Search Results

A path tracking controller is essential for an autonomous vehicle to navigate a complex environment while avoiding obstacles. Many research studies have proposed new controller designs and strategies. However, it is often unclear which control strategy is the most suitable for a specific Autonomous / ADAS user application. This study proposes a benchmark workflow by comparing different control observer models and their control strategies integration for an autonomous parking lot sweeper in a complex and dense environment at low-speed utilizing model-in-the-loop simulation. The systematic procedure consists of the following steps: (1) vehicle observer model validation (2) control strategy development (3) model-in-the-loop simulation benchmark for specific user scenarios. The kinematic and dynamic vehicle models were used to validate the truck’s behavior using physical data.

As computer-aided engineering software tools advance, more simulation-based processes are utilized to reduce development time and cost. Traditionally, during the development of a new control algorithm dyno or on-road testing is necessary to validate a new function, however, physical testing is both costly and time consuming. This study introduces a co-simulation platform and discusses its use as an improved method of powertrain control logic development. The simulation platform consists of a dynamic vehicle model, virtual road network and simulated traffic objects. Engineers can utilize Matlab/Simulink along with other programs such as PTV Vissim, Tass Prescan, and AVL Cruise to create an integrated platform capable of testing and validating new control strategies. The structure and configuration of this virtual platform is explained in this paper, and an example use case is demonstrated. A driver model was developed to simulate realistic vehicle inputs.

In this paper, a novel online coverage path planning (CPP) method for autonomous sweeper trucks in closed areas is proposed. This method can efficiently generate executable paths for sweeper trucks that cover all feasible uncleaned areas without getting tracked in dead-end, i.e., no backward behaviors required and avoid dynamic obstacles. To reach that end, a modified biological inspired neuron network method considering vehicle constrains is developed, where the dynamic of each neuron is determined by the shunting function. The path will be iteratively generated based on local neuron dynamics. In order to avoid dead-end, a detour algorithm combing with back iteration is introduced to search the nearest uncleaned area that can be reached within vehicle constrains. The proposed method is empirically approved to be computationally efficient and adaptive to maps with arbitrary shapes.

For commercial-vehicle Original Equipment Manufacturers (OEMs), predictive maintenance has drawn attention for the benefits of money saving and increased road safety. Data-driven models have been widely explored and implemented as predictive maintenance solutions. However, the working scenarios for different commercial-vehicles vary a lot, which makes it difficult to build a universal model suitable for all the cases. In this paper, we propose a Recurrent Neural Adaptive Processes (RNAPs) network to adapt to different scenarios by modeling the uncertain at the same time. The ensemble network combines the traits of neural processes, recurrent neural network and meta learning together. Neural processes consider the context information to calculate the uncertainty and improve the prediction results. Meta-learning works well when dealing with few-shot multi-tasks learning, and recurrent networks are utilized as the encoder of the proposed model to process time-series data.

In the current study, an automatic and interpretable predictive maintenance system is proposed. The system provides a fully automatic training process for predictive maintenance models without human intervention. On the other hand, as failure reasons are critical for product development. The proposed pipeline also demonstrates the interpretation on automatic trained model to present insights for engineers to acquire mechanism of interested events. To study the system, four automatic machine learning methods and two interpretation modules are evaluated for the pipeline with Isuzu’ real vehicle data correspondingly. The overall performance of the automatic and interpretable system is demonstrated as well. Key words: predictive maintenance, AutoML, interpretation

Idle Stop-and-go (ISG), also known as Auto Stop/Start, is a fuel saving technology common to many modern vehicles that enables the engine to shut down when the vehicle comes to a stop. Although it may help with fuel efficiency, many drivers in the North American market find the feature to be an annoyance due to hesitation in vehicle re-launch and engine shudder during stop or restart. This paper introduces the usage of traffic signal phase and timing (SPaT) information for controlling the activation of ISG with the goal of reducing driver complaints and increasing acceptance of the function. Previous studies proposed the utilization of Advanced Driver Assistance System (ADAS) to introduce adaptability in powertrain controls to traffic situation changes.

Recently developed gasoline engines utilize more aggressive EGR rate to meet the emissions and fuel economy regulations. The EGR temperature is often estimated by the ECU and its accuracy affects the estimations of EGR flow rate and intake air flow rate and temperature. Therefore, the accuracy of EGR temperature estimation becomes more important than ever for precise EGR rate control. Typical lookup map based EGR cooler model without the sensitivity to the coolant flow rate is acceptable and widely used if the heat capacity of the coolant side is high enough. However, the coolant flow rate under real vehicle driving conditions often visit low-speed high-load part of the engine map where the lookup map based model suffers from the accuracy issues. This paper presents an investigation of the accuracy of the lookup map based model under different heat capacity conditions. In this study, a simple EGR cooler model based on effectiveness-NTU method was also developed.

As the automotive industry faces tighter fuel economy and emission regulations, it is becoming increasingly important to improve powertrain system efficiency. One of the areas to improve powertrain efficiency is the thermal management system. By controlling how to distribute the heat rejected by the engine, especially during the warm-up stage under cold temperatures, an engine thermal management system can improve the overall energy efficiency of the powertrain system. Conventionally, engine thermal management systems have been operated by a mechanical water pump and a thermostat. However, the recent introduction of electric water pumps and electrically-controlled flow valves allow for more sophisticated control of the thermal management system. In this study, these two different thermal management system architectures are investigated by conducting simulations.

Global deployment of autonomous capability for commercial vehicles is a big challenge. In order to improve the robustness of autonomous approach under different traffic scenarios, environments, road conditions, and driver behaviors, a combined approach of virtual simulation, vehicle-in-the-loop (VIL) testing, proving ground testing, and final field testing have been established for algorithms validation. During the validation platform setup, different platforms for different functionalities have been studied, including open source virtual testing environment (CARLA, AirSim), and commercial one (IPG). We also cooperate with MCity to do proving ground validation. In virtual testing, the functionality of sensors (camera, radar, Lidar, GPS, IMU) and vehicle dynamic models can be applied in the virtual environment. In VIL testing, real world and virtual test will be connected for different validation purposes.

Field Issue (Malfunction) incidents are costly for the manufacturer’s service department. Especially for commercial truck providers, downtime can be the biggest concern for our customers. To reduce warranty cost and improve customer confidence in our products, preventive maintenance provides the benefit of fixing the problem when it is small and reducing downtime of scheduled targeted service time. However, a normal telematics system has difficulty in capturing useful information even with pre-set triggers. Some malfunction issue takes weeks to find the root cause due to the difficulty of repeating the error in a different vehicle and engineers must analyze large amounts of data. In order to solve these challenges, a machine-learning-based predictive software/hardware system has been implemented.

Water injection (WI) can improve gasoline engine performance and efficiency, and on-board water recovery technology could eliminate the need for customers to refill an on-board water reservoir. In this regard, the technical feasibility of exhaust water recovery (EWR) is described in this paper. Water injection testing was conducted at a full load condition (5000 rpm/18.1 bar BMEP) and a high load condition (3000 rpm/14.0 bar BMEP) on a turbocharged gasoline direction injection (GTDI) engine. Water recovery testing was conducted both after the exhaust gas recirculation (EGR) cooler and after the charge air cooler (CAC) at a high load (3000 rpm/14.0 bar BMEP), as well as a part load (2080 rpm/6.8 bar BMEP) condition, at temperatures ca. 10-15 °C below the dew point of the flow stream. Three types of water separation designs were tested: a passive cyclone separator (CS), a passive membrane separator (MEM), and an active separator (AS).

External Exhaust Gas Recirculation (EGR) has been used on diesel engines for decades and has also been used on gasoline engines in the past. It is recently reintroduced on gasoline engines to improve fuel economy at mid and high engine load conditions, where EGR can reduce throttling losses and fuel enrichment. Fuel enrichment causes fuel penalty and high soot particulates, as well as hydrocarbon (HC) emissions, all of which are limited by emissions regulations. Under stoichiometric conditions, gasoline engines can be operated at high EGR rates (> 20%), but more than diesel engines, its intake gas including external EGR needs extreme cooling (down to ~50°C) to gain the maximum fuel economy improvement. However, external EGR and its problems at low temperatures (fouling, corrosion & condensation) are well known.

Control of the timing and magnitude of heat release is one of the biggest challenges for premixed compression ignition, especially when attempting to operate at high load. Single-fuel strategies such as partially premixed combustion (PPC) use direct injection of gasoline to stratify equivalence ratio and retard heat release, thereby reducing pressure rise rate and enabling high load operation. However, retarding the heat release also reduces the maximum work extraction, effectively creating a tradeoff between efficiency and noise. Dual-fuel strategies such as reactivity controlled compression ignition (RCCI) use premixed gasoline and direct injection of diesel to stratify both equivalence ratio and fuel reactivity, which allows for greater control over the timing and duration of heat release. This enables combustion phasing closer to top dead center (TDC), which is thermodynamically favorable.

In the current work, a series-hybrid vehicle has been constructed that utilizes a dual-fuel, Reactivity Controlled Compression Ignition (RCCI) engine. The vehicle is a 2009 Saturn Vue chassis and a 1.9L turbo-diesel engine converted to operate with low temperature RCCI combustion. The engine is coupled to a 90 kW AC motor, acting as an electrical generator to charge a 14.1 kW-hr lithium-ion traction battery pack, which powers the rear wheels by a 75 kW drive motor. Full vehicle testing was conducted on chassis dynamometers at the Vehicle Emissions Research Laboratory at Ford Motor Company and at the Vehicle Research Laboratory at Oak Ridge National Laboratory. For this work, the US Environmental Protection Agency Highway Fuel Economy Test was performed using commercially available gasoline and ultra-low sulfur diesel. Fuel economy and emissions data were recorded over the specified test cycle and calculated based on the fuel properties and the high-voltage battery energy usage.

Four-wheel-drive electric vehicles (4WD Evs) utilize in-wheel electric motors and Electro-Hydraulic Braking system (EHB). Then, all wheels torque can be controlled independently, and the braking pressure can be controlled more accurately and more fast than conventional braking system. Because of these advantages, 4WD Evs have potential applications in control engineering. In this paper, the in-wheel electric motors and EHB are applied as actuators in the vehicle stability control system. Based on the Direct Yaw-moment Control (DYC), the optimized wheel force distribution is given, and the coordination control of the hydraulic braking and the motor braking torque is considered. Then the EHB hardware-in-the-loop test bench is established in order to verify the effectiveness of the vehicle stability control algorithm through experiments.

The present experimental engine efficiency study explores the effects of intake pressure and temperature, and premixed and global equivalence ratios on gross thermal efficiency (GTE) using the reactivity controlled compression ignition (RCCI) combustion strategy. Experiments were conducted in a heavy-duty single-cylinder engine at constant net load (IMEPn) of 8.45 bar, 1300 rev/min engine speed, with 0% EGR, and a 50% mass fraction burned combustion phasing (CA50) of 0.5°CA ATDC. The engine was port fueled with E85 for the low reactivity fuel and direct injected with 3.5% 2-ethylhexyl nitrate (EHN) doped into 91 anti-knock index (AKI) gasoline for the high-reactivity fuel. The resulting reactivity of the enhanced fuel corresponds to an AKI of approximately 56 and a cetane number of approximately 28. The engine was operated with a wide range of intake pressures and temperatures, and the ratio of low- to high-reactivity fuel was adjusted to maintain a fixed speed-phasing-load condition.

Reactivity Controlled Compression Ignition (RCCI) is an engine combustion strategy that utilizes in-cylinder fuel blending to produce low NOx and PM emissions while maintaining high thermal efficiency. The current study investigates RCCI and conventional diesel combustion (CDC) operation in a light-duty multi-cylinder engine over transient operating conditions using a high-bandwidth, transient capable engine test cell. Transient RCCI and CDC combustion and emissions results are compared over an up-speed change from 1,000 to 2,000 rev/min. and a down-speed change from 2,000 to 1,000 rev/min. at a constant 2.0 bar BMEP load. The engine experiments consisted of in-cylinder fuel blending with port fuel-injection (PFI) of gasoline and early-cycle, direct-injection (DI) of ultra-low sulfur diesel (ULSD) for the RCCI tests and the same ULSD for the CDC tests.

In-cylinder blending of gasoline and diesel to achieve Reactivity Controlled Compression Ignition (RCCI) has been shown to reduce NOX and particulate matter (PM) emissions while maintaining or improving brake thermal efficiency as compared to conventional diesel combustion (CDC). The RCCI concept has an advantage over many advanced combustion strategies in that the fuel reactivity can be tailored to the engine speed and load allowing stable low-temperature combustion to be extended over more of the light-duty drive cycle load range. Varying the premixed gasoline fraction changes the fuel reactivity stratification in the cylinder providing further control of combustion phasing and pressure rise rate than the use of EGR alone. This added control over the combustion process has been shown to allow rapid engine operating point exploration without direct modeling guidance.

Advanced combustion systems that simultaneously address PM and NOx while retaining the high efficiency of modern diesel engines, are being developed around the globe. One of the most difficult problems in the area of advanced combustion technology development is the control of combustion initiation and retaining power density. During the past several years, significant progress has been accomplished in reducing emissions of NOx and PM through strategies such as LTC/HCCI/PCCI/PPCI and other advanced combustion processes; however control of ignition and improving power density has suffered to some degree - advanced combustion engines tend to be limited to the 10 bar BMEP range and under. Experimental investigations have been carried out on a light-duty DI multi-cylinder diesel automotive engine. The engine is operated in low temperature combustion (LTC) mode using 93 RON (Research Octane Number) and 74 RON fuel.

The paper presents the development of a novel approach to the solution of detailed chemistry in internal combustion engine simulations, which relies on the analytical computation of the ordinary differential equations (ODE) system Jacobian matrix in sparse form. Arbitrary reaction behaviors in either Arrhenius, third-body or fall-off formulations can be considered, and thermodynamic gas-phase mixture properties are evaluated according to the well-established 7-coefficient JANAF polynomial form. The current work presents a full validation of the new chemistry solver when coupled to the KIVA-4 code, through modeling of a single cylinder Caterpillar 3401 heavy-duty engine, running in two-stage combustion mode.