Search Results

With the capability of avoiding failure in advance, failure prediction model is important not only to end users, but also to the service engineers in vehicle industry. This paper proposes an approach based on anomaly detection algorithms and telematic data to predict the failure of the engine air system with Turbo charger. Firstly, the relationship between air system and all obtained features are analyzed by both physical mechanism and data-wise. Then, the features including altitude, air temperature, engine output power, and charger pressure are selected as the input of the model, with the sampling interval of 1 minute. Based on the selected features, the healthy state for each vehicle is defined by the model as benchmark. Finally, the ‘Medium surface’ is determined for specific vehicle, which is a hyperplane with the medium points of the healthy state located at, to detect the minor weakness symptom (sub-health state).

With the rapid advancement in intelligent vehicle technologies, comprehensive environmental perception has become crucial for achieving higher levels of autonomous driving. Among various perception tasks, monitoring road types and evenness is particularly significant. Different road categories imply varied surface adhesion coefficients, and the evenness of the road reflects distinct physical properties of the road surface. This paper introduces a two-stage road perception framework. Initially, the framework undergoes pre-training on a large annotated drivable area dataset, acquiring a set of pre-trained parameters with robust generalization capabilities, thereby endowing the model with the ability to locate road areas in complex regions.

In order to realize the series-parallel switching control of hybrid electric vehicle (HEV) with dual-motor hybrid configuration, a method of unpowered interrupt switching based on the coordinated control of three power sources was proposed by analyzing the series-parallel driving mode of the dual-motor hybrid configuration. The series to parallel switching process is divided into three stages: speed regulation stage, clutch combination and power source switching. The distribution control of speed regulating torque is carried out in the speed regulating stage. The speed adjustment torque is preferentially allocated to the power source of the input shaft (engine and P1) to carry out the lifting torque. Due to the high speed adjustment accuracy and fast response of the P1 motor, the input shaft is preferentially allocated to P1 for speed adjustment, that is, the torque intervention of P1.

Ammonia and methanol are both future fuels with carbon-neutral potential. Ammonia has a high octane number, a slow flame speed, and a narrow ignition limit, while methanol has a fast flame speed with complementary combustion characteristics but is more likely to lead to pre-ignition and knock. In this paper, the combustion and emission characteristics of ammonia-methanol solution in a high compression ratio spark ignition engine are investigated. The experimental results show that the peak in-cylinder pressure and peak heat release rate of the engine when using ammonia-methanol solution are lower and the combustion phase is retarded compared with using methanol at the same spark timing conditions. Using ammonia-methanol solution in the engine resulted in a more ideal combustion phase than that of gasoline, leading to an increase in indicated thermal efficiency of more than 0.6% and a wider range of efficient operating conditions.

Ammonia (NH3), a zero-carbon fuel, has great potential for internal combustion engine development. However, its high ignition energy, low laminar burning velocity, narrow range of flammability limits, and high latent heat of vaporization are not conducive for engine application. This paper numerically investigates the feasibility of utilizing ammonia in a heavy-duty diesel engine, specifically through low-pressure direct injection (LP-DI) of hydrogen to ignite ammonia combustion. Due to the lack of a well-corresponding mechanism for the operating conditions of ammonia-hydrogen engines, this study serves only as a trend-oriented prediction. The paper compares the engine's combustion and emission performance by optimizing four critical parameters: excess air ratio, hydrogen energy ratio, ignition timing, and hydrogen injection timing. The results reveal that excessively high hydrogen energy ratios lead to an advanced combustion phase, reducing indicated thermal efficiency.

Lean combustion is an approach to achieving higher thermal efficiency for spark ignition engines. However, it faces low burning velocity and unstable combustion problems near the lean flammability limits region. The current work is attempting to investigate the combustion characteristics of iso-octane flame with 0% and 30% H2 up to near lean limits (λ = 1.7) at 100-300 kPa and 393-453 K. The flame appeared spherically by 37 mJ spark energy at λ = 0.8-1.2, whereas the ultra-lean mixtures, λ ≥ 1.3, ignited at 3000 mJ under wrinkles and buoyancy effects. The impact of initial pressure and temperature on the lean mixture was stronger than the stoichiometric mixture regarding flame radius and diffusional-thermal instability. The buoyancy appeared at the highest burning velocity of 27.41 cm/s.

Accurate identification of driver’s braking intention is essential in advanced driver assistance system and can make the driving process more comfortable and trustworthy. In this paper, a novel method for driver braking intention identification in cut-in scenarios was proposed by using driver’s gaze information and motion information of cut-in vehicles. Firstly, a "looking in and looking out" experimental platform including three eye-tracking cameras and one front-view camera was built to collect driver's gaze information and the vehicle motion information. Secondly, driver’s gaze features and motion features of cut-in vehicles were selected and the braking intention identification performance of several decision tree-based ensemble learning algorithms was compared. Thirdly, the feature importance was analyzed by using SHAP (SHapley Additive exPlanations) values. This novel method of braking intention identification makes full use of in-vehicle camera sensors.

This work presents a multi-objective adaptive cruise control (ACC) system via deep reinforcement learning (DRL). During the control period, it quantitatively considers three indexes: tracking accuracy, riding comfort, and fuel economy. The system balances contradictions between different indexes to achieve the best overall control results. First, a hierarchical control architecture is utilized, where the upper level controller is synthesized under DRL framework to give out the vehicle desired acceleration. The lower level controller executes the command and compensates vehicle dynamics. Then, four state variables that can comprehensively determine the car-following states are selected for better convergence. Multi-objective reward function is quantitatively designed referring to the evaluation indexes, in which safety constraints are considered by adding violation penalty. Thereafter, the training environment which excludes the disturbance of preceding car acceleration is built.

Octane number (ON) and octane sensitivity (S), the fuel anti-knock indices, are critical for the design of advanced jet ignition engines. In this study, ten fuels with different research octane number (RON) and varying S were formulated based on ethanol reference fuels (ERFs) to investigate the effect of S on combustion of jet ignition engine. To fully understand S effects, the combustion characteristics under EGR dilution and lean burn were further investigated. The results indicated that increasing S resulted in higher reactivity with shorter ignition delay and combustion duration. The increase of reactivity led to heavier knocking intensity. The competition between the flame speed and the reactivity of the mixture determined the auto-ignition fraction of mixture and the knocking onset crank angle as S varied. Medium S (S=3) was helpful to improve the combustion speed, reduce the auto-ignition fraction of mixture and retard the knocking onset crank angle.

A feasible method was developed to reconstruct the three-dimensional flame surface of SI combustion based on 2D images. A double-window constant volume vessel was designed to simultaneously obtain the side and bottom images of the flame. The flame front was reconstructed based on 2D images with a slicing model, in which the flame characteristics were derived by slicing flame contour modeling and flame-piston collision area analysis. The flame irregularity and anisotropy were also analyzed. Two different principles were used to build the slicing model, the ellipse hypothesis modeling and deep learning modeling, in which the ellipse hypothesis modeling was applied to reconstruct the flame in the optical SI engine. And the reconstruction results were analyzed and discussed. The reconstruction results show that part of the wrinkled and folded structure of the flame front in SI engines can be revealed based on the bottom view image.

According to the statistics of National Highway Traffic Safety Administration, driver’s cognitive distraction, which is usually caused by drivers using mobile phones, has become one of the main causes of traffic accidents. To solve this problem and guarantee the safety of man-vehicle-road system, the most critical work is to improve the accuracy of driver’s cognitive state detection. In this paper, a novel driver’s cognitive state detecting method based on LightGBM (Light Gradient Boosting Machine) is proposed. Firstly, cognitive distraction experiments of making calls are carried out on a driving simulator to collect vehicle states, eye tracking and EEG (electron encephalogram) data simultaneously and feature extraction is conducted. Then a classifier considering road and individual characteristics used for detecting cognitive states is trained based on LightGBM algorithm, with 3 predefined cognitive states including concentration, ordinary distraction and extreme distraction.

Fuel quality has a significant influence on the combustion engine operation. In recent years the increasing concerns about environmental protection, energy saving, energy security and the requirements of protecting fuel injection and aftertreatment systems have been major driving forces for the Chinese fuel specification evolution. The major property changes in the evolution of Chinese national gasoline and diesel standards are introduced and the reasons behind these changes are analyzed in this paper. The gasoline fuel development from State I to State VI-B involved a decrease of sulfur, manganese, olefins, aromatics and benzene content. The diesel fuel quality improvement from State I to State VI included achieving low sulfur fuels and a cetane number (CN) increase. Provincial fuel standards, stricter than corresponding national standards, were implemented in economically developed areas in the past.

Forecasting the motion of the leading vehicle is a critical task for connected autonomous vehicles as it provides an efficient way to model the leading-following vehicle behavior and analyze the interactions. In this study, a personalized time-series modeling approach for leading vehicle trajectory prediction considering different driving styles is proposed. The method enables a precise, personalized trajectory prediction for leading vehicles with limited inter-vehicle communication signals, such as vehicle speed, acceleration, space headway, and time headway of the front vehicles. Based on the learning nature of human beings that a human always tries to solve problems based on grouping and similar experience, three different driving styles are first recognized based on an unsupervised clustering with a Gaussian Mixture Model (GMM).

The combustion characteristics and soot emissions of three types of fuels were studied in a high pressure and temperature vessel. In order to achieve better volatility, proper cetane number and high oxygen content, the newly designed WDEP fuel was proposed and investigated. It is composed of wide distillation fuel (WD), PODE3-6 mixture (PODEn) and ethanol. For comparison, the test on WD and the mixture of PODEn-ethanol (EP) are also conducted. OH* chemiluminescence during the combustion was measured and instantaneous PLII was also applied to reveal the soot distribution. Abel transformation was adopted to calculate the total soot of axisymmetric flame. The results show that WDEP has similar ignition delays and flame lift-off lengths to those of WD at 870-920 K. But the initial ignition locations of WDEP flame in different cycles were more concentrated, particularly under the condition of low oxygen atmosphere.

Plug-in electric vehicle (PHEV) has a promising prospect to reduce greenhouse gas (GHG) emission and optimize engine operating in high-efficiency region. According to the maximum electric power and all-electric range, PHEVs are divided into two categories, including “all-electric PHEV” and “blended PHEV” and the latter provides a potential for more rational energy distribution because engine participates in vehicle driving during aggressive acceleration not just by motor. However, the frequent use of engine may result in severe emissions especially in low state of charge (SOC) and ahead of catalyst light-off. This study quantitatively investigates the impact of oil viscosity and driving mode (hybrid/conventional) on oil dilution and emissions including particle number (PN).

Batteries are exposed to dynamic load during vehicle driving. It is significant to clarify the load input of the battery system during vehicle driving for battery pack structural design and optimization. Currently, bolt connection is mostly applied for battery pack constraint to vehicle, as well as for module assembly inside the pack. However, accurate bolt load is always difficult to obtain, while directly force measurement is expensive and time consuming in engineering. In this paper, a precise data driven model based on Elman neural network is established to identify the dynamic bolt loads of the battery pack, using tested acceleration data near bolts. The dynamic bolt force data is measured at the same time with the acceleration data during vehicle running in different driving conditions, utilizing customized bolt force sensors.

The use of deposit control additives in European market gasoline is well documented for maintaining high levels of engine cleanliness and subsequent sustained fuel and emissions performance. Co-ordinating European Council (CEC) industry fuels tests have played a crucial role in helping to drive market relevant, effective and low-cost deposit control additives into European market fuels. Until now, there hasn’t been a Gasoline Direct Injection engine test available to fuel marketers in any market globally. However, a new CEC engine test is currently being developed to address that gap. Based on an in-house VW injector coking test, it shows promise for becoming a useful tool with which to develop and measure the performance of deposit control additives. A key requirement of industry tests should be to replicate issues seen in consumer vehicles, thereby providing a platform for relevant solutions.

The ignition of lubricating oil droplet has been proved to be the main factor for pre-ignition and the following super-knock in turbocharged gasoline direct injection engine. In this paper, the ignition process of lubricating oil droplet in combustible ambient gaseous mixture was investigated in a rapid compression machine (RCM). The pre-ignition induction by oil droplet of the ambient gaseous mixture was analyzed under different initial droplet volume and effective temperature conditions. The oil droplet was suspended on a tungsten fiber in the combustion chamber and the ignition process was recorded by a high-speed camera through the quartz window mounted at the end of the combustion chamber. The pressure traces were also obtained by a sensor in order to get the ignition delay and analyze the combustion process in detail.

Compression ratio and specific heat ratio are two dominant factors influencing engine thermal efficiency. Therefore, ultra-lean burn may be one method to deal with increasingly stringent fuel consumption and emission regulations in the approaching future. To achieve high efficiency and clean combustion, innovative combustion modes have been applied on research engines including homogeneous charge compression ignition (HCCI), spark-assisted compression ignition (SACI), and gasoline direct-injection compression ignition (GDCI), etc. Compared to HCCI, SACI can extend the load range and more easily control combustion phase while it is constrained by the limit of flame propagation. For SACI with ultra-lean burn in engines, equivalence ratio (φ), rich-fuel mixture around spark plug, and supercharging are three essentials for combustion stability.

Polyoxymethylene dimethyl ethers (PODEn) have high cetane number, high oxygen content and high volatility, therefore can be added to gasoline to optimize the performance and soot emission of Gasoline Compression Ignition (GCI) combustion. High speed imaging was used to investigate the spray and combustion process of gasoline/PODEn blends (PODEn volume fraction 0%-30%) under various ambient conditions and injection strategies in a constant volume vessel. Results showed that with an increase of PODEn proportion from 10% to 30%, liquid-phase penetration of the spray increased slightly, ignition delay decreased from 3.8 ms to 2.0 ms and flame lift off length decreased 29.4%, causing a significant increase of the flame luminance. For blends with 20% PODEn, when ambient temperature decreased from 893 K to 823 K, the ignition delay increased 1.3 ms and the flame luminance got lower.