Abstract

There is a rising demand for customised products with a high degree of complexity. To meet these demands, manufacturing lines are increasingly becoming autonomous, networked, and intelligent, with production lines being virtualised into a manufacturing cloud, and advertised either internally to a company, or externally in a public cloud. In this work, we present a novel approach to two key problems in such future manufacturing systems: the manufacturability problem (whether a product can be manufactured by a set of manufacturing resources) and the control problem (how a particular product should be manufactured). We show how both production recipes specifying the steps necessary to manufacture a particular product, and manufacturing resources and their topology can be formalised as labelled transition systems, and define a novel `task simulation relation’ which captures what it means for a recipe to be manufacturable on a production topology. We show how a controller that can orchestrate the resources in order to manufacture the product on the topology can be extracted from the task simulation relation, and give an algorithm to compute a task simulation relation and a controller.

This talk will be based on the following publications:

L de Silva, P Felli, J C Chaplin, B Logan, D Sanderson, S M Ratchev: Realisability of Production Recipes. European Conference on Artificial Intelligence (ECAI) 2016: 1449-1457

L de Silva, P Felli, J C Chaplin, B Logan, D Sanderson, S M Ratchev: Synthesising Industry-Standard Manufacturing Process Controllers. International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2017: 1811-1813

P Felli, L de Silva, B Logan, S M Ratchev: Process Plan Controllers for Non-Deterministic Manufacturing Systems. International Joint Conference on Artificial Intelligence (IJCAI) 2017: 1023-1030