Your Selections

Historical reference
Show Only


File Formats

Content Types











An Interactive Vehicle Recommender System Based on Decision Trees and Multi-Armed Bandits

Carnegie Mellon University-Tong Yu, Ole Mengshoel
Ford Motor Co., Ltd.-Dominique Meroux, Zhen Jiang
  • Technical Paper
  • 2019-01-1079
To be published on 2019-04-02 by SAE International in United States
Recommender systems guide a user to useful objects in a large space of possible options in a personalized way. In this paper, we study how to make recommendations for vehicle purchases. This can effectively reduce the human labor in the traditional setting, where customers get recommended vehicles through conversations with the salesmen in dealerships. Comparing a vehicle recommender system to one in other application domains (movies, music, etc.), we identify two major challenges. First, customers usually only purchase a limited number of vehicles, compared to the number of movies or songs. Thus, it is difficult to obtain rich information about a user's purchase history. Second, the content information obtained about the users (demographic, vehicle preference, etc.) is also very limited during their short stay in the dealership. To address these two challenges, we propose an interactive vehicle recommender system based on the methods of decision tree classification and multi-armed bandit. The decision tree effectively selects important questions for the user and understands the user's preference. With these preference as prior information, the multi-armed bandit algorithm…

Prediction of Human Actions in Assembly Process by a Spatial-Temporal End-to-End Learning Model

Clemson University-Zhujun Zhang, Weitian Wang, Yi Chen, Yunyi Jia
Harbin Institute of Technology-Zhujun Zhang, Gaoliang Peng
  • Technical Paper
  • 2019-01-0509
To be published on 2019-04-02 by SAE International in United States
It’s important to predict the future actions of human in the industry assembly process. Foreseeing future actions before they have happened is an essential part for flexible human-robot collaboration and crucial safety issues. Vision-based human actions prediction from videos provides intuitive and adequate knowledge for many complex applications. This problem can be interpreted as deducing the next action of people from a short video clip. The history information needs to be considered to learn these relations between each time step for predicting the future steps. However, it is difficult to extract the history information and use it to infer the future situation with the traditional methods. In this scenario, a model is needed to handle the spatial and temporal details stored in past human motions and construct the future action based on limited accessible human demonstrations. In this paper, we apply an autoencoder based deep learning framework for human actions construction, merging into the RNN pipeline for human future actions prediction. This contrasts with traditional approaches which use hand-crafted features and different domain output. The…

Accuracy and sensitivity of yaw speed analysis to available data

MEA Forensic Engineers & Scientists-Bradley Heinrichs, Janice Lee, Cole Young
  • Technical Paper
  • 2019-01-0417
To be published on 2019-04-02 by SAE International in United States
Accident reconstructions rarely have complete data with which to determine vehicle speed, and so must bracket the true value with a range. Previous work has shown the effect of friction uncertainty in determining speed from tire marks left by a vehicle in yaw. The goal of the current study was to assess improvements in the accuracy of vehicle speed estimated from yaw marks using progressively more scene and vehicle information. Data for this analysis came from staged S-turn maneuvers that in some cases led to rollover of the SUV test vehicles. Initial speeds were first calculated using the critical curve speed (CCS) formula on the yaw marks from the first portion of the S-maneuver. Then computer simulations were performed with progressively more input data: i) the complete tire marks from the whole S-maneuver, ii) measured vehicle mass, iii) measured suspension stiffness and damping, and iv) measured steering history. Simulations based on the complete tire marks improved the average error compared with the CCS equation. Adding the remaining input data to the simulations did not further…

Helicopter Transmission and Drivelines - A Brief Overview of

Boeing Co.-Patrick Robert Darmstadt, Mark Robuck
  • Technical Paper
  • 2019-01-1294
To be published on 2019-04-02 by SAE International in United States
Transmission and drivelines as they apply to helicopters are discussed including history, common configurations, and typical, industry design philosophies. A brief history of transmission use in helicopter applications is provided, including an emphasis on the flight critical nature of transmissions and drivelines in helicopter applications and how the helicopter transmission has evolved over their 100 years of service. Common helicopter drivelines are discussed for a variety of helicopter configurations (single main rotor, tandem rotor, and tilt rotor, among others), touching on typical shaft speed and horsepower ranges. Finally, typical helicopter transmission design practices are discussed for gear, bearing, and lubrication systems.

Reconstructing vehicle dynamics from on-board event data

MEA Forensic Engineers & Scientists-Brandon Tsuge, Mike Yang, Thomas Flynn, Peter Xing, Jonathan Lawrence, Bradley Heinrichs, Gunter Siegmund
  • Technical Paper
  • 2019-01-0632
To be published on 2019-04-02 by SAE International in United States
Modern vehicles record dynamic data from a number of on-board sensors for events that could precede a crash. This data can be used to reconstruct the behavior of a vehicle, although the accuracy of these reconstructions has not yet been quantified. Here we evaluated various methods of reconstructing the vehicle dynamics of two 2017 Toyota Corollas based on Vehicle Control History (VCH) data from overlapping events generated by the pre-collision system (PCS), sudden braking, and ABS activation. The vehicles were driven towards a stationary target at 32-64 km/h and then after the pre-collision alarm sounded the vehicle was steered sharply right or left and braked rapidly to rest. VCH data was then imaged for the PCS event at 2 Hz and for the sudden braking and ABS activation events at 6.7 Hz. The steering wheel angle and the vehicle’s longitudinal acceleration, lateral acceleration, and angular rate data were then extracted and used to predict the vehicle position and heading over the duration of the VCH data record preceding the vehicle coming to rest. These predictions…

The History of Human Factors in Seating Comfort at SAE’s World Congress

Ford Motor Co., Ltd.-Michael Kolich
  • Technical Paper
  • 2019-01-0405
To be published on 2019-04-02 by SAE International in United States
In many fields of technology, examinations of the past can provide insights into the future. This paper reviews the history of automotive seat comfort development and research as chronicled by SAE’s session titled “Human Factors in Seating Comfort”. Records suggest that “Human Factors in Seating Comfort” has existed as a separate session at SAE’s World Congress since the turn of the century. In that time there have been 149 papers published / presented. The history is fascinating because it reflects interests of the time which are driven by technology trends, customer wants and needs, and new theories. The list of contributors, in terms of authors and their affiliations, is also telling. It shows shifts in business models, strategies around collaboration, and career progressions of certain individuals. The paper ends with a discussion of what can be learned from this historical review and the major issues to be addressed. One of the more significant contributions of this paper is the reference list. It contains all 149 of SAE’s “Human Factors in Seating Comfort” papers in a…

How to meet compliance to software architectural design principles

Model Engineering Solutions-Scott Ranville, Ferry Bachmann
  • Technical Paper
  • 2019-01-1040
To be published on 2019-04-02 by SAE International in United States
As demand for ADAS and autonomous systems grows as well as the need to avoid lawsuits from software bugs, the desire for high integrity and functional safety applications is growing. While there are many process and technical factors that contribute to the overall quality of the software, it is becoming increasingly important to more formally define the software architecture and verify that the implementation satisfies all of the architecture requirements. Two factors impacting how many companies approach software architectures include their past history with not defining the architecture and converting existing models/code to comply with the newly defined architecture. Because defining the software architecture is new for many companies, they do not know what properties are important to specify. Also lacking are techniques needed to verify that the implementation is a “good” architecture and to improve an existing architecture. This paper/talk will address: - Important qualities to include in the software architecture definition - Discussion on what ISO 26262 recommends for the software architecture - Recommendations for implementing the software architecture in Simulink - Ways…

Regression Techniques for Parameter Estimation of a Synchronous Machine from Sudden Short-Circuit Testing

P.C. Krause And Associates Inc.-Brett A. Robbins, Will Perdikakis
US Air Force-Kevin J. Yost
  • Technical Paper
  • 2019-01-1354
To be published on 2019-03-19 by SAE International in United States
The Air Force Research Laboratory (AFRL) Intelligent Power program has procured several 40 kVA, 400 Hz, brushless synchronous generators at various stages of their life cycle. The history of these machines is unknown with differences in manufacturing, materials, ageing, heating, and non-ideal maintenance procedures contribute to the variability of the measured machine model parameters. The work presented in this paper summarizes efforts by AFRL to improve the fidelity of hardware parameterization of synchronous machine models by leveraging the sudden short-circuit (SSC) laboratory tests. This procedure is used to observed the dynamic response of the synchronous machines and determine the fitted d-axis operational impedances and time constants. Relevant background theory and captured data will be provided to demonstrate the process of approximating machine parameters; however, the primary contribution of this paper is the numerical regression used to curve fit the experimental data. The decomposition of the dynamic response of an electric machine in an SSC event is widely published. The typical approach of the curve fitment is often loosely explained, neglected, or leverages genetic algorithms. Furthermore,…

Next Generation Flexible Tooling System

Larry Kirby, Ronald Weddle
  • Technical Paper
  • 2019-01-1362
To be published on 2019-03-19 by SAE International in United States
Flexible Tooling Systems have been developed as a reconfigurable part support system to enable trimming of multiple part geometries utilizing a single router or waterjet. The driver for this development has been improved part quality, elimination of ergonomic issues associated with manually trimming, and elimination of cost for individual part hard trimming tools along with its associated cost for their manufacture, maintenance, and storage. This paper will briefly trace the evolution of aerospace parts trimming history. The remainder of the report will focus on the technical objective associated the development of the Next Generation Flexible Tooling System, how they were achieved including the process for validation of each support location in aircraft coordinates. This system is designed to increase part holding accuracy with specific support location validation, and significantly reduce system maintenance costs in wet or dry environments.

Theoretical modeling of the mechanical degradation of polymer composites due to moisture/water absorption and damage progression

Mississippi State University-Ge He, Yucheng Liu
  • Technical Paper
  • 2019-01-1376
To be published on 2019-03-19 by SAE International in United States
The moisture/water absorption and microvoids/cracks progression are two well-understood mechanisms that have significant degradation effects on the mechanical properties/behaviors of the polymer-based composites. To theoretically investigate the effects of above two mechanisms, we develop a simple fiber reinforced polymer composites model by employing the internal state variable (ISV) theory. The water content and the anisotropically distributed damage of the composites are considered as two ISVs (the water content is described by a scalar variable and the damage is defined as a second order tensor) whose histories are governed by two specific physically-based evolution equations. The proposed model can be easily cast into a general theoretical framework to capture more polymer composites behaviors such as viscoelasticity, viscoplasticity and the thermal effect. The results predicted by current model are in good agreement with the experimental data, which allows us to implement the model into FEA for future structural analysis.