Search Results

Cost reduction in the automotive industry becomes a widely-adopted operational strategy not only for Original Equipment Manufacturers (OEMs) that take cost leader generic corporation strategy, but also for many OEMs that take differentiation generic corporation strategy. Since differentiation generic strategy requires an organization to provide a product or service above the industry average level, a premium is typically included in the tag price for those products or services. Cost reduction measures could increase risks for the organizations that pursue differentiation strategy. Although manufacturers in the automotive industry dramatically improved production efficiency in past ten years, they are still facing the pressure of cost control. The big challenge in cost control for automakers and suppliers is increasing prices of raw materials, energy and labor costs. These costs create constraints for the traditional economic expansion model.

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.

The classical methods of measuring acoustic absorption coefficient using an impedance tube and a reverberation chamber are well established [1, 2]. However, these methods are not suitable for in-situ applications. The two in-situ methods; single channel microphone (P- probe) and dual channel acoustic pressure and particle velocity (Pu-probe) methods based on measurement of impulse response functions of the material surface under test, provide considerable advantage in data acquisition, signal processing, ease and mobility of measurement setup. This paper evaluates the measurement techniques of these two in-situ methods and provides results of acoustic absorption coefficient of a commercial artificial Astroturf, a Dow quash material, and a grass surface.

The Time Variant Discrete Fourier Transform was implemented as a real-time order tracking method using developed software and commercially available hardware. The time variant discrete Fourier transform (TVDFT) with the application of the orthogonality compensation matrix allows multiple tachometers to be tracked with close and/or crossing orders to be separated in real-time. Signal generators were used to create controlled experimental data sets to simulate tachometers and response channels. Computation timing was evaluated for the data collection procedure and each of the data processing steps to determine how each part of the process affects overall performance. Many difficulties are associated with a real-time data collection and analysis tool and it becomes apparent that an understanding of each component in the system is required to determine where time consuming computation is located.

Increasingly, the exchanges of data in complex ECM (Electronic Control Module) systems rely on multiple communication networks across various physical and network layers. This has greatly increased system flexibility and provided an excellent medium to create well-defined exchangeable interfaces between components; however this added flexibility comes with increased network complexity. A system-level approach allows for the optimization of data exchange and network configuration as well as the development of a comprehensive network failure strategy. Many current ECM systems utilize complex multi-network communication strategies to exchange and control data to components. Recently, Caterpillar implemented an HIL (Hardware-In-the-Loop) test system that provides an approach for developing and testing a comprehensive ECM network strategy.

Neural networks are useful tools for optimization studies since they are very fast, so that while capturing the accuracy of multi-dimensional CFD calculations or experimental data, they can be run numerous times as required by many optimization techniques. This paper describes how a set of neural networks trained on a multi-dimensional CFD code to predict pressure, temperature, heat flux, torque and emissions, have been used by a genetic algorithm in combination with a hill-climbing type algorithm to optimize operating parameters of a diesel engine over the entire speed-torque map of the engine. The optimized parameters are mass of fuel injected per cycle, shape of the injection profile for dual split injection, start of injection, EGR level and boost pressure. These have been optimized for minimum emissions. Another set of neural networks have been trained to predict the optimized parameters, based on the speed-torque point of the engine.

Neural networks have been used for engine computations in the recent past. One reason for using neural networks is to capture the accuracy of multi-dimensional CFD calculations or experimental data while saving computational time, so that system simulations can be performed within a reasonable time frame. This paper describes three methods to improve upon neural network predictions. Improvement is demonstrated for in-cylinder pressure predictions in particular. The first method incorporates a physical combustion model within the transfer function of the neural network, so that the network predictions incorporate physical relationships as well as mathematical models to fit the data. The second method shows how partitioning the data into different regimes based on different physical processes, and training different networks for different regimes, improves the accuracy of predictions.

This study investigates a methodology in which the general public's subjective interpretation of vehicle handling and performance can be predicted. Several vehicle handling measurements were acquired, and associated metrics calculated, in a controlled setting. Human evaluators were then asked to drive and evaluate each vehicle in a winter driving school setting. Using the acquired data, multiple linear regression and artificial neural network (ANN) techniques were used to create and refine mathematical models of human subjective responses. It is shown that artificial neural networks, which have been trained with the sets of objective and subjective data, are both more accurate and more robust than multiple linear regression models created from the same data.

The effect of flow direction towards the spark plug electrodes on ignition parameters is analyzed using an innovative spark aerodynamics fixture that enables adjustment of the spark plug gap orientation and plug axis tilt angle with respect to the incoming flow. The ignition was supplied by a long discharge high energy 110 mJ coil. The flow was supplied by compressed air and the spark was discharged into the flow at varying positions relative to the flow. The secondary ignition voltage and current were measured using a high speed (10MHz) data acquisition system, and the ignition-related metrics were calculated accordingly. Six different electrode designs were tested. These designs feature different positions of the electrode gap with respect to the flow and different shapes of the ground electrodes. The resulting ignition metrics were compared with respect to the spark plug ground strap orientation and plug axis tilt angle about the flow direction.

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.

A procedure has been developed to build system level predictive models that incorporate physical laws as well as information derived from experimental data. In particular a soot model was developed, trained and tested using experimental data. It was seen that the model could fit available experimental data given sufficient training time. Future accuracy on data points not encountered during training was estimated and seen to be good. The approach relies on the physical phenomena predicted by an existing system level phenomenological soot model coupled with ‘weights’ which use experimental data to adjust the predicted physical sub-model parameters to fit the data. This approach has developed from attempts at incorporating physical phenomena into neural networks for predicting emissions. Model training uses neural network training concepts.

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.

Lithium-ion and Lithium polymer batteries are fast becoming ubiquitous in high-discharge rate applications for military and non-military systems. Applications such as small aerial vehicles and energy transfer systems can often function at C-rates greater than 1. To maximize system endurance and battery health, there is a need for models capable of precisely estimating the battery state-of-charge (SoC) under all temperature and loading conditions. However, the ability to perform state estimation consistently and accurately to within 1% error has remained unsolved. Doing so can offer enhanced endurance, safety, reliability, and planning, and additionally, simplify energy management. Therefore, the work presented in this paper aims to study and develop experimentally validated mathematical models capable of high-accuracy battery SoC estimation.

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.

Predictive Signal Phase and Timing (SPAT) message set is one fundamental building block for vehicle-to-infrastructure (V2I) applications such as Eco-Approach and Departure (EAD) at traffic signal controlled urban intersections. Among the two complementary communication methods namely short-range sidelink (PC5) and long-range cellular radio link (Uu), this paper documents the work with long-range link: the complete data chain includes connecting to the traffic signals via existing backhaul communication network, collecting the raw signal phase state data, predicting the signal state changes and delivering the SPAT data via a geofenced service to requests over HTTP protocols. An Application Programming Interface (API) library is developed to support various cellular data transmission reduction and latency improvement techniques.

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.

Large channel count data acquisition systems have seen increasing use in the acquisition and analysis of rotating machinery, these systems have the ability to generate very large amounts of data for analysis. The most common operating measurement made on powertrains or automobiles on the road or on dynamometers has become the order track measurement. Order tracking analysis can generate a very large amount of information that must be analyzed, both due to the number of channels and orders tracked. Analysis methods to efficiently analyze large numbers of Frequency Response Function (FRF) measurements have been developed and used over the last 20 years in many troubleshooting applications. This paper develops applications for several FRF based analysis methods as applied for efficient analysis of large amounts of order track data.

We present an approach in which an open-source software infrastructure is used for testing the behavior of autonomous vehicles through computer simulation. This software infrastructure is called CAVE, from Connected Autonomous Vehicle Emulator. As a software platform that allows rapid, low-cost and risk-free testing of novel designs, methods and software components, CAVE accelerates and democratizes research and development activities in the field of autonomous navigation.

This paper presents the development of a reduced-order powertrain model for energy and SOC estimation of a multi-mode plug-in hybrid electric vehicle using only vehicle speed profile and route elevation as inputs. Such a model is intended to overcome the computational inefficiencies of higher fidelity powertrain and vehicle models in short and long horizon energy optimization efforts such as Coordinated Adaptive Cruise Control (CACC), Eco Approach and Departure (EcoAND), Eco Routing, and PHEV mode blending. The reduced-order powertrain model enables Connected and Automated Vehicles (CAVs) to utilize the onboard sensor and connected data to quickly react and plan their maneuvers to highly dynamic road conditions with minimal computational resources.

As the world searches for ways to reduce humanity’s impact on the environment, the automotive industry looks to extend the viable use of the gasoline engine by improving efficiency. One way to improve engine efficiency is through more effective control. Torque-based control is critical in modern cars and trucks for traction control, stability control, advanced driver assistance systems, and autonomous vehicle systems. Closed loop torque-based engine control systems require feedback signal(s); indicated mean effective pressure (IMEP) is a useful signal but is costly to measure directly with in-cylinder pressure sensors. Previous work has been done in torque and IMEP estimation using crankshaft acceleration and ion sensors, but these systems lack accuracy in some operating ranges and the ability to estimate cycle-cycle variation.