The European Commission is going to publish the new Euro7 standard shortly, with the target of reducing the impact on pollutants emission due to transportation systems. Besides forcing internal combustion engines to operate cleaner in a wider range of operating conditions, the incoming regulation will point out the role of On-Board Monitoring (OBM) as a key enabler to ensure limited emissions over the whole vehicle lifetime, necessarily taking into account the natural ageing of involved systems and possible electronic/mechanical faults and malfunctions. In this scenario, this work aims at studying the potential of data-driven approaches in detecting emission-relevant engine faults, supporting standard On-Board Diagnostics (OBD) in pinpointing of faulty components, which is part of the main challenges introduced by Euro7 OBM requirements. For this purpose, a data-driven model for detection and identification of different faults of engine's components and sensors, which takes as input available on-board measurements and Engine Control Unit (ECU) signals, has been developed using different classification algorithms. The classification model has been optimized, trained, and tested on simulation data generated by a validated 0-D Simulink model representative of a light-duty Diesel plug-in hybrid electric vehicle (PHEV). The best classification algorithm and configuration of hyperparameters have been chosen, and the selected model has been integrated in the ECU software developed in Simulink®. Possible faults significantly affecting pollutant emissions have been selected and simulated, and the accuracy of faults detection obtained with the implemented classification model has been evaluated. In view of a vehicle on-board application, the developed model has been implemented on a rapid prototyping control unit and tested at the Hardware-in-the-Loop (HiL) to evaluate its real-time capability. The preliminary results obtained in terms of effectiveness, robustness and real-world applicability pave the way for further investigations in this field, as a promising solution to help facing the upcoming Euro7 standard.

Stella Canè, L.B. (2024). A Data-driven Approach for Enhanced On-Board Fault Diagnosis to support Euro 7 Standard Implementation. SAE International [10.4271/2024-01-2872].

A Data-driven Approach for Enhanced On-Board Fault Diagnosis to support Euro 7 Standard Implementation

Stella Canè
Writing – Original Draft Preparation
;
Nicolo Cavina
2024

Abstract

The European Commission is going to publish the new Euro7 standard shortly, with the target of reducing the impact on pollutants emission due to transportation systems. Besides forcing internal combustion engines to operate cleaner in a wider range of operating conditions, the incoming regulation will point out the role of On-Board Monitoring (OBM) as a key enabler to ensure limited emissions over the whole vehicle lifetime, necessarily taking into account the natural ageing of involved systems and possible electronic/mechanical faults and malfunctions. In this scenario, this work aims at studying the potential of data-driven approaches in detecting emission-relevant engine faults, supporting standard On-Board Diagnostics (OBD) in pinpointing of faulty components, which is part of the main challenges introduced by Euro7 OBM requirements. For this purpose, a data-driven model for detection and identification of different faults of engine's components and sensors, which takes as input available on-board measurements and Engine Control Unit (ECU) signals, has been developed using different classification algorithms. The classification model has been optimized, trained, and tested on simulation data generated by a validated 0-D Simulink model representative of a light-duty Diesel plug-in hybrid electric vehicle (PHEV). The best classification algorithm and configuration of hyperparameters have been chosen, and the selected model has been integrated in the ECU software developed in Simulink®. Possible faults significantly affecting pollutant emissions have been selected and simulated, and the accuracy of faults detection obtained with the implemented classification model has been evaluated. In view of a vehicle on-board application, the developed model has been implemented on a rapid prototyping control unit and tested at the Hardware-in-the-Loop (HiL) to evaluate its real-time capability. The preliminary results obtained in terms of effectiveness, robustness and real-world applicability pave the way for further investigations in this field, as a promising solution to help facing the upcoming Euro7 standard.
2024
Sae Technical Papers
-
-
Stella Canè, L.B. (2024). A Data-driven Approach for Enhanced On-Board Fault Diagnosis to support Euro 7 Standard Implementation. SAE International [10.4271/2024-01-2872].
Stella Canè, Lorenzo Brunelli, Volker Müller, Giuseppe Sammito, Tobias Brinkmann, Joschka Schaub, Nicolo Cavina
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/964179
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact