Abstract
The prediction mechanism is very crucial in a smart factory as they widely help in improving the product quality and customer’s experience based on learnings from past trends. The implementation of analytics tools to predict the production and consumer patterns plays a vital rule. In this paper, we put our efforts to find integrated solutions for smart factory concerns by proposing an efficient task management mechanism based on learning to scheduling in a smart factory. The learning to prediction mechanism aims to predict the machine utilization for machines involved in the smart factory, in order to efficiently use the machine resources. The prediction algorithm used is artificial neural network (ANN) and the learning to prediction algorithm used is particle swarm optimization (PSO). The proposed task management mechanism is evaluated based on multiple scenario simulations and performance analysis. The comparisons analysis shows that proposed task management system significantly improves the machine utilization rate and drastically drops the tasks instances missing rate and tasks starvation rate.
Highlights
The virtual objects are contained in a virtual network, which replicates the physical representation, dependencies and context of the physical world objects
The learning to prediction mechanism predicts the tasks execution status and machine utilization under a given load of the machines/tasks based on history decisions
The variations of particle swarm optimization (PSO) are used in the learning to prediction mechanism as velocity boost PSO (VB-PSO)-NN and
Summary
The virtual objects are contained in a virtual network, which replicates the physical representation, dependencies and context of the physical world objects. The internet of things (IoT) enabled smart factory solutions help achieving the real-time production visualization with the identification of manufacturing objects. The technologies such as radio frequency identification (RFID) are used to interpret the real-world object into smart factory’s virtual objects along with their behaviors and interactions. The smart factory has interconnected supply chains and autonomous control of vehicles, machines and robots resulting in efficient production tasks management such as getting shipments ready based on tracking of arrivals and departures and avoiding delays with the help of self-driving vehicles and self-delivering robots. TThhee ssttuuddyy iinn [[77]],, pprreesseennttss aa bbaasseelliinnee pprreeddiiccttiivvee mmaaiinntteennaannccee ssoolluuttiioonn,, wwhhiicchh ccoonnssiissttss ooff ccoommppoonneennttss ssuucchh aass aa ttaarrggeett ddeevviiccee ((TTDD)),, ddeevviiccee hheeaalltthh iinnddeexx ((DDHHII)) aanndd rreemmaaiinniinngg--uusseeffuull--lliiffee ((RRUULL)) pprreeddiiccttiivvee mmooddeell. Artificial neural networks started to flourish once the processing power of computers increased dramatically, as computation power was one of the key issues faced in the progress of ANNs at the initial stages [34]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
