Sensor Data Fusion
The combination of optimization and optimal control techniques, which DEIX is able to offer, is fundamental in all of those contexts in which the decision-making problem to be solved is dynamic, i.e. it requires a planning of decisions over time. For example, in the management and control algorithms necessary for the correct operation of an automation system or in decision support in management and logistics. In fact, the introduction of a feedback mechanism in the decision-making process allows the proposed solution to adapt in a natural way to all possible variations from the expected behavior.
Control and decision optimization combines predictive mathematical models (describing the objectives and constraints of the decision problem and its evolution over time) with learning from data and reinforcement learning techniques if the models are not known analytically.
In the context of complex learning, control, decision and optimization problems, knowledge extraction from heterogeneous data and sensors plays a key role. In this area, Deix provides sensor & data fusion solutions that combine mathematical models with statistical inference techniques, learning from data and artificial intelligence.
These solutions enable the creation of virtual sensors, i.e., algorithms that can provide accurate real-time estimates of quantities of interest beyond those that can be directly measured.
This type of approach finds a natural application in the implementation of Digital Twins of processes and products.