Barbier, Alvin (Universitat Politècnica de València), Salavert, José Miguel (Universitat Politècnica de València), Palau, Carlos Enrique (Universitat Politècnica de València), Guardiola, Carlos (Universitat Politecnica de Valencia)

Analysis of Real-Driving Data Variability for Connected Vehicle Diagnostics

Scheduled for presentation during the Regular Session "Highly Automated and Connected Vehicular Systems-I" (MoAT4), Monday, August 29, 2022, 11:00−11:20, Ballroom

10th IFAC International Symposium on Advances in Automotive Control, August 28-31, 2022, Columbus, Ohio, USA

This information is tentative and subject to change. Compiled on April 24, 2024

Abstract

Connected vehicle paradigm allows the systematic recording of data, which may be made available for both on-board and cloud diagnostics functions. However, real-driving conditions may be highly dynamic, making the application of diagnostic methods cumbersome. This article analyzes the variability of real-world data coming from a mild hybrid vehicle at various levels (i.e., vehicle, powertrain and engine cycle). The results show that although non-steady, real-driving conditions can exhibit situations that could be leveraged to characterize the nominal operation of the vehicle over time and therefore ease the detection of faulty operation.