Search Results

The adoption of simulation is critical to reducing development time and enhancing system robustness for Advanced Driver Assistance Systems (ADAS). Automotive companies typically have an abundance of real data recorded from a vehicle which is suitable for open-loop simulations. However, recorded data is often not suitable to test closed-loop control systems since the recorded data cannot react to changes in vehicle movement. This paper introduces a methodology to create virtual driving scenarios from recorded vehicle data to enable closed-loop simulation. This methodology is applied to test a lane centering application. A lane centering application helps a driver control steering to stay in the current lane and control acceleration and braking to maintain a set speed or to follow a preceding vehicle. The driver’s vehicle is referred to as the ego vehicle. Other vehicles on the road are referred to as target vehicles.

In a hydraulic system, parameter variation, contamination, and/or operating conditions can lead to instabilities in the pressure response. The resultant erratic pressure profile reduces performance and can lead to hardware damage. Specifically, in a transmission control system, the inability to track pressure commands can result in clutch or variator slip which can cause driveline disturbance and/or hardware damage. A variator is highly sensitive to slip and therefore, it is advantageous to identify such pressure events quickly and take remedial actions. The challenge is to detect the condition in the least amount of time while minimizing false alarms. A Neyman-Pearson and an energy detector (based on auto-correlation) are evaluated for the detection of pressure disturbances. The performance of the detectors is measured in terms of speed of detection and robustness to measurement noise.

A Machine Learning (ML) approach is presented to correlate in-cylinder images of early flame kernel development within a spark-ignited (SI) gasoline engine to early-, mid-, and late-stage flame propagation. The objective of this study was to train machine learning models to analyze the relevance of flame surface features on subsequent burn rates. Ultimately, an approach of this nature can be generalized to flame images from a variety of sources. The prediction of combustion phasing was formulated as a regression problem to train predictive models to supplement observations of early flame kernel growth. High-speed images were captured from an optically accessible SI engine for 357 cycles under pre-mixed operation. A subset of these images was used to train three models: a linear regression model, a deep Convolutional Neural Network (CNN) based on the InceptionV3 architecture and a CNN built with assisted learning on the VGG19 architecture.

More than four decades ago, the concept of zero defects was coined by Phillip Crosby. It was only a vision at the time, but the introduction of Artificial Intelligence (AI) in manufacturing has since enabled it to become attainable. Since most mature manufacturing organizations have merged traditional quality philosophies and techniques, their processes generate only a few Defects Per Million of Opportunities (DPMO). Detecting these rare quality events is one of the modern intellectual challenges posed to this industry. Process Monitoring for Quality (PMQ) is an AI and big data-driven quality philosophy aimed at defect detection and empirical knowledge discovery. Detection is formulated as a binary classification problem, where the right Machine Learning (ML), optimization, and statistics techniques are applied to develop an effective predictive system.

Model-based system simulations play a critical role in the development process of the automotive industry. They are highly instrumental in developing embedded control systems during conception, design, validation, and deployment stages. Whether for model-in-the-loop (MiL), software-in-the-loop (SiL) or hardware-in-the-loop (HiL) scenarios, high-fidelity plant models are particularly valuable for generating realistic simulation results that can parallel or substitute for costly and time-consuming vehicle field tests. In this paper, the development of a powertrain plant model and its correlation performance are presented. The focus is on the following modules of the propulsion systems: transmission, driveline, and vehicle. The physics and modeling approach of the modules is discussed, and the implementation is illustrated in Amesim software. The developed model shows good correlation performance against test data in dynamic events such as launch, tip-in, tip-out, and gearshifts.

Model-based control system design improves quality, shortens development time, lowers engineering cost, and reduces rework. Evaluating a control system's performance, functionality, and robustness in a simulation environment avoids the time and expense of developing hardware and software for each design iteration. Simulating the performance of a design can be straightforward (though sometimes tedious, depending on the complexity of the system being developed) with mathematical models for the hardware components of the system (plant models) and control algorithms for embedded controllers. This paper describes a software tool and a methodology that not only allows a complete system simulation to be performed early in the product design cycle, but also greatly facilitates the construction of the model by automatically connecting the components and subsystems that comprise it.

Currently, Model Based Development (MBD) is the de-facto methodology in automotive industry. This has led to conversions of legacy code to Simulink models. Our previous work was related to implementing the C2M tool to automatically convert legacy code to Simulink models. While the tool has been implemented and deployed on few OEM pilot code-sets there were several improvement areas identified w.r.t. the generated models. One of the improvement areas identified was that the generated model used atomic blocks instead of abstracted blocks available in Simulink. E.g. the generated model used an ADD block and feedback loop to represent an integration operation instead of using an integrator block directly. This reduced the readability of the model even though the functionality was correct. Thus, as a user of the model, an engineer would like to see abstract blocks rather than atomic blocks.

Automotive technology is rapidly changing with electrification of vehicles, driver assistance systems, advanced safety systems etc. This advancement in technology is making the task of validation and verification of embedded software complex and challenging. In addition to the component testing, integration testing imposes even tougher requirements for software testing. To meet these challenges dSPACE is continuously evolving the Hardware-In-the-Loop (HIL) technology to provide a systematic way to manage this task. The paper presents developments in the HIL hardware technology with latest quad-core processors, FPGA based I/O technology and communication bus systems such as Flexray. Also presented are developments of the software components such as advanced user interfaces, GPS information integration, real-time testing and simulation models. This paper provides a real-world example of implication of integration testing on HIL environment for Chassis Controls.

Advanced driver assistance systems (ADAS) are being developed for more and more complicated application scenarios, which often require more predictive strategies with better understanding of driving environment. Taking traffic vehicles’ maneuvers into account can greatly expand the beforehand time span for danger awareness. This paper presents a maneuver-based strategy to vehicle collision threat assessment. First, a maneuver-based trajectory prediction model (MTPM) is built, in which near-future trajectories of ego vehicle and traffic vehicles are estimated with the combination of vehicle’s maneuvers and kinematic models that correspond to every maneuver. The most probable maneuvers of ego vehicle and each traffic vehicles are modeled and inferred via Hidden Markov Models with mixture of Gaussians outputs (GMHMM). Based on the inferred maneuvers, trajectory sets consisting of vehicles’ position and motion states are predicted by kinematic models.

In today’s race for improved fuel economy and lower emissions from gasoline engines, precise metering of delivered fuel is essential. Gasoline Direct Injection fuel systems provide the means for improved combustion efficiency through mixture preparation and better atomization. These improvements can be achieved from both increasing fuel pressure and using multiple injection events, which significantly reduce the required energizing time per injection, and in a number of cases, force the injector to operate at less than full stroke. When the injector operates in this condition, the influence of variation in injector dynamics account for a large percentage of the delivered fuel and require compensation to ensure accurate fuel delivery. Injector dynamics such as opening delay and closing time are influenced by operating conditions such as fuel pressure, energizing time, and temperature.

Stamped components play an important role in supporting various sub-systems within a typical engine and transmission assembly. In some cases, the stamped components will not initially meet the design criteria, and material may need to be added to strengthen it. However, in other cases the component may be overdesigned, and there will be opportunities to reduce mass while still meeting all design criteria. In this latter case, multiple CAE simulations are often performed to enhance the component design by varying design parameters such as thickness, bend radius, material, etc., The conventional process will assess changes in one parameter at a time, while holding other parameters constant. Though this helps in meeting the design criteria, it is often very difficult to produce the best optimized design within the limited time span with this approach. With the aid of Altair-HyperMorph techniques, multiple design parameters can be varied simultaneously.

Vehicle manufacturers conduct tests to develop crash sensing system calibrations. Ditch fall-over is one of a suite of laboratory tests used to develop rollover sensing calibrations that can trigger deployment of safety devices like roof rail airbags and seat belt pretensioners. The ditch fall-over test simulates a flat road followed by a ditch on one side of the road. The vehicle heads into the ditch and the driver applies swift steer input once the ditch slope is sensed. Typically, the steer input is applied when the two down-slope wheels on the ditch side enter the ditch. Multi-Body Dynamics (MBD) software can be used for virtual simulation of these test events. Conventionally in simulations, the vehicle-model is run without steer input and the marking line crossing time is observed/manually recorded from observation of simulation video. This recorded time is used to apply the steer input and the full event is then re-simulated.

This paper describes the design of a multivariable, constrained Model Predictive Control (MPC) system for torque tracking in turbocharged gasoline engines scheduled for production by General Motors starting in calendar year 2018. The control system has been conceived and co-developed by General Motors and ODYS. The control approach consists of a set of linear MPC controllers scheduled in real time based on engine operating conditions. For each MPC controller, a linear model is obtained by system identification with data collected from engines. The control system coordinates throttle, wastegate, intake and exhaust cams in real time to track a desired engine torque profile, based on measurements and estimates of engine torque and intake manifold pressure.

Although advanced driver assistance systems (ADAS) have been widely introduced in automotive industry to enhance driving safety and comfort, and to reduce drivers’ driving burden, they do not in general reflect different drivers’ driving styles or customized with individual personalities. This can be important to comfort and enjoyable driving experience, and to improved market acceptance. However, it is challenging to understand and further identify drivers’ driving styles due to large number and great variations of driving population. Previous research has mainly adopted physical approaches in modeling drivers’ driving behavior, which however are often very much limited, if not impossible, in capturing human drivers’ driving characteristics. This paper proposes a reinforcement learning based approach, in which the driving styles are formulated through drivers’ learning processes from interaction with surrounding environment.

General Motors’ 3rd generation eAssist propulsion systems build upon the experience gained from the 2nd generation 115v system and the 1st generation 36v system. Extensive architectural studies were conducted to optimize the new eAssist system to maintain the performance and fuel economy gains of the 2nd generation 115v system while preserving passenger and cargo space, and reducing cost. Three diverse vehicle applications have been brought to production. They include two similar pickup trucks with 5.3 liter V8 engines and 8 speed transmissions, a 4-door passenger car with 2.5 liter 4 cylinder normally aspirated gasoline engine and a 6-speed automatic transmission, and a crossover SUV with a 2.0-liter turbocharged engine and 9 speed transmission. The key electrification components are a new water cooled induction motor/generator (MG), new water cooled power electronics module, and two major variants of 86v lithium ion battery packs.

The overall technology trend of Active Safety and Driver Assistance systems is relatively clear: increasing capability to avoid crashes as well as convenience on a path toward autonomous driving. What's less obvious, though, is the selection of features/technologies will make sense at each step along the path. Specific vehicle contenting decisions get made early in the vehicle planning process and rely on forecasting factors such as technology readiness, consumer interest, the economics in the supply base, and projected government regulations and consumer metrics. Additionally, for these technologies to be effective, often they need to be introduced in conjunction with other features and grouped in ways that are intuitive and relevant to current consumer needs.

In an earlier paper, the authors described how Model-Based System Engineering could be utilized to provide a virtual Hardware-in-the-Loop simulation capability, which creates a framework for the development of virtual ECU software by providing a platform upon which embedded control algorithms may be developed, tested, updated, and validated. The development of virtual ECU software is increasingly valuable in automotive control system engineering because vehicle systems are becoming more complex and tightly integrated, which requires that interactions between subsystems be evaluated during the design process. Variational analysis and robustness studies are also important and become more difficult to perform with real hardware as system complexity increases. The methodology described in this paper permits algorithm development to be performed prior to the availability of vehicle and control system hardware by providing what is essentially a virtual integration vehicle.

Stochastic Preignition (SPI) is an abnormal combustion event that occurs in a turbocharged engine and can lead to the loss in fuel economy and engine hardware damage, and in turn result in customer dissatisfaction. It is a significant limiting factor on the use and continued downsizing of turbocharged spark ignited direct injection (SIDI) gasoline engines. Understanding and mitigating all the factors that cause and influence the rate and severity of SPI occurrence are of critical importance to the engine’s continued use and fuel economy improvements for future designs. Previous studies have shown that the heavy molecular weight components of the fuel formulations are one factor that influences the rate of SPI from a turbocharged SIDI gasoline engine. All the previous studies have involved analyzing the fuel’s petroleum hydrocarbon chemistry, but not specifically the additives that are put in the fuel to protect and clean the internal components over the life of the engine.

Premium instrument panels (IPs) contain passenger airbag (PAB) systems that are typically comprised of a stiff plastic substrate and a soft ‘skin’ material which are adhesively bonded. During airbag deployment, the skin tears along the scored edges of the door holding the PAB system, the door opens, and the airbag inflates to protect the occupant. To accurately simulate the PAB deployment dynamics during a crash event all components of the instrument panel and the PAB system, including the skin, must be included in the model. It has been recognized that the material characterization and modeling of the skin tearing behavior are critical for predicting the timing and inflation kinematics of the airbag. Even so, limited data exists in the literature for skin material properties at hot and cold temperatures and at the strain rates created during the airbag deployment.

Due to growing interest in automated driving, the need for better understanding of human driving behavior in uncertain environment, such as driving behavior at un-signalized crossroad and roundabout, has further increased. Driving behavior at roundabout is greatly influenced by different dynamic factors such as speed, distance and circulating flow of the potentially conflicting vehicles, and drivers should choose whether to leave or wait at the upcoming exit according to these factors. In this paper, the influential dynamic factors and driving behavior characteristics at the roundabout is analyzed in detail, random forest method is then deployed to predict the driving behavior. For training the driving behavior model, four typical roundabout layouts were created under a real-time driving simulator with PanoSim-RT and dSPACE. Traffic participants with different motion style were also set in the simulation platform to mimic real driving conditions.