Syntiant’s Latest Edge AI chip adds battery management models

Eatron Technologies is running its battery management algorithms on the latest edge AI system on chip from Syntiant.

The model and algorithms in the Eatron Intelligent Software Layer run on the Syntiant ultra-low power NDP120 Neural Decision Processor.

Eatron’s pre-trained AI models deliver state-of-health, state-of-charge, and remaining useful life assessments to provide higher accuracy out of the box, thereby maximising available power. Predictive diagnostics routines can detect potential battery issues long before they occur, enhancing safety.

The NDP120 uses a tensor processing core built from the ground up to support energy efficient inference without compromising ease of programming. This second generation architecture delivers 25x the tensor throughput of the previous core in the NDP100 and NDP101 devices that are currently shipping in high volumes.

The Syntiant Core 2 is built around a highly optimized tensor-based memory and processing system designed to avoid inefficiencies in stored program architectures. Each layer independently controls its parameter, input, and output tensors consistent with graph-based execution, enabling neural designers with full control of multiple concurrent independent networks, or swapping network configurations depending on operating conditions.

The resulting AI-BMS-on-chip can provide real-time analysis and decision-making without needing to rely on complex cloud infrastructure, boosting battery pack performance by 10%.

Eatron has also worked with UK battery modelling developer About:Energy on AI-based battery management algorithms.

The jointly-developed plug-and-play solution will bring performance, safety and longevity enhancements to a wide range of battery-powered applications, from consumer electronics and e-bikes to micro LCVs and forklifts.

The AI-BMS-on-chip can be customised through a user-friendly toolchain that allows it to be optimised to each individual application, while existing BMS hardware can be easily upgraded to take advantage of its best-in-class performance.

“We are now running our latest AI models completely integrated on the edge in the Syntiant chip. With AI-BMS-on-chip, we can ensure any battery-powered application can be deployed in the millions in complete safety while getting the most out of the battery.” - Amedeo Bianchimano, Chief Product Delivery Officer at Eatron Technologies

“Our NDP120 allows Eatron’s software to process all the data on the edge for batteries. It enhances battery life, safety and performance. This makes it perfect for everything from consumer electronics all the way to commercial vehicles.” - Mallik P. Moturi, Chief Business Officer at Syntiant