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.

Use of Neural Network and Discrete Wavelet Transformations in Estimation of Road Profile

Volume 2 ◽  
2004 ◽  
Author(s):  
Mohammad Durali ◽  
Alireza Kasaaizadeh
Keyword(s):  
Neural Network ◽  
Optimization Methods ◽  
Discrete Wavelet ◽  
Feed Forward Neural Network ◽  
The Road ◽  
The Neural Network ◽  
Road Profile ◽  
Road Roughness ◽  
Coding Method ◽  
Dynamic Experiments

This paper presents a method for estimation of road profile for automotive research applications with more accuracy and higher speed. Dynamic response of a car equipped with position and velocity sensors and driving on a sample road is used as basic data. A feed-forward neural network, trained with outputs from a car model in ADAMS, is used as the car inverse model. The neural network is capable of estimating the road roughness from the car response during test drives. The ADAMS model is corrected and validated using a series of dynamic experiments on the car, performed on a hydro-pulse test rig. The only problem in this approach, like other identification and optimization methods, is the large volume of generated data in time domain, acquired from car response during road test. This problem is solved using wavelet methods to code the acquired data. Unlike all frequency methods that eliminate a large portion of the data details during processing, the wavelet coding method restores most of the details, while the volume of the stored data is kept to a minimum. The results show that this method can estimate the road profile accurately and with great savings in processing time and effort.

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.

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 KOMPARASI ALGORITMA NEURAL NETWORK DAN NAÏVE BAYES UNTUK MEMPREDIKSI PENYAKIT JANTUNG

2019 ◽  
Vol 15 (2) ◽  
pp. 189-194 ◽  
Author(s):  
Hendri Mahmud Nawawi ◽  
Jajang Jaya Purnama ◽  
Agung Baitul Hikmah
Keyword(s):  
Neural Network ◽  
Heart Disease ◽  
Naive Bayes ◽  
Healthy Lifestyle ◽  
Naïve Bayes ◽  
The Body ◽  
Early Age ◽  
Regular Exercise ◽  
The Neural Network ◽  
Bayes Algorithm

Heart disease is one of the types of deadly diseases whose treatment must be dealt with as soon as possible because it can occur suddenly to the sufferer.  Factors of heart disease that are recognized based on the condition of the body of a sufferer need to be known from an early age so that the risk of possible instant attacks can be minimized or can be overcome in various ways such as a healthy lifestyle and regular exercise that can regulate heart health in the body.  By looking at the condition of a person's body based on sex, blood pressure, age, whether or not a smoker and some indicators that become a person's characteristics of heart disease are described in a study using the Neural Network and Naïve Bayes algorithm with the aim of comparing the level of accuracy to attributes influential to predict heart disease, so the results of this study can be used as a reference to predict whether a person has heart disease or not.

1⁄4 Car Model for Suspension Trim Corrector Performances Evaluation

2016 ◽  
Vol 823 ◽  
pp. 205-210
Author(s):  
Adrian Ioan Niculescu
Keyword(s):  
Contact Force ◽  
Harmonic Functions ◽  
Degrees Of Freedom ◽  
The Body ◽  
Vertical Acceleration ◽  
Vertical Movements ◽  
The Road ◽  
Quarter Car Model ◽  
Car Model ◽  
Quarter Car

The paper presents a complex quarter car model obtained with ADAMS software, View module, useful in the first stage of suspension dimensioning and optimization.The model is equipped with compression and rebound stopper buffer and suspension trim corrector.The proposed quarter car model with two degrees of freedom (wheel and body) performs all these goals allowing changing:Geometrical elementsPosition of equilibrium, depending on vehicle load;Trim correction;Elastic and dissipative characteristics of the suspension and tire;Suspension stroke;Road profile, assessed either by simple or summation of harmonic functions or reproducing real roadsBuffers (for stroke limitation) position and characteristics;The models developed provide information on:Vertical stability assessed by vertical movements of the body and the longitudinal and transversal stability evaluated based on adherence characterized by wheel ground contact force and frequency of soil detachment wheel.Comfort assessed on the basis of body vertical acceleration and collision forces to the stroke ends.The body-road clearanceThe trim corrector efficiencyAll above performances evaluated function the road unevenness, acceleration, deceleration, turning regime.The damping characteristic is defined by damping forces at different speed for each strokes respectively one for rebound and other for compression.The contact force road-wheel is defined based tire rigidity law.The stopper buffer forces on rebound and compression are defined based each specific rigidity characteristics.The road excitation is realized with a function generator.The software allow the model evolution visualisation in real time, also generating the diagrams of displacements, forces, accelerations, speeds, for each elements or for relative evolution between diverse elements.The simulation was realized for unloaded and fully loaded car using a road generated by a sum of harmonic functions presented in equation (8).The excitation covers the specific frequencies area, being under the body frequencies up to the wheel proper frequencies.The realized ¼ car model, have reached the goal to evaluate the suspension trim correction advantages.The simulations confirm the trim corrector increases the suspension performances, thus for the analyzed case the trim corrector increase simultaneous:Body-ground clearance (evaluated by body higher increasing) between 18.5÷55.1 %Body stability (evaluated by maximal body displacement) between 9.8÷11.4 %Body comfort (evaluated by maximal body acceleration) between 3.4÷35.5 %Adherence (evaluated by maximal and RMS wheel-groundcontact force variation) between 7.0÷12.1 %Body and axles protection (evaluated by buffer strike force) between 10.8÷38.2 %

scholarly journals A Novel Neural Network-Based SINS/DVL Integrated Navigation Approach to Deal with DVL Malfunction for Underwater Vehicles

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Wanli Li ◽  
Mingjian Chen ◽  
Chao Zhang ◽  
Lundong Zhang ◽  
Rui Chen
Keyword(s):  
Neural Network ◽  
Autonomous Navigation ◽  
Underwater Vehicles ◽  
The Body ◽  
Doppler Velocity ◽  
Integrated Navigation ◽  
Body Frame ◽  
Short Term ◽  
The Neural Network ◽  
Nonlinear Autoregressive

A navigation grade Strapdown Inertial Navigation System (SINS) combined with a Doppler Velocity Log (DVL) is widely used for autonomous navigation of underwater vehicles. Whether the DVL is able to provide continuous velocity measurements is of crucial importance to the integrated navigation precision. Considering that the DVL may fail during the missions, a novel neural network-based SINS/DVL integrated navigation approach is proposed. The nonlinear autoregressive exogenous (NARX) neural network, which is able to provide reliable predictions, is employed. While the DVL is available, the neural network is trained by the body frame velocity and its increment from the SINS and the DVL measurements. Once the DVL fails, the well trained network is able to forecast the velocity which can be used for the subsequent navigation. From the experimental results, it is clearly shown that the neural network is able to provide reliable velocity predictions for about 200 s–300 s during DVL malfunction and hence maintain the short-term accuracy of the integrated navigation.

scholarly journals Effect of different parameters of heterogeneous dams on safety factor using the neural network. Case study: Marvan dam

2019 ◽  
Vol 32 (02) ◽  
pp. 126-138
Author(s):  
B. Beiranvand ◽  
A. Mohammadzade ◽  
M. Komasi
Keyword(s):  
Neural Network ◽  
Factor Of Safety ◽  
Pore Water Pressure ◽  
Water Pressure ◽  
Drainage System ◽  
Friction Angle ◽  
The Body ◽  
The Neural Network ◽  
The Cost

The drainage system is used to guide the flow of water in the earth dams. Construction of drainage in the dam body to collect and direct the drainage formed in the dam body to keep the slope dry and prevent the increase of pore water pressure in the body. One of the main goals of the designers is to find the minimum factor of safety and, consequently, reduce the cost of construction. In this study, the Marvak dam is modeled with the actual characteristics of the materials in the Geostudio software, and with the change in the dimensions of the drain, the material and the slope of the dam body, the minimum Factor of safety of the dam is obtained. In order to predict the minimum Factor of safety, a two-layer neural network has been used. With the training of the neural network based on the data obtained from heterogeneous dams, a minimum Factor of safety has been extracted for optimization of drainage. Finally, it was determined that the internal friction angle of the body material and the slope of the dam have the greatest effect on the dam factor of safety.

scholarly journals Disease Prediction Based On Retinal Images using Neural Network Classification

2019 ◽  
Vol 8 (11) ◽  
pp. 3089-3095
Keyword(s):  
Neural Network ◽  
Cardiovascular Diseases ◽  
Vascular Diseases ◽  
Retinal Vessel ◽  
The Body ◽  
Diagnostic Purpose ◽  
Physical Body ◽  
The Neural Network ◽  
Digital Imaging Technology ◽  
Segmentation Approach

the eyes used to determine the health of someone. There are several maladies in human, like vascular diseases that leave telltale markings within the retina of human eyes. The image of the retina will be captured comparatively with a camera now each day with digital imaging technology there's abundantly advanced within the technology of computer analysis of the retinal pictures were accustomed identify the consequences of diseases like cardiovascular diseases in the human body. A retinal image provides the data of what's going to happen within the body of a human. Significantly, the retinal vessel shows the condition of the cardiovascular in the physical body. Retinal pictures will offer the data concerning pathological changes within the physical body caused due to the disease in the retina that reveals cardiovascular disease, disorder, diabetes, and stroke. Computer-aided analyzed the image of the retina for the diagnostic purpose of the malady. However, automation of retinal segmentation that is difficult as a result of that the retinal pictures are noisy, distinction low, and therefore the vessel breadth often varies from very large to very tiny. Therefore, during this project, we are able to implement automatic vessel segmentation approach supported the neural network strategies to offer info regarding blood vessel and vein within the human membrane. Finally, cardiovascular diseases and therefore the alternative diseases expected victimization the distinctive technique of comparison of CENTRAL RETINAL EQUIVALENT OF VEIN and CENTRAL RETINAL EQUIVALENT OF ARTERY measurements

Використання нейронної мережі для розроблення системи уникнення перешкод на дорозі

2020 ◽  
pp. 24-33
Author(s):  
Уляна Дзелендзяк ◽  
◽  
Мішель Вигриновський ◽  
Keyword(s):  
Neural Network ◽  
The Road ◽  
The Neural Network ◽  
On The Road

The possibility of using a neural network to implement a system of avoidance of obstacles on the road has been investigated. The algorithms based on which such a system can work has been reviewed, also the principle of learning of the neural network has been considered. In order to implement investigation the simulator based on Unity and ML Agents has been developed. Using simulator the efficiency of education and this neural network in different configurations has been investigated.

Sign in / Sign up

Export Citation Format

Share Document