Compensatory Fuzzy Neural Network Research Articles

Compensatory neural fuzzy networks with rule-based cooperative differential evolution for nonlinear system control

This study presents a rule-based cooperative differential evolution (RCDE) learning algorithm to optimize the parameters of a compensatory neural fuzzy network (CNFN) for solving control problems. CNFN uses the compensatory degree for fuzzy reasoning to dynamically adjust fuzzy operators that can make the fuzzy system more adaptive and effective. RCDE decomposes the fuzzy system into multiple rule-based subpopulations where each subpopulation represents a fuzzy rule set, and each individual within each subpopulation evolves by differential evolution (DE) separately. The proposed RCDE uses cooperative behavior among multiple subpopulations for combining their information and building the complete fuzzy system to accelerate the search and increase global search capacity. Finally, the experimental results show that the proposed RCDE method better approximates the global optimal solution and has a faster convergence rate than the other methods.

Prediction of CNC Thermal Deformation Based on the Compensation Fuzzy Neural Network

A new predictive model has proposed based on compensation fuzzy neural networks for thermal error in NC machine tools . The structure of model , fuzzy rule , training algorithm and some technological problems are discussed.And the result of intelligent prediction and accuracy evaluation are given.

Study on Temperature Control System of Film Laminating Machine

The recursive compensatory fuzzy neural network model was established against the characteristics of temperature control for film laminating machine. The neural network can be used to construct the fuzzy system, and the self-adaptive and self-learning capability of neural networks was used to automatically adjust fuzzy system parameters, BP network could be learned and trained by the gradient descent algorithm. Based on the test data for the study and testing of network, system error is less than the national standard error requirements, the results proved the effectiveness and feasibility of the algorithm.

Model Reference Control Based on Compensatory Fuzzy Neural Network for Gas Collectors of Coke Oven

The pressure system of gas collectors of coke oven is a multivariable non-linear process. In this paper, a model reference adaptive control using the compensatory fuzzy neural network for the pressure system of gas collectors of coke oven is presented. The dynamics model of the fuzzy neural network of the system is identified by the adaptive compensatory fuzzy learning algorithm, which can be employed as the identifier of the system. Another fuzzy neural network is trained to learn the inverse dynamics of the pressure system of gas collectors of coke oven so that it can be used as a nonlinear controller. The simulation results testify that the model obtained is satisfied and the control is effective.

Fuzzy-neural network compensator for Robot manipulator controlled by PD-like fuzzy system

Fuzzy-neural network compensator for Robot manipulator controlled by PD-like fuzzy system

The Water Level of Marine Boiler Control and Simulation System Based on Compensatory Fuzzy Neural Network

The Water Level of Marine Boiler Control and Simulation System Based on Compensatory Fuzzy Neural Network

DSP-based synchronous control of dual linear motors via Sugeno type fuzzy neural network compensator

A digital signal processor (DSP)-based complementary sliding mode control (CSMC) with Sugeno type fuzzy neural network (SFNN) compensator is proposed in this study for the synchronous control of a dual linear motors servo system installed in a gantry position stage. The dual linear motors servo system comprises two parallel permanent magnet linear synchronous motors (PMLSMs). The dynamics of the single-axis motion system with a lumped uncertainty which contains parameter variations, external disturbances and nonlinear friction force is briefly introduced first. Then, a CSMC is designed to guarantee the precision position tracking requirement in single-axis control for the dual linear motors. Moreover, to enhance the robustness to uncertainties and to eliminate the synchronous error of dual linear motors, the CSMC with a SFNN compensator is proposed where the SFNN compensator is designed mainly to compensate the synchronous error. Furthermore, to increase the control performance of the proposed intelligent control approach, a 32-bit floating-point DSP, TMS320VC33, is adopted for the implementation of the proposed CSMC and SFNN. In addition, some experimental results are illustrated to show the validity of the proposed control approach.

Fuzzy Neural Network Compensator for Gantry Stage Synchronous Motion

In this paper, a fuzzy neural network (FNN) compensator is proposed for the synchronous motion control of a gantry position stage. Firstly, the cascade control strategy is applied to reduce the single axis position tracking error. However, the synchronous error between dual servo systems is inevitable due to their inequality in characteristics and the environmental uncertainties. The FNN compensator and an online learning algorithm perform a fuzzy reasoning with two inputs of synchronous position and velocity errors between dual drive servo systems and generate the compensated force; the compensated force is fed back to the controller of each axis. The online learning algorithm adjusts the connected weighting of the neural network by using a supervised gradient descent methods, such that the define error function can be minimized. Finally, two kinds of position commands with high and low frequency are designed for the experiments, and the experimental results show that the proposed FNN compensator is feasible to improve the synchronous error of gantry stage.

A Compensatory Fuzzy Neural Network Modeling Method Based on Particle Swarm Clustering

According to modeling problem for complex systems, a compensatory fuzzy neural network (CFNN) modeling method based on particle swarm clustering is proposed: the particle swarm clustering is used to automatically separate the space of input-output data, obtain the numbers of inference rules of fuzzy model and find fuzzy rules. Based on the rules, we modified fuzzy reasoning process and established initial structure of compensatory fuzzy neural network. Then using adaptive rate algorithm optimized initial network parameters, which can obtain a faster training speed and more precision. Simulation results show that the proposed network has successfully modeled the oxidation decomposition reaction process.

Dynamic system identification using Pseudo‐Gaussian‐based recurrent compensatory fuzzy neural networks

In this paper, a Pseudo‐Gaussian‐based Recurrent Compensatory Fuzzy Neural Network (PG‐RCFNN) is proposed for identification of dynamic systems. The recurrent network is embedded in the PG‐RCFNN by adding feedback connections in the second layer, where the feedback units act as memory elements. The compensatorybased fuzzy reasoning method is using adaptive fuzzy operations of fuzzy neural networks that can make the fuzzy logic systems more adaptive and effective. The Pseudo‐ Gaussian membership function can provide the proposed model, which own a higher flexibility and can approach the optimal result more accurately. An on‐line learning algorithm that consists of structure learning and parameter learning is proposed to automatically construct the PG‐RCFNN. The structure learning is based on the degree measure and the parameter learning is based on the supervised gradient decent method. Computer simulations have been conducted to illustrate the performance and applicability of the proposed model.

Compensatory fuzzy neural networks-based intelligent detection of abnormal neonatal cerebral Doppler ultrasound waveforms.

Compensatory fuzzy neural networks (CFNN) without normalization, which can be trained with a backpropagation learning algorithm, is proposed as a pattern recognition technique for intelligent detection of Doppler ultrasound waveforms of abnormal neonatal cerebral hemodynamics. Doppler ultrasound signals were recorded from the anterior cerebral arteries of 40 normal full-term babies and 14 mature babies with intracranial pathology. The features of normal and abnormal groups as inputs to pattern recognition algorithms were extracted from the maximum velocity waveforms by using principal component analysis. The proposed technique is compared with the CFNN with normalization and other pattern recognition techniques applied to Doppler ultrasound signals from various arteries. The results show that the proposed method is superior to the others, and can be a powerful technique to be used in analyzing Doppler ultrasound signals from various arteries.