基于ANFIS的机器人系统建模的研究

针对机器人这种不确定性的复杂非线性系统很难建立其精确的数学模型这一问题,提出一种基于自适应神经模糊推理(ANFIS)的方法对机器人系统进行建模.此方法将模糊推理和神经网络的学习能力有机地结合起来,并利用神经网络的学习机制自动地从输入输出数据中提取规则.建模过程中为了给ANFIS赋予一个合适的初始状态,选用减法聚类对输入数据进行处理.ANFIS网络的所有参数采用混合算法进行调节,即前提参数采用误差反向传播法,结论参数采用最小二乘法.最后在Matlab中对二自由度机器人进行仿真研究,仿真结果表明该方法模型结构简单,建模速度快,辨识精度高,同时也验证了该方法的有效性,为进一步实现机器人鲁棒自适应控制打下基础.     

自相关噪声处理中神经模糊推理系统的应用

研究了自适应神经模糊推理系统(ANFIS)在去除相关噪声中的应用。介绍了ANFIS的结构、工作原理及方法,并给出了仿真试验结果。对ANFIS方法、BP神经网络方法、高阶神经网络方法进行了比较,说明了ANFIS方法的优越性。     

基于自适应模糊网络的在线辨识

研究了基于一阶Sugeno的自适应网络模糊推理系统（ANFIS）进行在线辨识的方法。给出了该自适应网络的结构,在此基础上给出了网络权值的修正算法,即综合最陡下降法和最小二乘法得到的一种混合学习算法。对一个非线性模型进行了数字仿真,得到的在线辨识的结果优于采用反传算法的普通神经网络辨识方法。由此证明,一阶Sugeno模糊推理模型和混合学习算法的采用,使得该辨识方法具备网络结构简单、收敛速度快的优势,便于工程实现。     

潜艇垂直面运动自适应神经网络模糊控制仿真

神经网络控制和模糊控制技术的广泛应用为潜艇自动舵控制器的设计提供了新的思路.而模糊规则的提取和隶属函数的学习是模糊推理系统设计中重要而困难的问题,自适应神经网络模糊推理系统(ANFIS)结合模糊控制和神经网络控制的优点,基于sugeno模糊模型采用反向传播法和最小二乘法调整模糊推理系统的参数,并自动产生模糊规则.利用方法对潜艇乖直面运动自动舵控制器进行了设计和仿真.从仿真结果来看,自适应神经网络模糊控制器能较好的实现对潜艇垂直面运动的操纵控制,是一种很好的控制方法.     

嵌入式蓄电池SoC检测系统研究与设计

系统建立了基于神经网络的电池荷电状态(SoC)的预测模型,可用于对电池电量有精确预测需求的设备中。首先,基于自适应神经网络模糊推理系统(ANFIS)的预测模型确定了网络学习算法,采用MATLAB仿真程序用不同方法构造初始ANFIS模型,利用实验数据对模型网络进行训练,分析ANFIS系统结构和参数的变化。其次,将模型值与实际测得的结果进行对比,对网络的各个参数进行调整后再次用仿真比对预测效果。最后,设计了嵌入式系统硬件和软件的结构,用正弦波注入法解决了电池内阻测量这一难点。     

基于ANFIS的非线性系统辨识研究

系统辨识是控制系统设计的基础，对非线性系统进行辨识是当前的难点；文献[1]提出了用模糊建模方法，文献[2]提出了用神经网络方法，在总结上述方法不足的基础上，该文提出了用自适应神经模糊推理系统(ANFIS)对非线性系统进行辨识的方法，仿真结果表明，ANFIS进行非线性系统辨识是可行的，其辨识精度很高。     

基于ANFIS的非线性信道的辨识

当前对高速通信的需求导致对信道资源的利用已经超出了可以采用线性模型建模的范围,所以必须采用适当的非线性模型进行描述,为了实现对高速通信中非线性信道的辨识,提出了采用自适应神经模糊推理系统(ANFIS)进行信道辨识的方法,并对ANFIS网络的结论参数采用最小二乘法进行辨识,对前提参数采用误差反传的方法进行学习,最后,运用MAT-LAB实现了对非线性信道进行辨识及均衡的仿真,并将仿真结果与BP网辨识结果进行比较,说明ANFIS网络能很好地逼近非线性信道的传递函数,并在收敛速度及辨识精度方面优于BP网络.     

自适应神经模糊推理系统用于症候诊断的研究

提出了基于T-S模型(Takagi-Sugeno型)的自适应神经网络模糊推理系统(AdaptiveNetwork-basedFuzzyInferenceSystem,ANFIS),介绍了高木—关野(Takagi-Sugeno型)模型结构和自适应神经网络模糊推理系统的结构和算法。该文采用减法聚类初始化模糊推理系统模型,把神经网络学习机制引入到逻辑推理中,使传统的逻辑推理不仅具有逻辑思维及语言表达能力而且具有自学习和联想能力,通过2型糖尿病症候数据库验证了ANFIS用于症候诊断的合理性和有效性。提示自适应神经网络模糊推理系统适合中医症候诊断的研究。     

自适应模糊神经网络在噪声消除中的应用

本文提出了一种基于模糊神经网络的噪声自适应消除方法,介绍了该方法的原理及实现算法,并利用特殊函数和一定的噪声作为样本信号,建立了基于模糊神经网络的自适应噪声消除模型。通过该模型对有用信号的参数进行了辨识,仿真结果表明该方法具有学习速度快、诊断精度高等优点,可用于通信线路及其他电子设备的噪声消除。     

关于目标跟踪定位的仿真方法研究

研究雷达定位精度和准确性问题,为了解决在目标定位跟踪中由于目标机动引起的无迹卡尔曼滤波(UKF)误差大和滤波发散问题,提出了一种基于UKF和自适应神经网络-模糊推理系统(ANFIS)的新的目标跟踪定位方法.将自适应神经网络-模糊推理系统应用于目标跟踪系统,利用状态变量的预测误差和预测误差的变化率来自适应地调整卡尔曼滤波器的系统噪声协方差矩阵,实现了模糊推理、神经网络和UKF的有效结合,并应用于雷达目标定位跟踪系统进行仿真.仿真结果表明,方法比UKF有更好的跟踪性能,收敛快,对目标机动有更好的适应能力,为设计提供了依据.     

基于GA的ANFIS在自适应噪声消除中的应用

介绍了应用基于GA的ANFIS的自适应噪声消除的方法,阐述了基本思想和算法实现过程。神经网络采用五层的ANFIS网络结构,采用自适应GA对模糊规则前件部分的隶属函数参数进行训练,避免了原有BP算法极易陷入局部最优的缺点,可获得全局最优解,用BP算法来调节和优化具有局部性的推理规则结论部分的权值。应用结果表明了该方法的有效性,收敛速度更快、误差更小,滤波率达到了预期要求。     

An expert system of price forecasting for used cars using adaptive neuro-fuzzy inference

An expert system for used cars price forecasting using adaptive neuro-fuzzy inference system (ANFIS) is presented in this paper. The proposed system consists of three parts: data acquisition system, price forecasting algorithm and performance analysis. The effective factors in the present system for price forecasting are simply assumed as the mark of the car, manufacturing year and engine style. Further, the equipment of the car is considered to raise the performance of price forecasting. In price forecasting, to verify the effect of the proposed ANFIS, a conventional artificial neural network (ANN) with back-propagation (BP) network is compared with proposed ANFIS for price forecast because of its adaptive learning capability. The ANFIS includes both fuzzy logic qualitative approximation and the adaptive neural network capability. The experimental result pointed out that the proposed expert system using ANFIS has more possibilities in used car price forecasting.     

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

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.     

Unsupervised adaptive neural-fuzzy inference system for solving differential equations

There has been a growing interest in combining both neural network and fuzzy system, and as a result, neuro-fuzzy computing techniques have been evolved. ANFIS (adaptive network-based fuzzy inference system) model combined the neural network adaptive capabilities and the fuzzy logic qualitative approach. In this paper, a novel structure of unsupervised ANFIS is presented to solve differential equations. The presented solution of differential equation consists of two parts; the first part satisfies the initial/boundary condition and has no adjustable parameter whereas the second part is an ANFIS which has no effect on initial/boundary conditions and its adjustable parameters are the weights of ANFIS. The algorithm is applied to solve differential equations and the results demonstrate its accuracy and convince us to use ANFIS in solving various differential equations.     

An adaptive wavelet network for function learning

In this article, a wavelet neural network (WNN) model is proposed for approximating arbitrary nonlinear functions. Our WNN model structure comes from the idea of adaptive neuro-fuzzy inference system (ANFIS) which is used for obtaining fuzzy rule base from the input–output data of an unknown function. The WNN model which is called in this study as adaptive wavelet network (AWN) consists of wavelet scaling functions in its processing units whereas in an ANFIS, mostly Gaussian-type membership functions are used for a function approximation. We present to train an AWN by a hybrid-learning method containing least square estimation (LSE) with gradient-based optimization algorithm to obtain the optimal translation and dilation parameters of our AWN for model accuracy. Simulation examples are also given to illustrate the effectiveness of the method.     

An adaptive neuro‐fuzzy system for stock portfolio analysis

We propose an adaptive neuro‐fuzzy inference system (ANFIS) for stock portfolio return prediction. Previous work has shown that portfolio optimization can be improved by using predicted stock earnings rather than historical earnings. We show that predicted portfolio returns can be improved by using ANFIS and taking as input a variety of technical and fundamental attributes about various indices of the stock market. To generate membership functions, we use a robust noise rejection‐clustering algorithm. The neuro‐fuzzy model is tested on portfolios constituted from the Tehran Stock Exchange. In our experiments, the proposed method performs better in predicting the portfolio return than the classical Markowitz portfolio optimization method, a multiple regression, a neural network, and the Sugeno–Yasukawa method. © 2010 Wiley Periodicals, Inc.     

Adaptive Decoupling Control of Pulp Levels in Flotation Cells

Control of the pulp levels in flotation cells directly affects the grade of the concentrate and the tailings in a concentration plant. Nevertheless, with strong coupling among cell levels and nonlinearities in the flotation process, conventional control strategies cannot achieve satisfactory control performance. In this paper, a nonlinear multi‐model adaptive decoupling control strategy based on adaptive‐network‐based fuzzy inference systems (ANFIS) is proposed for the flotation process, which includes a linear adaptive decoupling controller, an ANFIS‐based nonlinear adaptive decoupling controller, and a switching mechanism. The proposed method not only improves the transient performance and mitigates effects of the nonlinearities on the system, but also guarantees the input‐output stability of the closed‐loop system. Successful application to the flotation process has been made in a concentration plant in China, and the feasibility and efficiency of the proposed method have been validated.     

Influence of meta-heuristic optimization on the performance of adaptive interval type2-fuzzy traffic signal controllers

Intelligent traffic control systems optimized using meta-heuristic algorithms can greatly alleviate traffic congestions in urban areas. Meta-heuristics are broadly used as efficient approaches for complex optimization problems. Comparing the performance of optimization methods on different applications is a way to evaluate their effectiveness. The current literature lacks studies on how performance of traffic signal controllers is affected by utilized optimization algorithms. This paper evaluates the performance of three meta-heuristic optimization methods on an advanced interval type-2 adaptive neuro-fuzzy inference system (IT2ANFIS)-based controller for complex road networks. Simulated annealing (SA), genetic algorithm (GA), and the cuckoo search (CS) are applied for optimal tuning of IT2ANFIS controller. Optimizations methods adjust the parameters in a way to reduce the total travel time of vehicles in the road network. Paramics is used to design and simulate urban traffic network models and implement proposed timing controllers. Comprehensive simulation and performance evaluation are done for both single and multi-intersection traffic networks. Obtained results reveal significant superiority of IT2ANFIS trained using CS method over other controllers. The average performance of the CS-IT2ANFIS is about 31% better than the benchmark fixed-time controllers. This is 17% and only 3% for GA-IT2ANFIS and SA-IT2ANFIS controllers respectively.     

An efficient impulsive noise cancellation scheme for power-line communication systems using ANFIS and chaotic interleaver

Impulsive noise is one of the main disturbances that damage the data transmission over power-line communication (PLC) systems. This paper presents an adaptive noise cancellation approach based on the adaptive neuro-fuzzy inference system (ANFIS) and a chaotic interleaver, namely ANC-CI-ANFIS scheme for impulsive noise estimation and suppression from the OFDM PLC channel. The ANFIS is based on a hybrid learning algorithm to identify parameters of Sugeno-type fuzzy inference system. Accordingly, fuzzy membership function parameters are trained using a combination of both least-square and back propagation gradient descent algorithms to emulate a given training data set. Furthermore, transmitted data are managed with a chaotic interleaver to secure data transmission and give more robustness against impulsive bursts. Simulation results are carried out on an OFDM PLC transmission chain compatible with the HomePlug AV standard under different impulsive noise scenarios. The results demonstrated the scheme's ability to detect and remove the impulsive noise from the PLC channel while keeping a high security level by using the chaotic interleaver. The major advantage of this system is its ease of implementation and faster convergence rate.