Process time estimation for workstations in modular construction production line
Bibliographic record
Abstract
Modular construction companies produce module components following a make-to-order process to realize client-defined customization requirements. This customization leads to varying process times of prefabricating module components at workstations, making it difficult for production line managers to accurately predict their process times for planning purposes. To address these challenges, this paper proposes a novel method that employs Deep Neural Networks, artificial neural networks, and multiple linear regression models for predicting workstation production process times at a module prefabrication plant. A Genetic Algorithm is employed to refine the structure of the Deep Neural Networks and find a near-optimum number of hyperparameters. In a case study, a wood-based wall panel production line is analyzed to demonstrate the use of the developed method and test its performance. The developed method for process time prediction is found to achieve a mean absolute error of less than 2.50 min for most workstations, with the symmetric mean absolute percentage error ranging between 22% and 28%. The research contributions of this study include the development of prediction models for all the workstations of the production line and the implementation of a Genetic Algorithm to find the near-optimal hyperparameters of Deep Neural Networks. This assists production managers in making data drive decisions and overcomes the reliance on experience-based methods for estimating process times and creating production plans.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".