FT Microturbines incorporate a built-in microcontroller system with sensors and wireless communication capabilities, enabling remote control and monitoring from Android, iOS, or Windows devices to remotely optimise complex energy network dynamics and perform predictive maintenance.
FT Digital Twin is equipped with the sensors and communication devices necessary to monitor the entire performance and health of the turbine generator system, providing comprehensive reports to the user and sending data to a central control system.
The Digital Twin, with its internal predictive-maintenance algorithm, accurately predicts when equipment and infrastructure require maintenance, thereby reducing downtime and increasing efficiency.
The FT Digital Twin System utilises modelling and simulation data developed over a decade of research and development by Florestan.
It incorporates a mathematical representation of the physical machine, replicating its behaviour and performance in real time using data from sensors and signal processing algorithms.
Key Digital Twin functions include:
• Monitor the health condition of the machine in real-time and receive alerts before any issues arise.
• Utilise data analysis and Machine Learning to identify potential anomalies, predict future faults, and receive recommendations for maintenance actions.
• Test and validate different scenarios and solutions to aid in scheduling maintenance and minimise the impact on energy production.
Accurately estimating carbon emissions from multiple energy sources can be challenging, especially when different types of hydrogen are mixed with natural gas or other available fuels.
The FT Digital Twin system incorporates mathematical modelling and simulation techniques to align theoretical values with continuously updated sensor data and key environmental parameters.
This enables more precise real-time calculations of carbon emissions, thereby facilitating a more transparent audit and regulatory process.
One of the primary advantages of the FT Digital Twin, with its embedded internet connectivity, is its unlimited scalability (10MW and above) in smart grid configurations. This opens up further opportunities to expand its capabilities for global grid-level optimization by implementing AI and Energy Intelligence, effectively managing the complex dynamics of energy networks.
AI algorithms can accurately predict energy demand, monitor energy usage, and adjust energy supply accordingly, thereby reducing energy waste, cutting costs, and enhancing energy efficiency. Renewable energy sources like wind and solar power exhibit variability, with their energy output changing significantly over time.
The FT smart grid platform, incorporating a hydrogen production plant into the equation, can forecast energy demand and weather conditions to effectively manage intermittent renewable energy sources, determine the optimal timing for storing and releasing energy, and enable the efficient allocation of various renewable fuels in real-time. This approach helps stabilize the grid, improve efficiency, and ensure its reliability.