The paper shows how assigning different predefined dispatching rules for a number of times at any points in time using genetic algorithm can solve hybrid flow shop scheduling problem with sequence-dependent setup times, the example company producing printed circuit boards. describes implementation algorithm, analyses results four data sets and compares them applying standard rules. Using to assign achieves better solutions than simple often used industrial practice. already good after few...

The article investigates the application of NeuroEvolution Augmenting Topologies (NEAT) to generate and parameterize artificial neural networks (ANN) on determining allocation sequencing decisions in a two-stage hybrid flow shop scheduling environment with family setup times. NEAT is machine-learning architecture search algorithm, which generates both, structure hyper-parameters an ANN. Our experiments show that can compete state-of-the-art approaches terms solution quality outperforms them...

Discrete-event simulation is an established method to support decision making for planning tasks in production and logistics. However, there are still many enterprises, especially smaller companies that do not use discrete-event because of the high costs associated with buying maintaining commercial tools. The question whether or free software alternative tools solving typical paper analyzes modeling process three open-source Salabim, JaamSim CloudSim compares them two standard packages...

The introduction of various technologies in the context Industry 4.0 allowed collecting monitoring data for fields manufacturing. Shop-floor and production can be used further analysis to extract knowledge. In this paper, an extensive evaluation ten Machine Learning (ML) models anomaly detection manufacturing is conducted. conducted on multiple distinct ML algorithms, including conventional a representative Deep Neural Network (DNN) based algorithms. are trained real schedules detect...

In this paper, a brief review on the emergency department overcrowding problem and its associated solution methodologies is presented. addition, case study of an urgent care center investigated that demonstrates different simulation-based strategies to deal with Emergency Department problem. More precisely, simulation conducted identify critical aspects propose possible scenarios configure center. Based statistical data supported from international competition for simulation, several...

In this research article, the buzzwords of digital thread, twin, and Industry 4.0 are examined by means a systematic literature review. The key concepts shaping these paradigms investigated to achieve an overview existing solutions. First, body is explored provide general observations on similarities differences between concepts. Subsequently, technologies provided that necessary vision thread. Based identified technologies, state-of-the-art solutions relating thread discussed. Finally, work...

The paradigm shift in urban planning toward citizen participation originates from the Smart City concept, as politicians and scientists argue that citizens should be included design of their environment. This led to development platforms was enhanced by COVID-19 pandemic on-site unavailable. Past projects showed can reach thousands citizens, but it became apparent citizens' contributions vary widely are sometimes not understandable comprehensible which limits value for projects. Therefore,...

Smart manufacturing involves the use of a variety automation solutions, such as robotics, machines with embedded software, and advanced sensors collecting vast quantities data. Efficient control complex composition well analysis collected data, are essential for improving efficiency production processes decision-making. Data process optimization enabled through application state-of-the-art machine learning algorithms. However, efficient these algorithms often depends on careful selection...

The retailing industry witnessed a significant shift in the past years, which introduced modifications standard procedures and regular practices of supply chains (SC). These necessary worldwide distress caused major disruptions instabilities SC. Organizations started developing digital-transformation strategies, include integration analysis external data sources to detect SC retain competitive advantage market. Developing such strategies requires exploring current technologies investigating...

To achieve the objective of smart manufacturing, adoption cloud computing is inevitable. However, implications fully or partially moving manufacturing-related workloads to a strategic decision that rarely investigated thoroughly enough in literature, especially for standard off-the-shelf enterprise IT applications, such as various SAP products. Specifically, related research, it kept on high level conceptual representation without analysis specific products required infrastructure. In this...

Resource planning and management are essential strategic practices in the supply chain. allocation problems becoming more complex due to dynamic nature of these logistical systems. Since increasing popularity Deep Reinforcement Learning (DRL) algorithms Gaming Robotics, scholars have started investigating their potential for addressing chain concerns. The utilization DRL-based approaches optimization remains largely unexplored. Therefore, we present a systematic literature analysis...

Adaptive manufacturing and Cyber-Physical Systems (CPS) have recently emerged as main topics in academia the industry since recent projects even on a governmental level has been launched to investigate propose innovations under title "Smart Industry". This movement expressed trigger toward fourth industrial revolution. The concepts of smart represent future form network, which physical elements environments are coupled with IT-services achieve cyber representation real environments....

This paper describes the solution of a hybrid flow shop (HFS) scheduling problem printed circuit board assembly. The production comprises four surface-mount device placement machines on first stage and five automated optical inspection second stage. objective is to minimize makespan total tardiness. compares three approaches solve HFS problem: an integrated simulation-based optimization algorithm (ISBO) developed by authors two metaheuristics, simulated annealing tabu search. All lead...

We present a novel strategy to solve two-stage hybrid flow shop scheduling problem with family setup times. The is derived from an industrial case. Our involves the application of NeuroEvolution Augmenting Topologies - genetic algorithm, which generates arbitrary neural networks being able estimate job sequences. algorithm coupled discrete-event simulation model, evaluates different network configurations and provides training signals. compare performance computational efficiency proposed...

This paper describes the solution of a hybrid flow shop (HFS) scheduling problem printed circuit board assembly. The production comprises four surface-mount device placement machines on first stage and five automated optical inspection second stage. objective is to minimize makespan total tardiness. compares three approaches solve HFS problem: an integrated simulation-based optimization algorithm (ISBO) developed by authors two metaheuristics, simulated annealing tabu search. All lead...

Well-studied scheduling practices are fundamental for the successful support of core business processes in any manufacturing environment.Particularly, Hybrid Flow Shop (HFS) problems present many environments.The current advances field Deep Reinforcement Learning (DRL) attracted attention both practitioners and academics to investigate their adoption beyond synthetic game-like applications.Therefore, we an approach that is based on DRL techniques conjunction with a discrete event simulation...

Today, the amount and complexity of data that is globally produced increases continuously, surpassing abilities traditional approaches. Therefore, to capture analyze those data, new concepts techniques are utilized engineer powerful big systems. However, despite existence sophisticated approaches for engineering systems, testing not sufficiently researched. Hence, in this contribution, a comparison software testing, as common procedure, requirements drawn. The determined specificities domain...

Solving industrial scheduling problems remains challenging despite the heavy research efforts in last decade due to introduction of new technologies context industry 4.0. Such must be solved with light execution time support near-real-time decision-making processes. In addition, majority real Hybrid Flow Shop (HFS) minimize multi-objective values that are conflicting nature. proven NP-hard. Therefore, this paper, a hybrid approach is presented for solving HFS problems. The technique based on...

The proposed new technologies in the context of industry 4.0 challenge current practices scheduling and their associated research academia. conventional optimization techniques that are employed for solving problems either computationally expensive or lack required quality. Therefore, this paper, we propose an adaptive framework to address taking into account multi-objective optimality measures. is motivated by a hybrid design combine use heuristic metaheuristic approaches. main idea behind...