A neural network approach to the design of a vehicle's non-linear hybrid suspension system

2002 ◽  
Vol 216 (5) ◽  
pp. 833-838 ◽  
Author(s):  
K N Spentzas ◽  
S A Kanarachos
Keyword(s):  
Neural Network ◽  
Control Function ◽  
Design Method ◽  
Excitation Amplitude ◽  
Suspension System ◽  
Vertical Acceleration ◽  
Neural Network Approach ◽  
The Road ◽  
The Neural Network ◽  
Non Linear

In the following, a design method is presented for non-linear hybrid suspension systems of vehicles based on neural networks. A hybrid suspension system is one that behaves as an active suspension system only when the road excitation amplitude is above a prescribed value. Discontinuous operation of the controller helps to minimize the energy consumed by the actuator. The design targets of our method are the minimization of the vertical acceleration imposed on the passengers as well as the respect of all the design and construction constraints. The neural network used is obtained by a Taylor approximation of the unknown non-linear control function. Because of the existence of numerous local minima of the neural network, an evolutionary algorithm is used to solve the resulting neural network problem.

scholarly journals Research on Road Roughness Based on NARX Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Yingjie Liu ◽  
Dawei Cui
Keyword(s):  
Neural Network ◽  
The Body ◽  
Identification Accuracy ◽  
Vertical Acceleration ◽  
Plane Model ◽  
The Road ◽  
The Neural Network ◽  
Road Roughness ◽  
Network Identification ◽  
Narx Neural Network

In order to solve the problem of road roughness identification, a study on the nonlinear autoregressive with exogenous inputs (NARX) neural network identification method was carried out in the paper. Firstly, a 7-DOF plane model of vehicle vibration system was established to obtain the vertical acceleration and elevation acceleration of the body, which were set as ideal input samples for the neural network. Then, based on the plane model, with common speed, the road roughness was solved as the ideal output sample of the NARX neural network, and the road roughness of B-level and C-level was identified. The results show that the proposed method has ideal identification accuracy and strong antinoise ability. The relative error of C-level road roughness is larger than that of B-level road roughness. The identified road roughness can provide a theoretical basis for analyzing the dynamic response of expressway roads.

Dynamical Modeling and Neural Network Adaptive Control of Vehicle Suspension

2011 ◽  
Vol 148-149 ◽  
pp. 516-519
Author(s):  
Jun Tao Fei ◽  
Jing Xu
Keyword(s):  
Neural Network ◽  
Suspension System ◽  
The Body ◽  
Vehicle Suspension ◽  
Vertical Acceleration ◽  
Nonlinear Spring ◽  
Passive Suspension ◽  
The Neural Network ◽  
Spring Suspension ◽  
Suspension Model

This paper attempts to establish the vibration control technology based on neural network control. First, the dynamic model of vehicle suspension system is discussed, and the linear passive suspension model and nonlinear spring suspension model of the vertical acceleration are compared. It is shown that the performance of nonlinear spring suspension is better than that of the linear passive suspension model. Because of the great advantages of the neural network in dealing with the nonlinear property, secondly, model reference neural control module is introduced in the suspension system to realize the optimization of the body vertical acceleration. Simulation results demonstrate the effectiveness of the neural network adaptive controller with application to vehicle suspension.

scholarly journals Excitation Forces Estimation for Non-linear Wave Energy Converters: A Neural Network Approach

2020 ◽  
Vol 53 (2) ◽  
pp. 12334-12339
Author(s):  
M. Bonfanti ◽  
F. Carapellese ◽  
S.A. Sirigu ◽  
G. Bracco ◽  
G. Mattiazzo
Keyword(s):  
Neural Network ◽  
Wave Energy ◽  
Linear Wave ◽  
Network Approach ◽  
Neural Network Approach ◽  
Wave Energy Converters ◽  
Non Linear ◽  
Energy Converters

Neural Networks L2-Gain Controller Design for Nonlinear System

2011 ◽  
Vol 467-469 ◽  
pp. 1505-1510
Author(s):  
Dan Liu ◽  
Ni Hong Wang ◽  
Gui Ying Li
Keyword(s):  
Neural Network ◽  
Disturbance Rejection ◽  
Differential Inequality ◽  
Controller Design ◽  
Design Method ◽  
General Structure ◽  
The Neural Network ◽  
Network Weight ◽  
Finite Gain ◽  
L2 Gain

This paper proposes a new method that it uses the neural network to construct the solution of the Hamiltion-Jacobi inequality (HJ), and it carries on the optimization of the neural network weight using the genetic algorithm. This method causes the Lyapunov function to satisfy the HJ, avoides solving the HJ parital differential inequality, and overcomes the difficulty which the HJ parital differential inequality analysis. Beside this, it proposes a design method of a nonlinear state feedback L2-gain disturbance rejection controller based on HJ, and introduces general structure of L2-gain disturbance rejection controller in the form of neural network. The simulation demonstrates the design of controller is feasible and the closed-loop system ensures a finite gain between the disturbance and the output.

Investigation of the possibility of reconstructing strain diagrams using the neural network approach

2011 ◽  
Vol 47 (15) ◽  
pp. 1689-1695
Author(s):  
M. B. Bakirov ◽  
O. A. Mishulina ◽  
I. A. Kiselev ◽  
I. A. Kruglov
Keyword(s):  
Neural Network ◽  
Network Approach ◽  
Neural Network Approach ◽  
The Neural Network

An artificial neural network approach to discrete-event simulation

1995 ◽  
Vol 9 (1) ◽  
pp. 37-49 ◽  
Author(s):  
Ian Flood ◽  
Kenneth Worley
Keyword(s):  
Neural Network ◽  
Discrete Event Simulation ◽  
Network Architecture ◽  
Discrete Event ◽  
Network Approach ◽  
Neural Network Approach ◽  
Event Simulation ◽  
The Neural Network ◽  
Component Processes ◽  
And Performance

AbstractThis paper proposes and evaluates a neural network-based method for simulating manufacturing processes that exhibit both noncontinuous and stochastic behavior processes more conventionally modeled, using discrete-event simulation algorithms. The incentive for developing the technique is its potential for rapid execution of a simulation through parallel processing, and facilitation of the development and improvement of models particularly where there is limited theory describing the dependence between component processes. A brief introduction is provided to a radial-Gaussian neural network architecture and training process, the system adopted for the work presented in this paper. A description of the basic approach proposed for applying this technology to simulation is then described. This involves the use of a modularized neural network approach to model construction and the prediction of the occurrence of events using information retained from several previous states of the simulation. A class of earth-moving systems, comprising a push-dozer and a fleet of scrapers, is used as the basis for assessing the viability and performance of the proposed approach. A series of experiments show the neural network to be capable of both capturing the characteristic behavior and making an accurate prediction of production rates of scraper-based earth-moving systems. The paper concludes with an indication of some areas for further development and evaluation of the technique.

Estimation of Annual Average Daily Traffic on Low-Volume Roads: Factor Approach Versus Neural Networks

2000 ◽  
Vol 1719 (1) ◽  
pp. 103-111 ◽  
Author(s):  
Satish C. Sharma ◽  
Pawan Lingras ◽  
Guo X. Liu ◽  
Fei Xu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Traffic Monitoring ◽  
Network Approach ◽  
Annual Average ◽  
Neural Network Approach ◽  
The Neural Network ◽  
Low Volume Roads ◽  
Annual Average Daily Traffic ◽  
Low Volume

Estimation of the annual average daily traffic (AADT) for low-volume roads is investigated. Artificial neural networks are compared with the traditional factor approach for estimating AADT from short-period traffic counts. Fifty-five automatic traffic recorder (ATR) sites located on low-volume rural roads in Alberta, Canada, are used as study samples. The results of this study indicate that, when a single 48-h count is used for AADT estimation, the factor approach can yield better results than the neural networks if the ATR sites are grouped appropriately and the sample sites are correctly assigned to various ATR groups. Unfortunately, the current recommended practice offers little guidance on how to achieve the assignment accuracy that may be necessary to obtain reliable AADT estimates from a single 48-h count. The neural network approach can be particularly suitable for estimating AADT from two 48-h counts taken at different times during the counting season. In fact, the 95th percentile error values of about 25 percent as obtained in this study for the neural network models compare favorably with the values reported in the literature for low-volume roads using the traditional factor approach. The advantage of the neural network approach is that classification of ATR sites and sample site assignments to ATR groups are not required. The analysis of various groups of low-volume roads presented also leads to a conclusion that, when defining low-volume roads from a traffic monitoring point of view, it is not likely to matter much whether the AADT on the facility is less than 500 vehicles, less than 750 vehicles, or less than 1,000 vehicles.

Prediction of Remaining Life Time Based on Measurements of Stress for Thermal Barrier Coatings

2001 ◽  
Author(s):  
E. H. Jordan ◽  
W. Xie ◽  
M. Gell ◽  
L. Xie ◽  
F. Tu ◽  
...  
Keyword(s):  
Neural Network ◽  
Optical Measurement ◽  
Life Time ◽  
Remaining Life ◽  
Neural Network Approach ◽  
Regression Methods ◽  
Signal Features ◽  
The Neural Network ◽  
Network Methods ◽  
Non Destructive

Abstract Non-destructive determination of the remaining life of coatings of gas turbine parts is highly desirable. The present paper describes early attempts to prove the feasibility of doing this based on the optical measurement of the stress in the oxide that attaches the coating to the metal component. Both regression methods and neural network methods are compared and it was found that the neural network approach was superior for the case where multiple signal features were present. All methods provide useful predictions for the idealized case considered. Challenges presented by more complicated thermal cycles are discussed briefly.

Sign in / Sign up

Export Citation Format

Share Document