• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.4
• /
• pp.730-737
• /
• 2001

In this paper, an stabilization control method using adaptive neuro-fuzzy controller(ANFC) is proposed for modeling of nonlinear complex systems. The proposed adaptive neuro-fuzzy controller implements system structure and parameter identification using the intelligent schemes together with optimization theory, linguistic fuzzy implication rules, and neural networks from input and output data of processes. The results show that the proposed method can produce the intelligence model with higher accuracy than other works achieved previously.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.26 no.3
• /
• pp.167-175
• /
• 2021

Reusing electric vehicle batteries after they have been retired from mobile applications is considered a feasible solution to reduce the demand for new material and electric vehicle costs. However, the evaluation of the value and the performance of second-life batteries remain a problem that should be solved for the successful application of such batteries. The present work aims to estimate the remaining useful life of Li-ion batteries through the neuro-fuzzy system with the equivalent circuit parameters obtained by Electrochemical Impedance Spectroscopy (EIS). To obtain the impedance spectra of the Li-ion battery over the life, a 18650 cylindrical cell has been aged by 1035 charge/discharge cycles. Moreover, the capacity and the parameters of the equivalent circuit of a Li-ion battery have been recorded. Then, the data are used to establish a neuro-fuzzy system to estimate the remaining useful life of the battery. The experimental results show that the developed algorithm can estimate the remaining capacity of the battery with an RMSE error of 0.841%.

• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.725-730
• /
• 1994

A sodium chloride crystallizer shows oscillatory and nonlinear characteristics under its nucleating and growing process. Because these characteristics vary with operational condition, we can't control the product crystal size exactly with a PID controller or a sequence controller. Then, we make a model with threefold neural networks for the laboratory equipment that is a jet mixing crystallizer. We try to control the product crystal size with its neuro-model, and we reach the conclusion that our neuro-model is applicable to the practical crystallizer.

• Proceedings of the KIEE Conference
• /
• 1999.07f
• /
• pp.2496-2498
• /
• 1999

The SRM is modeled by the database of torque profiles for every small variation in currents and rotor angles, which is inferred from the several measured data by the adaptive neuro-fuzzy inference technique. Simulation results demonstrating the effectiveness of proposed torque modeling technique are presented.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.161.4-161
• /
• 2001

This paper presents adaptive control of robot manipulator using neuro-fuzzy controller Fuzzy logic is control incorrect system without correct mathematical modeling. And, neural network has learning ability, error interpolation ability of information distributed data processing, robustness for distortion and adaptive ability. To reduce the number of fuzzy rules of the FLS(fuzzy logic system), we consider the properties of robot dynamic. In fuzzy logic, speciality and optimization of rule-base creation using learning ability of neural network. This paper presents control of robot manipulator using neuro-fuzzy controller. In proposed controller, fuzzy input is trajectory following error and trajectory following error differential ...

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.809-812
• /
• 1999

The pendulum is a SIMO(Single-input multi-output) system that both angle of pendulum and position of cart controlled simultaneously by one actuator. In this paper, propose a hybrid neuro-controller to apply to pendulum system. We design the conventional optimal controller and the neural network as a identifier, which can identify the uncertainty of plant not modeled, respectively. Then we combine them into a novel controller, with a structure that the error between plant and identifier is added in conventional optimal control input Finally, the paper shows the validity of the proposed controller through computer simulations and experiments.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.145-148
• /
• 2003

In this paper an nonlinear neuro PID controller is constructed by the control system of general PID controller using a Self-Recurrent Neural Network. And the games of the PID controller in the proposed control system are automatically adjusted by back-propagation algorithm of the neural network. Applying to the position control system, it's performance is verified through the results of computer simulation.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.5
• /
• pp.676-682
• /
• 2014

In this paper, precipitation echo(PRE) and non-precipitaion echo(N-PRE)(including ground echo and clear echo) through weather radar data are identified with the aid of neuro-fuzzy algorithm. The accuracy of the radar information is lowered because meteorological radar data is mixed with the PRE and N-PRE. So this problem is resolved by using RBFNN and judgement module. Structure expression of weather radar data are analyzed in order to classify PRE and N-PRE. Input variables such as Standard deviation of reflectivity(SDZ), Vertical gradient of reflectivity(VGZ), Spin change(SPN), Frequency(FR), cumulation reflectivity during 1 hour(1hDZ), and cumulation reflectivity during 2 hour(2hDZ) are made by using weather radar data and then each characteristic of input variable is analyzed. Input data is built up from the selected input variables among these input variables, which have a critical effect on the classification between PRE and N-PRE. Echo judgment module is developed to do echo classification between PRE and N-PRE by using testing dataset. Polynomial-based radial basis function neural networks(RBFNNs) are used as neuro-fuzzy algorithm, and the proposed neuro-fuzzy echo pattern classifier is designed by combining RBFNN with echo judgement module. Finally, the results of the proposed classifier are compared with both CZ and DZ, as well as QC data, and analyzed from the view point of output performance.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.9
• /
• pp.430-438
• /
• 2001

In this study, we introduce the adaptive Polynomial Neuro-Fuzzy Networks(PNFN) architecture generated from the fusion of fuzzy inference system and PNN algorithm. The PNFN dwells on the ideas of fuzzy rule-based computing and neural networks. Fuzzy inference system is applied in the 1st layer of PNFN and PNN algorithm is employed in the 2nd layer or higher. From these the multilayer structure of the PNFN is constructed. In order words, in the Fuzzy Inference System(FIS) used in the nodes of the 1st layer of PNFN, either the simplified or regression polynomial inference method is utilized. And as the premise part of the rules, both triangular and Gaussian like membership function are studied. In the 2nd layer or higher, PNN based on GMDH and regression polynomial is generated in a dynamic way, unlike in the case of the popular multilayer perceptron structure. That is, the PNN is an analytic technique for identifying nonlinear relationships between system's inputs and outputs and is a flexible network structure constructed through the successive generation of layers from nodes represented in partial descriptions of I/O relatio of data. The experiment part of the study involves representative time series such as Box-Jenkins gas furnace data used across various neurofuzzy systems and a comparative analysis is included as well.

• Molecules and Cells
• /
• v.41 no.12
• /
• pp.1061-1071
• /
• 2018

From Xenopus embryo studies, the BMP4/Smad1-targeted gene circuit is a key signaling pathway for specifying the cell fate between the ectoderm and neuro-ectoderm as well as the ventral and dorsal mesoderm. In this context, several BMP4/Smad1 target transcriptional factors have been identified as repressors of the neuro-ectoderm. However, none of these direct target transcription factors in this pathway, including GATA1b, Msx1 and Ventx1.1 have yet been proven as direct repressors of early neuro-ectodermal gene expression. In order to demonstrate that Ventx1.1 is a direct repressor of neuro-ectoderm genes, a genome-wide Xenopus ChIP-Seq of Ventx1.1 was performed. In this study, we demonstrated that Ventx1.1 bound to the Ventx1.1 response cis-acting element 1 and 2 (VRE1 and VRE2) on the promoter for zic3, which is a key early neuro-ectoderm gene, and this Ventx1.1 binding led to repression of zic3 transcription. Site-directed mutagenesis of VRE1 and VRE2 within zic3 promoter completely abolished the repression caused by Ventx1.1. In addition, we found both the positive and negative regulation of zic3 promoter activity by FoxD5b and Xcad2, respectively, and that these occur through the VREs and via modulation of Ventx1.1 levels. Taken together, the results demonstrate that the BMP4/Smad1 target gene, Ventx1.1, is a direct repressor of neuro-ectodermal gene zic3 during early Xenopus embryogenesis.