Wicaksono, Hendro; Prohl, Enrst Victor; Ovtcharova, Jivka Hyper heuristc based production process scheduling to improve productivity in sustainable manufacturing Inproceedings Proceeding the 22nd International Conference on Production Research, Brazil, 28 July – 1 August, 2013, 2013. Abstract | BibTeX | Tags: energy efficiency, hyper heuristics, manufacturing, production scheduling @inproceedings{Wicaksono2013d,
title = {Hyper heuristc based production process scheduling to improve productivity in sustainable manufacturing},
author = {Hendro Wicaksono and Enrst Victor Prohl and Jivka Ovtcharova},
year = {2013},
date = {2013-08-01},
booktitle = {Proceeding the 22nd International Conference on Production Research, Brazil, 28 July – 1 August, 2013},
abstract = {In recent years, increased customer-demand in individualized and timely products has changed the playing field for manufacturing industries. The production process is perpetually gaining complexity whereas its life-cycle is shortening. Additionally, a growing ecological conscience enforces the consideration of energy effi-ciency. Intelligent production process scheduling is a core instrument to increase efficiency of the value-added chain whilst acknowledging existing constraints. This paper introduces a hyper-heuristic based framework for production scheduling that incorporates economic and ecological aspects. In contrast to meta heuristics that aim for easily reusable solution-methods to NP-Hard scheduling problems, hyper-heuristics try to automate the search for the best solution methods. Thus a hyper-heuristic does not seek for the best solution, but for a heuristic that solves the problem best. Other than conventional scheduling described in lit-erature, the proposed approach in this paper copes with many aspects (constraints and objectives) at once, such as retooling activities, energy efficiency, energy peak load avoidance, product lot size, operation multi-plicity, and shift work. Furthermore, this paper will introduce the incorporation possibilities of prior knowledge coming from both human and machine learning (data mining) into the hyper-heuristic framework. },
keywords = {energy efficiency, hyper heuristics, manufacturing, production scheduling},
pubstate = {published},
tppubtype = {inproceedings}
}
In recent years, increased customer-demand in individualized and timely products has changed the playing field for manufacturing industries. The production process is perpetually gaining complexity whereas its life-cycle is shortening. Additionally, a growing ecological conscience enforces the consideration of energy effi-ciency. Intelligent production process scheduling is a core instrument to increase efficiency of the value-added chain whilst acknowledging existing constraints. This paper introduces a hyper-heuristic based framework for production scheduling that incorporates economic and ecological aspects. In contrast to meta heuristics that aim for easily reusable solution-methods to NP-Hard scheduling problems, hyper-heuristics try to automate the search for the best solution methods. Thus a hyper-heuristic does not seek for the best solution, but for a heuristic that solves the problem best. Other than conventional scheduling described in lit-erature, the proposed approach in this paper copes with many aspects (constraints and objectives) at once, such as retooling activities, energy efficiency, energy peak load avoidance, product lot size, operation multi-plicity, and shift work. Furthermore, this paper will introduce the incorporation possibilities of prior knowledge coming from both human and machine learning (data mining) into the hyper-heuristic framework. |