Edge Computing Applied to Industrial Machines

Abstract

This paper will review specific aspects of the edge computing architecture and its correlation to industrial applications as part of a literal revision, performed to provide evidences supporting the use of edge solutions in challenging conditions which arise in Industry 4.0, including smart factories and smart agriculture. Further it presents findings about accuracy improvements comparing conventional machine learning techniques for many important tasks, such as image classification and speech recognition, how edge applications are adopting Artificial Intelligence (AI) to assist users in tasks like augmented reality, face recognition, and intelligent personal assistants. Studies like this leads the present review to acknowledge that AI has great potential when combined with edge devices and might maximize the potential of “not-smart” existing applications. This paper aims to present some important findings on this area, compare main architectural aspects and provide a broad view of how edge solutions might be built. Having discussed how the edge computing works and having provided an overview about how it may be applied to industrial plants, the final section of this paper addresses ways to foment the use of artificial intelligence on edge solutions, forming a new source of “smart capabilities” to existing environments.