Adopting a Deep Learning Split-Protocol Based Predictive Maintenance Management System for Industrial Manufacturing Operations

EasyChair Preprint 9540

Abstract

This paper presents the best computational modeling (AI/ML and Quantum Computing) methods to predict the performance optimization of predictive maintenance and management of the shop floor activities in manufacturing sites within the industrial manufacturing facility. For industrial manufacturing sites, shop floor activities play a vital role in the productivity and operational efficiencies of any industrial manufacturing site/facility. In manufacturing units, production planners and supervisors have a critical time to predict the production downtimes and predictive maintenance, and sometimes with the production line, a tiny milling bit breaks, shutting down the line. Some cases of unplanned downtime are not only costly deals but also hamper the unplanned delay and downtime for the supervisors at the production sites/factories in industrial productions. In this paper, we introduce a failure detection system that focuses only most probable failure state at maximum utilization and is delicate in incoming jobs to the backup unit while the overloaded unit will recover and resume in the very fresh state. Our proposed scheme introduces an additional parallel system component with help of split protocol and improves overall systems reliability in case of a component failure.

Keyphrases: AI, Cybersecurity, IoT, ML, SAP HANA, SAP S/4

@booklet{EasyChair:9540,
  author    = {Biswaranjan Senapati Senapati and Bharat Rawal},
  title     = {Adopting a Deep Learning Split-Protocol Based Predictive Maintenance Management System for Industrial Manufacturing Operations},
  howpublished = {EasyChair Preprint 9540},
  year      = {EasyChair, 2023}}