurofuzzy operating point dependent models. The algorithm is an extension of a forward modified Gram-Schmidt orthogonal least squares procedure for a linear model structure which is modified to accommodate nonlinear system modeling by incorporating piecewise locally linear model fitting. The proposed input nodes selection procedure effectively tackles the problem of the curse of dimensionality associated with lattice-based modeling algorithms such as radial basis function neurofuzzy networks, enabling the resulting neurofuzzy operating point dependent model to be widely applied in control and estimation. Some numerical examples are given to demonstrate the effectiveness of the proposed construction algorithm     

Neurofuzzy network based self-tuning control with offset eliminating

The design of nonlinear controllers involves first selecting the input and then determining the nonlinear functions for the controllers. Since systems described by smooth nonlinear functions can be approximated by linear models in the neighbourhood of the selected operating points, the input of the nonlinear controller at these operating points can be chosen to be identical to those of the local linear controllers. Following this approach, it is proposed that the input of the nonlinear controller are similarly chosen, and that the local linear controllers are designed based on the integrating and k-incremental suboptimal control laws for their ability to remove offsets. Neurofuzzy networks are used to implement the nonlinear controllers for their ability to approximate nonlinear functions with arbitrary accuracy, and to be trained from experimental data. These nonlinear controllers are referred to as neurofuzzy controllers for convenience. As the integrating and k-incremental control laws have also been applied to implement self-tuning controllers, the proposed neurofuzzy controllers can also be interpreted as self-tuning nonlinear controllers. The training target for the neurofuzzy controllers is derived, and online training of the neurofuzzy controllers using a simplified recursive least squares (SRLS) method is presented. It is shown that using the SRLS method, computing time to train the neurofuzzy controllers can be drastically reduced and the ability to track varying dynamics improved. The performance of the neurofuzzy controllers and their ability to remove offsets are demonstrated by two simulation examples involving a linear and a nonlinear system, and a case study involving the control of the drum water level in the boiler of a power generation system.     

基于模糊神经网络的积分自适应控制

将模糊神经网络应用于传统线性积分自适应控制,构造了一类模糊神经自适应方法,用于消除非线性系统响应偏差.模糊神经网构成直接非线性自适应控制器.对线性及非线性对象的仿真控制以及与经典自适应控制的比较,表明了模糊神经自适应控制器的有效性.     

Generalized neurofuzzy network modeling algorithms usingBezier-Bernstein polynomial functions and additive decomposition

This paper introduces a new neurofuzzy model construction algorithm for nonlinear dynamic systems based upon basis functions that are Bezier-Bernstein polynomial functions. This paper is generalized in that it copes with n-dimensional inputs by utilising an additive decomposition construction to overcome the curse of dimensionality associated with high n. This new construction algorithm also introduces univariate Bezier-Bernstein polynomial functions for the completeness of the generalized procedure. Like the B-spline expansion based neurofuzzy systems, Bezier-Bernstein polynomial function based neurofuzzy networks hold desirable properties such as nonnegativity of the basis functions, unity of support, and interpretability of basis function as fuzzy membership functions, moreover with the additional advantages of structural parsimony and Delaunay input space partition, essentially overcoming the curse of dimensionality associated with conventional fuzzy and RBF networks. This new modeling network is based on additive decomposition approach together with two separate basis function formation approaches for both univariate and bivariate Bezier-Bernstein polynomial functions used in model construction. The overall network weights are then learnt using conventional least squares methods. Numerical examples are included to demonstrate the effectiveness of this new data based modeling approach.     

Self-learning neurofuzzy control of a liquid helium cryostat

The paper demonstrates that a self-learning neurofuzzy controller is able to regulate the temperature in a liquid helium cryostat. In order to simplify the task of commissioning the controller, a strategy for choosing the user-selected parameters from an equivalent proportional-plus-integral controller (PI) is derived. Experimental results which illustrate the potential of the proposed control scheme are presented. The performance of the self-learning neurofuzzy controller is also compared with that of a commercial gain-scheduled PI controller.     

ESTIMATION OF SOLID WASTE BIOMETHANIZATION: DEVELOPMENT OF NOVEL METHODOLOGY AND ANFIS MODELS

This article presents the application of a technique of artificial intelligence (AI) that explores the possibility of using a model to estimate the biomethanization of municipal solid waste (MSW). The model uses data from an experiment in which MSW is anaerobically digested under three different moisture regimes by leachate recycling. A method utilizing a neurofuzzy inference system is used because AI systems have a high capacity for empiric learning.

Considering the importance of finding an effective selection of the most valuable variables for the model, this methodology includes the following techniques: Exhaustive Search (or brute-force search); Stepwise, a step-by-step regression method; and the use of Expert Knowledge. With the use of the fuzzy logic toolbox (MATLAB®), nine models were generated. However, when a case study is used to detail the method, the proposed methodology can also be used with any other system with a set of input and output data.     

Predicting Chaotic Time Series Using Neural and Neurofuzzy Models: A Comparative Study

The prediction accuracy and generalization ability of neural/neurofuzzy models for chaotic time series prediction highly depends on employed network model as well as learning algorithm. In this study, several neural and neurofuzzy models with different learning algorithms are examined for prediction of several benchmark chaotic systems and time series. The prediction performance of locally linear neurofuzzy models with recently developed Locally Linear Model Tree (LoLiMoT) learning algorithm is compared with that of Radial Basis Function (RBF) neural network with Orthogonal Least Squares (OLS) learning algorithm, MultiLayer Perceptron neural network with error back-propagation learning algorithm, and Adaptive Network based Fuzzy Inference System. Particularly, cross validation techniques based on the evaluation of error indices on multiple validation sets is utilized to optimize the number of neurons and to prevent over fitting in the incremental learning algorithms. To make a fair comparison between neural and neurofuzzy models, they are compared at their best structure based on their prediction accuracy, generalization, and computational complexity. The experiments are basically designed to analyze the generalization capability and accuracy of the learning techniques when dealing with limited number of training samples from deterministic chaotic time series, but the effect of noise on the performance of the techniques is also considered. Various chaotic systems and time series including Lorenz system, Mackey-Glass chaotic equation, Henon map, AE geomagnetic activity index, and sunspot numbers are examined as case studies. The obtained results indicate the superior performance of incremental learning algorithms and their respective networks, such as, OLS for RBF network and LoLiMoT for locally linear neurofuzzy model.     

Structure selection of neurofuzzy networks based on support vector regression

Neurofuzzy networks are being used increasingly to model non-linear dynamic systems, since they have the approximating ability of neural networks and the transparency of fuzzy systems. However, good generalization results can only be obtained if the structure of the network is suitably chosen. It is shown here that the structure of neurofuzzy networks with scatter partitioning can be obtained from the support vectors (SV) of the Support Vector Regression (SVR), since the SVR can be transformed to a neurofuzzy network. The main advantage of this approach is that the structure of the neurofuzzy networks can now be objectively chosen, as the SV are obtained by constrained optimization for a given modelling error bound. Since neurofuzzy networks are linear-inweights networks, the estimate of the weights of the networks can be obtained by the linear least-squares method. The properties of neurofuzzy networks based on the SV are derived, and its performance is illustrated by a simulation example involving a nonlinear system, and the modeling of Southern Oscillation Index.