Your Selections

Western Michigan 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.

Western Michigan University-Tushar Gaikwad, Farhang Motallebiaraghi, Zachary Asher, Alvis Fong, Rick Meyer
Colorado State University-Aaron Rabinowitz, Thomas Bradley
  • 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.

Using Reinforcement Learning and Simulation to Develop Autonomous Vehicle Control Strategies

Western Michigan University-Nick Goberville, Johan Fanas Rojas, Zachary Asher
Amazon Web Services-Sahika Genc, Premkumar Rangarajan
  • Technical Paper
  • 2020-01-0737
To be published on 2020-04-14 by SAE International in United States
While machine learning in autonomous vehicles development has increased significantly in the past few years, the use of reinforcement learning (RL) methods has only recently been applied. Convolutional neural networks (CNNs) became common for their powerful object detection and identification and even provided end-to-end control of an autonomous vehicle. However, one of the requirements of a CNN is a large amount of labeled data to inform the neural network. While data is becoming more accessible, these networks are still sensitive to the format and collection environment which makes the use of others’ data more difficult. In contrast, RL develops solutions in a simulation environment by trial and error without labeled data. Our research expands upon previous research in RL and proximal policy optimization (PPO) and the application of these algorithms to 1/18th scale cars by expanding the application of this control strategy to a full-sized passenger vehicle. By using this method of unsupervised learning, our research demonstrates the ability to learn new control strategies while in a simulation environment without the need for large amounts…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Experimental and Computational Studies of the No-Load Churning Loss of a Truck Axle

Western Michigan University-Luis Silva, William Liou, Yang Yang, John Bair, Claudia M. Fajardo
Dana Incorporated-Steven Wesolowski
  • Technical Paper
  • 2020-01-1415
To be published on 2020-04-14 by SAE International in United States
This paper describes the work performed in predicting and measuring the contribution of oil churning to the no-load losses of a commercial truck axle at typical running speeds. A computational fluid dynamics (CFD) analysis of the churning losses was conducted. The CFD model accounts for design geometry, operating speed, temperature, and lubricant properties. The model calculates the oil volume fraction and the torque loss caused by oil churning due to the viscous and inertia effects of the fluid. CFD predictions of power losses were then compared with no-load measurements made on a specially developed, dynamometer-driven test stand. The same axle used in the CFD model was tested in three different configurations: with axle shafts, with axle shafts removed, and with ring gear and carrier removed. This approach to testing was followed to determine the contribution of each source of loss (bearings, seals, and churning) to the total loss. After bearing and seal loss measurements and predictions were factored in, the churning loss measurement and prediction comparisons were made. Experimental and computational results compared favorably. This…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Observer for Faulty Perception Correction in Autonomous Vehicles

Western Michigan University-Mark Omwansa, Rick Meyer, Zachary Asher, Nick Goberville
  • Technical Paper
  • 2020-01-0694
To be published on 2020-04-14 by SAE International in United States
Operation of an autonomous vehicle (AV) carries risk if it acts on inaccurate information about itself or the environment. The perception system is responsible for interpreting the world and providing the results to the path planning and other decision systems. The perception system performance is a result of the operating state of the sensors, e.g. is a sensor in fault or being adversely affected by the weather or environmental conditions, and approach to sensor measurement interpretation. We propose a trailing horizon switched system observer that minimizes the difference between reference tracking values developed from sensor fusion performed at an upper level and the values from a potentially faulty sensor based upon the convex combination of different sensor observation model outputs; the sensor observations models are associated with different sensor operating errors. The preferred observer target is a stationary landmark so as to remove additional uncertainty resulting from tracking of moving targets. Results for five scenarios show the observer identifies the appropriate sensor model in no more than a few sample intervals.
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Analysis of LiDAR and Camera Data in Real-World Weather Conditions for Autonomous Vehicle Operations

Western Michigan University-Nick Goberville, Mohammad El-Yabroudi, Mark Omwanas, Johan Rojas, Rick Meyer, Zachary Asher, Ikhlas Abdel-Qader
  • Technical Paper
  • 2020-01-0093
To be published on 2020-04-14 by SAE International in United States
Autonomous vehicle technology has the potential to improve the safety, efficiency, and cost of our current transportation system by removing human error. With sensors available today, it is possible for the development of these vehicles, however, there are still issues with autonomous vehicle operations in adverse weather conditions (e.g. snow-covered roads, heavy rain, fog, etc.) due to the degradation of sensor data quality and insufficiently robust software algorithms. Since autonomous vehicles rely entirely on sensor data to perceive their surrounding environment, this becomes a significant issue in the performance of the autonomous system. The purpose of this study is to collect sensor data under various weather conditions to understand the effects of weather on sensor data. The sensors used in this study were one camera and one LiDAR. These sensors were connected to an NVIDIA Drive Px2 which operated in a 2019 Kia Niro. Two custom scenarios (static and dynamic objects) were chosen to collect sensor data operating in four real-world weather conditions: fair, cloudy, rainy, and light snow. An algorithm developed herein was used…
   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

Western Michigan University-Tushar Gaikwad, Zachary Asher
Colorado State University-Aaron I. Rabinowitz, Samantha White, Thomas Bradley
  • 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.

CVT Ratio Scheduling Optimization with Consideration of Engine and Transmission Efficiency

Western Michigan University-Paresh Deshmukh, Steven Beuerle, Jennifer Hudson
Ford Motor Company-Weitian Chen, Edward Dai, Guopeng Hu, Yang Xu
Published 2019-04-02 by SAE International in United States
This paper proposes a transmission ratio scheduling and control methodology for a vehicle with a Continuous Variable Transmission (CVT) and a downsized gasoline engine. The methodology is designed to deliver the optimal vehicle fuel economy within drivability and performance constraints. Traditionally, the Optimum Operating Line (OOL) generated from an engine brake specific fuel consumption map is considered to be the best option for ratio scheduling, as it defines the points at which engine efficiency is maximized. But the OOL does not consider transmission efficiency, which may be a source of significant losses. To develop a CVT ratio schedule that offers the best fuel economy for the complete powertrain, an empirical approach was used to minimize fuel consumption by considering engine efficiency, CVT efficiency, and requested vehicle power. A backward-looking model was used to simulate a standard driving cycle (FTP-75) and develop a new powertrain-optimal operating line (P-OOL). Simulation results using the backward-looking model show a significant improvement in overall fuel economy when using the P-OOL (considers engine and CVT efficiency) compared to the OOL (considers…
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Vehicle Velocity Prediction and Energy Management Strategy Part 2: Integration of Machine Learning Vehicle Velocity Prediction with Optimal Energy Management to Improve Fuel Economy

Western Michigan University-Tushar D. Gaikwad, Zachary D. Asher
Toyota Motor North America-Mike Huang
Published 2019-04-02 by SAE International in United States
An optimal energy management strategy (Optimal EMS) can yield significant fuel economy (FE) improvements without vehicle velocity modifications. Thus it has been the subject of numerous research studies spanning decades. One of the most challenging aspects of an Optimal EMS is that FE gains are typically directly related to high fidelity predictions of future vehicle operation. In this research, a comprehensive dataset is exploited which includes internal data (CAN bus) and external data (radar information and V2V) gathered over numerous instances of two highway drive cycles and one urban/highway mixed drive cycle. This dataset is used to derive a prediction model for vehicle velocity for the next 10 seconds, which is a range which has a significant FE improvement potential. This achieved 10 second vehicle velocity prediction is then compared to perfect full drive cycle prediction, perfect 10 second prediction. These various velocity predictions are used as an input into an Optimal EMS derivation algorithm to derive an engine torque and engine speed control strategy that improves FE compared to current vehicle operation. Dynamic programming…
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Two-Point Spatial Velocity Correlations in the Near-Wall Region of a Reciprocating Internal Combustion Engine

Western Michigan University-James R. MacDonald, Claudia M. Fajardo
University of Michigan-Mark Greene, David Reuss, Volker Sick
Published 2017-03-28 by SAE International in United States
Developing a complete understanding of the structure and behavior of the near-wall region (NWR) in reciprocating, internal combustion (IC) engines and of its interaction with the core flow is needed to support the implementation of advanced combustion and engine operation strategies, as well as predictive computational models. The NWR in IC engines is fundamentally different from the canonical steady-state turbulent boundary layers (BL), whose structure, similarity and dynamics have been thoroughly documented in the technical literature. Motivated by this need, this paper presents results from the analysis of two-component velocity data measured with particle image velocimetry near the head of a single-cylinder, optical engine. The interaction between the NWR and the core flow was quantified via statistical moments and two-point velocity correlations, determined at multiple distances from the wall and piston positions. The analysis was conducted on instantaneous and Reynolds-decomposed flow fields, enabling the assessment of mean flow effects on the results. It is proposed that the turbulence in IC engine near-wall-layers is created by both wall-shear (as in canonical BL flows) and dissipation of…
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Stress Analysis of 2D-Cylindrical Pressure Vessel with Torispherical Endclosure

Western Michigan University-Darshan Bennur
Visvesvaraya Technological University-Anand A, Jeevan TP
Published 2014-04-01 by SAE International in United States
Pressure vessels are being widely employed worldwide as a means to carry, store or receive fluids. The pressure differential is dangerous and many fatal accidents have occurred in the history of their development and operation. Therefore, it is imperative to understand the behavioral effect of cylindrical pressure vessel with torispherical endclosure subjected to an internal pressure. In this paper, two dimensional static stress analyses are performed using the finite element method for different vessel thicknesses in order to understand the stresses and deflections in the vessel walls due to internal pressure. From the analysis, it is observed that the stress variation over the section of the geometry and thickness of the vessel play an important role in withstanding the applied internal pressure.
Annotation ability available