Method for the Automatic Generation of Vehicle-Specific Individual Test Sequences

Abstract

AbstractIn vehicle development, more and more test sequences (diagnostic scripts) are established for function testing of individual components, systems and cross-functional methods. Due to decentralization and the modular approach, modern development vehicles consist of different numbers of electronic control units (ECU). The high number of ECUs in purpose and number poses a challenge for test creation and updating.The ECU software is also developed in cycles within the vehicle cycle. This results in a high software variance. This variance leads to the fact that in the vehicle development with global test conditions works. The vehicle structure (ECU and their software status) is uncertain, so errors and a longer script runtime must be expected during test execution.Due to this initial situation a concept was developed, which excludes the individual vehicle structure (global pattern) and verifies and stores this supported by an Artificial Intelligence (AI) database. This always ensures traceability of the vehicle condition. In addition, it is possible to create individualized test sequences for each vehicle and to keep them up to date. Furthermore, the AI can identify the user and to generate user-specific test sequences. Finally, the AI evaluates the quality of the measured values in order to provide the ECU developer with a tool to detect discrepancies.KeywordsArtificial intelligenceECUIoT-devicesTest sequencesVehicle developmentBig dataKubernetesDockerSoftware engineering/architecture