Cerebellar Model Articulation Controller Research Articles

Two model-free schemes for solving kinematic tracking control of redundant manipulators using CMAC networks

Kinematic tracking control of robotic manipulators is a basic and vital issue in robotics. However, how to achieve the control of robotic manipulators with unknown kinematic models remains challenging. Existing studies show that cerebellum, a pivotal region of brain, plays a major role in human motion control, which motivates us to devise two schemes based on cerebellum model articulation controller (CMAC) for the tracking control of redundant manipulators with unknown kinematic models in this article. The first scheme is based on a CMAC network and a gradient neural dynamics (GND) algorithm. The CMAC network is utilized to generate approximate joint angle commands for the manipulator. By using the Jacobian matrix of the manipulator which is estimated by the GND algorithm, task space error is transformed into joint space error, which is taken as the teaching signal for training the CMAC. For the second scheme, another CMAC network replaces the GND algorithm to achieve the estimation of the Jacobian matrix of the manipulator. The effectiveness and robustness of the proposed control schemes are verified by both simulations and physical experiments.

Neural longitudinal control of hypersonic vehicles with constrained aerodynamic surfaces

This paper presents a neural adaptive flight control for longitudinal dynamics of air-breathing hypersonic vehicles (AHVs) with constrained aerodynamic surfaces. Multiple actuator constraints including magnitude, rate, and first-order dynamic model in both the elevator and canard are transformed into a specific control allocation problem, which can be readily solved using the standard model predictive control (MPC) technique. Furthermore, an adaptive control scheme is developed combining with the above control allocation and the recurrent cerebellar model articulation controller (RCMAC), which well handles actuator constraints and uncertain factors including aerodynamic coefficients, external disturbances, and flexible dynamics. Numerous simulation results verify performance and robustness of the proposed neural adaptive control.

Torque Ripple Suppression Method of Switched Reluctance Motor Based on an Improved Torque Distribution Function

Currently, torque ripple is a crucial factor hindering the application of the switched reluctance motor (SRM). Hence, it is of crucial importance to suppress this undesirable torque ripple. This paper proposes a new torque ripple suppression method of SRM based on the improved torque distribution function. Firstly, the electromagnetic characteristic model of a 8/6-pole four-phase SRM is established, and the cerebellar model articulation controller (CMAC) is used to complete the learning of each model. Then, the improved torque distribution function is planned based on the torque model to give the reference torque of each phase, and the inverse torque model is used to realize the mapping of the reference torque to the reference flux linkage. Finally, the duty of each phase voltage PWM wave modulation is output based on the PID control theory. The proposed accurate model-based planning scheme is implemented on the simulation platform, and the results shows that the maximum torque fluctuation of the output results is reduced to within 3%, and the average error is reduced to within 1%, which is much lower than the error of 15% under the traditional direct torque control method.

Basic Theory and Practice Teaching Method Based on the Cerebellar Model Articulation Controller Learning Algorithm

With the continuous in-depth development of science and technology in my country, the field of artificial intelligence has also made considerable progress. For example, the comprehensiveness and operability of technology have been enhanced. Artificial intelligence, as a comprehensive and intersecting research field in the fields of computer science, information science, and mathematics, has also made a certain contribution to the progress of international students in colleges and universities. This article is aimed at studying the problems based on basic theories and time teaching methods, mainly through a comprehensive data analysis of artificial intelligence technology and fusion differential evolution algorithm, and then improving the learning ability of students and comprehensive quality. This paper proposes a swarm intelligence algorithm, K -means clustering algorithm, and vector machine algorithm and summarizes the process and application fields of the swarm intelligence algorithm. In addition, the CMAC learning algorithm is proposed, which shows that robots under the background of industrial intelligence and machine learning can organize themselves to form groups to perform complex tasks. The experimental results of this paper show that the communication range is between 0 and 1, which can enable more robots to communicate in order to improve the individual’s social learning opportunities, thereby enhancing the individual’s learning ability to improve the performance of learning behavior and improving the efficiency of practical teaching and research, making the efficiency reach 0.9.

An Innovative Approach for Water Distribution Systems

Water Distribution System (WDS) is one of the important phases of the Water Treatment Plant (WTP) and plays a crucial role in plant, animal, and human life. The WDS aims not only to supply a continuous, stable water amount but also to reduce energy consumption as little as possible during operation. To keep the continuous, stable water amount, the water pressure in the pipe network of the WDS must be maintained at desired set points under the effecting of uncertainties, disturbances, and noises. For saving the energy requirement, a Variable Frequency Driver (VFD) was utilized to control the speed of the Water Boost Pump (WBP) as speed as the WDS requires and a Recurrent Cerebellar Model Articulation Control System (RCMACS) was proposed to keep the water pressure at desired reference under abnormal events. Furthermore, to adapt to the industrial environment, the RCMACS was implemented on the Allen-Bradly Programmable Logic Controller (PLC), and industrial networks were also proposed to connect and transfer data between control stations and field devices.

Wavelet Interval Type-2 Takagi-Kang-Sugeno Hybrid Controller for Time-Series Prediction and Chaotic Synchronization

This paper presents a new hybrid neural network for time series prediction and chaotic synchronization. The proposed controller consists of a wavelet interval type-2 Takagi Sugeno Kang fuzzy brain emotional learning controller (WIT2TFBELC), a wavelet interval type-2 Takagi Sugeno Kang fuzzy cerebellar model articulation controller (WIT2TFCMAC), and a robust compensator (RB). The main controller combines the WIT2TFBELC and the WIT2TFCMAC. A TSK fuzzy system is used to create a hybrid structure with the WIT2TFBELC and the WIT2TFCMAC. The TSK fuzzy system can effectively adjust the weighting for the main controller to achieve the time series prediction and chaotic prediction with better tracking response. Morever a robust compensator is used to achieve robust ability of the system. A Lyapunov function was used to establish the adaptive laws and effectively adjust the system parameters online. Finally, two examples of the application of the proposed algorithm are presented to point out the performance of proposed method.

An Adaptive Fuzzy Trajectory Tracking Control via Improved Cerebellar Model Articulation Controller for Electro-Hydraulic Shovel

Most of existing model-based control strategies for trajectory tracking of electro-hydraulic shovel (EHS) are limited to the condition that full state variables can be measured. This article proposes an adaptive control system consisting of a terminal sliding mode controller and a novel neural network controller for trajectory tracking of EHS, and only the system position signal is adopted in the control law. The newly designed hybrid cerebellar model articulation controller contains a radial basis function neural network (RBFNN) preprocessor and a main CMAC controller that generated final output. The RBFNN preprocessor can decrease input range and dimensions for CMAC, which can speed up learning and reduce computing cost. The control law is derived based on the Lyapunov stability theory and finite-time convergence can be realized. Furthermore, an adaptive compensation term is introduced to compensate the combination errors. Finally, comparative simulation and experimental results have confirmed that the proposed method can accommodate the lumped uncertainties well and has better performance with high computational efficiency.

Direct Fuzzy CMAC Sliding Mode Trajectory Tracking for Biaxial Position System

High-precision trajectory control is considered as an important factor in the performance of industrial two-axis contour motion systems. This research presents an adaptive direct fuzzy cerebellar model articulation controller (CMAC) sliding mode control (DFCMACSMC) for the precise control of the industrial XY-axis motion system. The FCMAC was utilized to approximate an ideal controller, and the weights of FCMAC were on-line tuned by the derived adaptive law based on the Lyapunov criterion. With this derivation in mind, the asymptotic stability of the developed motion system could be guaranteed. The two-axis stage system was experimentally investigated using four contours, namely, circle, bowknot, heart, and star reference contours. The experimental results indicate that the proposed DFCMACSMC method achieved the improved tracking capability, and so reveal that the DFCMACSMC scheme outperformed other schemes of the model uncertainties and cross-coupling interference.

Research on parallel control of CMAC and PD based on U model

In this paper, the nonlinear U model with time-varying coefficients is investigated and the transformation of the nonlinear model is accomplished by the Newton iterative algorithm. Based on the nonlinear U model, a control algorithm with cerebellar model articulation controller and proportional derivative (PD) in parallel is proposed. The algorithm learns online through a neural network while optimizing the output of the PD, which ultimately enables the actual output of the system to track up to the desired output. Considering that the nonlinear object has the characteristic of rapid change with time, the article improves the PD algorithm to nonlinear PD control algorithm to complete the design of the system. The algorithm automatically adjusts the weights according to the error magnitude to complete the controller parameter adjustment, thus reducing the error of the system. The simulation results show that the nonlinear PD algorithm is better than the PD algorithm, meanwhile, the tracking speed and control precision of the system are improved.

A fuzzy CMAC learning approach to image based visual servoing system

This study presents a fuzzy robotic joint controller using a cerebellar model articulation controller (CMAC) integrating a Takagi-Sugeno (T-S) framework with an online compensator for an articulated manipulator. The proposed controller is applied to image-based visual servoing (IBVS), including closed-loop feedback control and the kinematic Jacobian calculation. This approach learns a mapping from image feature errors for each joint’s velocity instead of the classical kinematics, thereby reducing the computational complexity and improving the self-regulation ability of the control system. These connecting weights of the cerebellar model learn offline, and an online compensator that uses reinforcement learning is developed to resolve system noise and uncertainties in an unknown environment. Compared with the classical inverse kinematics model, this approach does not need an excessive computational expense so that this proportional controller can be implemented in general scenarios with an eye-in-hand configuration. Experimental results show the proposed method can outperform the classical IBVS controller.

Adaptive robust controller using intelligent uncertainty observer for mechanical systems under non-holonomic reference trajectories

Non-holonomic reference trajectories and uncertainties are typically encountered in a class of mechanical systems. For such systems, this paper investigates the development of a novel explicit adaptive robust controller. By employing the structure of the Udwadia controller, the designed controller can deal with holonomic and non-holonomic reference trajectories in a unified manner. To avoid degradation of performance due to uncertainties, an observer is proposed to identify the uncertainties; the observer is designed using a fuzzy cerebellar model articulation controller neural network. A robust term is designed to restrain the initial deviations and to enhance the robustness of systems. Moreover, a compensatory term is designed to compensate for the residual errors resulted from the uncertainty observer. Rigorous theoretical analysis of the proposed controller is verified via the Lyapunov stability method, and an illustrative example is presented to demonstrate the effectiveness of the designed controller.

Deeply feature learning by CMAC network for manipulating rehabilitation robots

Human action recognition is a key component in modern artificial intelligent systems that greatly enhance the manipulating of various robots, such as rehabilitation robtos and industrial robots. Existing action recognition algorithms mainly depend on a predefined spatial sequence code book, which may fail to discover discriminative spatial–temporal features to mimic robots. In this paper, we propose to engineer the spatial–temporal action features that can deeply encode the similarity of within-class human actions and dissimilarity of between-class human actions. Specifically, given a series of training action video samples, we first segment each video into multiple key sections based on human contour. These sections of a video are related to time and space. Then, local robot action and appearance information are combined using a cerebellar model articulation controller (CMAC) to represent each video section. We quantize these extracted features into a feature vector, which can represent category-specific robot actions. Subsequently, we develop an improved linear discriminative analysis to project the data points to a subspace, where data points with the same label are close while data points with different labels are far from each other. Experimental results on the well-known HMDB51 and KTH datasets have shown the effectiveness and robustness of our method. Moreover, our action recognition can be applied as a key module in the real-world rehabilitation robots.

Design of Adaptive TSK Fuzzy Self-Organizing Recurrent Cerebellar Model Articulation Controller for Chaotic Systems Control

The synchronization and control of chaos have been under extensive study by researchers in recent years. In this study, an adaptive Takagi–Sugeno–Kang (TSK) fuzzy self-organizing recurrent cerebellar model articulation controller (ATFSORC) is proposed, which is composed of a set of TSK fuzzy rules, a cerebellar model articulation controller (CMAC), a recurrent CMAC (RCMAC), a self-organizing CMAC (SOCMAC), and a compensation controller. Specifically, SOCMAC, RCMAC, and adaptive laws are adopted so that the association memory layers of ATFSORC can be modulated in accordance with the layer decision-making mechanism in order to reduce the structure complexity and improve the control performance of ATFSORC. Moreover, the Takagi–Sugeno–Kang fuzzy rules are introduced to increase the learning speed of ATFSORC, and the improved compensating controller is designed to dispel the errors between an ideal controller and the TFSORC. Moreover, the proposed ATFSORC is applied to chaotic systems in order to validate its performance and feasibility. Several simulation schemes are demonstrated to show the effectiveness of the proposed method. Simulation results show that the proposed ATFSORC can obtain a favorable control performance when the chaotic systems are operated at different parameters. Specifically, ATFSORC can achieve faster convergence of the tracking error than fuzzy CMAC (FCMAC) and CMAC.

Microsatellite attitude control approach: combined with Generation Adversarial Networks fault-detection and Cerebellar Model Articulation Controller fault-tolerant control

Microsatellite attitude control approach: combined with Generation Adversarial Networks fault-detection and Cerebellar Model Articulation Controller fault-tolerant control

Synchronization of Chaotic System Using a Brain-Imitated Neural Network Controller and Its Applications for Secure Communications

This paper proposes a new hybrid algorithm for secure communication applications. The proposed algorithm includes a fuzzy brain emotional learning controller (FBELC), a recurrent cerebellar model articulation controller (RCMAC), and a robust compensator (RC). The main brain-imitated neural network controller is a combination of the RCMAC and the FBELC, which is a mathematical model that approximates the decision and emotional activity of a human brain. A fuzzy inference system is also merged into the FBELC to produce an efficient hybrid structure, then it is used for secure communication applications. The 3-dimensional (3D) Genesio chaotic system is used for audio and image secure communication systems to show the potency and performance of the proposed algorithm. In the first application, a new image encryption algorithm is proposed to enhance security for information transmission, then several standard images are applied for the chaotic synchronization of image secure communication. In the second application, the audio signal is embedded in a 3D chaotic trajectory, which is used as an encryption carrier signal, after using the proposed method for the decryption, the source signal can be retrieved. The comparisons of simulation results using security analyses and root mean square error for recent algorithms are performed to validate the performance and efficiency of the proposed hybrid algorithm. The simulation results point out that our algorithm can attain better synchronization performance, and achieve more efficient audio and image secure communications.

Robust attitude control of micro-satellite based on Generation Adversarial Networks fault detection and Cerebellar Model Articulation Controller fault tolerant control

Robust attitude control of micro-satellite based on Generation Adversarial Networks fault detection and Cerebellar Model Articulation Controller fault tolerant control

A bionic cerebellar motion control model and its application in arm control

How to realize the control of limb movement and apply it to intelligent robot systems at the level of cerebellar cortical neurons is a hot topic in the fields of artificial intelligence and rehabilitation medicine. At present, the cerebellar model usually used is only for the purpose of controlling the effect, borrowing from the functional mode of the cerebellum, but it ignores the structural characteristics of the cerebellum. In fact, in addition to being used for controlling purposes, the cerebellar model should also have the interpretability of the control process and be able to analyze the consequences of cerebellar lesions. Therefore, it is necessary to establish a bionic cerebellar model which could better express the characteristics of the cerebellum. In this paper, the process that the cerebellum processes external input information and then generates control instructions at the neuron level was explored. By functionally segmenting the cerebellum into homogeneous structures, a novel bionic cerebellar motion control model incorporating all major cell types and connections was established. Simulation experiments and force feedback device control experiments show that the bionic cerebellar motion control model can achieve better control effect than the currently widely used cerebellar model articulation controller, which verifies the effectiveness of the bionic cerebellar motion control model. It has laid the foundation for real brain-like artificial intelligence control.

ADAPTIVE WAVELET FUZZY CMAC TRACKING CONTROL FOR INDUCTION SERVOMOTOR DRIVE SYSTEM

In this study, a control system is proposed for the induction servomotor to achieve the highprecision speed tracking based on wavelet fuzzy cerebellar model articulation controller. In this proposed scheme, the wavelet fuzzy cerebellar model articulation controller (WFCMAC) is used to imitate an ideal controller due to it incorporates the advantages of the wavelet decomposition property with a fuzzy CMAC fast learning ability and the smooth compensator controller with bound estimation is designed to attenuate the effect of the approximation error caused by the WFCMAC approximator. The online tuning laws of WFCMAC and the smooth compensator with bound estimation parameters are derived in gradient-descent learning method and Lyapunov function so that the stability of the system can be guaranteed. Finally, through the experimental results of proposed control system is developed for induction servomotor is provided to verify the effectiveness of the proposed control methodology even the dynamical model of the induction servomotor is complete unknown.

Method to Expand the CMAC Model to Composite-Type Model

Neural networks (NNs) are effective for the learning of nonlinear systems, and thus they achieve satisfactory results in various fields. However, they require significant amount of training data and learning time. Notably, the cerebellar model articulation controller (CMAC), which is modeled after the cerebellar neural transmission system, proposed by Albus can effectively reduce learning time, compared with NNs. The CMAC model is often used to learn nonlinear systems that have continuously changing outputs, i.e., regression problems. However, the structure of the CMAC model must be expanded to apply it to classification problems as well. Additionally, the CMAC model finds it difficult to simultaneously classify categories and estimate their proportional linear measure because designated learning algorithms are required for both regression and classification problems. Therefore, we aim to build a composite-type CMAC model that combines classification and regression algorithms to simultaneously classify categories and estimate their proportional linear measures.

Error prediction and structure determination for CMAC neural network based on the uniform design method

AbstractInsufficient study on error bound of cerebellar model articulation controller (CMAC) severely limits its application. To investigate the error prediction and structure determination of CMAC for multi‐dimensional and data‐generation objects, this paper builds a 10‐input 2‐output model for a desulfurization system to test 44,640 sets of operation data. Four test groups and one prediction group are designed and performed based on uniform design method. Regression analysis and curve fitting methods are applied for error analyses. The focus of regression analysis method is the influence of uniform table's level on its prediction formulas' accuracies, whereas curve fitting's is the impact of theoretical memory space (location number) and actual storage space (address number) of CMAC on output error. Based on the results, the following conclusions are obtained. (a) The prediction accuracy of the linear regression equation is not monotonous with the level of the uniform design table, but there is a distinct region with local high precision. (b) Compared with regression analysis and address number fitting methods, location number analysis method has distinct advantages of prediction range, accuracy and flexibility. (c) In terms of location number analysis, different intervals may correspond to different optimal fitting functions, but only power function maintains high prediction accuracy in the whole range where the method works. Besides, the scope of location number analysis is also studied, of which the lower borders are 109 and 1010 approximately for model's two outputs, respectively.