Estimation of Acceleration Amplitude of Vehicle by Back Propagation Neural Networks

Abstract

This paper investigates the variation of vertical vibrations of vehicles using a neural network (NN). The NN is a back propagation NN, which is employed to predict the amplitude of acceleration for different road conditions such as concrete, waved stone block paved, and country roads. In this paper, four supervised functions, namely, newff, newcf, newelm, and newfftd, have been used for modeling the vehicle vibrations. The networks have four inputs of velocity ( ), damping ratio ( ), natural frequency of vehicle shock absorber ( ), and road condition (R.C) as the independent variables and one output of acceleration amplitude (AA). Numerical data, employed for training the networks and capabilities of the models in predicting the vehicle vibrations, have been verified. Some training algorithms are used for creating the network. The results show that the Levenberg-Marquardt training algorithm and newelm function are better than other training algorithms and functions. This method is conceptually straightforward, and it is also applicable to other type vehicles for practical purposes.

Research on Improvement of Truck Vibration Based on Systematic G8D Method

“…e damping force of the shock absorber of the front axle is not large enough [29]; when the front axle resonates, the amplitude of the resonance cannot be attenuated to the design level; the shock absorbers of the engine and the cab are unable to provide sufficient damping because of inconsistent manufacturing quality. Figure 3, the vertical acceleration of the middle rear axle near 65 km/h is large [30], up to 4.76 m/s 2 ; magnified to 5.21 m/s 2 from the rear axle spring to the frame (at balance suspension). From the frame to the cab, the cab front suspension amplifies the vibration (1.78 m/s 2 to 3.05 m/s 2 ) and the cab rear suspension attenuates the vibration (3.11 m/s 2 to 2.05 m/s 2 ).…”

Comparison of Support Vector Machine‐Based Techniques for Detection of Bearing Faults

“…SVM is a learning method based on statistical theory and risk minimization [7]. Its core idea is to transform the problem of linear inseparability through the kernel formula, and then find the best classification surface in the space and the solution to the problem using convex quadratic programming [8]. It successfully solved over learning and the local minimum problem.…”

Corrigendum to “Estimation of Acceleration Amplitude of Vehicle by Back Propagation Neural Networks”

“…e article titled "Estimation of Acceleration Amplitude of Vehicle by Back Propagation Neural Networks" [1] was found to contain material from Yildirim and Uzmay [2], which was cited. Details of the similarity are as follows:…”