Your Selections

Neural networks
Show Only

Collections

File Formats

Content Types

Dates

Sectors

Topics

Authors

Publishers

Affiliations

Committees

Events

Magazine

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

Research on the Subjective Rating Prediction Method for the Ride Comfort with Deep Learning

Hitachi Automotive Systems, Ltd-Ryusuke Hirao
Hitachi Automotive Systems, Ltd.-Nobuyuki Ichimaru
  • Technical Paper
  • 2020-01-1566
To be published on 2020-06-03 by SAE International in United States
Suspension is an important chassis part which is vital to ride comfort. However, it is difficult to achieve our targeted comfortability level in a short time. Therefore, improving efficiency of damper development is our primary challenge. We have launched a project which aims to reduce the workload on developing dampers by introducing analytical approaches to the improvement of ride comfort. To be more specific, we have been putting effort into developing subjective rating prediction, vehicle dynamics prediction, the damping force prediction. This paper describes the subjective rating prediction method which output a subjective rating corresponding to the physical value of the vehicle dynamics with Deep Learning. As a result of verifying with the unlearning data, DNN(Deep Neural Network) prediction method could almost predict the subjective rating of the expert driver.
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Time Domain Full Vehicle Interior Noise Calculation from Component Level Data by Machine Learning

Mercedes-Benz AG-Dimitrios Ernst Tsokaktsidis, Clemens Nau
Technical University of Munich-Steffen Marburg
  • Technical Paper
  • 2020-01-1564
To be published on 2020-06-03 by SAE International in United States
Computational models directly derived from data gained increased interest in recent years. Data-driven approaches have brought breakthroughs in different research areas such as image-, video- and audio-processing. Often denoted as Machine Learning (ML), today these approaches are not widely applied in the field of vehicle Noise, Vibration and Harshness (NVH). Works combining ML and NVH mainly discuss the topic with respect to psychoacoustics, traffic noise, structural health monitoring and as improvement to existing numerical simulation methods. Vehicle interior noise is a major quality criterion for today’s automotive customers. To estimate noise levels early in the development process, deterministic system descriptions are created by utilizing time-consuming measurement techniques. This paper examines whether pattern-recognizing algorithms are suitable to conduct the prediction process for a steering system. Starting from operational measurements, a procedure to calculate the sound pressure level in the passenger cabin is developed and investigated. Component time domain data serves as basis for the computation. The important inputs are determined by a correlation analysis. Input selection is followed by data reduction. After preprocessing, a supervised learning…
   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 low error velocity prediction. We developed an LSTM deep neural network that uses different groups of datasets collected in Fort Collins, Colorado. 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-derived transit time and signal phase and timing. The effect of different groups of input datasets on forward velocity prediction windows of 10, 15, 20, and 30 seconds was studied. The…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Driver Distraction Detection with a Two-stream Convolutional Neural Network

Wuhan University of Technology-Yuefeng Ma, Zhishuai Yin, Linzhen Nie
  • Technical Paper
  • 2020-01-1039
To be published on 2020-04-14 by SAE International in United States
Driver distraction detection is crucial to driving safety when autonomous vehicles are co-piloted. Recognizing drivers’ behaviors that are highly related with distraction from real-time video stream is widely acknowledged as an effective approach mainly due to its non-intrusiveness. In recently years, deep learning neural networks have been adopted to by-pass the procedure of designing features artificially, which used to be the major downside of computer-vision based approaches. However, the detection accuracy and generalization ability is still not satisfying since most deep learning models extracts only spatial information contained in images. This research develops a driver distraction model based on a two-stream, spatial and temporal, convolutional neural network (CNN). The CNN in both stream is improved with Batch Normalization-Inception (BN-Inception) modules which increase the sparsity in the inception modules in GoogLeNet, so that the network is further speeded up and also more adapted to features at various-scales. The original RGB image is fed into the spatial stream CNN to extract static information, and the feature map of optical flow field extracted from adjacent image frames is…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

A Pre-Warning Method for Cornering Speed of Concrete Mixer Truck

Suizhou-WUT Industry Research Institute-Gangfeng Tan
Wuhan University of Technology-Yifeng Jiang, Haoyu Wang, Zelong Wang, Zhenyu Wang, Ming Li
  • Technical Paper
  • 2020-01-1003
To be published on 2020-04-14 by SAE International in United States
The high gravity center of the concrete mixer truck reduces the truck’s stability while steering. The rolling stirring tank makes the stability even worse than the regular engineering vehicle due to the dynamic variation of the centroid position. Most of the researches on the rollover stability of concrete mixer trucks focus on the rollover model establishment and dynamic simulation module. The change of concrete centroid is ignored when the safety cornering speed is calculated. This paper proposes a pre-warning method for the cornering speed of concrete mixer trucks based on centroid dynamic simulation. In the method, the mixing tank stirring model and the vehicle driving dynamic model are established on the Fluent and TruckSim simulation platforms, respectively. The theoretical speed threshold obtained by simulation is used as the evaluation index of the warning speed in the curve. Firstly, the dynamic simulation of the stirring tank model is carried out by Fluent. According to Newton Leibniz numerical calculation method, Matlab is used to obtain the mathematical model of the centroid position and the main parameters of…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Comparison of CNN and LSTM for Modeling Virtual Sensors in an Engine

Chalmers University of Technology-Mauro Bellone, Yiannis Karayiannidis
Volvo AB Volvo Penta-Ethan Faghani
  • Technical Paper
  • 2020-01-0735
To be published on 2020-04-14 by SAE International in United States
The automotive industry makes extensive use of virtual models to increase efficiency during the development stage. The complexity of such virtual models increases with the complexity of the process that they describe, and thus new methods for their development are constantly evaluated. Among many others, data-driven techniques and machine learning offer promising results, creating deep neural networks that map complex input-output relations. This work aims at comparing the performance of two different neural network architectures for the estimation of the engine state and emissions (flow fuel, NOx and soot). More specifically, Convolutional Neural Network (CNN) and Long-Short Term Memory (LSTM) will be evaluated in terms of performance, using different techniques to increase the model generalization. During the learning stage data from different engine cycles are fed to the neural networks. In order to evaluate the generalization of the model, the networks are tested over new, previously unseen, engine cycles. Results show that our models over-perform other state-of-the-art models, the best performance was found for the LSTM model with 2.40%, 2.80% and 18.19% error for flow…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Heterogeneous Machine Learning on High Performance Computing for End to End Driving of Autonomous Vehicles

National Renewable Energy Laboratory-Xiangyu Zhang, Peter Graf
Oak Ridge National Laboratory-Robert Patton, Shang Gao, Spencer Paulissen, Nicholas Haas, Brian Jewell
  • Technical Paper
  • 2020-01-0739
To be published on 2020-04-14 by SAE International in United States
Current artificial intelligence techniques for end to end driving of autonomous vehicles typically rely on a single form of learning or training processes along with a corresponding dataset or simulation environment. Relatively speaking, success has been shown for a variety of learning modalities in which it can be shown that the machine can successfully “drive” a vehicle. However, the realm of real-world driving extends significantly beyond the realm of limited test environments for machine training. This creates an enormous gap in capability between these two realms. With their superior neural network structures and learning capabilities, humans can be easily trained within a short period of time to proceed from limited test environments to real world driving. For machines though, this gap is guarded by at least two challenges: 1) machine learning techniques remain brittle and unable to generalize to a wide range of scenarios, and 2) effective training data that enhances generalization and generates the desired driving behavior. Further, each challenge can be computationally intensive on its own thereby exasperating the gap. Moreover, is has…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Driver Visual Focus of Attention Estimation in Autonomous Vehicles

Dura Automotive Systems-Iyad Mansour
Oakland University-Alaaldin Hijaz, Wing-Yue Louie, Matthew Bellafaire, Osamah Rawashdeh
  • Technical Paper
  • 2020-01-1037
To be published on 2020-04-14 by SAE International in United States
Abstract-An existing challenge in current state-of-the-art autonomous vehicles is the process of safely transferring control from autonomous driving mode to manual mode because the driver may be distracted with secondary tasks. Such distractions may impair a driver’s situational awareness of the driving environment which will lead to fatal outcomes during a handover. Current state-of-the-art vehicles notify a user of an imminent handover via auditory, visual, and physical alerts but are unable to improve a driver’s situational awareness before a handover is executed. The overall goal of our research team is to address the challenge of providing a driver with relevant information to regain situational awareness of the driving task. In this paper, we introduce a novel approach to estimating a driver’s visual focus of attention using a 2D RGB camera as input to a Multi-Input Convolutional Neural Network with shared weights. The system was validated in a realistic driving scenario. The developed approach is a first step towards estimating a driver’s situational awareness from their observable indicators which will in the future be utilized to…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Kalman Filter Slope Measurement Method Based on Improved Genetic Algorithm-Back Propagation

Wuhan University of Technology-Haoyu Wang, Donghua Guo, Gangfeng Tan, Zhenyu Wang, Ming Li, Yifeng Jiang, Meng Ye, Kailang Chen
  • Technical Paper
  • 2020-01-0897
To be published on 2020-04-14 by SAE International in United States
How to improve the measurement accuracy of road gradient is the key content of the research on the speed warning of commercial vehicles in mountainous roads. The large error of the measurement causes a significant effect of the vehicle speed threshold, which causes a risk to the vehicle's safety. Conventional measuring instruments such as accelerometers and gyroscopes generally have noise fluctuation interference or time accumulation error, resulting in large measurement errors. To solve this problem, the Kalman filter method is used to reduce the interference of unwanted signals, thereby improving the accuracy of the slope measurement. However, the Kalman filtering method is limited by the estimation error of various parameters, and the filtering effect is difficult to meet the project research requirements. In this paper, the acceleration of vehicle gravity, driving speed and acceleration of parallel slope are utilied as auxiliary measurement parameters to improve the measurement method. Based on the Kalman model, GA (genetic algorithm) and BP (Back Propagation) neural network are employed to carry out the innovation, covariance matrix and the last Kalman…
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Nonlinear Identification Modeling for PCCI Engine Emissions Prediction Using Unsupervised Learning and Neural Networks

RWTH Aachen University-Wang Pan, Metin Korkmaz, Joachim Beeckmann, Heinz Pitsch
  • Technical Paper
  • 2020-01-0558
To be published on 2020-04-14 by SAE International in United States
Premixed charged compression ignition (PCCI) is an advanced combustion strategy, which has the potential to achieve ultra-low nitrogen oxide and soot emissions at high thermal efficiencies. PCCI combustion is characterized by a complex nonlinear chemical-physical process, which indicates that a physical description involves significant development times and also high computation cost. This paper presents a method to use cylinder pressure data and engine operations parameters for prediction of PCCI engine emissions by unsupervised learning and nonlinear identification techniques. The proposed method first uses principal component analysis (PCA) to reduce the dimension of the cylinder-pressure data. Based on the PCA analysis, a multi-input multi-out model was developed for nitrogen oxide and soot emission prediction by multi-layer perceptron (MLP) neural network. Before the training process, a second principal component analysis was done to reduce the input dimension with hyper-parameters thereby reducing memory requirements of the models. The algorithm is applied to an experimental data set from a single-cylinder light-duty engine with piezo injection system. By comparing the model predictions with experimental results, it is shown that the…