Decision Support for Smart Manufacturing

Decision Support for Smart Manufacturing

Marzieh Khakifirooz, Mahdi Fathi, Panos M. Pardalos, Daniel J. Power
Copyright: © 2021 |Pages: 14
DOI: 10.4018/978-1-7998-9023-2.ch015
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

This work introduces a formation and variety of decision-making models based on operations research modeling and optimization techniques in smart manufacturing environments. Unlike traditional manufacturing, the goal of Smart manufacturing is to optimizing concept generation, production, and product transaction and enable flexibility in physical processes to address a dynamic, competitive and global supply chains by using intelligent computerized control, advanced information technology, smart manufacturing technologies and high levels of adaptability. While research in the broad area of smart manufacturing and its challenges in decision making encompasses a wide range of topics and methodologies, we believe this chapter provides a good snapshot of current quantitative modeling approaches, issues, and trends within the field. The chapter aims to provide insights into the system engineering design, emphasizing system requirements analysis and specification, the use of alternative analytical methods and how systems can be evaluated.
Chapter Preview
Top

Background

Mathematical models and optimization techniques are the driver for model-driven DSS. With regards to the structure of data and a problem’s objective and constraints, many programming tools and mathematical algorithms are available to aid decision-makers in building a DSS with optimal recommendations. The critical step is to know the type of optimization algorithm needed to solve the problem. For more details on a taxonomy of optimization problems, one can refer to a comprehensive collection of optimization resources at https://neos-guide.org/.

Mathematical algorithms support convergence towards optimal solutions. This review classifies optimization problems in terms of traditional and intelligent approaches. The most commonly used intelligent optimization models are search-based (i.e., metaheuristic models), learning-based (i.e., machine learning models), uncertainty-based (i.e., robust optimization; stochastic optimization), simulation-based (i.e., Markov Chain Monte Carlo) and Markov Decision Process (MDP) (see Tao et al., 2016, for a comprehensive review on intelligent optimization).

Although using an intelligent optimization algorithm can gradually adapt a specific model-driven DSS for smart manufacturing, such a DSS requires several other criteria be met to be adequately intelligent. More intelligent DSS are created with a learning algorithm, a knowledge sharing system, and with cognitive computing capabilities. Nevertheless, in a smart manufacturing system, with connectivity among all manufacturing processes, an intelligent, integrated DSS is required to manage a manufacturing system. Features of an integrated, intelligent DSS include expert knowledge, risk management, production control, quality monitoring, marketing and sales management, project management, and supply chain (SC) support. Guo (2016) provides an extensive collection of DSS capabilities and features needed for managerial tasks of smart manufacturing integrated with intelligent optimization algorithms.

Complete Chapter List

Search this Book:
Reset