Model Based Reusable and Reliable Software Validation for Functional Coverage using Virtual ECUs 2007-01-1742
In embedded software world, development and testing are becoming far more complex with growing functionality and fail safe strategies. As a result of that, model-based software development is getting increasingly popular in capturing the functional requirements and auto generating the code from these validated models to avoid any functional deficiency. However, the complexity in the model may not be correctly interpreted by the code generation tool and may result to an incorrect code behavior. In this paper, a methodology has been proposed and implemented to validate the generated code against the models. Simulation test scripts are recorded in the modeling environment to generate the desired set of test inputs. These input scripts are designed to get complete transition and state exposure to maximize the functional coverage. With these test scripts, expected outputs are recorded for downstream validation in the simulation environment with mature models. When the virtual ECU (created from the auto generated code) executes the captured inputs, generated outputs are recorded and compared against prerecorded expected outputs. Furthermore, the same validation can be done for all future releases to make sure that the generated code integrity is maintained with each modification. It is a step forward towards bringing the virtual world ECU validation as close as possible to the real world.