Making an updated and as-built model plays an important role in the life-cycle of a process plant. In particular, Digital Twin models must be precise to guarantee the efficiency and reliability of the systems. Data-driven models can simulate the latest behavior of the sub-systems by considering uncertainties and life-cycle related changes. This paper presents a step-by-step concept for hybrid Digital Twin models of process plants using an early implemented prototype as an example. It will detail the steps for updating the first-principles model and Digital Twin of a brownfield process system using data-driven models of the process equipment. The challenges for generation of an as-built hybrid Digital Twin will also be discussed. With the help of process history data to teach Machine Learning models, the implemented Digital Twin can be continually improved over time and this work in progress can be further optimized.

Ongoing standardization in Industry 4.0 supports tool vendor neutral representations of Piping and Instrumentation diagrams as well as 3D pipe routing. However, a complete digital plant model requires combining these two representations. 3D pipe routing information is essential for building any accurate first-principles process simulation model. Piping and instrumentation diagrams are the primary source for control loops. In order to automatically integrate these information sources to a unified digital plant model, it is necessary to develop algorithms for identifying corresponding elements such as tanks and pumps from piping and instrumentation diagrams and 3D CAD models. One approach is to raise these two information sources to a common level of abstraction and to match them at this level of abstraction. Graph matching is a potential technique for this purpose. This article focuses on automatic generation of the graphs as a prerequisite to graph matching. Algorithms for this purpose are proposed and validated with a case study. The paper concludes with a discussion of further research needed to reprocess the generated graphs in order to enable effective matching.

The global ambitions of a carbon-neutral society necessitate a stable and robust smart grid that capitalises on frequency reserves of renewable energy. Frequency reserves are resources that adjust power production or consumption in real time to react to a power grid frequency deviation. Revenue generation motivates the availability of these resources for managing such deviations. However, limited research has been conducted on data-driven decisions and optimal bidding strategies for trading such capacities in multiple frequency reserves markets. We address this limitation by making the following research contributions. Firstly, a generalised model is designed based on an extensive study of critical characteristics of global frequency reserves markets. Secondly, three bidding strategies are proposed, based on this market model, to capitalise on price peaks in multi-stage markets. Two strategies are proposed for non-reschedulable loads, in which case the bidding strategy aims to select the market with the highest anticipated price, and the third bidding strategy focuses on rescheduling loads to hours on which highest reserve market prices are anticipated. The third research contribution is an Artificial Intelligence (AI) based bidding optimization framework that implements these three strategies, with novel uncertainty metrics that supplement data-driven price prediction. Finally, the framework is evaluated empirically using a case study of multiple frequency reserves markets in Finland. The results from this evaluation confirm the effectiveness of the proposed bidding strategies and the AI-based bidding optimization framework in terms of cumulative revenue generation, leading to an increased availability of frequency reserves.