Refine Your Search

Search Results

Viewing 1 to 6 of 6
Technical Paper

The Driving Behavior Data Acquisition and Identification Based on Vehicle Bus

This research is based on the Controller Area Network (CAN) bus, and briefly analyzed its communication protocol with reference to the layered model of Open System Interconnect Reference Model (OSI). Subsequently, a data acquisition system was designed and developed including a Vehicle Communication Interface (VCI) and a laptop. After the overall architecture was built, the communication mechanism of the VCI was studied. Furthermore, the lap top app was built using the layered design followed by the implementation of a scheme for data collection and experimentation involving the test driving of a real car on road. Finally, the driving style was identified by means of fuzzy reasoning and solving ambiguity based on fuzzy theory; via training the acceleration sample and forecast using the excellent learning and generalization ability of Support Vector Machine (SVM) for high-dimensional, finite samples.
Technical Paper

Nonlinear System Identification of Road Simulation Platform

On road simulation, both the traditional iterative method based on frequency response function (FRF) and adaptive control method based on the CARMA model are realized by using linear model to identify the target test system. However the real test system is very complicated because of various nonlinear factors. Linear models approximately describe the system only in a small range. Therefore, system simulation methods can not be used to validate the developed control algorithm and the uncertainty of test accordingly increases. As mentioned above, this paper presents a model to identify the nonlinear test system using NARMA dynamic neural network and discusses how to make the model parameters in detail. Using the test input-output series data, this network was trained by Levenberg-Marquardt method. Results of verification simulation show the validation of the nonlinear model.
Technical Paper

Driving Fatigue Detection based on Blink Frequency and Eyes Movement

The development of the vehicle quantity and the transportation system accompanies the rise of traffic accidents. Statistics shows that nearly 35-45% traffic accidents are due to drivers’ fatigue. If the driver’s fatigue status could be judged in advance and reminded accurately, the driving safety could be further improved. In this research, the blink frequency and eyes movement information are monitored and the statistical method was used to assess the status of the driving fatigue. The main tasks include locating the edge of the human eyes, obtaining the distance between the upper and lower eyelids for calculating the frequency of the driver's blink. The velocity and position of eyes movement are calculated by detecting the pupils’ movement. The normal eyes movement model is established and the corresponding database is updated constantly by monitoring the driver blink frequency and eyes movement during a certain period of time.
Technical Paper

Big-Data Based Online State of Charge Estimation and Energy Consumption Prediction for Electric Vehicles

Whether the available energy of the on-board battery pack is enough for the driver’s next trip is a major contributor in slowing the growth rate of Electric Vehicles (EVs). What’s more, the actual capacity of the battery pack depend on so many factors that a real-time estimation of the state of charge of the battery pack is often difficult. We proposed a big-data based algorithm to build a battery pack dynamic model for the online state of charge estimation and a stochastic model for the energy consumption prediction. And the good performance of sensors, high-bandwidth communication systems and cloud servers make it convenient to measure and collect the related data, which are grouped into three categories: standard, historical and real-time data. First a resistance-capacitance ( RC )-equivalent circuit is taken consideration to simplify the battery dynamics.
Technical Paper

Analysis and Modeling of Transmission Efficiency of Vehicle Driveline

This work analyzes the transmission efficiency of vehicle driveline including the gearbox, universal transmission and differential. Based on the structure of transmission, mathematic models are built to analyze transmission's characteristics. However, an experiment reveals the limitation of this method. Then, the paper statistically analyzes the experimental data and mainly analyzes the influencing factors. Then Neural Network is used to build the efficiency model. A method called “filling data and gradually extrapolating” is used when building neural network model. Finally, the neural network model is used in the simulation of fuel consumption. The conclusion is Neural Network model can imitate the transmission efficiency of vehicle driveline efficiently, but its internal structure is not clear so other modeling methods are needed to be found.
Journal Article

A Wavelet Neural Network Method to Determine Diesel Engine Piston Heat Transfer Boundary Conditions

This paper presents a method of calculating temperature field of the piston by using a wavelet neural network (WNN) to identify the unknown boundary conditions. Because of the complexity of the heat transfer and limitations of experimental conditions of heat transfer analysis of the piston in a diesel engine, boundary conditions of the piston temperature field were usually obtained empirically, and thus the result itself was uncertain. By employing the capability of resolution analysis from a wavelet neural network, the method obtains improved boundary heat transfer coefficients with a limited number of measured temperatures. Using FEA software iteratively, results show the proposed wavelet neural network analysis method improves the prediction of unknown boundary conditions and temperature distribution consistent with the experimental data with an acceptable error.