Hyperdimensional Computing for Sustainable Manufacturing: An Initial Assessment

TL;DR

This paper evaluates HyperDimensional Computing (HDC) as an energy-efficient alternative to traditional AI models in smart manufacturing, demonstrating comparable accuracy with significantly reduced energy use and faster processing times.

Contribution

It introduces HDC for geometric quality prediction in smart machining and quantifies its energy and time efficiency improvements over conventional AI models.

Findings

HDC achieves accuracy comparable to traditional models.

HDC reduces training energy by 200× and inference energy by 175-1000×.

HDC significantly accelerates training and inference times.

Abstract

Smart manufacturing can significantly improve efficiency and reduce energy consumption, yet the energy demands of AI models may offset these gains. This study utilizes in-situ sensing-based prediction of geometric quality in smart machining to compare the energy consumption, accuracy, and speed of common AI models. HyperDimensional Computing (HDC) is introduced as an alternative, achieving accuracy comparable to conventional models while drastically reducing energy consumption, 200$\times$ for training and 175 to 1000$\times$ for inference. Furthermore, HDC reduces training times by 200$\times$ and inference times by 300 to 600$\times$, showcasing its potential for energy-efficient smart manufacturing.