Due to computational burden and dynamic uncertainty, the model based decoupling control approach is hard to be implemented in a multivariable robotic system. Here, a model-free model reference adaptive fuzzy sliding mode controller (MRAFSC) is proposed to control a five degree-of-freedom (DOF) robot. MRAFSC drives the system state variables to hit a user-defined sliding surface and then slide along it to approach a reference model. Consequent parameters of the fuzzy control can be initialized at zero, and then adjusted by using a novel online parameters tuning algorithm derived from the Lyapunov stability theory. A boundary layer function is introduced into the updating law to eliminate the chattering phenomenon which is inherent to the sliding mode control. The state errors converge into a specified error bound which depends on the boundary layer, parameter errors and modeling errors. The experimental results show that this novel controller has good control performance, stability and robustness. © 2004 Elsevier Ltd. All rights reserved.

A kind of recurrent fuzzy wavelet neural network (RFWNN) is constructed by using recurrent wavelet neural network (RWNN) to realize fuzzy inference. In the network, temporal relations are embedded in the network by adding feedback connections on the first layer of the network, and wavelet basis function is used as fuzzy membership function. An adaptive control scheme based on RFWNN is proposed, in which, two RFWNN are used to identify and control plant respectively. The proposed adaptive control scheme is applied on AC servo control problem, and simulation results are given.

A sliding mode control strategy compensated by neural network is proposed, and that is applied to robotic trajectory control. First, a three-layer neural network is used to compensate the uncertainties in the robotic system. Then the structure of sliding mode controller with neural network compensation and the learning algorithm of the neural network are designed based on Lyapunov theorem to guarantee the stability of the system and improve the dynamic performance of the system. The simulation results show that the proposed control strategy can not only reduce the phenomenon of chattering in effect, but also has good robustness and dynamic performance.

Wavelet networks are a class of neural networks consisting of wavelets. In this paper, wavelet network is used for estimating model of robot manipulator. An algorithm is introduced for constructing wavelet network, and BP algorithm is used for training wavelet network An example on two-joint robot manipulator identification is presented for illustration

An adaptive fuzzy controller is developed for AC servo system to guarantee both global stability and performance. AC motor dynamics under consideration may include large nonlinear uncertainties, such as nonlinearload variations. The Controller Output Method (COEM) isintroduced and applied to the design of adaptive fuzzycontrol system. The method employs a gradient descentalgorithm to minimize a cost function that is based on theerror of the controller output. The cost function can beminimized through adapting some or all of the parameters of fuzzy controller. The proposed adaptive fuzzy controlleris applied to a AC servo control problem and comparedwith a standard fuzzy controller. The simulation resultsshow that the proposed control is effective and yieldssuperior performance.

针对磁共振图像分割的特点，将小波分析优异的局部特性、模糊逻辑的定性知识表达能力和神经网络的自学习能力结合起来，提出了一种基于模糊小波神经网络的磁共振图像分割方法。该方法采用小波函数作为模糊隶属函数，利用神经网络实现模糊推理，并采用反向误差传播算法对网络进行训练。实验结果表明，这种基于模糊小波神经网络的磁共振图像分割方法与普通神经网络分割方法相比，具有更高的分割精度和更快的训练收敛速度。

小脑模型关节控制器（CMAC）具有结构简单，学习快速的优点，但是它的空间划分方式不能在线进行调整，影响了其自适应能力的提高。本文将模糊理论引入CMAC，提出了一种能够反映人类小脑认知的模糊性和连续性的模糊小脑模型关节控制器（FCMAC）。 该控制器对CMAC的空间划分方式进行了模糊化处理，可通过BP学习算法对CMAC的空间划分方式进行在线调整，大大提高了CMAC的自适应能力。所提出的FCMAC被应用于机器人的轨迹跟踪控制系统以克服机器人系统中非线性和不确定性因素的影响。仿真实验结果表明， 所提FCMAC与传统的CMAC相比性能上有了很大的改善。

提出一种模糊神经网络控制器并用于机器人轨迹跟踪控制。这种模糊神经网络利用了小波基函数作为隶属函数，可在线根据误差调整隶属函数的形状，使模糊神经网络具有更强的学习和适应能力。仿真与实验结果表明这种网络能很好的用于机器人的轨迹跟踪控制，具有很好的性能。

定子电阻的准确估计是改善直接转矩控制低速性能的关键技术。为了提高定子电阻的在线估计精度和速度，本文将小波分析、自组织算法和神经网络技术相结合，提出了一种自组织小波神经风格定子电阻估计器，该网络继承了小波分析优异的局部特性和神经网络的自学习能力，具有较高的估计精度，并采用自组织算法对小波元的数量进行了离线优化，大大简化了网络结构，提高了在线估计的实时性。

提出了一种基于神经网络的规则自校正模糊控制器，设计了一种在线的模糊推理算法,利用神经网络调整模糊控制规则，并将其用于交流伺服系统的控制中，仿真实验结果表明：该控制器响应快、鲁棒性强,采用该控制器的系统具有较好的动、静态性能和抗干扰能力。