scholarly journals Neuro-fuzzy-based Electronic Brake System Modeling using Real Time Vehicle Data

10.29007/q7pr ◽  
2019 ◽  
Author(s):  
Ana Farhat ◽  
Kyle Hagen ◽  
Ka C Cheok ◽  
Balaji Boominathan
Keyword(s):  
System Modeling ◽  
Least Square ◽  
Brake System ◽  
Model Parameters ◽  
Vehicle Data ◽  
Neuro Fuzzy ◽  
Marquardt Algorithm ◽  
Levenberg Marquardt ◽  
Network Method ◽  
Fuzzy Network

Electronic Brake System (EBS) is considered as one of the most complicated systems whose performance depends on the subsystems parameters. Usually these parameters are difficult to predict. Based on the task to improve the EBS performance, this article presents a mathematical modeling approach based on neuro-fuzzy network method to model a subsystem of EBS. For the model parameters identification, a neuro-fuzzy network has been implemented based on Least Square Error (LSE) and Levenberg- Marquardt Algorithm (LMA) as the optimization algorithms. Finally, the performance of identified model has been evaluated.

Mass properties identification and automatic mass balancing system for satellite attitude dynamics simulator

2017 ◽  
Vol 233 (3) ◽  
pp. 896-907
Author(s):  
Ghasem Sharifi ◽  
Mehran Mirshams ◽  
Hamed Shahmohamadi Ousaloo
Keyword(s):  
Center Of Mass ◽  
Least Square ◽  
Attitude Dynamics ◽  
Satellite Attitude ◽  
Marquardt Algorithm ◽  
Mass Properties ◽  
Levenberg Marquardt ◽  
Mass Balancing ◽  
Satellite Attitude Dynamics ◽  
Automatic Mass

A Satellite Attitude Dynamics Simulator is a low-cost, ground-based system made to simulate the conditions of a weightless satellite in space. The identification of the mass characteristics is crucial for Satellite Attitude Dynamics Simulator application and so the center of mass place is necessary for balancing the platform and moment of inertia which is a significant factor in designing controllers and selecting actuators. The purposes of this paper are the mass properties identification and design, experimentation, and validation of an automatic mass balancing system, which is assembled on the Satellite Attitude Dynamics Simulator at the Space Research Laboratory. This paper presents a process of mass properties estimation for the Satellite Attitude Dynamics Simulator using classical Levenberg–Marquardt as an optimization method. By employing this technique lack of repeatability and difficulties in implementation will be eliminated. In order to verify this technique, a MATLAB® SIMULINK® model of the Satellite Attitude Dynamics Simulator is established. The gap between the center of mass and center of rotation is decreased by means of the automatic mass balancing system in order to remove gravity disturbance. The results of this identification process are compared to the recursive least square algorithm, which is commonly employed in identification of mass properties. The analytical and experimental results prove that the proposed characteristic estimation process using classical Levenberg–Marquardt algorithm is more effective and appropriate. Proper excitation of the platform will guarantee the accuracy of estimation and compensation of the center of gravity offset utilizing the balancing system.

Parameter Identification Research Based on ARX Model

2012 ◽  
Vol 190-191 ◽  
pp. 292-296
Author(s):  
Huai Yuan Liu ◽  
Jian Hua He ◽  
Song Chen
Keyword(s):  
System Identification ◽  
Programming Model ◽  
System Modeling ◽  
Estimation Method ◽  
Information Criterion ◽  
Least Square ◽  
Model Parameters ◽  
Least Square Estimation ◽  
Model Order ◽  
Arx Model

Based on the principle of the system identification, combined Simulink with System Identification Toolbox from MATLAB, the least square estimation method is selected to establish a system of ARX model, and Akaike Information Criterion (AIC) was used in the identification of model order, compared with the original model to study the fitting accuracy, and the validity of the model is examined by residual analysis. This approach overcomes the disadvantages of the complexity and difficulty in traditional programming model. Compared to other program identification method, it has a short modeling time, and it is clear, reliable, intuitive visual, good scalability. Furthermore, the model parameters, result and system can be easily modified, assessed and verified. This method of system modeling and simulation can be used for reference to aerospace and other fields.

scholarly journals On damping parameters of Levenberg-Marquardt algorithm for nonlinear least square problems

2021 ◽  
Vol 1734 ◽  
pp. 012018
Author(s):  
A O Umar ◽  
I M Sulaiman ◽  
M Mamat ◽  
M Y Waziri ◽  
N Zamri
Keyword(s):  
Least Square ◽  
Marquardt Algorithm ◽  
Levenberg Marquardt ◽  
Least Square Problems

scholarly journals Improving Levenberg-Marquardt Algorithm Inversion Result Using Singular Value Decomposition

2016 ◽  
Vol 5 (2) ◽  
pp. 20
Author(s):  
Widodo Widodo ◽  
Durra Handri Saputera
Keyword(s):  
Singular Value Decomposition ◽  
Singular Value ◽  
Parameter Analysis ◽  
Model Parameters ◽  
Inversion Result ◽  
One Dimensional ◽  
Marquardt Algorithm ◽  
Levenberg Marquardt ◽  
Value Decomposition ◽  
Lm Algorithm

Inversion is a process to determine model parameters from data. In geophysics this process is very important because subsurface image is obtained from this process. There are many inversion algorithms that have been introduced and applied in geophysics problems; one of them is Levenberg-Marquardt (LM) algorithm. In this paper we will present one of LM algorithm application in one-dimensional magnetotelluric (MT) case. The LM algorithm used in this study is improved version of LM algorithm using singular value decomposition (SVD). The result from this algorithm is then compared with the algorithm without SVD in order to understand how much it has been improved. To simplify the comparison, simple synthetic model is used in this study. From this study, the new algorithm can improve the result of the original LM algorithm. In addition, SVD is allowing more parameter analysis to be done in its process. The algorithm created from this study is then used in our modeling program, called MAT1DMT.

Inverse problem of Mueller polarimetry for metrological applications

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Tatiana Novikova ◽  
Pavel Bulkin
Keyword(s):  
Inverse Problem ◽  
Nonlinear Problem ◽  
Optimization Problem ◽  
Global Minimum ◽  
Mueller Matrix ◽  
Least Square ◽  
Marquardt Algorithm ◽  
Geometrical Features ◽  
Levenberg Marquardt

Abstract Inverse problem of Mueller polarimetry is defined as a determination of geometrical features of the metrological structures (i.e. 1D diffraction gratings) from its experimental Mueller polarimetric signature. This nonlinear problem was considered as an optimization problem in a multi-parametric space using the least square criterion and the Levenberg–Marquardt algorithm. We demonstrated that solving optimization problem with the experimental Mueller matrix spectra taken in conical diffraction configuration helps finding a global minimum and results in smaller variance values of reconstructed dimensions of the grating profile.

scholarly journals LEVENBERG-MARQUARDT METHOD APPLIED TO THE DETERMINATION OF VAPOR-LIQUID EQUILIBRIUM MODEL PARAMETERS

2014 ◽  
Vol 44 (4) ◽  
pp. 319-324
Author(s):  
J.A. F. OLIVEIRA ◽  
M.M. L. DUARTE ◽  
E. L. FOLETTO ◽  
O. CHIAVONE-FILHO
Keyword(s):  
Structural Parameters ◽  
Pure Component ◽  
Estimation Methods ◽  
Model Parameters ◽  
Arbitrary Matrix ◽  
Marquardt Algorithm ◽  
Levenberg Marquardt ◽  
Equilibrium Data ◽  
Parameter Estimation Methods ◽  
Vaporliquid Equilibrium

 In order to correlate and optimize experimental data either from the laboratory or industry, one needs a robust method of data regression. Among the non-linear parameter estimation methods it may be pointed out of Levenberg, which applies the conversion of an arbitrary matrix into a positive definite one. Later, Marquardt applied the same procedure, calculating  parameter in an iterative form. The Levenberg-Marquardt algorithm is described and two routine for correlating vaporliquid equilibrium data for pure component and mixtures, based on this efficient method, have been applied. The routines have been written with an interface very accessible for both users and programmers, using Python language. The flexibility of the developed programs for introducing the desired details is quite interesting for both process simulators and modeling properties. Furthermore, for mixtures with electrolytes, it was obtained a coherent and compatible relation for the structural parameters of the salt species, with the aid of the method and the graphical interface designed.

Comparison of an Artificial Neural Network and a Multiple Linear Regression in Predicting the Heat of Combustion of Diesel Fuel Based on Hydrocarbon Groups

2020 ◽  
Vol 71 (6) ◽  
pp. 66-74
Author(s):  
Younis M. Younis ◽  
Salman H. Abbas ◽  
Farqad T. Najim ◽  
Firas Hashim Kamar ◽  
Gheorghe Nechifor
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Diesel Fuel ◽  
Back Propagation ◽  
Second Step ◽  
Heating Value ◽  
Network Training ◽  
Marquardt Algorithm ◽  
Levenberg Marquardt ◽  
Propagation Network

A comparison between artificial neural network (ANN) and multiple linear regression (MLR) models was employed to predict the heat of combustion, and the gross and net heat values, of a diesel fuel engine, based on the chemical composition of the diesel fuel. One hundred and fifty samples of Iraqi diesel provided data from chromatographic analysis. Eight parameters were applied as inputs in order to predict the gross and net heat combustion of the diesel fuel. A trial-and-error method was used to determine the shape of the individual ANN. The results showed that the prediction accuracy of the ANN model was greater than that of the MLR model in predicting the gross heat value. The best neural network for predicting the gross heating value was a back-propagation network (8-8-1), using the Levenberg�Marquardt algorithm for the second step of network training. R = 0.98502 for the test data. In the same way, the best neural network for predicting the net heating value was a back-propagation network (8-5-1), using the Levenberg�Marquardt algorithm for the second step of network training. R = 0.95112 for the test data.

An improved nonlinear innovation-based parameter identification algorithm for ship models

2021 ◽  
pp. 1-9
Author(s):  
Baigang Zhao ◽  
Xianku Zhang
Keyword(s):  
Parameter Identification ◽  
Test Data ◽  
Stochastic Gradient ◽  
Least Square ◽  
Gradient Algorithm ◽  
Model Parameters ◽  
Identification Algorithm ◽  
Process Innovations ◽  
Stochastic Gradient Algorithm ◽  
Tangent Function

Abstract To solve the problem of identifying ship model parameters quickly and accurately with the least test data, this paper proposes a nonlinear innovation parameter identification algorithm for ship models. This is based on a nonlinear arc tangent function that can process innovations on the basis of an original stochastic gradient algorithm. A simulation was carried out on the ship Yu Peng using 26 sets of test data to compare the parameter identification capability of a least square algorithm, the original stochastic gradient algorithm and the improved stochastic gradient algorithm. The results indicate that the improved algorithm enhances the accuracy of the parameter identification by about 12% when compared with the least squares algorithm. The effectiveness of the algorithm was further verified by a simulation of the ship Yu Kun. The results confirm the algorithm's capacity to rapidly produce highly accurate parameter identification on the basis of relatively small datasets. The approach can be extended to other parameter identification systems where only a small amount of test data is available.

Sign in / Sign up

Export Citation Format

Share Document