Structure Of Cerebellar Model Articulation Controller Research Articles

Hybrid Neural Network Cerebellar Model Articulation Controller Design for Non-linear Dynamic Time-Varying Plants.

This study proposes a hybrid method to control dynamic time-varying plants that comprises a neural network controller and a cerebellar model articulation controller (CMAC). The neural-network controller reduces the range and quantity of the input. The cerebellar-model articulation controller is the main controller and is used to compute the final control output. The parameters for the structure of the proposed network are adjusted using adaptive laws, which are derived using the steepest-descent gradient approach and back-propagation algorithm. The Lyapunov stability theory is applied to guarantee system convergence. By using the proposed combination architecture, the designed CMAC structure is reduced, and it makes it easy to design the network size and the initial membership functions. Finally, numerical-simulation results demonstrate the effectiveness of the proposed method.

Hierarchical fuzzy CMAC control for nonlinear systems

In this study, a novel indirect adaptive controller is introduced for a class of unknown nonlinear systems. The proposed method provides a simple control architecture that merges from the cerebellar model articulation controller (CMAC) network and hierarchical fuzzy logic; therefore, the complicated CMAC structure can be simplified. The overall adaptive scheme guarantees the uniform stability of the closed-loop system. A simulation is presented to demonstrate the performance of the proposed methodology.

Self-organizing adaptive wavelet CMAC backstepping control system design for nonlinear chaotic systems

A novel self-organizing wavelet cerebellar model articulation controller (CMAC) is proposed. This self-organizing wavelet CMAC (SOWC) can be viewed as a generalization of a self-organizing neural network and of a conventional CMAC, and it has better generalizing, faster learning and faster recall than a self-organizing neural network and a conventional CMAC. The proposed SOWC has the advantages of structure learning and parameter learning simultaneously. The structure learning possesses the ability of on-line generation and elimination of layers to achieve optimal wavelet CMAC structure, and the parameter learning can adjust the interconnection weights of wavelet CMAC to achieve favorable approximation performance. Then a SOWC backstepping (SOWCB) control system is proposed for the nonlinear chaotic systems. This SOWCB control system is composed of a SOWC and a fuzzy compensator. The SOWC is used to mimic an ideal backstepping controller and the fuzzy compensator is designed to dispel the residual of approximation errors between the ideal backstepping controller and the SOWC. Moreover, the parameters of the SAWCB control system are on-line tuned by the derived adaptive laws in the Lyapunov sense, so that the stability of the feedback control system can be guaranteed. Finally, two application examples, a Duffing–Holmes chaotic system and a gyro chaotic system, are used to demonstrate the effectiveness of the proposed control method. The simulation results show that the proposed SAWCB control system can achieve favorable control performance and has better tracking performance than a fuzzy neural network control system and a conventional adaptive CMAC.

Self-Structured Organizing Single-Input CMAC Control for Robot Manipulator

This paper represents a self-structured organizing single-input control system based on differentiable cerebellar model articulation controller (CMAC) for an n-link robot manipulator to achieve the high-precision position tracking. In the proposed scheme, the single-input CMAC controller is solely used to control the plant, so the input space dimension of CMAC can be simplified and no conventional controller is needed. The structure of single-input CMAC will also be self-organized; that is, the layers of single-input CMAC will grow or prune systematically and their receptive functions can be automatically adjusted. The online tuning laws of single-input CMAC parameters are derived in gradient-descent learning method and the discrete-type Lyapunov function is applied to determine the learning rates of proposed control system so that the stability of the system can be guaranteed. The simulation results of robot manipulator are provided to verify the effectiveness of the proposed control methodology.

Self-Structured Organizing Single-Input CMAC Control for De-icing Robot Manipulator

This paper presents a self-structured organizing single-input control system based on differentiable cerebellar model articulation controller (CMAC) for an n-link robot manipulator to achieve the high-precision position tracking. In the proposed scheme, the single-input CMAC controller is solely used to control the plant, so the input space dimension of CMAC can be simplified and no conventional controller is needed. The structure of single-input CMAC will also be self-organized; that is, the layers of single-input CMAC will grow or prune systematically and their receptive functions can be automatically adjusted. The online tuning laws of single-input CMAC parameters are derived in gradient-descent learning method and the discrete-type Lyapunov function is applied to determine the learning rates of the proposed control system so that the stability of the system can be guaranteed. The simulation results of three-link De-icing robot manipulator are provided to verify the effectiveness of the proposed control methodology.

Self-Organizing CMAC Control for a Class of MIMO Uncertain Nonlinear Systems

This paper presents a self-organizing control system based on cerebellar model articulation controller (CMAC) for a class of multiple-input-multiple-output (MIMO) uncertain nonlinear systems. The proposed control system merges a CMAC and sliding-mode control (SMC), so the input space dimension of CMAC can be simplified. The structure of CMAC will be self-organized; that is, the layers of CMAC will grow or prune systematically and their receptive functions can be automatically adjusted. The control system consists of a self-organizing CMAC (SOCM) and a robust controller. SOCM containing a CMAC uncertainty observer is used as the principal controller and the robust controller is designed to dispel the effect of approximation error. The gradient-descent method is used to online tune the parameters of CMAC and the Lyapunov function is applied to guarantee the stability of the system. A simulation study of inverted double pendulums system and an experimental result of linear ultrasonic motor motion control show that favorable tracking performance can be achieved by using the proposed control system.

FCMAC-Yager: A Novel Yager-Inference-Scheme-Based Fuzzy CMAC

The cerebellum is a brain region important for a number of motor and cognitive functions. It is able to generate error correction signals to drive learning and for the acquisition of memory skills. The cerebellar model articulation controller (CMAC) is a neural network inspired by the neurophysiologic theory of the cerebellum and is recognized for its localized generalization and rapid algorithmic computation capabilities. The main deficiencies in the basic CMAC structure are: (1) it is difficult to interpret the internal operations of the CMAC network and (2) the resolution (quantization) problem arising from the partitioning of the input training space. These limitations lead to the synthesis of a fuzzy quantization technique and the mapping of a fuzzy inference scheme onto the CMAC structure. The discrete incremental clustering (DIC) technique is employed to alleviate the quantization problem in the CMAC structure, resulting in the fuzzy CMAC (FCMAC) network. The Yager inference scheme (Yager), which possesses firm fuzzy logic foundation and maps closely to the logical implication operations in the classical (binary) logic framework, is subsequently mapped onto the FCMAC structure. This results in a novel fuzzy neural architecture known as thefuzzy cerebellar model articulation controller-Yager (FCMAC-Yager) system. The proposed FCMAC-Yager network exhibits learning and memory capabilities of the cerebellum through the CMAC structure while emulating the human way of reasoning through the Yager. The new FCMAC-Yager network employs a two-phase training algorithm consisting of structural learning based on the DIC technique and parameter learning using hebbian learning (associative long-term potentiation). The proposed FCMAC-Yager architecture is evaluated using an extensive suite of real-life applications such as highway traffic-trend modeling and prediction and performing as an early warning system for bank failure classification and medical diagnosis of breast cancer. The experimental results are encouraging.

Multiple Hyperball CMAC Structure for Large Dimension Mapping

The cerebellar model articulation controller (CMAC) is often used in neural computation and neurocontrol systems as output predictors or models of dynamic systems through static mapping from input space to output space. Hyperball CMAC (HCMAC) is presented in the paper. As a fast learning network, its performance is very easy to be analyzed. The simulation results, from the application of three kinds of CMAC, demonstrate that the HCMAC has a better learning performance than CMAC with general basis functions (Chiang; Lin, 1996) and general Albus CMAC (Albus, 1975). For mapping with large-dimensional input, the conventional CMACs need large weight memory space, while the need usually is not met. In order to overcome the issue, a new CMAC structure containing several HCMACs is proposed, the input space of each HCMAC is a subset of input space to be mapped. The CMAC structure is called SHCMAC. Simulations for the SHCMAC used in a multivariable nonlinear dynamic system modelling are performed to demonstrate its powerful associative memory performance and the accuracy in modeling

Generalization Ability and Learning Accuracy of Hyperball CMAC and Parallel CMAC Structure

A cerebellar model articulation controller (CMAC) is often used as nonlinear function approximator in pattern recognition, system identification, and neurocontrol systems. Generalization ability and learning accuracy are among important performance of a CMAC besides learning speed, and they are affected significantly by quantization level and the ratio of adjusted weights at each learning with a sample to all weights, called weigh adjusting ratio (WAR) in this paper. There is always a trade-off between generalizatinn ability and learning accuracy in conventional neural networks. In many cases, quantization level is increased to enhance learning accuracy without consideration of changing the WAR, this may result in decreasing generalization ability. In this paper, we studied Hyperball CMAC (HCMAC), and found the relation of generalization ability or learning accuracy with quantization level and WAR, a large number simulations illustrate that the CMAC is very effective in approximating nonlinear functions. On one hand, for fixed quantization level, the generalization error and learning error will conformably decrease with increasing WAR until WAR reaches a certain value, and they remain unchanged when the WAR is greater than the value. On the other hand, when the WAR fixed. learning error is decreasing with large quantization level, whereas generalization error has no clear relation with quantization level. These unique properties can be applied to improve the performance of designed CMAC. For further enhancing generalization ability and learning accuracy, a multiple CMAC structure (called parallel CMAC structure in this paper) is proposed based on the CMAC to approximate a highly nonlinear function very accurately. A simulation example demonstrates that the structure has powerful generalization and learning ability

Logic-based neural networks

Realization of two-valued or many-valued functions carried out by fuzzy set logical operations is studied. Two basic types of computational nodes performing generalized (weighted) AND and OR operations form generic components of neural networks. Their functional and numerical properties are carefully studied. The combination of these two nodes into a structure of logic processors is used to approximate manyinput-single-output logical relationships. Relevant learning algorithms are proposed and analyzed. Numerical considerations are included as well. Generalization aspects of this architecture are studied. A new interpretation of the paradigm of a fuzzy controller realized as a cerebellar model articulation controller structure with the aid of logic processors are discussed as well.