• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.349-351
• /
• 2004

The classical dynamic backpropagation learning algorithm has the problems of learning speed and the determine of learning parameter. The Extend Kalman Filter(EKF) is used effectively for a state estimation method for a non linear dynamic system. This paper presents a learning algorithm using Dual Extended Kalman Filter(DEKF) for Fully Recurrent Neural Network(FRNN). This DEKF learning algorithm gives the minimum variance estimate of the weights and the hidden outputs. The proposed DEKF learning algorithm is applied to the system identification of a nonlinear SISO system and compared with dynamic backpropagation learning algorithm.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.2
• /
• pp.158-163
• /
• 2013

The fusion of the GPS (Global Positioning System) and DR (Dead Reckoning) is widely used for position and latitude estimation of vehicles such as a mobile robot, aerial vehicle and marine vehicle. Among the many types of aerial vehicles, grater focus is given on the quad-rotor and accuracy of the position information is becoming more important. In order to exactly estimate the position information, we propose the fusion method of GPS and Gyroscope sensor using the DEKF (Dual Extended Kalman Filter). The DEKF has an advantage of simultaneously estimating state value and a parameter of dynamical system. It can also be used even if state value is not available. In order to analyze the performance of DEKF, the computer simulation for estimating the position, the velocity and the angle in a circle trajectory of quad-rotor was done. As it can be seen from the simulation results using own proposed DEKF instead of EKF on own fusion method in the navigation of a quad-rotor gave better performance values.

• Journal of Power Electronics
• /
• v.12 no.1
• /
• pp.1-9
• /
• 2012

This study investigates an application of the Hamming network-dual extended Kalman filter (DEKF) based on pattern recognition for high accuracy state-of-charge (SOC)/capacity estimation and state-of-health (SOH) prediction at various temperatures. The averaged nine discharging/charging voltage-temperature (DCVT) patterns for ten fresh Li-Ion cells at experimental temperatures are measured as representative patterns, together with cell model parameters. Through statistical analysis, the Hamming network is applied to identify the representative pattern that matches most closely with the pattern of an arbitrary cell measured at any temperature. Based on temperature-checking process, model parameters for a representative DCVT pattern can then be applied to estimate SOC/capacity and to predict SOH of an arbitrary cell using the DEKF. This avoids the need for repeated parameter measuremet.

• Journal of the Microelectronics and Packaging Society
• /
• v.31 no.1
• /
• pp.16-22
• /
• 2024

Along with the high interest in electric vehicles and new renewable energy, there is a growing demand to apply lithium-ion batteries in the construction equipment industry. The capacity of heavy construction equipment that performs various tasks at construction sites is rapidly decreasing. Therefore, it is essential to accurately predict the state of batteries such as SOC (State of Charge) and SOH (State of Health). In this paper, the errors between actual electrochemical measurement data and estimated data were compared using the Dual Extended Kalman Filter (DEKF) algorithm that can estimate SOC and SOH at the same time. The prediction of battery charge state was analyzed by measuring OCV at SOC 5% intervals under 0.2C-rate conditions after the battery cell was fully charged, and the degradation state of the battery was predicted after 50 cycles of aging tests under various C-rate (0.2, 0.3, 0.5, 1.0, 1.5C rate) conditions. It was confirmed that the SOC and SOH estimation errors using DEKF tended to increase as the C-rate increased. It was confirmed that the SOC estimation using DEKF showed less than 6% at 0.2, 0.5, and 1C-rate. In addition, it was confirmed that the SOH estimation results showed good performance within the maximum error of 1.0% and 1.3% at 0.2 and 0.3C-rate, respectively. Also, it was confirmed that the estimation error also increased from 1.5% to 2% as the C-rate increased from 0.5 to 1.5C-rate. However, this result shows that all SOH estimation results using DEKF were excellent within about 2%.

• Proceedings of the KIPE Conference
• /
• 2014.07a
• /
• pp.401-402
• /
• 2014

State of Charge (SOC) and State of Health (SOH) are the key issues for the application of Absorbent Glass Mat (AGM) type battery in Idle Start Stop (ISS) system which is popularly integrated in Electric Vehicles (EVs). However, battery parameters strongly depend on SOC, current rate and temperature and significantly change over the battery life cycles. In this research, a novel method for SOC, SOH estimation which combines the Auto Regressive with external input (ARX) method using for online parameters prediction and Dual Extended Kalman Filter (DEKF) algorithm considering hysteresis is proposed. The validity of the proposed algorithm is verified by the simulation and experiments.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.18 no.1
• /
• pp.50-58
• /
• 2009

For precise tracking control of a servo system with nonlinear friction, a robust friction compensation scheme is presented in this paper. The nonlinear friction is difficult to identify the friction parameters exactly through experiments. Friction parameters can be also varied according to contact conditions such as the variation of temperature and lubrication. Thus, in order to overcome these problems and obtain the desired position tracking performance, a robust adaptive back-stepping control scheme with a dual friction observer is developed. In addition, to estimate lumped friction uncertainty due to modeling errors, a DEKF recurrent neural network and adaptive reconstructed error estimator are also developed. The feasibility of the proposed control scheme is verified through the experiment fur a ball-screw system.