Cerebellar Model Articulation Controller Research Articles

Design and Implementation of a Data-Oriented Nonlinear PID Controller

PID control schemes have been widely used in most industrial control systems. However, it is difficult to determine a suitable set of PID gains, because most industrial systems have nonlinearity. On the other hands, Cerebellar Model Articulation Controller (CMAC) classified as neural networks has been proposed, and design scheme of an intelligent PID controller by using the CMAC-PID tuner has been proposed. However, the CMAC-PID tuner has two problems. One is that the CMAC must be trained in an online manner to get their optimum weights. Another is that the CMAC requires lots of memories and high computational cost for some microcontrollers. In order to train CMAC in an offline manner, CMACFRIT scheme which is a combination of CMAC and Fictitious Reference Iterative Tuning (FRIT) scheme has been proposed in a previous research. FRIT is a scheme to determine control parameters by using a set of experimental data. According to the CMAC-FRIT scheme, CMAC-PID tuner can be trained in an offline manner by using a set of operating data. In this paper, to address the problem of required memory and computational cost, a method that expresses CMAC-PID tuner as a simple nonlinear function by using Group Method of Data Handling (GMDH) is proposed. According to the proposed method, CMAC-PID tuner (which is trained in advance by using a set of operating data) is replaced by a network of N-Adalines (units expressed by a simple nonlinear function). Thus, the proposed algorithmcan be easily added to a microcontroller even if it is a commodity type. The effectiveness of the proposed method is validated by a simulation example. Moreover, to show the usefulness of the proposed method, the algorithm is added to a commodity type microcontroller, and the controller is applied to a magnetic levitation device.

Parameter Self-Adjusting Path Tracking Algorithm of Mobile Robots

For conventional fuzzy path tracking controller need to manually updated the control parameters in order to get better tracking control deficiencies and the lack of robustness of the problem when the control object is disturbed. Parameters self-adjusting tracking algorithm is proposed based on Cerebellum Model Articulation Controller(CMAC) and fuzzy logic composite of the control. The CAMC control logarithm first charged with tracking through learning objects charged with approximation of the object model, to learning cycle worth to control corresponding to the amount of correction corresponding weight value according to the error between input and output of the system and set the learning rate. When the object or environment changes can make the control performance of the system is automatically adjusting within a certain range, since the role of the CAMC. Tracking experiments show that. The tracking control algorithm has high tracking accuracy and good robustness, is conducive to the overall optimization of robot path tracking.

CMAC-Based Backstepping Sliding Mode Control of PMSM

The paper describes a hybrid approach to the problem of controlling permanent magnet synchronous motor (PMSM) with unmodelled dynamics and unknown external disturbances. First, the backstepping sliding mode (BS) controller based on the equation of PMSM is elaborated. Its effect is to achieve a stable control. Then the cerebellar model arithmetic computer (CMAC) controller is implemented to compensate uncertainties. Furthermore, the nonlinear disturbance observer (DO) is applied to estimate the time-varying lumped disturbance D(t) for improving the precision of the tracking control. The proposed CMAC-based method can acquire high control performance in the presence of disturbance and guarantee the stability of closed-loop systems on the basis of the Lyapunov theorem. The effectiveness and robustness are demonstrated through simulation results obtained for the tracking control of PMSM.

Cerebellar model articulation controller proportional velocity parameters variations and learning schemes—A study on electrohydraulic servo system

Cerebellar model articulation controller neural networks is one of the computational intelligence tools that can be applied for modeling, classification, and control. Proportional velocity controller is a servo-type controller, which is commonly applied to motion control systems. This paper presents a novel combination of cerebellar model articulation controller neural networks and optimal proportional velocity controller. A simple mathematical model for applying and studying cerebellar model articulation controller is introduced, and a study of its parameters is presented individually. The effect of parameters variation on cerebellar model articulation controller performance is identified. Learning algorithms highly affect the cerebellar model articulation controller behavior even when the parameters are optimized, and proper selection of the learning scheme must be taken under consideration. Three different learning algorithms are studied for evaluating transient and steady-state cerebellar model articulation controller responses. The results showed that the change of cerebellar model articulation controller generalization size and scale of the control signal has a marked effect on the performance of cerebellar model articulation controller. Furthermore, the constant learning rate algorithm gives the best overall performance.

Islanding Detection Method of a Photovoltaic Power Generation System Based on a CMAC Neural Network

This study proposes an islanding detection method for photovoltaic power generation systems based on a cerebellar model articulation controller (CMAC) neural network. First, islanding phenomenon test data were used as training samples to train the CMAC neural network. Then, a photovoltaic power generation system was tested with the islanding phenomena. Because the CMAC neural network possesses association and induction abilities and characteristics that activate similar input signals in approximate memory during training process, the CMAC only requires that the weight values of the excited memory addresses be adjusted, thereby reducing the training time. Furthermore, quantification of the input signals enhanced the detection tolerance of the proposed method. Finally, the simulative and experimental data verified the feasibility of adopting the proposed detection method for islanding phenomena.

Down-Shift Control for Wet Dual Clutch Transmission Based on FCMAC

In order to solve the problems existed in gearshift with wet dual clutch transmission; the down-shift control strategy is developed on the basis of analysis on gear shift process. Clutch pressure intelligent control arithmetic based on FCMAC (Fuzzy Cerebellar Model Articulation Controller) is designed to realize accuracy control of clutch pressure. The transmission control unit is designed, and the control program is written. Taking down-shift from 2 to 1 for example, down-shifting control strategy was drawn. After applied the introduced method into the experiments on both power-on and power-off downshift under different throttle positions, ideal shifting quality was achieved. The result indicated that the speed of vehicle changed gently without distinct impact. This essay verifies the validity of the proposed method of the strategy of shifting control.

Tension Control Study in the Finishing Mill of Aluminum Hot Rolling Mills Based on PSO+CMAC

Aimed at decreasing the tension variation during transforming process of 1+4 aluminum hot rolling mills unit in one factory of Henan, we analyzed the factors affecting tension variation and improved the tension formula of hot rolling mills process considering the influence of tension on forward slip value. The tension forming process of hot rolling mills from stand 1 to stand 4 is simulated, and the tension structure diagrams of the four-stands are constructed. Due to non-linear characteristics of the aluminum hot rolling mills tension system, conventional PID controller could not meet the requirement of the system. So we proposed the mixed control of Cerebellar Model Articulation Controller (CMAC) coupled with PID to solve the problem of online parameters control and we used Particle Swarm Optimization (PSO) algorithm to optimize PID controller parameters. By simulation, it could be found that the using of PSO+CMAC significantly reduced surplus adjustment and transition time, and strip tension coupling degree among stands was also reduced.

Adding Active Learning to LWR for Ping-Pong Playing Robot

In this brief, we consider the problem of controlling the racket attached to the ping-pong playing robot, so that the incoming ball is returned to a desired position. The maps that are used to calculate the racket's initial parameters are described. They are implemented with the locally weighted regression (LWR). An active learning approach based on the fuzzy cerebellar model articulation controller (FCMAC) is proposed, and then it is added to the LWR, which is regarded as lazy learning. A learning algorithm that is used for updating the experience data in the fuzzy CMAC according to the errors between the actual and desired landing positions is presented. A series of experiments has been performed to demonstrate the applicability of the proposed method.

Design of Robust Adaptive Inverse Controller for a Hypersonic Aircraft Based on CMAC Neural Network

A new control structure based on dynamic inversion (DI) and neural network technology for a class of nonlinear uncertain system is proposed. DI is an effective nonlinear tracking and decoupling control method. However, the performance of the current DI may significantly degrade when internal unmodeled dynamics and external disturbances exist. In this paper, a Cerebellar Model Articulation Controller (CMAC) neural network is used to improve overall system performance of robust tracking control. The algorithm convergence condition is shown. Based on Lyapunov stability theory, all signals are proved to be uniform convergence. Finally, the flight control system of the hypersonic vehicle is designed based on the proposed method and the simulation results demonstrate the excellent performance and robustness of the controllers.

Estimator-based fuzzy credit-assigned cerebellar model articulation controller design for vector-controlled induction motor drives

This study has designed and implemented a novel speed controller and multi-estimator in a sensorless field-oriented control system for controlling induction motor (IM) speed. The speed controller was designed based on a fuzzy credit-assigned cerebellar model articulation controller (FCA-CMAC) to provide the online learning ability required for IM speed control. In contrast to the fuzzy cerebellar model articulation controller, the FCA-CMAC provides a faster convergence speed in the learning process for approximating a nonlinear function. Additionally, the multi-estimator provides a real-time adaptive estimation of motor speed and rotor resistance for achieving robustness for the IM controller against varying motor parameters. The multi-estimator is implemented by designing a cerebellar model articulation controller (CMAC) PI controller based on model reference adaptive system theory to adjust the adaptive pseudo-reduced-order flux observer parameters. Experiments performed on a 3-hp IM confirmed the effectiveness of the proposed approach. The experimental results confirm that the proposed control scheme achieves excellent dynamic and tracking responses to varying motor parameters.

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.

The Kernel Recursive Least Squares CMAC with Vector Eligibility

The cerebellar model articulation controller (CMAC) neural network is an associative memory that is biologically inspired by the cerebellum, which is found in the brains of animals. In recent works, the kernel recursive least squares CMAC (KRLS---CMAC) was proposed as a superior alternative to the standard CMAC as it converges faster and does not require tuning of a learning rate parameter. One improvement to the standard CMAC that has been discussed in the literature is eligibility, and vector eligibility. With vector eligibility the CMAC is able to control online motion control problems that it could not previously, stabilize the system much faster, and converge to a more intelligent solution. This paper integrates vector eligibility with the KRLS---CMAC and shows how the combination is advantageous through two simulated control experiments.

An Efficient Interval Type-2 Fuzzy CMAC for Chaos Time-Series Prediction and Synchronization

This paper aims to propose a more efficient control algorithm for chaos time-series prediction and synchronization. A novel type-2 fuzzy cerebellar model articulation controller (T2FCMAC) is proposed. In some special cases, this T2FCMAC can be reduced to an interval type-2 fuzzy neural network, a fuzzy neural network, and a fuzzy cerebellar model articulation controller (CMAC). So, this T2FCMAC is a more generalized network with better learning ability, thus, it is used for the chaos time-series prediction and synchronization. Moreover, this T2FCMAC realizes the un-normalized interval type-2 fuzzy logic system based on the structure of the CMAC. It can provide better capabilities for handling uncertainty and more design degree of freedom than traditional type-1 fuzzy CMAC. Unlike most of the interval type-2 fuzzy system, the type-reduction of T2FCMAC is bypassed due to the property of un-normalized interval type-2 fuzzy logic system. This causes T2FCMAC to have lower computational complexity and is more practical. For chaos time-series prediction and synchronization applications, the training architectures with corresponding convergence analyses and optimal learning rates based on Lyapunov stability approach are introduced. Finally, two illustrated examples are presented to demonstrate the performance of the proposed T2FCMAC.

A New Control Method Based on Artificial Immune Adaptive Strategy

An Artificial Immune Adaptive Strategy combining immune adaptive control and immune genetic optimization is proposed based on the simulation of the immune mechanisms such as the antibodies’ bifunctional structure and the immune cells’ regulation principle. This strategy is capable of optimizing online parameters of the immune controller with fixed framework, better simulating the behavior of the biological immune system. The proposed artificial immune adaptive strategy is applied to the control of Continuous Stirred Tank Reactor and its performance is compared with that of Cerebellar Model Articulation Controller. The results validate the effectiveness of artificial immune adaptive strategy.DOI: http://dx.doi.org/10.5755/j01.eee.19.4.1246

Design and Implementation of Adaptive Fuzzy Cerebellar Model Articulation Controller for Direct Torque Control System

This study implemented fuzzy control theory with a cerebellar controller to design a fuzzy cerebellar model articulation controller (FCMAC), ensuring system stability by deriving an adaptive FCMAC weight update rule from the Lyapunov theory. The speed estimator design in this study is based on the structure of an adaptive stator flux observer (ASFO) to achieve rapid sensorless control. According to results from experiments, installing the adaptive FCMAC speed controller in the induction motor’s direct torque control system demonstrates excellent speed dynamic response.

Wind Shear Encountered Landing Control Based on CMACs

This paper presents an intelligent control scheme that uses different cerebellar model articulation controllers (CMACs) in aircraft automatic landing control. The proposed intelligent control system can act as an experienced pilot and guide the aircraft landed safely in wind shear condition. Lyapunov theory is applied to obtain adaptive learning rule and stability analysis is also provided. Furthermore, the proposed controllers are implemented in a DSP. The simulations by MatLab are demonstrated.

Visual Servo Tracking Control for Slider Robot Using CMAC Neural Network Recognition Approach

This paper describes an image-based visual servo tracking control scheme using CMAC neural network as object recognition feedback methodology. A web camera based image capture system is mounted on the slider robot to capture the desired object and a CMAC (Cerebellar Model Articulation Controller) based object recognition scheme is developed to recognize the captured object image. Comparing the relative location of the recognized object and the web camera, then the position feedback signal can be obtained. Using the feedback signal, a PID (Proportional-Integral-Derivative) controller is designed to track the desired object by moving a single-axis slider robot, such that the captured object image located on the center of the captured frame always.

Takagi-Sugeno Fuzzy Estimator Design for Adaptive Vector Control Systems

This paper presents an adaptive pseudo reduced-order Takagi-Sugeno (T-S) fuzzy flux estimator for the induction motor direct field orientation control system. The estimator gain can be obtained by solving a set of linear matrix inequalities (LMIs) to estimate the rotor flux accurately. It is well known that, because of changes in temperature, variations of stator and rotor resistances affect the accuracy of rotor flux estimation. To resolve this problem, a cerebellar model articulation proportional integral controller (CMAPIC) is proposed to estimate the stator and rotor resistances during temperature variations. These estimated quantities, including stator and rotor resistances, are taken as the T-S fuzzy flux estimator inputs, so that the flux estimation is uninfluenced by these parameter variations. Thus the estimators enhance the robustness of the system. Moreover, this work uses a cerebellar model articulation controller to estimate the rotor speed, which is fed back to the adaptive supervisory fuzzy cerebellar model articulation speed controller (ASFCMAC) to achieve the speed sensor-less control.

Application of CMAC Neural Network to Solar Energy Heliostat Field Fault Diagnosis

Solar energy heliostat fields comprise numerous sun tracking platforms. As a result, fault detection is a highly challenging problem. Accordingly, the present study proposes a cerebellar model arithmetic computer (CMAC) neutral network for automatically diagnosing faults within the heliostat field in accordance with the rotational speed, vibration, and temperature characteristics of the individual heliostat transmission systems. As compared with radial basis function (RBF) neural network and back propagation (BP) neural network in the heliostat field fault diagnosis, the experimental results show that the proposed neural network has a low training time, good robustness, and a reliable diagnostic performance. As a result, it provides an ideal solution for fault diagnosis in modern, large-scale heliostat fields.

Applying a Cerebellar Model Articulation Controller Neural Network to a Photovoltaic Power Generation System Fault Diagnosis

This study employed a cerebellar model articulation controller (CMAC) neural network to conduct fault diagnoses on photovoltaic power generation systems. We composed a module array using 9 series and 2 parallel connections of SHARP NT-R5E3E 175 W photovoltaic modules. In addition, we used data that were outputted under various fault conditions as the training samples for the CMAC and used this model to conduct the module array fault diagnosis after completing the training. The results of the training process and simulations indicate that the method proposed in this study requires fewer number of training times compared to other methods. In addition to significantly increasing the accuracy rate of the fault diagnosis, this model features a short training duration because the training process only tunes the weights of the exited memory addresses. Therefore, the fault diagnosis is rapid, and the detection tolerance of the diagnosis system is enhanced.