A leader in edge-native artificial intelligence (AI) and machine learning (ML) solutions, MicroAI, has integrated its AtomML technology with Renesas’s RA Microcontroller (MCU). Through the collaboration with Renesas, an industry leader in microcontrollers, MicroAI can train machine learning models directly in embedded systems, a first in the industry.
MicroAI chief executive officer Yasser Khan, said, “Companies around the globe have been asking for predictive insight into how their assets are performing, behaving, and being utilized to increase the productivity of the equipment they deploy. Working with Renesas, MicroAI is delivering that capability by utilizing our technology to bring machine learning to MCUs, providing the ability to train machine learning models directly in the embedded environment.
By integrating Edge AI into their systems, owners and manufacturers of industrial, commercial, and consumer products can now quickly integrate MicroAI into their products. It enables AI-powered solutions to be deployed faster to market thanks to lower connectivity, cloud, and operational costs. MicroAI is embedded in machines and IoT devices to provide next-generation intelligence.
Mohammed Dogar, senior director of global business development, Renesas, said, “We are excited to work with MicroAI to support its technology on our MCUs. The industry has been asking to bring more insight and intelligence into the performance of their assets closer to the source of the data, and, working with MicroAI, we have a solution.”
MicroAI provides manufacturers and asset owners with a deep insight into the behavior, health, and performance of their equipment by using patented machine learning algorithms. In the automotive industry, robot welding arms are used on assembly lines, while greenhouse gas efficiency is used in agriculture. Manufacturers and asset owners have to manage unplanned downtime and static maintenance schedules, which generate unnecessary costs and wasted service hours. They can only respond when a problem arises without visibility into asset performance.
