Deep learning and WLC: how to set realistic delivery dates in high variety manufacturing systems

Mezzogori, Davide; Romagnoli, Giovanni; Zammori, Francesco

doi:10.1016/j.ifacol.2019.11.514

Cited by 6 publications

(15 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2.1, WLC does not include a standard framework for DDs setting: even if the DD definition problem has been mentioned by many studies, a robust solution has not yet been presented, and only some simple and generic rules can be found in the literature. A first consistent attempt was made by Mezzogori et al (2019) who propose integrating WLC with and effective forecasting system, based on statistic or machine learning techniques. In the present study, we continue and complete that preliminary study, by implementing and assessing the performances of a forecasting system based on a multi-layer-perceptron.…”

Section: Problem Description and Proposed Approachmentioning

confidence: 99%

“…We note that a preliminary study that used this approach can be found in the conference paper presented in Berlin by Mezzogori et al (2019), of which this work is an extension. However, the level of analysis of the present work is significantly higher than that of the previous conference paper and, most of all, many additional tests have been made and new operating conditions have been considered, so as to verify and make clear the operational aspects of our approach and the competitive advantages that it can provide to companies wishing to implement it.…”

Section: Introductionmentioning

confidence: 99%

“…However, the level of analysis of the present work is significantly higher than that of the previous conference paper and, most of all, many additional tests have been made and new operating conditions have been considered, so as to verify and make clear the operational aspects of our approach and the competitive advantages that it can provide to companies wishing to implement it. In detail, concerning technical elements related to WLC, if compared to the previous work by Mezzogori et al (2019), in the present study we (i) analyze another job dispatching rule, namely the Operation Due Date, in addition to the already considered Earliest Due Date; (ii) add a different norm optimization method, beyond the previously used minimization of WIP levels, to find the norms that minimize the percentage of tardy jobs and (iii) checked whether or not a polynomial regression could be used in place of the multi-layer-perceptron.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Defining accurate delivery dates in make to order job-shops managed by workload control

2020

Self Cite

View full text Add to dashboard Cite

Workload control (WLC) is a lean oriented system that reduces queues and waiting times, by imposing a cap to the workload released to the shop floor. Unfortunately, WLC performance does not systematically outperform that of push operating systems, with undersaturated utilizations levels and optimized dispatching rules. To address this issue, many scientific works made use of complex job-release mechanisms and sophisticated dispatching rules, but this makes WLC too complicated for industrial applications. So, in this study, we propose a complementary approach. At first, to reduce queuing time variability, we introduce a simple WLC system; next we integrate it with a predictive tool that, based on the system state, can accurately forecast the total time needed to manufacture and deliver a job. Due to the non-linearity among dependent and independent variables, forecasts are made using a multi-layer-perceptron; yet, to have a comparison, the effectiveness of both linear and non-linear multi regression model has been tested too. Anyhow, if due dates are endogenous (i.e. set by the manufacturer), they can be directly bound to this internal estimate. Conversely, if they are exogenous (i.e. set by the customer), this approach may not be enough to minimize the percentage of tardy jobs. So, we also propose a negotiation scheme, which can be used to extend exogenous due dates considered too tight, with respect to the internal estimate. This is the main contribution of the paper, as it makes the forecasting approach truly useful in many industrial applications. To test our approach, we simulated a 6-machines job-shop controlled with WLC and equipped with the proposed forecasting system. Obtained performances, namely WIP levels, percentage of tardy jobs and negotiated due dates, were compared with those of a set classical benchmark, and demonstrated the robustness and the quality of our approach, which ensures minimal delays.

show abstract

Section: Problem Description and Proposed Approachmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Defining accurate delivery dates in make to order job-shops managed by workload control

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…The system admits new jobs when the work-in-process (WIP) falls below workload limits or norms. The system pushes jobs along the line, preserving the usual features of batches and queues manufacturing, which characterises a hybrid pushpull control technique (Mezzogori et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

“…Control can extend from the initial consultation of customers to the final delivery, exploring workload hierarchies (Kingsman et al, 1989). Such integration between production and sales helps enhance the dependability of the manufacturing process (Mezzogori et al, 2019). It may also help boost other competitive factors, such as flexibility and cost reduction (Szabó, 2018).…”

Section: Introductionmentioning

confidence: 99%

Workload Control and Order Dispatching Rules

Couto

Sellitto

2022

Period. Polytech. Soc. Man. Sci.

View full text Add to dashboard Cite

The purpose of this study is to choose an order dispatching rule and measure the work-in-process and lead-time in the production process of a conveyor chain manufacturer. The main strategic issue for the manufacturer is dependability, which requires meeting deadlines and managing internal lead-times. The study integrates two techniques, workload control (WLC) and an analytical hierarchy process (AHP), respectively systems for production planning and control, and multi-criteria decision support, both widely used in handling manufacturing strategic issues. The research method is a field experiment. Supported by the AHP and according to strategic criteria, practitioners selected the early due date rule (the order with the closest due date comes first) to release 231 orders. Then, employing a methodology designed to support WLC applications, the study measured key parameters that provide information regarding the overall performance of the manufacturer, the input rate, work-in-process, lead-time, throughput performance, and the level of safety stock. Using the model and a graphical tool derived from queuing theory, the throughput diagram, the study provides evidence that, although the manufacturing process is satisfactorily balanced and achieves acceptable performance, the level of safety stock is small and should be increased to prevent starvation on the shop floor.

show abstract

Digital Twin Framework for Machine Learning-Enabled Integrated Production and Logistics Processes

Greis

Nogueira

Rohde

2021

Advances in Production Management Systems. Artificial Intelligence for Sustainable and Resilient Production Systems

View full text Add to dashboard Cite

Deep learning and WLC: how to set realistic delivery dates in high variety manufacturing systems

Cited by 6 publications

References 12 publications

Defining accurate delivery dates in make to order job-shops managed by workload control

Defining accurate delivery dates in make to order job-shops managed by workload control

Workload Control and Order Dispatching Rules

Digital Twin Framework for Machine Learning-Enabled Integrated Production and Logistics Processes

Contact Info

Product

Resources

About