@inproceedings{ChenBremerSchmittetal., author = {Chen, Mei-Hui and Bremer, Peik and Schmitt, Jan and Tsai, Kune-muh}, title = {Reentrant Flow Shop Production Control with the Theory of Constraints for Wafer Fabrication Having Parallel Machines}, series = {Proceedings of the 28th International Symposium on Logistics (ISL 2024) Building Sustainable Connectivity through Logistics and Supply Chains}, booktitle = {Proceedings of the 28th International Symposium on Logistics (ISL 2024) Building Sustainable Connectivity through Logistics and Supply Chains}, isbn = {978-0-85358-354-7}, pages = {131-132}, abstract = {Purpose of this paper: In a production line with capacity constraint resources (CCR) or bottleneck stations, the production control and the throughput rate are determined by the CCR station. In this study, we consider a production system with parallel machines and there are many rounds of reentrants during the production processes, and can be regarded as a reentrant flow shop process (RFS). In most RFS systems, the release of jobs is a push type without considering the WIP in each layer of reentrance. To resolve the excessive WIP in an RFS system, we consider the theory of constraints (TOC) and implement the DBR (drum, bottleneck and rope) to model RFS scheduling and to define appropriate buffer sizes at the CCR stations of diverse reentrant layers. Design/methodology/approach STS: We obtain production data of a type of semiconductor chip where the photolithography process is the most frequent reentrant. We designed nine scenarios based on the current RFS of the case company by applying the TOC and considering the time differences in parallel machines. A simulation model for the photolithography process was established using AutoMod simulation. Thirty simulation runs were performed for the mean and standard deviation. The goal is to identify the best scenario among the nine proposed ones. Findings: The simulation results demonstrated that Scenario 9, which involves dynamic buffers and assigning higher priority to products with more processing reentrance layers, achieved the highest throughput of finished products. The throughput of finished products in Scenario 9 is 22\% higher than in the base scenario. It also shows improvements in maximum product stack-up and input-output ratio compared to the base scenario. Value: The paper studies dispatching rules for reentrant flow lines having parallel machines with data from the semiconductor industry, and this type of production system is common for producing a wide range of electronic devices. With limited buffer sizes on the shop floor, the number of WIPs is significant, especially for reentrant flow shops, to avoid being clogged with too many WIPs. Implementing DBR modeling from TOC, the nine scenarios demonstrate the effects of controlling buffer sizes on system performances. Research limitations/implications: The nine scenarios are designed based on the case company situations and may not be readily implemented in other industries. Moreover, the DBR modeling of the buffer sizes and CCR station schedule control should also be adjusted when employed in other applications.}, language = {en} } @inproceedings{ChenBremerGuoetal., author = {Chen, Mei-Hui and Bremer, Peik and Guo, Shin-Ming and Lin, Po-Jen and Tsai, Kune-muh}, title = {Material stacking problem detection with Mask R-CNN for Storage safety}, publisher = {International Symposium on Logistics "Managing Supply Chains during Geopolitical Turbulence", Enschede, 9.-12- Juli}, pages = {6}, abstract = {Purpose of this paper: Image processing technology has gained much improvement in recent years. In smart warehousing, most focus is on warehouse operations to improve efficiency and save human labors. However, in put-away, re-warehousing or picking process, after being handled by forklifts or laborers, the stacking of inventory items may change its shape and balance due to deviation, compression, tilting, etc., which may jeopardize the safety of stored goods and even people working in the warehouse. If there is a system that could monitor the stacking of inventory items all the time and could alarm managers should the stacking tilts or deforms to a certain level, inventory safety could be vastly improved. This study is on smart warehouse safety problems emphasizing at goods stacking to avoid the possibility of falling or collapse through image processing via Mask R-CNN. Our experiment is limited to items that form a rectangular block on a pallet, such as wooden bars, cartons or any box-shaped items. Design/methodology/approach STS: Mask R-CNN is a deep learning software and can be used in a wide range of applications. In this study, we used Mask R-CNN to detect the images of stacked items to see if the stacking is stable. We took photos from a warehouse and divided them into three classes - training, validation and production. VGG Image Annotator (VIA) was used for object annotation. To detect the tilt degree of stacked items, we derived formulation from book- stacking problems and retrieved dot coordinates of square frames encompassing objects in an image from the result of Mask R-CNN for calculation. Findings: Because there is a limited number of photos for training, validation and production, we applied image enhancement techniques such as flipping, affinity, multiplication, etc. to increase the total number of images to avoid over-fitting during the training process. The trained Mask R-CNN network demonstrated its capability in framing objects and after retrieving the dot coordinates of the frames, it could compute the degree of tilt as a reference for block stacking alarm. Value: The paper presents a relatively rare study of applying deep learning techniques on images as applied to material stacking safety problems. It contributes to a special smart warehousing domain. The same technique can be applied to inventory counting and help improve labor-saving in counting and in locating items in a warehouse. Research limitations/implications: Due to the limited number of images and restricted angles of taking the images, Mask R- CNN may not be so capable in framing objects of special angles of images. More images with diverse angles of them should be obtained for training to improve the capability of the trained network. Practical implications: Successful implementation of the technology developed in this study in a warehouse monitoring system can help industries in smart detection of improper stacking to assist human in improving the accuracy of safety judgement and can also save labors in reviewing images or records of a warehouse.}, language = {en} }