Future energy systems will face serious operational challenges with system reliability due to fluctuations caused by progressive integration of solar and wind power. Reliable and sustainable energy sources that can be utilized in large parts of Europe and that are able to balance these fluctuations are needed. Geothermal energy has the potential to become an excellent source for both base and flexible energy demands, providing much lower environmental footprint than both fossil and biomass fuels, as well as much less risks and societal resistance than nuclear power. There are however some techno-economic challenges which needs to be addressed to facilitate highly flexible operation of geothermal power plants. In GeoSmart, we propose to combine thermal energy storages with flexible ORC solutions to provide a highly flexible operational capability of a geothermal installation. During periods with low demand, energy will be stored in the storage to be released at a later stage when the demand is higher. As this approach does not influence the flow condition at the wellhead, critical infrastructures will be unaffected under variable energy generation. To improve efficiency, we also propose a hybrid cooling system for the ORC plant to prevent efficiency degradation due to seasonal variations. Efficiency will be further improved by larger power plant heat extraction enabled due to a scaling reduction system consisting of specially design retention tank, heat exchanger, and recombining with extracted gases. The scaling reduction system has the potential to almost double power production of many medium enthalpy geothermal plants. Overall, GeoSmart technologies will drastically reduce geothermal energy costs, making it cost competitive with its fossil fuel-based counterparts. To bring GeoSmart technology to TRL7/8, we will demonstrate it in a medium/high (Turkey) and low (Belgium) temperature fields to show its potential benefits and applicability in different settings.

The overall concept of MANTIS is to provide a proactive maintenance service platform architecture based on Cyber Physical Systems that allows to estimate future performance, to predict and prevent imminent failures and to schedule proactive maintenance. Maintenance is no longer a necessary evil that costs what it costs, but an important function that creates additional value in the business process as well as new business models with a stronger service orientation. Physical systems (e.g. industrial machines, vehicles, renewable energy assets) and the environment they operate in, are monitored continuously by a broad and diverse range of intelligent sensors, resulting in massive amounts of data that characterise the usage history, operational condition, location, movement and other physical properties of those systems. These systems form part of a larger network of heterogeneous and collaborative systems (e.g. vehicle fleets or photovoltaic and windmill parks) connected via robust communication mechanisms able to operate in challenging environments. MANTIS consists of distributed processing chains that efficiently transform raw data into knowledge while minimising the need for bandwidth. Sophisticated distributed sensing and decision making functions are performed at different levels in a collaborative way, ranging from local nodes to locally optimise performance, bandwidth and maintenance; to cloud-based platforms that integrate information from diverse systems and execute distributed processing and analytics algorithms for global decision making. The research addressed in MANTIS will contribute to companies' assets availability, competitiveness, growth and sustainability. Use cases will be the testing ground for the innovative functionalities of the proactive maintenance service platform architecture and for its future exploitation in the industrial world. Results of MANTIS can be utilised directly in several industry areas and different fields of maintenanance.

Thanks to the increasing capabilities of digital technologies, the next generation of industrial control systems are expected to learn from streams of data and to take optimal decisions in real-time, leading to increased performance, safety, energy efficiency, and ultimately value creation. Numerical optimization is at the very core of both learning and decision-making, and machine learning algorithms and artificial intelligence raise huge worldwide research interest, often using cloud computing and large data centers for their optimization computations. However, in order to bring learning- and optimization-based automated decision-making into smart industrial control systems (SICS), two important bottlenecks have to be overcome: (1) computational resources on industrial control systems are locally embedded and limited, and (2) industrial control applications require reliable algorithms, with interpretable and verifiable behavior. Both requirements partially stem from safety aspects, which are crucial in appl

With a multidisciplinary consortium combining key skills in AI, manufacturing, edge computing and robotics, ASSISTANT aims to create intelligent digital twins through the joint use of machine learning (ML), optimization, simulation and domain models. The resulting tools permit to design and operate complex collaborative and reconfigurable production systems based on data collected from various sources such as IoT devices. ASSISTANT targets a significant increase in flexibility and reactivity, products/processes quality, and in robustness of manufacturing systems, by integrating human and machine intelligence in a sustainable learning relationship. ASSISTANT provides decision makers with generative design based software for all manufacturing decisions. Rather than writing ad hoc code for each manufacturing sector, it provides a set of intelligent digital twins that self adapt to the manufacturing environment. It promote a methodology that enhances generative design with learning aspects of AI thanks to the data available in manufacturing. ASSISTANT aims to synthesize predictive/prescriptive models adjusted to the shop floor for each decision levels. Digital twins will be used as oracles by ML in order to converge towards models in phase with reality. This means that rather than writing specific code to cover a restricted set of goals/scenarios/hypotheses for a manufacturing system and a decision level, ASSISTANT will aim at learning models that can be used by standard optimization libraries. In this context, ML is used to predict parameter values, characterize parameters uncertainty, and acquire physical constraints. ASSISTANT will experiment this methodology on a significant panel of use cases selected for their relevance in the current context of the digital transformation of production in major manufacturing sectors undergoing rapid transformations like the energy, the industrial equipment, and automotive sectors which already make extensive use of digital twins.