TY - CHAP

T1 - A Genetic Algorithm for the Dynamic Management of Cellular Reconfigurable Manufacturing Systems

AU - Maier, Janine Tatjana

AU - Schmidt, Matthias

AU - Galizia, Fransesco Gabriele

AU - Bortolini, Marco

AU - Ferrari, Emilio

N1 - Conference code: 9

PY - 2023/1/1

Y1 - 2023/1/1

N2 - Globalization and rapid technological changes have led to increased customer requirements and an intensified competition. To remain cost-efficient, manufacturing companies move from traditional manufacturing systems towards flexible manufacturing systems. Reconfigurable manufacturing systems have proven to be an effective way of adapting to the rapidly changing market conditions. Although, an increasing interest in this topic is visible in academics and industrial practice, the research is still limited. From an industrial point of view, a fast and easy adaptable solution for managing such a system dynamically is required. Based on an optimization model, a genetic algorithm for the dynamic management of cellular reconfigurable manufacturing systems was developed. A case study shows the effects of varying the selection method, the crossover operator, and the values for the occurrence of crossover and mutation processes. The application of the genetic algorithm resulted in an improvement of around 3% compared to the best solution of the initial population. Random selection showed the best results in the respective case. Nevertheless, it can be assumed that this selection method is outperformed by others as the number of generations increases.

AB - Globalization and rapid technological changes have led to increased customer requirements and an intensified competition. To remain cost-efficient, manufacturing companies move from traditional manufacturing systems towards flexible manufacturing systems. Reconfigurable manufacturing systems have proven to be an effective way of adapting to the rapidly changing market conditions. Although, an increasing interest in this topic is visible in academics and industrial practice, the research is still limited. From an industrial point of view, a fast and easy adaptable solution for managing such a system dynamically is required. Based on an optimization model, a genetic algorithm for the dynamic management of cellular reconfigurable manufacturing systems was developed. A case study shows the effects of varying the selection method, the crossover operator, and the values for the occurrence of crossover and mutation processes. The application of the genetic algorithm resulted in an improvement of around 3% compared to the best solution of the initial population. Random selection showed the best results in the respective case. Nevertheless, it can be assumed that this selection method is outperformed by others as the number of generations increases.

KW - Engineering

KW - Reconfigurable manufacturing

KW - Genetic algorithm

KW - Selection

KW - Crossover

KW - Mutation

KW - Parameter variation

UR - http://www.scopus.com/inward/record.url?scp=85147850633&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/acbf6022-9560-3f6e-a864-79f6ccec1027/

U2 - 10.1007/978-981-19-9205-6_3

DO - 10.1007/978-981-19-9205-6_3

M3 - Article in conference proceedings

SN - 978-981-19-9204-9

T3 - Smart Innovation, Systems and Technologies

SP - 21

EP - 32

BT - Sustainable Design and Manufacturing

A2 - Scholz, Steffen G.

A2 - Howlett, Robert J.

A2 - Setchi, Rossi

PB - Springer Singapore

T2 - Conference - Proceedings of the 9th International<br/>Conference on Sustainable Design and<br/>Manufacturing (SDM 2022)

Y2 - 14 September 2022 through 16 September 2022

ER -