Real-time discrete event simulation: a framework for an intelligent expert system approach utilising decision trees
- PDF / 2,589,625 Bytes
- 19 Pages / 595.276 x 790.866 pts Page_size
- 51 Downloads / 222 Views
ORIGINAL ARTICLE
Real-time discrete event simulation: a framework for an intelligent expert system approach utilising decision trees N. Prajapat 1 & C. Turner 2 & A. Tiwari 3 & D. Tiwari 3 & W. Hutabarat 3 Received: 27 April 2020 / Accepted: 3 September 2020 # Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract This paper explores the use of discrete event simulation (DES) for decision making in real time based on the potential for data streamed from production line sensors. Technological innovations for data collection and an increasingly competitive global market have led to an increase in the application of discrete event simulation by manufacturing companies in recent years. Scenario analysis and optimisation methods are often applied to these simulation models to improve objectives such as cost, profit and throughput. The literature review has identified key research gaps as the lack of example cases where multi-objective optimisation methods have been applied to simulation models and the need for a framework to visualise the relationship between inputs and outputs of simulation models. A framework is presented to enable the optimisation DES simulation models and optimise multiple objectives simultaneously using design of experiments and meta-models to create a Pareto front of solutions. The results show that the resource allocation meta-model provides acceptable prediction accuracy whilst the lead time metamodel was not able to provide accurate prediction. Regression trees have been proposed to assist stakeholders with understanding the relationships between input and output variables. The framework uses regression and classification trees with overlaid values for multiple objectives and random forests to improve prediction accuracy for new points. A real-life test case involving a turbine assembly process is presented to illustrate the use and validity of the framework. The generated regression tree expressed a general trend by demonstrating relationships between input variables and two conflicting objectives. Random forests were implemented for creating higher accuracy predictions and they produced a mean square error of ~ 0.066 on the training data and ~ 0.081 on test data. Keywords Simulation . Discrete event simulation (DES) . Expert system . Decision tree . Random forest . Flexible manufacturing system
* C. Turner [email protected] N. Prajapat [email protected] A. Tiwari [email protected] D. Tiwari [email protected]
Abbreviations AI Artificial intelligence CART Classification and regression tree DES Discrete event simulation DT Decision tree FMS Flexible manufacturing system IDEF Icam DEFinition for Function Modelling IGRIP Interactive Graphical Robot Instruction Program KPI Key performance indicator NCR Non-conformance report OLH Optimal Latin hypercube
W. Hutabarat [email protected] 1
Manufacturing Department, Cranfield University, Bedford, UK
2
Surrey Business School, University of Surrey, Guildford, UK
3
Department of Automatic
Data Loading...
