Automotive Big Data Applications Insights from Patents
0 likes194 views
The document discusses various automotive big data applications, focusing on systems for analyzing driving range estimations of electric vehicles and recommending vehicle repair parts. These systems utilize standard, historical, and real-time data, employing big data analytics to create vehicle models and improve repair recommendations based on diverse data sources. Additionally, it covers methods for processing vehicle driving data to manage driving history, accident causes, and maintenance needs through statistical analysis and pattern recognition.
Automotive Big Data Applications Insights from Patents
- 1. ©2016 TechIPm, LLC All Rights Reserved http://www.techipm.com/ 1 Automotive Big Data Applications Insights from Patents Alex G. Lee ([email protected]) US 20160114698 illustrate a system for analyzing big data related to the remaining driving range estimation of an electric vehicle (EV). The system collects attribute data affecting the driving range of the EV. The attribute data includes standard data, historical data, and real-time data. The standard data is the data that does not vary as the vehicle is driven. For example, the standard data includes test data for a capacity degradation of the vehicle battery provided by the battery manufacturer, the nominal driving range of the vehicle etc. The historical data is the data related to the previous probabilistic behavior of a driver. For example, the historical data includes the previous average energy consumption of the vehicle, a battery misuse history etc. The real-time data is the data associated with current driving data and stochastic data. For example, the real-time data includes a traffic jam due to an accident, abrupt rainfall during driving, a detour due to a closed road etc. The system analyzes a correlation between the attribute data and a driving range of the vehicle utilizing a big data analytics. Then, the system generates a vehicle driving range estimation model based on the analyzed correlation. The system analyzes the sensitivity between the vehicle driving range estimation model and the attribute data
- 2. ©2016 TechIPm, LLC All Rights Reserved http://www.techipm.com/ 2 utilizing a big data analytics. Finally, the system modifies the vehicle driving range estimation model based on the fed-back sensitivity. US20160078403 illustrates a system for recommending parts to repair a malfunctioning vehicle. The recommendation is based on the recommendation rules. The system can identify all parts in parts database that are compatible with the specific vehicle using the recommendation rules. Then, the system recommends the subsets of the parts catalog based on information such as the automobile year, make, model, and condition of the vehicle. The recommendation rules are obtained using big data analysis techniques to correlate the data sets in the form of videos, written repair instructions, wiring schematics, bulletins, and other technical and marketing materials. Such data can be produced byOEMs, aftermarket manufacturers, distributors, and experienced mechanics that produce video content, blog descriptions, etc. regarding general or specific vehicle repair and maintenance tasks. US20150317844 illustrates a system of processing and analyzing vehicle driving big data. The vehicle driving big data includes identification data and sensing data. The identification data includes a vehicle identification number, a vehicle type, a vehicle registration number, a driver identification codeetc. The sensing data includes a travel distance, a driving time, starting time, a data acquisition period, a data acquisition time, a speed, an RPM, a break signal, a position, an azimuth, and acceleration, location of the vehicle etc. The system refines the vehicle driving data and acquires statistical data based on the refined vehicle driving data. Then, the system performs big data mining analysis based on the refined vehicle driving data and the acquired statistical data. The acquired statistical
- 3. ©2016 TechIPm, LLC All Rights Reserved http://www.techipm.com/ 3 data can be used for driving history management, establishment of cause of the accident during accident occurrence, accident prevention, and energy saving management. For example, the system analyzes a repeated pattern based on a specific period, the refined vehicle driving data and the acquired statistical data. The driving tendency of the vehicle driver at the specific period can be obtained based on the repeated pattern. The statistical data can include records for accident history and maintenance history. Then, the system performs the mining analysis that generates a learning mode for predicting a change in the accident history and maintenance history data. The accident risk and a maintenance time of the vehicle can be obtained by using the learning model.
- 4. ©2016 TechIPm, LLC All Rights Reserved http://www.techipm.com/ 4