Advanced search
Publication Cover
Production & Manufacturing Research
An Open Access Journal
Volume 10, 2022 - Issue 1
Submit an article Journal homepage
2,566
Views
0
CrossRef citations to date
0
Altmetric
Articles

Generation of synthetic manufacturing datasets for machine learning using discrete-event simulation

K. C. Chana School of Business, University of Southern Queensland, Springfield, Australia;b School of Mechanical & Manufacturing Engineering, The University of New South Wales, Sydney, AustraliaCorrespondence[email protected]
ORCID Iconhttps://orcid.org/0000-0002-8756-2991
ORCID Icon,
Marsel Rabaevb School of Mechanical & Manufacturing Engineering, The University of New South Wales, Sydney, Australia
&
Handy Pratamab School of Mechanical & Manufacturing Engineering, The University of New South Wales, Sydney, Australia
Pages 337-353 | Received 01 Aug 2019, Accepted 28 May 2022, Published online: 13 Jun 2022

Figures & data

Figure 1. Layout of model 1 and 2.

Figure 1. Layout of model 1 and 2.

Figure 2. Layout of model 3 – flexible manufacturing cells.

Figure 2. Layout of model 3 – flexible manufacturing cells.

Table 1. Demand parameters by layout and product type

Table 2. Process parameters of the first layout

Figure 3. Model 1 – production rate and machine utilisation.

Figure 3. Model 1 – production rate and machine utilisation.

Figure 4. Time requirements to generate synthetic data for all three models.

Figure 4. Time requirements to generate synthetic data for all three models.

Table 3. Model 2 – summary of time requirement parameters for data generation

Table 4. Process parameters of the second layout

Figure 5. Model 2 – parts produced per day and machine utilisation.

Figure 5. Model 2 – parts produced per day and machine utilisation.

Table 5. Model 2 – summary of time requirement parameters for data generation

Table 6. Parameters of the SKUs in Model 3

Table 7. Model 3 – matrix of data features

Figure 6. Model 3 – total production and production by SKU per day.

Figure 6. Model 3 – total production and production by SKU per day.

Figure 7. Model 3 – total product assembled by SKU in each cell per day and assembly cell utilisation.

Figure 7. Model 3 – total product assembled by SKU in each cell per day and assembly cell utilisation.

Table 8. Model 3 – summary of time requirement parameters for data generation

Figure 8. The average and marginal time increase vs. number of data features.

Figure 8. The average and marginal time increase vs. number of data features.
Supercharge Your Next Research Paper: Research and write your next paper with Jenni AI.

Related research

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.