Analysis of Real-Driving Data Variability for Connected Vehicle Diagnostics. Issue 24 (2022)

• Record Type: Journal Article
• Authors: Barbier, Alvin; Salavert, José Miguel; Palau, Carlos E.; Guardiola, Carlos
• Is Part Of: IFAC-PapersOnLine. Volume 55:Issue 24(2022)
• Page Start: 45
• Page End: 50
• Publication Date: 2022
• Subjects: Real-driving conditions -- data-driven diagnostic -- in-cylinder pressure -- connected vehicle; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2022.10.260
• Languages: English
• ISSNs: 2405-8963

Abstract

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.