Designing a control system that can robustly detect faulted emission control devices under all environmental and driving conditions is a challenging task for OEMs. In order to gain confidence in the control strategy and the values of tunable parameters, the test vehicles need to be subjected to their limits during the development process. Complexity of modern powertrain systems along with the On-Board Diagnostic (OBD) monitors with multidimensional thresholds make it difficult to anticipate all the possible scenarios. Finding optimal solutions to these problems using traditional calibration processes can be time and resource intensive. A possible solution is to take a data driven calibration approach. In this method, a large amount of data is collected by collaboration of different groups working on the same powertrain. Later, the data is mined to find the optimum values of tunable parameters for the respective vehicle functions. This large scale data (terabytes) gives the engineers more samples to analyze and confidence in the calibration. A robust data analysis platform capable of handling large scale data and flexible enough to cater to different engineers’ needs is required to accomplish this task. In this paper, some salient features of such a platform developed by Ford Motor Company are presented. The memory efficiency, Model-In-Loop and parallel processing capability of this platform are highlighted. The use of MapReduce programming techniques to analyze large scale calibration data is also discussed.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Data Driven Calibration Approach


    Additional title:

    Sae Int. J. Commer. Veh


    Contributors:

    Conference:

    WCX™ 17: SAE World Congress Experience ; 2017



    Publication date :

    2017-03-28


    Size :

    7 pages




    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    Data-driven Parameter Calibration in Wake Models

    Liu, Bingjie / Plumlee, Matthew / Byon, Eunshin | AIAA | 2018


    A data-driven approach for fast controller calibration of Brake-by-Wire actuators

    Radrizzani S. / Todeschini D. / Riva G. et al. | BASE | 2020

    Free access

    QAR Data-Driven Calibration of Physics-based Aircraft Performance Models using a Machine-Learning Approach

    del Pozo Dominguez, Maria / Lopez Leones, Javier / Roling, Paul C. | AIAA | 2023


    QAR Data-Driven Calibration of Physics-Based Aircraft Performance Models Using a Machine- Learning Approach

    Dominguez, Maria Del Pozo / Leones, Javier Lopez / Roling, Paul C. | TIBKAT | 2023


    Data-Driven Automotive Development: Federated Reinforcement Learning for Calibration and Control

    Rudolf, Thomas / Schürmann, Tobias / Skull, Matteo et al. | Springer Verlag | 2022