The SAE MOBILUS platform will continue to be accessible and populated with high quality technical content during the coronavirus (COVID-19) pandemic. x

Your Selections

Colorado State University
Show Only

Collections

File Formats

Content Types

Dates

Sectors

Topics

Authors

Publishers

Affiliations

Events

   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Vehicle Velocity Prediction Using Artificial Neural Network and Effect of Real World Signals on Prediction Window.

Colorado State University-Aaron Rabinowitz, Thomas Bradley
Western Michigan University-Tushar Gaikwad, Farhang Motallebiaraghi, Zachary Asher, Alvis Fong, Rick Meyer
  • Technical Paper
  • 2020-01-0729
To be published on 2020-04-14 by SAE International in United States
Prediction of vehicle velocity is important since it can realize improvements in the fuel economy/energy efficiency, drivability and safety. Velocity prediction has been addressed in many publications. Several references considered deterministic and stochastic approaches such as Markov chain, autoregressive models, and artificial neural networks. There are numerous new sensor and signal technologies like vehicle-to-vehicle and vehicle-to-infrastructure communication that can be used to obtain inclusive datasets. Using these inclusive datasets of sensors in deep neural networks, high accuracy velocity predictions can be achieved. This research builds upon previous findings that Long Short-Term Memory (LSTM) deep neural networks provide the highest velocity prediction fidelity. We developed LSTM deep neural network which uses different groups of datasets collected in Fort Collins. Synchronous data was gathered using a test vehicle equipped with sensors to measure ego vehicle position and velocity, ADAS-derived near-neighbor relative position and velocity, and infrastructure-level transit time and signal phase and timing. Effect of different group of datasets on forward velocity prediction window of 10, 15, 20 and 30 seconds is studied. Developed algorithm is tested…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Chip and Board Level Digital Forensics of Cummins Heavy Vehicle Event Data Recorders

Colorado State University-Jeremy Daily, Duy Van
Delta v Forensic Engrg-Matthew DiSogra
  • Technical Paper
  • 2020-01-1326
To be published on 2020-04-14 by SAE International in United States
Crashes involving Cummins powered heavy vehicle can damage the electronic control modules (ECMs) containing heavy vehicle event data recorder (HVEDR) data. When ECMs are broken and data cannot be extracted using vehicle diagnostics tools, more invasive and low level techniques are needed to forensically preserve and decode HVEDR data. A technique for extracting non-volatile memory contents using non-destructive board level techniques with the available JTAG port. Additional chip level data extraction techniques can also provide access to the data. Once the data is obtained and preserved in a forensically sound manner, the binary record is decoded to reveal typical HVDER data like engine speed, vehicle speed, accelerator pedal position, and other status flag data. The memory contents from the ECM can be written to a surrogate and decoded with traditional maintenance and diagnostic software. The research also shows the diagnostic trouble codes from the ECM are preserved in its as-found state. In other words, the digital forensic technique of extracting memory contents through the JTAG port does not introduce any new fault codes. Cryptographic hashing…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Synchronous and Open, Real World, Vehicle, ADAS, and Infrastructure Data Streams for Automotive Machine Learning Algorithms Research

Colorado State University-Aaron I. Rabinowitz, Samantha White, Thomas Bradley
Western Michigan University-Tushar Gaikwad, Zachary Asher
  • Technical Paper
  • 2020-01-0736
To be published on 2020-04-14 by SAE International in United States
The suite of CAVs-derived data streams have been demonstrated to enable improvements in system-level safety, emissions and fuel economy. This describes the gathering, processing, and use of on-road data collected from probe vehicles in Fort Collins, Colorado. Several synchronous datasets were gathered using a test vehicle equipped with sensors to measure ego vehicle position and velocity, ADAS-derived near-neighbor relative position and velocity, and infrastructure-level transit time and signal phase and timing. The datasets in both raw and data-fused formats is made available to the research community. The utility of these types of open data projects is briefly demonstrated by using them in the applications of vehicle velocity prediction, and real-time fuel economy modeling.
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Colorado State University EcoCAR 3 Final Technical Report

Colorado State University-Gabriel Christian DiDomenico, Jamison Bair, Vipin Kumar Kukkala, Jordan Tunnell, Marco Peyfuss, Michael Kraus, Joshua Ax, Jeremy Lazarri, Matthew Munin, Corey Cooke, Eric Christensen, Logan Peltz, Nathan Peterson, Logan Wolfe, Zach Vinski, Daniel Norris, Corrie Kaiser, Jacob Collier, Nick Schott, Yi Wang, Thomas Bradley
Published 2019-04-02 by SAE International in United States
Driven by consumer demand and environmental regulations, market share for plug-in hybrid electric vehicles (PHEVs) continues to increase. An opportunity remains to develop PHEVs that also meet consumer demand for performance. As a participant in the EcoCAR 3 competition, Colorado State University’s Vehicle Innovation Team (CSU VIT) has converted a 2016 Chevy Camaro to a PHEV architecture with the aim of improving efficiency and emissions while maintaining drivability and performance. To verify the vehicle and its capabilities, the CSU Camaro is rigorously tested by means of repeatable circumstances of physical operation while Controller Area Network (CAN) loggers record various measurements from several sensors. This data is analyzed to determine consistent output and coordination between components of the electrical charge and discharge system, as well as the traditional powertrain. The aim is to improve drivability and efficiency as measured by vehicle technical specifications (VTS) including acceleration, energy consumption, and emissions. In this interest, the team focused on the areas of mass reduction, efficient powertrain operation as well as optimal engine and motor use. While there is…
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Development and Validation of a CFD Simulation to Model Transient Flow Behavior in Automotive Refueling Systems

Colorado State University-T. McKay Stoker, Mangesh Dake, Luke Nibbelink, Bret Windom
Honda R & D Americas Inc.-Marc Henderson, Joshua Shaw
Published 2019-04-02 by SAE International in United States
Government regulations restrict the evaporative emissions during refueling to 0.20 grams per gallon of dispensed fuel. This requires virtually all of the vapors generated and displaced while refueling to be stored onboard the vehicle. The refueling phenomenon of spitback and early-clickoff are also important considerations in designing refueling systems. Spitback is fuel bursting past the nozzle and into the environment and early-clickoff is the pump shutoff mechanism being triggered before the tank is full. Development of a new refueling system design is required for each vehicle as packaging requirements change. Each new design (or redesign) must be prototyped and tested to ensure government regulations and customer satisfaction criteria are satisfied. Often designs need multiple iterations, costing money and time in prototype-based validation procedures. To conserve resources, it is desired to create a Computational Fluid Dynamics (CFD) tool to assist in design validation. A model that simulates the entire refueling system will be discussed here. This includes boundary conditions of the pump nozzle, the vapor return line, and an orifice that mimics the pressure drop across…
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Enabling Prediction for Optimal Fuel Economy Vehicle Control

Colorado State University-Zachary D. Asher, Jordan A. Tunnell, David A. Baker, Sudeep Pasricha, Thomas H. Bradley
University of Colorado Denver-Robert J. Fitzgerald, Farnoush Banaei-Kashani
Published 2018-04-03 by SAE International in United States
Vehicle control using prediction based optimal energy management has been demonstrated to achieve better fuel economy resulting in economic, environmental, and societal benefits. However, research focusing on prediction derivation for use in optimal energy management is limited despite the existence of hundreds of optimal energy management research papers published in the last decade. In this work, multiple data sources are used as inputs to derive a prediction for use in optimal energy management. Data sources include previous drive cycle information, current vehicle state, the global positioning system, travel time data, and an advanced driver assistance system (ADAS) that can identify vehicles, signs, and traffic lights. To derive the prediction, the data inputs are used in a nonlinear autoregressive artificial neural network with external inputs (NARX). Two real world drive cycles were developed for analysis in the Denver, Colorado region: a city-focused drive cycle that passes through downtown as well as a highway-focused drive cycle that transitions across multiple interstates. A validated model of a 2010 Toyota Prius in Autonomie is used to determine the vehicle…
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Development of an Autonomous Vehicle Control Strategy Using a Single Camera and Deep Neural Networks

Colorado State University-Zachary Asher
Akka Technologies-Jendrik Joerdening
Published 2018-04-03 by SAE International in United States
Autonomous vehicle development has benefited from sanctioned competitions dating back to the original 2004 DARPA Grand Challenge. Since these competitions, fully autonomous vehicles have become much closer to significant real-world use with the majority of research focused on reliability, safety and cost reduction. Our research details the recent challenges experienced at the 2017 Self Racing Cars event where a team of international Udacity students worked together over a 6 week period, from team selection to race day. The team’s goal was to provide real-time vehicle control of steering, braking, and throttle through an end-to-end deep neural network. Multiple architectures were tested and used including convolutional neural networks (CNN) and recurrent neural networks (RNN). We began our work by modifying a Udacity driving simulator to collect data and develop training models which we implemented and trained on a laptop GPU. Then, in the two days between car delivery and the start of the competition, a customized neural network using Keras and Tensorflow was developed. The deep learning network algorithm predicted car steering angles using a single front-facing…
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Measured and Predicted Vapor Liquid Equilibrium of Ethanol-Gasoline Fuels with Insight on the Influence of Azeotrope Interactions on Aromatic Species Enrichment and Particulate Matter Formation in Spark Ignition Engines

Colorado State University-Stephen Burke, Bret Windom
National Renewable Energy Laboratory-Matthew Ratcliff, Robert McCormick
Published 2018-04-03 by SAE International in United States
A relationship has been observed between increasing ethanol content in gasoline and increased particulate matter (PM) emissions from direct injection spark ignition (DISI) vehicles. The fundamental cause of this observation is not well understood. One potential explanation is that increased evaporative cooling as a result of ethanol’s high HOV may slow evaporation and prevent sufficient reactant mixing resulting in the combustion of localized fuel rich regions within the cylinder. In addition, it is well known that ethanol when blended in gasoline forms positive azeotropes which can alter the liquid/vapor composition during the vaporization process. In fact, it was shown recently through a numerical study that these interactions can retain the aromatic species within the liquid phase impeding the in-cylinder mixing of these compounds, which would accentuate PM formation upon combustion. To better understand the role of the azeotrope interactions on the vapor/liquid composition evolution of the fuel, distillations were performed using the Advanced Distillation Curve apparatus on carefully selected samples consisting of gasoline blended with ethanol and heavy aromatic and oxygenated compounds with varying vapor…
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Towards Improving Vehicle Fuel Economy with ADAS

Colorado State University-Jordan A. Tunnell, Zachary D. Asher, Sudeep Pasricha, Thomas H. Bradley
Published 2018-04-03 by SAE International in United States
Modern vehicles have incorporated numerous safety-focused Advanced Driver Assistance Systems (ADAS) in the last decade including smart cruise control and object avoidance. In this paper, we aim to go beyond using ADAS for safety and propose to use ADAS technology to enable predictive optimal energy management and improve vehicle fuel economy. We combine ADAS sensor data with a previously developed prediction model, dynamic programming optimal energy management control, and a validated model of a 2010 Toyota Prius to explore fuel economy. First, a unique ADAS detection scope is defined based on optimal vehicle control prediction aspects demonstrated to be relevant from the literature. Next, during real-world city and highway drive cycles in Denver, Colorado, a camera is used to record video footage of the vehicle environment and define ADAS detection ground truth. Then, various ADAS algorithms are combined, modified, and compared to the ground truth results. Lastly, the impact of four vehicle control strategies on fuel economy is evaluated: 1) the existing vehicle control, 2) actual ADAS detection for prediction and optimal energy management (we…
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Considerations for CFD Simulations of a Refueling Pump Nozzle with Application to the Computer Aided Engineering of a Vehicle Refueling System

Colorado State University-Mangesh Rajendra Dake, Joseph FitzWilliam, Bret Windom
Honda R & D Americas Inc.-Marc Henderson, Joshua Shaw, Matthew Swanson
Published 2018-04-03 by SAE International in United States
A vehicle’s refueling system including components, which make up the onboard refueling vapor recovery (ORVR) system, must be designed to meet federally set evaporative hydrocarbon emission regulations and other performance issues inherent to the refueling process, such as premature click-off and spit-back. A Computational Fluid Dynamics (CFD) model able to predict the performance of a vehicle’s refueling system could be a valuable tool towards the development of future designs, saving the Original Equipment Manufacturer’s (OEM) time and money in the research and development phases. To create an adequate model required for Computer Aided Engineering (CAE) of a modern refueling system, it is paramount to accurately predict the fluid dynamics through and out of a gasoline refueling nozzle, as this is a key inlet condition of any refueling system. This study aims to validate CFD simulations, which predict the fluid dynamics through a refueling gasoline pump nozzle. The commercial CFD software Star-CCM+ was used to model gasoline flow through two gasoline nozzle geometries. The CFD domain for a Husky X1 and an OPW 11B were created…
This content contains downloadable datasets
Annotation ability available