Machine operator-centric parameterization of Artificial Intelligence for tightly coupled, distributed, networked control systems.
Complex, industrial control systems are often heavily dependent on human experience and intuition. However, the best possible control of machines is crucial for their efficient use. While AI methods offer the potential to emulate human knowledge and thus make it usable, they often fail in practical applications due to the complexity on the one hand and the distributed architecture of industrial control systems on the other. OpAI4DNCS explores the use of AI at the control level in mobile hydraulic-electric machines using the example of complex drilling rigs and their hydraulic subsystems to accelerate setup and increase the efficiency of operation, especially for inexperienced machine operators. To this end, first, adaptive, intelligent, learning control systems on a multi-agent basis need to be explored and more tightly coupled across delivery boundaries to reduce dead times. Second, the systematic collection and use of human experiential knowledge ensures explainability and safe machine operation even in limit situations. A platform for the practical, industrial design and use of shared control approaches between machine operator and MAS, usable in complex machines with distributed control systems, is to be developed and tested and established on the basis of a drilling rig.