Real-World Driving Data Research Articles

Machine Learning Prediction of a Battery’s Thermal-Related Health Factor in a Battery Electric Vehicle Using Real-World Driving Data

Electric vehicles (EVs) are alternatives to traditional combustion engine-powered vehicles. This work focuses on a thermal management system for battery EVs using liquid cooling and a machine learning (ML) model to predict their thermal-related health. Real-world data of EV operation, battery and cooling conditions were collected. Key influencing factors on the thermal-related health of batteries were identified. The ML model’s effectiveness was evaluated against experimental test data. The ML model proved effective in predicting and analyzing battery thermal health, suggesting its potential for use with the thermal management system.

Energy Consumption Estimation Method of Battery Electric Buses Based on Real-World Driving Data

Energy Consumption Estimation Method of Battery Electric Buses Based on Real-World Driving Data

Driving Characteristics Analysis Method Based on Real-World Driving Data

All vehicles available for sale undergo certification tests mandated by law, and their certified fuel efficiency from these tests is indicated and disclosed. However, to address discrepancies between the certified fuel efficiency and actual driving conditions, more sophisticated certified modes, post-certification systems, and real-world driving tests have been introduced to complement the fuel efficiency certification system. The incorporation of a real-world driving mode, similar to certification modes, in vehicle research and development is of paramount importance from a directional perspective. To achieve this, various methods of configuring real-world driving modes have been proposed and applied in research. However, the validation of the correlation between fuel efficiency in real-world driving modes and certified driving modes is relatively limited. This study aimed to construct real-road driving cycles that are similar to the federal test procedure (FTP-75) and highway fuel economy test (HWFET) certification modes to determine the differences between the driving characteristics of the certification modes and real-road driving. The present study employed the commonly used relative positive acceleration analysis method along with a segmented short-trip technique for analysis. Additionally, variables such as fuel consumption and driving time were utilized to diversify our analytical methods. Test Routes A and B were configured for comparison with the fuel efficiency certification mode. An analysis of the relative positive acceleration (RPA) in both the test routes and certification mode confirmed that Test Route B, reflecting the actual driving patterns, closely follows the RPA distribution of the certification mode. Additionally, the fuel consumption for each short trip on each route was graphically represented, addressing aspects where determining the driving characteristics based solely on the RPA, such as the road grade, was difficult.

Real-World Driving Data Indexes Dopaminergic Treatment Effects in Parkinson's Disease.

Driving is a complex, everyday task that impacts patient agency, safety, mobility, social connections, and quality of life. Digital tools can provide comprehensive real-world (RW) data on driver behavior in patients with Parkinson's disease (PD), providing critical data on disease status and treatment efficacy in the patient's own environment. This pilot study examined the use of driving data as a RW digital biomarker of PD symptom severity and dopaminergic therapy effectiveness. Naturalistic driving data (3974 drives) were collected for 1 month from 30 idiopathic PD drivers treated with dopaminergic medications. Prescriptions data were used to calculate levodopa equivalent daily dose (LEDD). The association between LEDD and driver mobility (number of drives) was assessed across PD severity, measured by the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS). PD drivers with worse motor symptoms based on self-report (Part II: P = 0.02) and clinical examination (Part III: P < 0.001) showed greater decrements in driver mobility. LEDD levels >400 mg/day were associated with higher driver mobility than those with worse PD symptoms (Part I: P = 0.02, Part II: P < 0.001, Part III: P < 0.001). Results suggest that comprehensive RW driving data on PD patients may index disease status and treatment effectiveness to improve patient symptoms, safety, mobility, and independence. Higher dopaminergic treatment may enhance safe driver mobility in PD patients with worse symptom severity.

Electric Vehicle Energy Consumption Analysis and Prediction Based on Real-world Driving Data

Electric Vehicle Energy Consumption Analysis and Prediction Based on Real-world Driving Data

Lithium-ion Battery State of Health Estimation Based on Real-world Driving Data

Lithium-ion Battery State of Health Estimation Based on Real-world Driving Data

Automotive Electrification Challenges Shown by Real-World Driving Data and Lifecycle Assessment

Electric mobility is considered a solution to reduce carbon emissions. We expanded a lifecycle assessment with data on technical limitations and driving habits (based on real-world data) in order to identify the environmentally optimal drivetrain for each individual driving behavior with current and projected technologies, focusing on CO2 emissions. By combining all data, an environmentally optimal European drivetrain mix is calculated, which is dominated by fuel-cell electric vehicles (50% in 2020, 47% in 2030), followed by plug-in hybrid-electric vehicles (37%, 40%), battery-electric vehicles (BEV) (5%, 12%), and Diesel vehicles (2%, 1%). Driving behavior defines the most environmental drivetrain and the coexistence of different drivetrains is currently still necessary. Such information is crucial to identify limitations and unmet technological needs for full electrification. If range is not considered a limitation, the environmentally optimal drivetrain mix is dominated by BEVs (71%, 75%), followed by fuel cell electric vehicles (25%, 19%) and plug-in electric vehicles (4%, 6%). This confirms the potential environmental benefits of BEVs for current and future transportation. Developments in battery energy density, charging, and sustainable production, as well as a change in driving behavior, will be crucial to make BEVs the environmentally optimal drivetrain choice.

Automotive Electrification Challenges Shown by Real-World Driving Data and Lifecycle Assessment

Automotive Electrification Challenges Shown by Real-World Driving Data and Lifecycle Assessment

Identifying and Labeling Potentially Risky Driving: A Multistage Process Using Real-World Driving Data

Every year, over 50 million people are injured and 1.35 million die in traffic accidents. Risky driving behaviors are responsible for over half of all fatal vehicle accidents. Identifying risky driving behaviors within real-world driving (RWD) datasets is a promising avenue to reduce the mortality burden associated with these unsafe behaviors, but numerous technical hurdles must be overcome to do so. Herein, we describe the implementation of a multistage process for classifying unlabeled RWD data as potentially risky or not. In the first stage, data are reformatted and reduced in preparation for classification. In the second stage, subsets of the reformatted data are labeled as potentially risky (or not) using the Iterative-DBSCAN method. In the third stage, the labeled subsets are then used to fit random forest (RF) classification models—RF models were chosen after they were found to be performing better than logistic regression and artificial neural network models. In the final stage, the RF models are used predictively to label the remaining RWD data as potentially risky (or not). The implementation of each stage is described and analyzed for the classification of RWD data from vehicles on public roads in Ann Arbor, Michigan. Overall, we identified 22.7 million observations of potentially risky driving out of 268.2 million observations. This study provides a novel approach for identifying potentially risky driving behaviors within RWD datasets. As such, this study represents an important step in the implementation of protocols designed to address and prevent the harms associated with risky driving.

Trip Energy Estimation Methodology and Model Based on Real-World Driving Data for Green-Routing Applications

A data-informed model to predict energy use for a proposed vehicle trip has been developed in this paper. The methodology leverages roughly one million miles of real-world driving data to generate the estimation model. Driving is categorized at the sub-trip level by average speed, road gradient, and road network geometry, then aggregated by category. An average energy consumption rate is determined for each category, creating an energy rate look-up table. Proposed vehicle trips are then categorized in the same manner, and estimated energy rates are appended from the look-up table. The methodology is robust and applicable to a wide range of driving data. The model has been trained on vehicle travel profiles from the Transportation Secure Data Center at the National Renewable Energy Laboratory and validated against on-road fuel consumption data from testing in Phoenix, Arizona. When compared against the detailed on-road conventional vehicle fuel consumption test data, the energy estimation model accurately predicted which route would consume less fuel over a dozen different tests. When compared against a larger set of real-world origin–destination pairs, it is estimated that implementing the present methodology should accurately select the route that consumes the least fuel 90% of the time. The model results can be used to inform control strategies in routing tools, such as change in departure time, alternate routing, and alternate destinations to reduce energy consumption. This work provides a highly extensible framework that allows the model to be tuned to a specific driver or vehicle type.

Effectiveness of Plug-in Hybrid Electric Vehicle Validated by Analysis of Real World Driving Data

In recent years, the usage of various alternative energies is considered from a viewpoint of CO2 emission reduction. Toyota Motor Corporation considers that Plug-in Hybrid Electric Vehicles (PHEVs) is the best practical solution, and has launched Prius Plug-in Hybrid in January 2012. Prior to this, in December 2009, Toyota sold 650 PHEVs through lease programs for validation testing in Europe, the U.S. and Japan. As a result, not only the fuel reduction effect in case of real market usage was confirmed, but also the relationship between frequency of charging and fuel reduction effect. This paper discusses the analysis of the validation test results.

Analysis and Modeling of Sudden Crossing Behavior of Pedestrian in Urban Narrow Road Based on Real World Driving Data

Analysis and Modeling of Sudden Crossing Behavior of Pedestrian in Urban Narrow Road Based on Real World Driving Data

Optical Information for Car Following: The Driving by Visual Angle (DVA) Model

The present study developed and tested a model of car following by human drivers. Previous models of car following are based on 3-D parameters such as lead vehicle speed and distance information, which are not directly available to a driver. In the present paper we present the driving by visual angle (DVA) model, which is based on the visual information (visual angle and rate of change of visual angle) available to the driver. Two experiments in a driving simulator examined car-following performance in response to speed variations of a lead vehicle defined by a sum of sine wave oscillations and ramp acceleration functions. In addition, the model was applied to six driving events using real world-driving data. The model provided a good fit to car-following performance in the driving simulation studies as well as in real-world driving performance. A comparison with the advanced interactive microscopic simulator for urban and nonurban networks (AIMSUN) model, which is based on 3-D parameters, suggests that the DVA was more predictive of driver behavior in matching lead vehicle speed and distance headway. Car-following behavior can be modeled using only visual information to the driver and can produce performance more predictive of driver performance than models based on 3-D (speed or distance) information. The DVA model has applications to several traffic safety issues, including automated driving systems and traffic flow models.