In a complex systems failures can be detected in advance by analysing the sensor’s data. Each single sensor reading on its own could meaningless, but Artificial Intelligence can control 1000’s of variables at the same time and estimate the residual life expectancy for the system or the components.
We develop algorithms that learn from historical data and predict the future load requests by using the learned models together with the available weather forecasts. We have been developed a class of algorithms that is completely data-agnostic and can work just as well on both industrial and commercial utilities.
The thermal management of buildings can be improved in several ways: dynamic thermostats set-points, performance indicators, diagnostics and optimal control of HVACs. To do this kind of analysis we need an accurate thermal model of the building. Our solution shows fundamental advantages over existing systems.
Flow Meters are expensive and difficult to install and maintain. In this case the Virtual flow Meters can be used both to continuously check the health status of the physical devices or to replace or integrate the physical sensors in flow assurance applications.
Machining devices and tools and measuring equipment are affected by thermal deformation. This affects both the machining precision as well as the control systems of the machine. Our nonlinear data driven approach based on Neural Networks can give good results in estimating those values.
OpenGeo is a customized platform that enables the management of a Geomechanical Laboratory, the data analysis and the integration of various laboratory testing apparatus.