Improving the multiple errors detection coverage in distributed embedded systems

Currently, a lot of critical applications in automobile and aircraft avionics are built on fault-tolerant real-time distributed embedded systems. Fault injection techniques have been used extensively in the experimental validation of these systems and it is a challenge to adapt them to the demands of new technologies. This paper deals with the effect of physical faults at pin level on the Communication Network Interface in a prototype based on time-triggered architecture. Due to the essential necessity of observing system behavior during injection experiments, a suitable monitor for distributed embedded systems is proposed. The monitor is used to detect failures in the value domain that could lead a system to violate its main concern of fail-silence. With the encouragement to improve detection coverage in the value domain, an error detection code is presented, which is useful for dealing with both unidirectional multiple errors as well as random multiple errors. In order to understand how much the code can increase the coverage, it is tested with a realistic brake-by-wire control application.