There is a growing interest in using Kalman filter models in brain modeling. The question arises whether Kalman filter models can be used on-line not only for estimation but for control. The usual method of optimal control of Kalman filter makes use of off-line backward recursion, which is not satisfactory for this purpose. Here, it is shown that a slight modification of the linear-quadratic-gaussian Kalman filter model allows the on-line estimation of optimal control by using reinforcement learning and overcomes this difficulty. Moreover, the emerging learning rule for value estimation exhibits a Hebbian form, which is weighted by the error of the value estimation.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1162/089976604772744884 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Real time SOC estimation for Li-ion batteries in Electric vehicles using UKBF with online parameter identification.
Sci Rep
January 2025
School of Electrical Engineering, VIT University, Tamilnadu, 632014, India.
Article Synopsis
- Lithium-ion batteries are crucial for the electric vehicle (EV) industry due to their high energy density, low discharge rate, and long lifespan, making accurate State of Charge (SOC) estimation important for performance improvement.
- The proposed method combines the Thevenin 2RC battery model to capture the battery's non-linear dynamics with the Unscented Kalman Bucy Filter (UKBF) to enhance SOC estimation by dealing with measurement noise and nonlinearities.
- A simulation in Matlab Simulink reveals that the UKBF outperforms other estimation methods like EKF and UKF, achieving a notably lower Root Mean Square Error (RMSE) of 0.003276 for SOC estimation.
System identification and fault reconstruction in solar plants via extended Kalman filter-based training of recurrent neural networks.
ISA Trans
January 2025
Dept. de Ingeniería de Sistemas y Automática, University of Seville, Camino de los Descubrimientos, no number E-41092, Seville, Spain. Electronic address:
This article proposes using the extended Kalman filter (EKF) for recurrent neural network (RNN) training and fault estimation within a parabolic-trough solar plant. The initial step involves employing an RNN to model the system. Given the challenge of fault discernibility in the collectors, parallel EKFs are employed to reconstruct the parameters of the faults.
View Article and Find Full Text PDFNoninteracting optimal and adaptive torque control using an online parameter estimation with help of polynomials in EKF for a PMSM.
ISA Trans
January 2025
Leuphana University of Lueneburg, Universitaetsallee 1, 21335 Lueneburg, Germany. Electronic address:
This paper addresses a non-interacting torque control strategy to decouple the d- and q-axis dynamics of a permanent magnet synchronous machine (PMSM). The maximum torque per ampere (MTPA) method is used to determine the reference currents for the desired torque. To realize the noninteracting control, knowledge concerning the inductances L and L of the electrical machine is necessary.
View Article and Find Full Text PDFSquare Root Unscented Kalman Filter-Based Multiple-Model Fault Diagnosis of PEM Fuel Cells.
Sensors (Basel)
December 2024
Institute of Autmatic Control, University of Kaiserslautern-Landau, 67653 Kaiserslautern, Germany.
Harsh operating conditions imposed by vehicular applications significantly limit the utilization of proton exchange membrane fuel cells (PEMFCs) in electric propulsion systems. Improper/poor management and supervision of rapidly varying current demands can lead to undesired electrochemical reactions and critical cell failures. Among other failures, flooding and catalytic degradation are failure mechanisms that directly impact the composition of the membrane electrode assembly and can cause irreversible cell performance deterioration.
View Article and Find Full Text PDFAccurate colorectal cancer detection using a random hinge exponential distribution coupled attention network on pathological images.
Abdom Radiol (NY)
January 2025
Department of Computer Engineering, Vishwakarma Institute of Information Technology, Pune, India.
Colorectal cancer (CRC) is one of the most common and deadly forms of cancer worldwide, necessitating accurate and early detection to improve treatment outcomes. Traditional diagnostic methods often rely on manual examination of pathological images, which can be time-consuming and prone to human error. This study presents an advanced approach for colorectal cancer detection using a Random Hinge Exponential Distribution coupled Attention Network (RHED-CANet) on pathological images.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!