Yang Zhifa

An active driver fatigue identification technique using multiple physiological features

A system that can actively monitor the drivers fatigue level in real time is urgently needed for the prevention of accidents. Support vector machine (SVM) technique is used to identify drivers fatigue based on psychological features, such as EEG and ECG. Drivers fatigue is expressed as alert, mild fatigue, deep fatigue and drowsiness, and they are used as output variables of SVM model. Field experiments are carried out in JiangYan freeway to collect the required data to validate the SVM model. Results show that the model can recognize drivers fatigue levels effectively and recognition precisions of all states are larger than 87.5%.

The brake system reliability evaluation of a type of Jiefang truck based on GO methodology

The basic process of modeling of GO methodology was analyzed, the key steps and notes was pointed out. After analyzing the structure of Jiefang truck brake system, according the principle of GO methodology, the GO figure of the brake system was built; state combination and value of all parts was calculated by qualitative GO operation, and the reliability of this brake system was calculated by quantitative GO operation. From the results, when all parts work successfully, the reliability of this brake system is 72.17%.

Research on method for real-time monitoring dynamic vehicle loading based on multi-sensors

In view of real-time monitoring dynamic vehicle loading, a nonlinear quarter-vehicle vibration model with two degrees of freedom and four parameters was established. The dynamic performance of suspension under different operating conditions was simulated. The general linear relation of dynamic suspension load and displacement was obtained through phase plane method. According to simulation results, a method for analyzing dynamic vehicle loading based on multi-sensors was put forward. A system of monitoring dynamic vehicle load status was designed and developed, which was installed on a FAW CA1169PK2L2EA80 heavy-duty truck and calibrated. Road tests were fulfilled under A-level road, 30 km/h and pre-set change of position of goods. The results of road tests showed that this method could real-time monitor the change of vehicle loading, which provided a new method of early-warning abnormal vehicle loading status.

System of real-time monitoring dynamic vehicle load status

In order to Real-time monitoring of vehicle load status, device for measuring suspension displacement with overload protection function had been operated on collecting information of vehicle axle load in this research, then the axle load signal with noise was filtered by using the EMD method and steady-state values of load were obtained. A monitoring system of vehicle load status was designed on FAW truck based on above key technologies. the system uses the vehicle terminal microcontroller acquisition and processing axle load voltage signal which sensor output, processed load information was output to the PC and displayed by the Human-Computer Interaction to achieve the purpose of real-time monitoring of the load status. Finally, system was tested in the conditions of different load, speed, type of road; measurement error is less than 5% that meet the requirement of real-time monitoring of vehicle loading status. This research laid the foundation for follow-up development of vehicle early-warning technology.

Study on the simulation model of landscape impact on traffic safety in road traffic system

Landscape is one of main impact factors to traffic safety; through simulation to study the inherent relationship between road-side landscape and road safety is an extremely effective means and methods; quality of models will decided the validity of simulation. As a starting point of the sight-distance (SD), considering the main impact factors and the impact discipline, driver model, vehicle model, road model and landscape model are built. These models will provide basis for estimating the effect of landscape impact on traffic safety in simulation.