Papers by Keyword: Fuzzy Neural Network (FNN)

Abstract: The characteristic of unit coordinated control in thermal power plants having complex, nonlinear, larger time delay, and establishing mathematical models are very difficult. In the paper establish mathematical models of using fuzzy neural network system, make full use of the ability of fuzzy logic reasoning and neural network self-learning; using multivariable generalized predictive control strategy, Simulation results show that the use of fuzzy neural network generalized predictive control for good stability of main steam pressure , strong effectiveness of tracking the power grid load, and little fluctuation of different load conversion.

Abstract: To solve the problem that wheeled robot in the path tracking is prone to slip or roll over at a sharp curve, structure of the wheeled robot and its path tracking features are analyzed, and a new Fuzzy-Neural Network (FNN) based path tracking method of two-stage (route and speed) control is proposed. In the first stage, a FNN controller determines the robot’s turning radius by processing robot’s pose information. In the second stage, the secondary controller adjusts angular and linear velocities by taking advantage of the turning radius and condition of the path ahead. The experiments show that the controlled robot can track the planned path accurately and robustly when it runs at high speed; the process of path tracking is stable and no slipping and rolling occur.

Abstract: Most Automotbile Electric Power Steering (EPS) controller designs are based on a simplified accurate model,however,EPS controller is affected by many nonlinear friction and damping easily, such as road condition,sensor noises and the lateral wind disturbance.These uncertainties affect the accuracy of assist current, the EPS performance and the driving safety. Aimed at the nonlinear MIMO system of electric power steering system,the mechanism and dynamic characteristic of EPS is analysed,and EPS model is developed. Then the fuzzy-neural network controller is designed and the corresponding simulation is performed.The results show that the proposed EPS control strategy can provide good performance of stability and controllability and can increase the anti-jamming capability of vehicle.

Abstract: Has the advantages of quick response of PMSM using the method of DTC, but will make the high torque and big magnetic flux linkage ripples. In order to solve this problem, using the fuzzy neural network hybrid system to replace the traditional hysteresis controller, Strong learning ability and fuzzy logic in handling uncertain information has the adaptive ability of neural network, the fuzzy neural network hybrid system to produce the expected voltage vector, the speed of a smooth transition of permanent magnet synchronous motor. The proposed method is validated by simulation under external disturbances in motor is very effective to reduce the ripple of torque and flux, the speed of the fast response and smooth transition.

Abstract: Many machine learning approaches in the field of Artificial Intelligence (AI) have been developed. Most of them rely on using large data sets to build up knowledge. However, the traffic system usually has only few data. In this article, the so-called adaptive neural fuzzy inference systems (ANFIS) is employed to predict the traffic time-series with few data, including flow, speed and occupancy

Abstract: This paper proposes a pattern recognition approach based on the fuzzy neural network for identifying insulation defects of cast resin current transformer (CRCT) arising from partial discharge (PD). Pattern recognition of PD is used for identifying defects causing the PD, such as internal discharge, external discharge, corona, etc. This information is vital for estimating the harmfulness of the discharge in the insulation. The PD patterns are collected by a PD detecting system in the laboratory. Several statistical methods are used on the phase related distributions in this paper to extract the features for recognition. A set of features, used as operators, for each PD pattern is extracted through statistical methods. To verify the proposed approach, experiments were conducted to demonstrate the field-test PD pattern recognition of CRCT models with artificial defects are purposely created to produce the common PD activities of insulators by using feature vectors of field-test PD patterns. The experimental data are found to be in close agreement with the recognized data. The test results show that the proposed approach may achieve quite satisfactory recognition of PD patterns.

Abstract: Credit risk is the main risk that Chinese commercial banks are facing. Taking into account three categories of risk factors, namely risk factors of enterprise, risk factors of commercial bank and risk factors of macroscopic economy, an index system was set up. Then, according to the index system and the characteristics of fuzzy neural network and expert system, a credit risk rating system based on fuzzy neural network and expert system was proposed.

Abstract: This paper transforms a common conjugate gradient algorithm, based on the fuzzy neural network for line. This thesis systematically studies the performances and learning algorithms of two FNN models, monolithic FNN and polygonal FNN, based on the past progress of FNN theory and application. The major issues in the thesis are the perturbation of monolithic FNN, the learning algorithms and universal approximation of polygonal FNN and the achievements obtained here are applied to fuzzy control area.

Abstract: In this paper, a new DNA based genetic algorithm is proposed to optimize a fuzzy neural network model for a pH neutralization process. In the proposed algorithm, each individual presents a fuzzy neural network encoded by nucleotide base sequence, and modified DNA based crossover operation and three types of mutation operators are designed to improve the searching ability of the algorithm. The study on the performance for two functions shows that the proposed algorithm outperforms GA. Finally, to verify the effectiveness of the established model, it is compared with two models optimized with other methods. Comparison results show that the model optimized by DNA based GA is more accurate.

Abstract: In order to make a research on the vehicle`s ABS and AFS system,the fuzzy neural network controller was designed on the basis of the electric vehicle`s steering and braking models. Then the genetic algorithms was used to improve the parameters of the membership function. Finally, the Matlab/Simulink simulation software has been used in the simulation analysis. The result of simulation proves that the designed system has good tracking performance and more stronger systemic robustness .