Ontology-based approach for legal provision retrieval

In this paper, we present an ontology-based approach for legal provision retrieval. The approach aims at assisting the man who knows little about legal knowledge to inquire appropriate provisions. Legal ontology and legal concept probability model are main functional components in our approach. Legal ontology is extracted from Chinese laws by the natural language processing (NLP) techniques. Legal concept probability model is built from corpus, and the model is used to bridge the gap between legal ontology and natural language inquiries.     

Mining evolving association rules for e-business recommendation

Association analysis is an effective data mining approach capable of unveiling interesting associations within a large dataset. Although widely adopted in e-business areas, it still has many difficulties when applied in practice. For instance, there is a mismatch between the static rules discovered and the drifting nature of the user interests, and it is difficult to detect associations from a huge volume of raw user data. This paper presents an effective approach to mine evolving association rules in order to tackle these problems. It is followed by a recommendation model based on the evolving association rules unveiled. Experimental results on an online toggery show that it can effectively unveil people’s shifting interests and make better recommendations accordingly.     

Effects of Injection Timing on Transient Performance of A Regulated Two-Stage Turbocharged Diesel Engine with Turbine Bypass Valve

The object of this paper is to reduce soot emissions under typical 5s transient conditions of constant speed and increasing torque. And effects of fuel injection timing on combustion and emissions parameters were experimentally and numerically studied in a regulated two-stage turbocharged diesel engine with a turbine bypass valve (TBV). The test results indicated that: the smaller TBV opening could improve deterioration of smoke emissions and BSFC at medium and heavy loads. Afterward, the full-stage injection timing (FSIT) strategies (delaying injection timing during the entire transient process) could reduce soot and NO_X emissions simultaneously. However, when TBV opening became larger, smoke emissions and BSFC were deteriorated gradually. Moreover, the sectional-stage injection timing (SSIT) strategies (advancing injection timing from 10 % load to a preset load and delaying injection timing from the preset load to 100 % load) could markedly reduce soot emissions by 75.8 % with TBV opening 20 %; the degradation of fuel consumption could be effectively suppressed. Finally, coupling the SSIT strategies with the TBV control strategies could significantly improve the transient performance.     

Vehicle stability control based on driver’s emergency alignment intention recognition

In this work, the reference model modification strategy for vehicle stability control based on driver's intention recognition under emergent obstacle avoidance situation was proposed. First the conflicts between the driver's emergency alignment (EA) intention and vehicle response characteristics were analyzed in critical emergent obstacle avoidance situation. Second combining steering wheel angle and its speed, the driver's EA intention was recognized. The reference model modification strategy based on steering operation index (SOI) was presented. Then a LQR model following controller with tire cornering stiffness adaption was used to generate direct yaw moment for tracking modified reference yaw rate and reference sideslip angle. Finally based on the four-in-wheel-motor-drive (FIWMD) electric vehicles (EV), double lane change and slalom tests were conducted to compare the results using modified reference model with the results using normal reference model. The experimental tests have proved the effectiveness of the reference model modification strategy based on driver's intention recognition.     

Hydraulic retarders for heavy vehicles: Analysis of fluid mechanics and computational fluid dynamics on braking torque and temperature rise

Hydraulic retarders are auxiliary braking devices that reduce the velocity of a vehicle, particularly when a vehicle is driven downhill. Such velocity reduction could reduce the potential risk caused by brake failure caused by the service brake working for a long time and the temperature of the brake shoe becomes extremely high. This paper introduces the construction of the hydraulic retarder and proposes two mathematical models for the hydraulic retarder. The first mathematical model is deduced by using fluid mechanics, which is used to analyze the mechanism of how braking torque is produced and the key factors that can influence the value of the braking torque. The second mathematical model is deduced by using thermodynamics, which is used to quantify the heat produced by the hydraulic retarder. This research emphasizes that the flow rate and the average velocity of the working fluid in the working chamber mainly determine the braking torque of the hydraulic retarder. The flow rate into and out of the working chamber determines the temperature rise of the working fluid. Computational fluid dynamics (CFD) simulations are conducted with the Reynolds-averaged Navier-Stokes (RANS) and Shear Stress Transport (SST) turbulent models. Experiments are carried out to justify the two mathematical models and the CFD simulations. The results show that the mathematical models are capable of describing the force analysis and energy conversion of the hydraulic retarder and SST is more accurate for CFD simulation and the error is within 6 %.     

Iterative Learning Control Algorithm for Feedforward Controller of EGR and VGT Systems in a CRDI Diesel Engine

The modern diesel engines equip the exhaust gas recirculation (EGR) system to suppress the NOx emissions. In addition, the variable geometric turbocharger (VGT) system is installed to improve the drivability and fuel efficiency. These EGR and VGT systems have cross-coupled behavior because they interact with the intake and the exhaust manifolds. Furthermore, the turbocharger time delay, gas flow dynamics through EGR pipe cause the nonlinearity characteristics. These nonlinear multi-input-multi-output characteristics cause the degradation of control accuracy, especially during the transient condition. In order to improve the control accuracy, this study proposes an iterative learning control (ILC) algorithm for feedforward controller of EGR and VGT systems. The feedforward controller obtains the values about EGR and VGT actuators using the previous control results in predefined transient states. The ILC algorithm consists of a PD-type learning function and a low-pass filter. The control gains of learning function are determined to guarantee the convergence of learning results. In addition, the low-pass filter is designed for robustness against plant disturbance. The proposed control algorithm was validated by engine experiment which repeated predefined transient states. The error was reduced by 15 % according to the gain. As a result, the proposed algorithm is affordable for improving the transient control performance.     

Autonomous Emergency Braking Considering Road Slope and Friction Coefficient

The Autonomous Emergency Braking (AEB) systems have been actively studied for the safety enhancement and commercialized for the past few years. Because the driver tends to overly rely upon active safety systems, AEB needs to be designed to reflect the real road situations such as various road slope and friction coefficient. In this study, an AEB control algorithm is proposed to compensate for the effects of the slope and the friction of road. Based on the maximum possible deceleration for the real road conditions, the minimum braking distance is described with margin parameters for AEB activation control. The deceleration controller with a feedforward term is designed to avoid the collision during AEB operation on real road conditions. The proposed algorithm is validated in simulations first and the experimental verification is performed in the various slope conditions.     

Development of a Driving Behavior-Based Collision Warning System Using a Neural Network

An advanced driver assistance system (ADAS) uses radar, visual information, and laser sensors to calculate variables representing driving conditions, such as time-to-collision (TTC) and time headway (THW), and to determine collision risk using empirically set thresholds. However, the empirically set threshold can generate differences in performance that are detected by the driver. It is appropriate to quickly relay collision risk to drivers whose response speed to dangerous situations is relatively slow and who drive defensively. However, for drivers whose response speed is relatively fast and who drive actively, it may be better not to provide a warning if they are aware of the collision risk in advance, because giving collision warnings too frequently can lower the reliability of the warnings and cause dissatisfaction in the driver, or promote disregard. To solve this problem, this study proposes a collision warning system (CWS) based on an individual driver’s driving behavior. In particular, a driver behavior model was created using an artificial neural network learning algorithm so that the collision risk could be determined according to the driving characteristics of the driver. Finally, the driver behavior model was learned using actual vehicle driving data and the applicability of the proposed CWS was verified through simulation.     

Component Sizing of Parallel Hybrid Electric Vehicle Using Optimal Search Algorithm

In designing a parallel hybrid electric vehicle, it is essential to select the optimal capacity of power sources and the optimal gear ratio of the torque coupler. The capacity of the power sources and the gear ratio of the torque coupler should be optimized simultaneously. However, since this process is excessively time-consuming, previous studies have selected the gear ratio of the torque coupler and then selected the capacity of power source. However, this approach cannot guarantee global optimization. In this paper, a feasible region is defined to satisfy the required performance of vehicle such as maximum speed, hill-climbing. and feasible points are selected inside the feasible region. In the conventional technique, the global optimal solution is obtained by simulating all feasible points. In the optimization technique, optimal points are simulated within the feasible region using several optimal search algorithms, such as the golden section search algorithm and the hillclimbing search algorithm. And using these algorithms, the number of simulations is reduced and the capacity of the power source and the gear ratio of the torque coupler are optimized simultaneously. Finally, the validity of the component sizing results is verified by comparing the global optimal solution obtained by applying the conventional technique with the solution obtained by applying the proposed optimization technique.     

Load Transfer Analysis of a Bus Bay Section Under Standard Rollover Test Using <Emphasis Type="Italic">U</Emphasis>*<Subscript>M</Subscript> Index

Bus rollover accidents are receiving increasing attention due to the associated high fatality rate. In order to improve the bus structural performance during the rollover collision, it is necessary to investigate how the impact force is transferred within the bus superstructure. This paper introduced a method for studying the load transfer behavior of the bus superstructure during the standard rollover test by using the U * _M index. A bus bay section was used as the sample structure to demonstrate the proposed method. The result of the paper reveals that the load transfer analysis based on the U * _M index can provide engineers with the insight of the structural issues and the direction to improve the structural performance, which cannot be accomplished through the conventional finite element analysis.