Ai-Enabled Power Management System on The Edge
We are developing a prototype of an AI-enabled Battery/Power Management System. The architecture is a transformative AI-enabled power electronics solution in which the battery is directly connected to AI hardware on the edge of the network. In this innovative intelligent solution, the AI algorithm will monitor the health and reliability of the system with unprecedented performance metrics, resulting in increasing optimization of the battery/power source.
To give an example, let’s say an Electric Vehicle (EV) has a range of X miles, with a certain battery set. With implementing our AI-enabled power management system, we are able to optimize the power usage in our EV, resulting in increasing its range. Our solution, can even go further and do health monitoring of the battery, providing the user with recommendations about the health of the power source, which results in prolonging the batteries life.
The applications of our proprietary technology is in electric vehicles, and unmanned electric vehicles such as drones, and battery-powered robots.
Power Electronics RealTime Reliability Assessment and Health Monitoring
AI to ensure maintenance tasks are performed in the most efficient, cost-effective, reliable, and safe manner.
Maintenance is a key area that can drive major cost savings and production value around the world. The cost of machine downtime is high: according to the International Society of Automation, $647 billion is lost globally each year.
Power electronics systems are essential components of the energy-conversion process. According to a report by U.S. Department of Energy, it is expected by 2030, power converters will be used in 80% of applications in the generation, transmission, distribution, and consumer electronics. Controllable power semiconductor devices play the most dominant role in the switching power converters. Operating at high current and voltage creates extreme stresses on the power devices, which often makes them the most susceptible components in the energy conversion process. Therefore, understanding, modeling and predicting the reliability models of the power converters are crucial for enabling emerging technologies and future applications such as electric vehicles, smart grids, and renewable energy.
Our prototype which was developed in 2019 is a light-weight AI-enabled tool that can assess multiple variables in a power semiconductor device in REALTIME and on the edge of the network #edgecomputing, and predicts when and which one of the devices will have a failure in the near future.
The results were published in this paper: