Several use cases from the areas of manufacturing and process industry, require highly accurate sensor data. As sensors always have some degree of uncertainty, methods are needed to increase their reliability. The common approach is to regularly calibrate the devices to enable traceability according to national standards and Système International (SI) unitswhich follows costly processes. However, sensor networks can also be represented as Cyber Physical Systems (CPS) and a single sensor can have a digital representation (Digital Twin) to use its data further on. To propagate uncertainty in a reliable way in the network, we present a system architecture to communicate measurement uncertainties in sensor networks utilizing the concept of Asset Administration Shells alongside methods from the domain of Organic Computing. The presented approach contains methods for uncertainty propagation as well as concepts from the Machine Learning domain that combine the need for an accurate uncertainty estimation. The mathematical description of the metrological uncertainty of fused or propagated values can be seen as a first step towards the development of a harmonized approach for uncertainty in distributed CPS in the context of Industrie 4.0. In this paper, we present basic use cases, conceptual ideas and an agenda of how to proceed further on.

State-of-the-art Deep Reinforcement Learning Algorithms such as DQN and DDPG use the concept of a replay buffer called Experience Replay. The default usage contains only the experiences that have been gathered over the runtime. We propose a method called Interpolated Experience Replay that uses stored (real) transitions to create synthetic ones to assist the learner. In this first approach to this field, we limit ourselves to discrete and non-deterministic environments and use a simple equally weighted average of the reward in combination with observed follow-up states. We could demonstrate a significantly improved overall mean average in comparison to a DQN network with vanilla Experience Replay on the discrete and non-deterministic FrozenLake8x8-v0 environment.

No abstract

No abstract