SCUD - Smart Culinary Utility Device: Leveraging edge AI for battery optimization and operation cycles.

Current day society pursues a lifestyle that is simpler, more efficient, reliable, faster, and progressively automated. Culinary Utility Device available in the market exhibit drawbacks including substantial investment costs, increased labor requirements, and excessive time consumption. Adding intelligence to the these devices may make once life happy. Embedded devices with limited resources are now poised to leverage machine learning techniques thanks to the convergence of Edge Computing and the Internet of Things (IoT). Traditional machine learning often demands significant computational resources for predictive tasks. TinyML, which focuses on Embedded Machine Learning, aims to transition a considerable portion of users from high-end devices to low-end gadgets. This paradigm strives to ensure the accuracy of learning models while enabling training and deployment on micro edge devices with resource constraints. It also seeks to optimize processing capabilities and enhance system resilience. This article provides an intuitive overview of Data-Driven State of Charge (SoC) estimation for Li-Ion Batteries. It begins by specification table followed by the hardware in context introducing the background of SoC estimation, followed by discussions on Hardware and signal , links to the design files and BOM in specific. The article delves into essential aspects related to Build and Operational instructions. In conclusion, the article addresses critical challenges and outlines a future road map.