Anomaly Detection in Fleet Vehicle Data and Statistical approach to develop Engine System OBD thresholds

2024-28-0195

To be published on 12/05/2024

Event
11th SAEINDIA International Mobility Conference (SIIMC 2024)
Authors Abstract
Content
On-Board-Diagnostics are crucial for ensuring the proper functioning of Vehicle’s emission control system by continuously monitoring various sensors and components. When the failure is detected, the Check Engine Light (CEL) is triggered on Vehicle’s dashboard, alerting the driver to seek professional service to address the issue. However, the task of developing the Diagnostics strategies and perform robust calibration is a challenging and time consuming. Model in Loop Testing and Simulation is a technique used to understand and estimate the behavior of system or sub system. The diagnostics model can be tested and refined within the model-based environment allowing a complex system to be efficiently regulated. Model in loop framework could be used at various stages of development from very early in the design phase to later stages of series developments through vehicle fleet data. This framework allows an early identification and correction of errors and bugs. In this paper, the statistical data is used to detect anomaly in Fleet Vehicle data and understand the relativity with different systems. A data driven MIL Simulation set up is established to validate and iterate for robust calibration. The drift monitor controller model is selected as a case study to replicate the behavior and resolve the real time calibration issue. This approach on OBD systems to assess the reliability of models and make robust calibration through Performance Offset Number (PON) is carried out in Simulink environment. Different combination of Calibration input data and Fleet Vehicle data are taken for validation to ensure repeatability of performance and decisions related to fault detection criteria. The key emphasis of this paper is to discuss on framework to identify anomaly from fleet data and resolve through MIL simulation to optimize monitor performance.
Meta TagsDetails
Citation
Kumar, A., Hegde, K., Challa, K., and H, Y., "Anomaly Detection in Fleet Vehicle Data and Statistical approach to develop Engine System OBD thresholds," SAE Technical Paper 2024-28-0195, 2024, .
Additional Details
Publisher
Published
To be published on Dec 5, 2024
Product Code
2024-28-0195
Content Type
Technical Paper
Language
English