Şahin Yildirim

Vibration control of vehicle active suspension system using a new robust neural network control system

The main problem of vehicle vibration comes from road roughness. For that reason, it is necessary to control vibration of vehicle’s suspension by using a robust artificial neural network control system scheme. Neural network based robust control system is designed to control vibration of vehicle’s suspensions for full suspension system. Moreover, the full vehicle system has seven degrees of freedom on the vertical direction of vehicle’s chassis, on the angular variation around X-axis and on the angular variation around Y-axis. The proposed control system is consisted of a robust controller, a neural controller, a model neural network of vehicle’s suspension system. On the other hand, standard PID controller is also used to control whole vehicle’s suspension system for comparison. Consequently, random road roughnesses are used as disturbance of control system. The simulation results are indicated that the proposed control system has superior performance at adapting random road disturbance for vehicle’s suspension.

Noise and Vibration Analysis of Car Engines using Proposed Neural Network

An experimental design method for noise and vibration analysis of two car engines by feedforward and radial basis neural networks is presented. Two types of car engines are experimentally analyzed by using intelligent data acquisition card with software. Measured vibration and noise parameters of two car engines are used as desired values of the neural networks. The effectiveness of using Radial Basis Neural Network (RBNN) with backpropagation algorithm is demonstrated for predicting the vibrations and noises of two car engines. The robustness of the proposed RBNN predictor to parameters of vibration and noise as well measurement disturbances is investigated. The result of experiments and simulation show that the proposed RBNN is able to adapt effectively under disturbances.

Neural network applications to vehicle's vibration analysis

Abstract This paper investigates the variation of vertical vibrations of vehicles using a neural network (NN). The NN is a radial basis NN, which is employed to predict the amplitude of acceleration for different road conditions such as concrete, waved stone block paved and country roads. Proposed neural system is also tested for different natural frequencies of the vehicle’s body and the damping ratios of shock absorber. This method is conceptually straightforward, and it is also applicable to other type vehicles for practical purposes.

Sound quality analysis of cars using hybrid neural networks

Abstract In this paper, a procedure of testing and evaluation on the sound quality of cars are proposed and sound quality is analysed through the cars’ road running test on the providing ground, which was carried out with varying running speed. In addition to this experimental analysis, a neural network predictor is also designed to model the system for possible experimental applications. The proposed neural network is a recurrent type network, which consists of two types of neuron function in the hidden layer. As basic factors for sound quality, only objective factors are considered such as loudness, sharpness, speech intelligibility, and sound pressure level. The correlation between sound pressure level and another factor are discussed from a point of view of running speed dependency. Results of both computer simulations and experiments show that the neural predictor algorithm gives good results at accommodating different cases and provides superior prediction on two cars’ sound analysis.

Vibration analysis of an experimental suspension system using artificial neural networks

This study analyzes effects of vibrations on comfort and road holding capability of vehicles as observed in variations of suspension springs, road roughness etc. Also, design of non-linear experimental car suspension system for ride qualities using neural networks is presented. Proposed active suspension system has been found more effective in vibration isolation of car body than linear active suspension system. Proposed neural network predictor could be used in vehicle’ s suspension vibration analysis .

Analysis of pressure variations on journal bearing system using artificial neural network

This paper investigates the pressure variations on the steel shafts on the journal bearing system with low temperature and variable speed. This paper mainly consist of two parts, experimental and simulation. In the experimental work, journal bearing system is tested with different shafts speed and temperature conditions. The temperature of the systems working conditions was under minus. The collected experimental data such as pressure variations are employed as training and testing data for an artificial neural network. The neural network is a feed forward three layered network. Quick propagation algorithm is used to update the weight of the network during the training. Finally, neural network predictor has superior performance for modelling journal bearing systems with load disturbances.

Neural Network Analysis of Leakage Oil Quantity in the Design of Partially Hydrostatic Slipper Bearings

This paper presents an investigation for analyzing the efficiency of axial piston pumps in a variety conditions using a proposed neural network. Since slippers affect the performance of the system considerably, the effects of surface roughness on lubrication have been studied in slippers with varying hydrostatic bearing areas and surface roughness. The neural network structure is very suitable for this kind of system. The network is capable of predicting the leakage oil quantity of the experimental system. The network has parallel structure and fast learning capacity. It is also easy to see from the experimental results that the leakage oil quantity was caused by surface roughness, orifice diameter and the size of hydrostatic bearing area, loading pressure and the number of rotations. It can be outlined from the results for both approaches, neural network could be modeled slipper bearing systems in real time applications.

Analysis of a hydrodynamic thrust bearing with elastic deformation using a recurrent neural network

A theoretical analysis on the general behaviour of a thrust bearing is presented in this paper. The model programme using a method adaptation of finite differences was developed to solve the Reynolds equation for lubrication. The model in the theoretical analysis uses a single one-dimensional grid. The altering of total lubrication load obtained in the result of under-cutting in the thrust bearing have been determined together with the parameters such as oil film thickness and pressure. Parameters such as the pressure and thickness of the oil film were determined. The hydrodynamic behaviour of thrust bearing was analysed by considering of different dimensionless system pressure, speed and geometry of the bearing. The effect of the elastic load due to elastic deflection is taken into account as on the load-bearing characteristics is included. Also, a proposed neural network predictor is utilised to analyse of the general behaviour of thrust bearing. The results of the proposed neural network predictor gives superior performance for analysing of the behaviour of a thrust bearing undergoing in elastic deformation.

An artificial neural network application to fault detection of a rotor bearing system

Purpose – To improve the application neural networks predictors on bearing systems and to investigate the exact neural model of the ball‐bearing system.Design/methodology/approach – A feed forward neural network is designed to model‐bearing system. Two results are compared for finding the exact model of the system.Findings – The results of the proposed neural network predictor gives superior performance for analysing the behaviour of ball bearing undergoing loading deformation.Research limitations/implications – The results of the proposed neural network exactly follows desired results of the system. Neural network predictor can be employed in practical applications.Practical implications – As theoretical and practical study is evaluated together, it is hoped that ball‐bearing designers and researchers will obtain significant results in this area.Originality/value – This paper fulfils an identified research results need and offers practical investigation for an academic career and research. Also, It shoul...

Design of Neural Networks Model for Transmission Angle of a Modified Mechanism

This paper discusses Neural Networks as predictor for analyzing of transmission angle of slider-crank mechanism. There are different types of neural network algorithms obtained by using chain rules. The neural network is a feedforward neural network. On the other hand, the slider-crank mechanism is a modified mechanism by using an additional link between connecting rod and crank pin. Through extensive simulations, these neural network models are shown to be effective for prediction and analyzing of a modified slider-crank mechanism’s transmission angle.