Signal Abstraction for Root Cause Identification of Control Systems Malfunctions in Connected Vehicles

Abstract

Today’s automotive control systems have gained huge advantage from using integrated software and hardware to reliably manage the performance of vehicles. The integration of largescale software with many hardware components, however, have increased the complexity of diagnosis and root cause analysis for a detected malfunction. High level of expertise and detailed knowledge of the underlying software and hardware are typically required to analyze a large list of variables and precisely identify the root cause of the malfunction. In this paper, an abstraction method is presented to identify the most important signals for a root cause analysis by leveraging data collected from a connected fleet of field vehicles. A novel label propagation methodology is proposed to select the most relevant signals for the root cause analysis by detecting linear and nonlinear correlations between an observed malfunction and candidate test signals of the control system. The proposed label propagation method eliminates the requirement for a priori known correlation kernel that is needed for a regression analysis. The signal abstraction method is applied and successfully tested for abstracting signals in the fuel control system, with high degree of interconnection between software and hardware, using data from more than 5000 connected vehicles.