Low Size, Weight, and Power Neuromorphic Computing to Improve Combustion Engine Efficiency

Neuromorphic computing offers one path forward for AI at the edge. However, accessing and effectively utilizing a neuromorphic hardware platform is non-trivial. In this work, we present a complete pipeline for neuromorphic computing at the edge, including a small, inexpensive, low-power, FPGA-based...

Full description

Saved in:
Bibliographic Details
Published in2020 11th International Green and Sustainable Computing Workshops (IGSC) pp. 1 - 8
Main Authors Schuman, Catherine D., Young, Steven R., Mitchell, J. Parker, Johnston, J. Travis, Rose, Derek, Maldonado, Bryan P., Kaul, Brian C.
Format Conference Proceeding
LanguageEnglish
Published IEEE 19.10.2020
Subjects
combustion
combustion engine efficiency
complete pipeline
engine control unit
engine simulations
Engines
field programmable gate arrays
FPGA
FPGA-based neuromorphic hardware platform
Fuels
Hardware
hardware-compatible spiking neural networks
Heat engines
ignition
inexpensive power
internal combustion engine
internal combustion engines
low size
neural chips
neural nets
neuromorphic
neuromorphic hardware simulations
Neuromorphics
open-loop engine control
power estimates
power neuromorphic computing
spark-ignition internal combustion engine
Training
training algorithm
training software
Online AccessGet full text

Cover

More Information
Summary:Neuromorphic computing offers one path forward for AI at the edge. However, accessing and effectively utilizing a neuromorphic hardware platform is non-trivial. In this work, we present a complete pipeline for neuromorphic computing at the edge, including a small, inexpensive, low-power, FPGA-based neuromorphic hardware platform, a training algorithm for designing spiking neural networks for neuromorphic hardware, and a software framework for connecting those components. We demonstrate this pipeline on a real-world application, engine control for a spark-ignition internal combustion engine. We illustrate how we connect engine simulations with neuromorphic hardware simulations and training software to produce hardware-compatible spiking neural networks that perform engine control to improve fuel efficiency. We present initial results on the performance of these spiking neural networks and illustrate that they outperform open-loop engine control. We also give size, weight, and power estimates for a deployed solution of this type.
DOI:10.1109/IGSC51522.2020.9291228