Industrial control systems need to be highly reliable and precise at all times to ensure operational efficiency and prevent costly downtime. Early fault detection is crucial and is partially realized by runtime monitoring components. A correct-by-construction approach based on contract specifications allows early intervention in case of potential faults. In this paper, we suggest to combine the time-sensitive behavioral contracts with a multi-domain system model specifically designed for fault injection to improve the model as well as the contract specification at design time. This allows for early detection of potential faults and a more reliable system specification based on the analyzed behavior. We successfully realized a co-simulation environment comprising a fault-injection tool and contract-based monitors. We discussed the proposed approach using the example of a DC motor highlighting the benefits and potential enhancements of this systematic methodology.

The paradigm shift to more unified network topologies for industrial distributed systems is fueled by the uptake of the Time Sensitive Networking (TSN) standard, which enables the separation of time critical traffic following the Time-Division Multiple Access (TDMA) scheme. However, the configuration of such systems is currently cumbersome and potentially error prone. To provide support at design time when modelling distributed real-time applications that communicate using TSN, this work proposes a general concept for automated configuration and deployment. Our proof-of-concept implementation is based on the IEC 61499 modelling standard for industrial automation systems and is validated in ten representative scenarios, including heterogeneous setups using several hardware platforms. We show that our method upholds the expected synchronisation and timing behaviour for TSN, and provides a significant reduction in configuration steps while functioning correctly in various setups without adjustment.

The Time Sensitive Networking (TSN) standard was introduced to provide deterministic Ethernet-based communication for industrial distributed systems. However, configuration needs to be done manually and is error prone. Combining TSN with the IEC 61499 modeling standard opens up new opportunities for automatic network configuration. A prerequisite is to have an in depth understanding of the requirements for a TSN/IEC 61499 control system and especially of the communication time behavior. We developed a time measurement concept to analyze the timing effects on three important layers under different traffic configurations. We deployed our IEC 61499 implementation on two directly connected Intel I210 evaluation boards based on a minimized Linux Operating System to reduce non-deterministic external influences. The results show the expected effect of using a TSN configuration and a particularly positive impact with TSN transmission windows that are long enough for the IEC 61499 application, especially at the receiving device. The measured delays are shorter for the IEC 61499 application when it is scheduled as time-critical with competing traffic compared to when it runs without a TSN schedule and competing traffic. This is evidence that IEC 61499 performs very well together with a TSN configuration, which opens the door for automatic network configuration in IEC 61499 Ethernet/TSN control applications.

Precisely timed execution of resource constrained bare-metal applications is difficult, because the embedded software developer usually has to implement and check the timeliness of the executed application through manual interaction with timers or counters. In the scope of this work, we propose a combined timing specification and concept for time annotation and control blocks in C++. Our proposed blocks can be used to measure and profile software block execution time. Furthermore, it can be used to control and enforce the software time behavior at runtime. After the application of these time blocks, a trace-based verification against the block-based timing specification can be performed to obtain evidence on the correct implementation and usage of the time blocks on the target platform. We have implemented our time block concept in a C++ library and tested it on an ARM Cortex A9 bare-metal platform. The combined usage of timing specification and our time block library has been successfully evaluated on a critical flight-control software for a multi-rotor system.

Real-time communication of distributed automation systems come with many challenges as there is no common time basis. Often a periodic execution of applications is considered which leads to time phenomena like drifts or jitter. Thus, this type of communication requires observance and enforcement of real-time properties to guarantee reliability of distributed systems. New industrial technologies like Time-Sensitive Networking (TSN) and the IEC 61499 standard provide support to conquer upcoming challenges. Therefore, we are using these jointly with contract-based design to propose a design methodology for verification of real-time communication in IEC 61499 systems. We implemented a simulation-based verification environment and performed postmortem trace-based verification against timing specifications. The evaluation confirms the possibility of integrating our proposed representation for non-local communication into IEC 61499 for analyzing time behavior of applications.

Precisely timed execution of resource constrained bare-metal applications is difficult, because the embedded software developer usually has to implement and check the timeliness of the executed application through manual interaction with timers or counters. In the scope of this work, we propose a concept for time annotation and control blocks in C++. Our proposed blocks can be used to measure and profile software block execution time. Furthermore, it can be used to control and enforce the software time behavior at run-time. We have implemented our concept in a C++ library and tested it on an ARM Cortex A9 bare-metal platform. The usage of our library has been evaluated on a critical flight-control software for a multi-rotor system. The results show that our concept is working, while still having some room for systematic accuracy testing and optimization.