In this paper, the researchers study the operations of an imaginary coffee shop with a focus on the barista’s actions. They also show how the sequence of actions affects the overall performance of the coffee shop by using reinforcement learning and simulation as its policy training environment. This model acts as a guiding example that shows the ease of applying RL in AnyLogic models using the Pathmind Library.
The Predictive Maintenance technique offers a possibility to improve productivity in semiconductor manufacturing. Current research on Predictive Maintenance mainly focuses on its technical implementation. By applying discrete-event simulation, the research team provide results on how maintenance strategies can help optimize machine operations, and how the technique contributes to an overall improvement of productivity in wafer fabrication.
In this work, the researchers undertake a root-cause enabling Vendor Managed Inventory performance measurement approach to assign responsibilities for poor performance. Additionally, the work proposes a solution methodology based on reinforcement learning for determining optimal replenishment policy in a VMI setting. Using a simulation model as a training environment, different demand scenarios are generated based on real data from Infineon Technologies AG and compared based on key performance indicators.
This paper proposes a simulation-based decentralized planning and scheduling approach to improve the performances of a job-shop production system, compliant with a semi-heterarchical Industry 4.0 architecture. To this extent, to face the increasing complexity of such a scenario, a parametric simulation model able to represent a wide number of job-shop systems is introduced.
Especially in complex manufacturing systems and uncertain conditions, sequencing operations in a machines’ queue can pose a difficult problem. To solve the problem, intelligent, adaptable, and autonomous systems have been developed using machine learning and simulation to sequence operations under uncertainty within large manufacturing systems.
This work aims at optimizing a public transportation network and its maintenance. In particular, it focuses on determining routes for replacement services and adjusting headways in case of scheduled shutdowns of subway lines. A simulation-based two-layer optimization approach is proposed to solve the problem.
Factors including hospital space layout, patient behavior, patient flow, and medical procedures interact and relate to each other, and ultimately affect efficiency and performance of healthcare facilities. And hospital layout planning can’t ignore such interdependencies.
This research integrates discrete event simulation (DES) and agent-based simulation (ABS) to help managers examine, plan, and compare different spatial design schemes through the modeling of patient behavior, patient flow, and the establishment of evaluation indexes.
This paper focuses on optimizing the production of a real-world pre-assembly facility in a high-volume and high-mix semiconductor wafer fab. In simulation software, the researchers built an in-depth, deterministic discrete-event model. With it, they tested release policies in two stages, using real production data and demands.
In Ireland, cheese is one of the most exported products. Due to Brexit, it will be most impacted by delays at ports caused by the potential reintroduction of customs or border controls. To predict forthcoming changes and analyze their impact on the cheese supply chain in Ireland, a simulation model was built. To develop the model, the research team used a combination of the agent-based and discrete event modeling approaches along with geographic information system (GIS) included in AnyLogic simulation software.
This paper presents a comprehensive production scheduling approach that combines optimization and simulation to cope with parameter uncertainty.
The approach allows for identifying and including demand fluctuations and scrap rates. Furthermore, the researchers adapt seven optimization algorithms for two-stage hybrid flow shops with unrelated machines, machine qualifications, and skipping stages with the objective to minimize the makespan.
The combination of methods is validated on a real production case of the automobile industry.