TU Ilmenau

Dr. Niclas Feldkamp

Raum
Werner-Bischoff-Bau
Raum F1110

niclas.feldkamp@tu-ilmenau.de 

+49 (0) 3677 69-4044

 

Sprechstunde

Sprechstunden finden nur nach vorheriger individueller Vereinbarung statt.

Einträge in Zitationsdatenbanken

Research Gate

ACM Digital Library

Forschungsschwerpunkte

  • Data Farming
  • Innovative Methoden zur Simulationsdatenanalyse, Data Mining, Visual Analytics
  • Nutzen von KI Methoden im Kontext der Simulation
 

Lehre

  • Data Science für industrielle Anwendungen
  • Simulation 1, Simulation 2
  • Methoden und Werkzeuge der Digitalen Fabrik
  • Industrie 4.0

Mitgliedschaften

  • ACM Special Interest Group for Simulation and Modeling (ACM PADS)
  • Arbeitsgemeinschaft Simulation (ASIM) der Gesellschaft für Informatik (GI)
     

Gutachtertätigkeit

  • Information Sciences
  • Journal of Simulation
  • Winter Simulation Conference
  • Hawaii International Conference on System Sciences (HICSS)
  • ASIM Fachtagung Simulation in Produktion und Logistik
 

Publikationsliste

Anzahl der Treffer: 35
Erstellt: Wed, 27 Mar 2024 23:36:48 +0100 in 0.2024 sec


Bergmann, Sören; Feldkamp, Niclas; Souren, Rainer; Straßburger, Steffen
Simulation in Produktion und Logistik 2023 : ASIM Fachtagung : 20. Fachtagung, 13.-15. September 2023, TU Ilmenau. - Ilmenau : Universitätsverlag Ilmenau, 2023. - 1 Online-Ressource (XII, 485 Seiten). - (ASIM-Mitteilung ; Nr. 187)
https://doi.org/10.22032/dbt.57476
Feldkamp, Niclas; Straßburger, Steffen
From explainable AI to explainable simulation: using machine learning and XAI to understand system robustness. - In: ACM SIGSIM-PADS 2023, (2023), S. 96-106

Evaluating robustness is an important goal in simulation-based analysis. Robustness is achieved when the controllable factors of a system are adjusted in such a way that any possible variance in uncontrollable factors (noise) has minimal impact on the variance of the desired output. The optimization of system robustness using simulation is a dedicated and well-established research direction. However, once a simulation model is available, there is a lot of potential to learn more about the inherent relationships in the system, especially regarding its robustness. Data farming offers the possibility to explore large design spaces using smart experiment design, high performance computing, automated analysis, and interactive visualization. Sophisticated machine learning methods excel at recognizing and modelling the relation between large amounts of simulation input and output data. However, investigating and analyzing this modelled relationship can be very difficult, since most modern machine learning methods like neural networks or random forests are opaque black boxes. Explainable Artificial Intelligence (XAI) can help to peak into this black box, helping us to explore and learn about relations between simulation input and output. In this paper, we introduce a concept for using Data Farming, machine learning and XAI to investigate and understand system robustness of a given simulation model.



https://doi.org/10.1145/3573900.3591114
Feldkamp, Niclas; Genath, Jonas; Straßburger, Steffen
Explainable AI for data farming output analysis: a use case for knowledge generation through black-box classifiers. - In: 2022 Winter Simulation Conference (WSC), (2022), S. 1152-1163

Data farming combines large-scale simulation experiments with high performance computing and sophisticated big data analysis methods. The portfolio of analysis methods for those large amounts of simulation data still yields potential to further development, and new methods emerge frequently. Among the most interesting are methods of explainable artificial intelligence (XAI). Those methods enable the use of black-box-classifiers for data farming output analysis, which has been shown in a previous paper. In this paper, we apply the concept for XAI-based data farming analysis on a complex, real world case study to investigate the suitability of such concept in a real world application, and we also elaborate on which black-box classifiers are actually the most suitable for large-scale simulation data that accumulates in a data farming project.



https://doi.org/10.1109/WSC57314.2022.10015304
Genath, Jonas; Bergmann, Sören; Feldkamp, Niclas; Spieckermann, Sven; Stauber, Stephan
Development of an integrated solution for data farming and knowledge discovery in simulation data. - In: Simulation Notes Europe, ISSN 2164-5353, Bd. 32 (2022), 3, S. 121-126

Simulation is an established methodology for planning and evaluating manufacturing and logistics systems. In contrast to classical simulation studies, the method of knowledge discovery in simulation data uses a simulation model as a data generator (data farming). Subsequently, hidden, previously unknown and potentially useful cause-effect relationships can be uncovered on the generated data using data mining and visual analytics methods. So far, however, there was a lack of integrated, easy-to-use software solutions for the application of the data farming in operational practice. This paper presents such an integrated solution, which allows generating experiment designs, implements a method to distribute the necessary experiment runs, and provides the user with tools to analyze and visualize the result data.



https://dx.doi.org/10.11128/sne.32.tn.10611
Feldkamp, Niclas; Bergmann, Sören; Straßburger, Steffen
Simulationsbasiertes Deep Reinforcement Learning für Modulare Produktionssysteme. - In: ASIM SST 2022 Proceedings Langbeiträge, (2022), S. 65-72

Modulare Produktionssysteme sollen die traditionelle Fließbandproduktion in der Automobilindustrie ablösen. Die Idee dabei ist, dass sich hochgradig individualisierte Produkte dynamisch und autonom durch ein System flexibler Arbeitsstationen bewegen können. Dieser Ansatz stellt hohe Anforderungen an die Planung und Organisation solcher Systeme. Da jedes Produkt seinen Weg durch das System frei und individuell bestimmen kann, kann die Implementierung von Regeln und Heuristiken, die die Flexibilität des Systems zur Leistungssteigerung ausnutzen, in diesem dynamischen Umfeld schwierig sein. Transportaufgaben werden in der Regel von fahrerlosen Transportsystemen (FTS) ausgeführt. Daher bietet die Integration von KI-basierten Steuerungslogiken eine vielversprechende Alternative zu manuell implementierten Entscheidungsregeln für den Betrieb der FTS. In diesem Beitrag wird ein Ansatz für den Einsatz von Reinforcement Learning (RL) in Kombination mit Simulation vorgestellt, um FTS in modularen Produktionssystemen zu steuern. Darüber hinaus werden Untersuchungen zu dessen Flexibilität und Skalierbarkeit durchgeführt.



https://dx.doi.org/10.11128/arep.20.a2007
Feldkamp, Niclas; Bergmann, Sören; Conrad, Florian; Straßburger, Steffen
A method using generative adversarial networks for robustness optimization. - In: ACM transactions on modeling and computer simulation, ISSN 1558-1195, Bd. 32 (2022), 2, S. 12:1-12:22

The evaluation of robustness is an important goal within simulation-based analysis, especially in production and logistics systems. Robustness refers to setting controllable factors of a system in such a way that variance in the uncontrollable factors (noise) has minimal effect on a given output. In this paper, we present an approach for optimizing robustness based on deep generative models, a special method of deep learning. We propose a method consisting of two Generative Adversarial Networks (GANs) to generate optimized experiment plans for the decision factors and the noise factors in a competitive, turn-based game. In a case study, the proposed method is tested and compared to traditional methods for robustness analysis including Taguchi method and Response Surface Method.



https://doi.org/10.1145/3503511
Genath, Jonas; Bergmann, Sören; Feldkamp, Niclas; Straßburger, Steffen
Automation within the process of knowledge discovery in simulation data : characterization of the result data
Automatisierung im Prozess der Wissensentdeckung in Simulationsdaten : Charakterisierung der Ergebnisdaten. - In: Simulation in Produktion und Logistik 2021, (2021), S. 367-376
Literaturangaben

The traditional application of simulation in production and logistics is usually aimed at changing certain parameters in order to answer clearly defined objectives or questions. In contrast to this approach, the method of knowledge discovery in simulation data (KDS) uses a simulation model as a data generator (data farming). Subsequently using data mining methods, hidden, previously unknown and potentially useful cause-effect relationships can be uncovered. So far, however, there is a lack of guidelines and automatization-tools for non-experts or novices in KDS, which leads to a more difficult use in industrial applications and prevents a broader utilization. This paper presents a concept for automating the first step of the KDS, which is the process of characterization of the result data, using meta learning and validates it on small case study.



Feldkamp, Niclas;
Data farming output analysis using explainable AI. - In: 2021 Winter Simulation Conference (WSC), (2021), insges. 12 S.

Data Farming combines large-scale simulation experiments with high performance computing and sophisticated big data analysis methods. The portfolio of analysis methods for those large amounts of simulation data still yields potential to further development, and new methods emerge frequently. Especially the application of machine learning and artificial intelligence is difficult, since a lot of those methods are very good at approximating data for prediction, but less at actually revealing their underlying model of rules. To overcome the lack of comprehensibility of such black-box algorithms, a discipline called explainable artificial intelligence (XAI) has gained a lot of traction and has become very popular recently. This paper shows how to extend the portfolio of Data Farming output analysis methods using XAI.



https://doi.org/10.1109/WSC52266.2021.9715470
Genath, Jonas; Bergmann, Sören; Spieckermann, Sven; Stauber, Stephan; Feldkamp, Niclas
Development of an integrated solution for data farming and knowledge discovery in simulation data :
Entwicklung einer integrierten Lösung für das Data Farming und die Wissensentdeckung in Simulationsdaten. - In: Simulation in Produktion und Logistik 2021, (2021), S. 377-386
Literaturangaben

Simulation is an established methodology for planning and evaluating manufacturing and logistics systems. In contrast to classical simulation studies, the method of knowledge discovery in simulation data uses a simulation model as a data generator (data farming). Subsequently, hidden, previously unknown and potentially useful cause-effect relationships can be uncovered on the generated data using data mining and visual analytics methods. So far, however, there is a lack of integrated, easy-to-use software solutions for the application of the data farming in operational practice. This paper presents such an integrated solution, which allows for generating experiment designs, implements a method to distribute the necessary experiment runs, and provides the user with tools to analyze and visualize the result data.



Feldkamp, Niclas; Bergmann, Sören; Straßburger, Steffen
Simulation-based deep reinforcement learning for modular production systems. - In: 2020 Winter Simulation Conference (WSC), (2020), S. 1596-1607

Modular production systems aim to supersede the traditional line production in the automobile industry. The idea here is that highly customized products can move dynamically and autonomously through a system of flexible workstations without fixed production cycles. This approach has challenging demands regarding planning and organization of such systems. Since each product can define its way through the system freely and individually, implementing rules and heuristics that leverage the flexibility in the system in order to increase performance can be difficult in this dynamic environment. Transport tasks are usually carried out by automated guided vehicles (AGVs). Therefore, integration of AI-based control logics offer a promising alternative to manually implemented decision rules for operating the AGVs. This paper presents an approach for using reinforcement learning (RL) in combination with simulation in order to control AGVs in modular production systems. We present a case study and compare our approach to heuristic rules.



https://doi.org/10.1109/WSC48552.2020.9384089
Feldkamp, Niclas; Bergmann, Sören; Straßburger, Steffen
Knowledge discovery in simulation data. - In: ACM transactions on modeling and computer simulation, ISSN 1558-1195, Bd. 30 (2020), 4, S. 24:1-24:25

This article provides a comprehensive and in-depth overview of our work on knowledge discovery in simulations. Application-wise, we focus on manufacturing simulations. Specifically, we propose and discuss a methodology for designing, executing, and analyzing large-scale simulation experiments with a broad coverage of possible system behavior targeted at generating knowledge about the system. Based on the concept of data farming, we suggest a two-phase process which starts with a data generation phase, in which a smart experiment design is used to set up and efficiently execute a large number of simulation experiments. In the second phase, the knowledge discovery phase, data mining and visually aided analysis methods are applied on the gathered simulation input and output data. This article gives insights into this knowledge discovery phase by discussing different machine learning approaches and their suitability for different manufacturing simulation problems. With this, we provide guidelines on how to conduct knowledge discovery studies within the manufacturing simulation context. We also introduce different case studies, both academic and applied, and use them to validate our methodology.



https://doi.org/10.1145/3391299
Bergmann, Sören; Feldkamp, Niclas; Conrad, Florian; Straßburger, Steffen
A method for robustness optimization using generative adversarial networks. - In: SIGSIM-PADS '20, (2020), S. 1-10

This paper presents an approach for optimizing the robustness of production and logistic systems based on deep generative models, a special method of deep learning. Robustness here refers to setting controllable factors of a system in such a way that variance in the uncontrollable factors (noise) has a minimal effect on given output parameters. In a case study, the proposed method is tested and compared to a traditional method for robustness analysis. The basic idea is to use deep neural networks to generate data for experiment plans and rate them by use of a simulation model of the production system. We propose to use two Generative Adversarial Networks (GANs) to generate optimized experiment plans for the decision factors and the noise factors, respectively, in a competitive, turn-based game. In one turn, the controllable factors are optimized and the noise remains constant, and vice versa in the next turn. For the calculations of the robustness, the planned experiments are conducted and rated using a simulation model in each learning step.



https://doi.org/10.1145/3384441.3395981
Feldkamp, Niclas;
Wissensentdeckung im Kontext der Produktionssimulation. - Ilmenau : Universitätsverlag Ilmenau, 2020. - 1 Online-Ressource (XII, 217, XIV-XX Seiten)
Technische Universität Ilmenau, Dissertation 2019

Die diskrete Simulation stellt eine wichtige und etablierte Methode zur Untersuchung des dynamischen Verhaltens von komplexen Produktions- und Logistiksystemen dar. Sie ist daher zur Planung, Steuerung und Kontrolle solcher Systeme unerlässlich, beispielsweise in der Automobilindustrie oder in der Halbleiterfertigung. Klassische Simulationsstudien zielen in diesem Kontext üblicherweise darauf ab, typische, vorab definierte Fragestellungen zu beantworten. Dies geht oftmals einher mit der Simulation und Analyse einiger weniger vorab definierter Szenarien. Wirkzusammenhänge, die über diesen definierten Projektrahmen hinausgehen, bleiben daher eventuell unentdeckt. Auf der anderen Seite erwachsen mit steigender Rechenleistung und der allgemeinen Verfügbarkeit von Big-Data-Infrastrukturen neue Möglichkeiten zur Durchführung von sehr großen Bandbreiten von Simulationsexperimenten, um das Verhalten des Modells möglichst vollständig abzudecken und automatisiert auszuwerten. Dies wird allgemein als Data Farming bezeichnet. Ziel dieser Arbeit war es, die Methode des Data Farming für die Nutzung zur Wissensentdeckung in Produktionssimulationen zu übertragen und weiterzuentwickeln. Dazu wurde ein ganzheitliches Konzept ausgearbeitet, um unbekannte, versteckte und potenziell nützliche Wirkzusammenhänge in großen Mengen von Simulationsdaten entdecken zu können. Das Konzept beinhaltet hierzu die Auswahl geeigneter Experimentdesignmethoden, die Anwendung und Ausgestaltung von geeigneten Data-Mining-Verfahren in einem dafür zweckmäßigen und zielgerichteten Analyseprozess sowie die Definition geeigneter Visualisierungs- und Interaktionsmethoden zur iterativen, anwenderorientierten Analyse großer Mengen von Simulationsdaten. Darüber hinaus wurde das Konzept in einem ganzheitlichen Softwareframework prototypisch implementiert. Die Anwendbarkeit des Konzeptes wurde anhand von vier Fallstudien aufgezeigt und validiert. Die Fallstudien beinhalteten hierbei zwei akademische Laborstudien sowie zwei Industrieanwendungsfälle.



https://www.db-thueringen.de/receive/dbt_mods_00040526
Feldkamp, Niclas; Bergmann, Sören; Straßburger, Steffen; Schulze, Thomas
Visualization and interaction for knowledge discovery in simulation data. - In: Hawaii International Conference on System Sciences 2020, (2020), S. 1340-1349

Discrete-event simulation is an established and popular technology for investigating the dynamic behavior of complex manufacturing and logistics systems. Besides traditional simulation studies that focus on single model aspects, data farming describes an approach for using the simulation model as a data generator for broad scale experimentation with a broader coverage of the system behavior. On top of that we developed a process called knowledge discovery in simulation data that enhances the data farming concept by using data mining methods for the data analysis. In order to uncover patterns and causal relationships in the model, a visually guided analysis then enables an exploratory data analysis. While our previous work mainly focused on the application of suitable data mining methods, we address suitable visualization and interaction methods in this paper. We present those in a conceptual framework followed by an exemplary demonstration in an academic case study.



https://doi.org/10.24251/HICSS.2020.165
Feldkamp, Niclas; Bergmann, Sören; Straßburger, Steffen
Modelling and simulation of modular production systems :
Modellierung und Simulation von modularen Produktionssystemen. - In: Simulation in Produktion und Logistik 2019, (2019), S. 391-401

Modular production systems aim to supersede the traditional line production in the automobile industry. The idea here is that highly customized products can move dynamically and autonomously through a system of flexible workstations without fixed production cycles. This approach has challenging demands regarding planning and organization of such systems. The use of modelling and simulation methods is therefore indispensable. This paper presents simulation approaches for modelling modular production systems and discusses a comparison between an agent-based and a process-oriented implementation of an example model.



Wörrlein, Benjamin; Bergmann, Sören; Feldkamp, Niclas; Straßburger, Steffen
Deep learning based prediction of energy consumption for hybrid simulation :
Deep-Learning-basierte Prognose von Stromverbrauch für die hybride Simulation. - In: Simulation in Produktion und Logistik 2019, (2019), S. 121-131

Modern production facilities need to prepare for changing market conditions within the energy market due to ongoing implementation of governmental policies. This results in higher volatility of the availability of energy and therefore energy costs. If a simulation model of a machinery model can estimate its own future consumption, and according time frames for said consumption, this information could be used for optimized scheduling of energy consuming jobs. This would result in lower procurement costs. To make said estimation about the dynamic behaviour of jobs, methods of time series prediction tend to be applied. Here a proposal is made to apply a Hybrid System Model incorporating a recurrent neural network (RNN)-Encoder-Decoder-Architecture, which returns a discrete times series when a behavioural sequence (such as an NC-Code) has been put into a neural net model of the respective machinery. Those discrete time series reflect the machines energy consumption for each job that it has been operated on. This neural net, if weighted and called, emits the length value of a job and an according time series which displays the quasi-continuous time consumption of said job. Such generative models combined with classic simulation paradigm qualify as potent applications of hybrid simulation approaches.



Bergmann, Sören; Feldkamp, Niclas; Straßburger, Steffen
Knowledge discovery and robustness analysis for simulation models of global networks :
Wissensentdeckung und Robustheitsanalyse für Simulationsmodelle weltweiter Netze, (2019), S. 64-76
http://ceur-ws.org/Vol-2397/paper9.pdf
Schulte, Julian; Feldkamp, Niclas; Bergmann, Sören; Nissen, Volker
Knowledge discovery in scheduling systems using evolutionary bilevel optimization and visual analytics. - In: Evolutionary multi-criterion optimization, (2019), S. 439-450

https://doi.org/10.1007/978-3-030-12598-1_35
Feldkamp, Niclas; Bergmann, Sören; Straßburger, Steffen; Borsch, Erik; Richter, Magnus; Souren, Rainer
Combining data farming and data envelopment analysis for measuring productive efficiency in manufacturing simulations. - In: Simulation for a noble cause, (2018), S. 1440-1451

Discrete event simulation is an established methodology for investigating the dynamic behavior of complex manufacturing and logistics systems. In addition to traditional simulation studies, the concept of data farming and knowledge discovery in simulation data is a current research topic that consist of broad scale experimentation and data mining assisted analysis of massive simulation output data. While most of the current research aims to investigate key drivers of production performance, in this paper we propose a methodology for investigating productive efficiency. We therefore developed a concept of combining our existing approach of data farming and visual analytics with data envelopment analysis (DEA), which is used to investigate efficiency in operations research and economics. With this combination of concepts, we are not only able to determine key factors and interactions that drive productive efficiency in the modeled manufacturing system, but also to identify the most productive settings.



https://doi.org/10.1109/WSC.2018.8632300
Schulze, Thomas; Feldkamp, Niclas; Bergmann, Sören; Straßburger, Steffen
Data Farming und simulationsbasierte Robustheitsanalyse für Fertigungssysteme. - In: ASIM 2018 - 24. Symposium Simulationstechnik, (2018), S. 243-252

Diskrete Simulation ist eine etablierte Methodik zur Untersuchung des dynamischen Verhaltens von komplexen Fertigungs- und Logistiksystemen. Konventionelle Simulationsstudien fokussieren auf einzelne Modellaspekte und spezifische Analysefragen. Der Umfang der ausgeführten Szenarien ist häufig gering. Das Konzept des Data-Farming verwendet das Simulationsmodell als Datengenerator für eine breite Skale von Experimenten und ermöglicht unter Nutzung von Data-Mining-Methoden eine wesentlich breitere Untersuchung des simulierten Systems sowie eine höhere Komplexität in den abgeleiteten Erkenntnissen. Anforderungen an Simulationssysteme und -modelle zur Durchführung von Data-Farming werden erläutert. Eine Erweiterung des Ansatzes ist die simulationsbasierte Robustheitsanalyse auf der Basis von Verlustfunktionen nach Taguchi. Beide Vorgehensweisen werden an einer Fallstudie aus dem Fahrzeugbau demonstriert.



Schulte, Julian; Feldkamp, Niclas; Bergmann, Sören; Nissen, Volker
Bilevel innovization: knowledge discovery in scheduling systems using evolutionary bilevel optimization and visual analytics. - In: GECCO'18 companion, ISBN 978-1-4503-5764-7, (2018), S. 197-198

https://doi.org/10.1145/3205651.3205726
Feldkamp, Niclas; Bergmann, Sören; Straßburger, Steffen
Online analysis of simulation data with stream-based data mining. - In: SIGSIM-PADS'17, (2017), S. 241-248

https://doi.org/10.1145/3064911.3064915
Feldkamp, Niclas; Bergmann, Sören; Straßburger, Steffen; Schulze, Thomas; Akondi, Praneeth; Lemessi, Marco
Knowledge discovery in simulation data - a case study for a backhoe assembly line. - In: WSC'17, ISBN 978-1-5386-3428-8, (2017), S. 4456-4458

Discrete event simulation is an established and popular technology for investigating the dynamic behavior of complex manufacturing and logistics systems. Besides conventional simulation studies that focus on single model aspects answering project specific analysis questions, new methods of broad scale experiment design and system analysis emerge alongside new developments of computational power and data processing. This enables to investigate the bandwidth of possible system behavior in a more in-depth way. In this work we applied our previously developed methodology of knowledge discovery in simulation data onto an industrial case study for a backhoe loader manufacturing facility.



https://doi.org/10.1109/WSC.2017.8248162
Feldkamp, Niclas; Bergmann, Sören; Straßburger, Steffen; Schulze, Thomas
Knowledge discovery and robustness analysis in manufacturing simulations. - In: WSC'17, ISBN 978-1-5386-3428-8, (2017), S. 3952-3963

Discrete event simulation is an established methodology for investigating the dynamic behavior of complex manufacturing and logistics systems. Traditionally, simulation experts conduct experiments for predetermined system specifications focusing on single model aspects and specific analysis questions. In addition to that, the concept of data farming and knowledge discovery is an ongoing research issue that consists of broad scale experimentation and data mining assisted analysis of massive simulation output data. As an extension to this approach, we propose a concept for investigating the robustness of complex manufacturing and logistic systems which are often very sensitive to variation and noise. Based on Taguchis loss function, we developed a concept including data farming and visual analytics methodologies to investigate sources of variation in a model and the factor values that make a configuration robust. The concept is demonstrated on an exemplary case study model.



https://doi.org/10.1109/WSC.2017.8248105
Feldkamp, Niclas; Bergmann, Sören; Straßburger, Steffen; Schulze, Thomas
Data farming for production and logistics :
Data Farming im Kontext von Produktion und Logistik. - In: Simulation in Produktion und Logistik 2017, ISBN 978-3-7376-0192-4, (2017), S. 169-178

Simulation is an established methodology for planning and evaluating manufacturing and logistics systems. Usually simulations experts conduct experiments for a prior defined goal and by minimizing the number of simulation runs. In contrast to that, data farming describes an approach for using the simulation model as a data generator for broad scale experimentation with a broader coverage of system behaviour. This paper demonstrates how to apply data farming methodologies on simulation models in the context of production and logistics and how to analyse massive amounts of simulation data using data mining and visual analytics.



Bergmann, Sören; Feldkamp, Niclas; Straßburger, Steffen
Emulation of control strategies through machine learning in manufacturing simulations. - In: Journal of simulation, ISSN 1747-7786, Bd. 11 (2017), 1, S. 38-50

Discrete-event simulation is a well-accepted method for planning, evaluating, and monitoring processes in production and logistics. To reduce time and effort spent on creating simulation models, automatic simulation model generation is an important area in modeling methodology research. When automatically generating a simulation model from existing data sources, the correct reproduction of dynamic behavior of the modeled system is a common challenge. One example is the representation of dispatching and scheduling strategies of production jobs. When generating a model automatically, the underlying rules for these strategies are typically unknown but yet have to be adequately emulated. In this paper, we summarize our work investigating the suitability of various data mining and supervised machine learning methods for emulating job scheduling decisions based on data obtained from production data acquisition. We report on the performance of the algorithms and give recommendations for their application, including suggestions for their integration in simulation systems.



http://dx.doi.org/10.1057/s41273-016-0006-0
Feldkamp, Niclas; Bergmann, Sören; Straßburger, Steffen; Schulze, Thomas
Knowledge discovery in simulation data: a case study of a gold mining facility. - In: Simulating complex service systems, ISBN 978-1-5090-4486-3, (2016), S. 1607-1618

Discrete event simulation is an established methodology for investigating the dynamic behavior of complex systems. Apart from conventional simulation studies, which focus on single model aspects and answering specific analysis questions, new methods of broad scale experiment design and analysis emerge in alignment with new possibilities of computation and data processing. This paper outlines a visually aided process for knowledge discovery in simulation data which is applied onto a real world case study of a mining facility in Western Australia.



https://doi.org/10.1109/WSC.2016.7822210
Feldkamp, Niclas; Bergmann, Sören; Straßburger, Steffen
Innovative Analyse- und Visualisierungsmethoden für Simulationsdaten. - In: , (2016), S. 1737-1748

https://nbn-resolving.org/urn:nbn:de:gbv:ilm1-2016100035
Bergmann, Sören; Feldkamp, Niclas; Straßburger, Steffen
Gestaltungsmöglichkeiten selbst-adaptierender Simulationsmodelle. - In: , (2016), S. 1713-1724

https://nbn-resolving.org/urn:nbn:de:gbv:ilm1-2016100035
Bergmann, Sören; Feldkamp, Niclas; Straßburger, Steffen
Approximation of dispatching rules for manufacturing simulation using data mining methods. - In: Proceedings of the 2015 Winter Simulation Conference, ISBN 978-1-4673-9743-8, (2015), S. 2329-2340

Discrete-event simulation is a well-accepted method for planning, evaluating, and monitoring processes in production and logistics contexts. In order to reduce time and effort spent on creating the simulation model, automatic simulation model generation is an important area in modeling methodology research. When automatically generating a simulation model from existing data sources, the correct reproduction of the dynamic behavior of the modelled system is a common challenge. One example is the representation of dispatching and scheduling strategies of production jobs. When generating a model automatically, the underlying rules for these strategies are typically unknown but yet have to be adequately emulated. In previous work, we presented an approach to approximate the behavior through artificial neural networks. In this paper, we investigate the suitability of various other data mining and supervised machine learning methods for emulating job scheduling decisions with data obtained from production data acquisition.



http://dx.doi.org/10.1109/WSC.2015.7408344
Feldkamp, Niclas; Bergmann, Sören; Straßburger, Steffen
Visual analytics of manufacturing simulation data. - In: Proceedings of the 2015 Winter Simulation Conference, ISBN 978-1-4673-9743-8, (2015), S. 779-790

Discrete event simulation is an accepted technology for investigating the dynamic behavior of complex manufacturing systems. Visualizations created within simulation studies often focus on the animation of the dynamic processes of a single simulation run, supplemented with graphs of certain performance indicators obtained from replications of a simulation run or a few manually conducted simulation experiments. This paper suggests a much broader visually aided analysis of simulation input and output data and their relations than it is commonly applied today. Inspired from the idea of visual analytics, we suggest the application of data farming approaches for obtaining datasets of a much broader spectrum of combinations of input and output data. These datasets are then processed by data mining methods and visually analyzed by the simulation experts. This process can uncover causal relationships in the model behavior that were previously not known, leading to a better understanding of the systems behavior.



http://dx.doi.org/10.1109/WSC.2015.7408215
Bergmann, Sören; Feldkamp, Niclas; Hinze, Ulrich; Straßburger, Steffen
Emulation of control strategies through machine learning in manufacturing simulations :
Abbildung von Steuerungslogiken durch maschinelles Lernen für die Simulation von Produktionssystemen. - In: Simulation in production and logistics 2015, (2015), S. 481-490

In the context of discrete-event simulation of production and logistics systems, modelling an exact representation of the real system is needed for obtaining sound and reliable results. The automatic generation of simulation models is an approach for saving time and effort for creating models and, therefore, it is a recurring issue in modelling methodology research. In automatic model generation, the approximation of dynamic behaviour is a challenging problem. This is for example the case when the dispatching and scheduling of production jobs needs to be adequately emulated, but the underlying rules are unknown. In previous work, we presented an approach for approximating dynamic behaviour through artificial neural networks. In this paper, we propose an improved approach and investigate its suitability again with artificial neuronal networks as well as with other data mining and supervised machine learning methods.



Feldkamp, Niclas; Bergmann, Sören; Bergmann, Sören *1979-*; Straßburger, Steffen;
Knowledge discovery in manufacturing simulations. - In: SIGSIM PADS'15, ISBN 978-1-4503-3565-2, (2015), S. 3-12

Discrete event simulation studies in a manufacturing context are a powerful instrument when modeling and evaluating processes of various industries. Usually simulation experts conduct simulation experiments for a predetermined system specification by manually varying parameters through educated assumptions and according to a prior defined goal. Moreover, simulation experts try to reduce complexity and number of simulation runs by excluding parameters that they consider as not influential regarding the simulation project scope. On the other hand, today's world of big data technology enables us to handle huge amounts of data. We therefore investigate the potential benefits of designing large scale experiments with a much broader coverage of possible system behavior. In this paper, we propose an approach for applying data mining methods on simulation data in combination with suitable visualization methods in order to uncover relationships in model behavior to discover knowledge that otherwise would have remained hidden. For a prototypical demonstration we used a clustering algorithm to divide large amounts of simulation output datasets into groups of similar performance values and depict those groups through visualizations to conduct a visual investigation process of the simulation data.



Feldkamp, Niclas; Straßburger, Steffen;
Automatic generation of route networks for microscopic traffic simulations. - In: Winter Simulation Conference (WSC), 2014, ISBN 978-1-4799-7487-0, (2014), S. 2848-2859

Microscopic traffic simulation is a well-accepted simulation approach for simulation problems where the effects of individual driver behavior and/or vehicle interactions need to be taken into account at a fairly detailed level. Such problems include the optimization of traffic light controls patterns or the design of lane layouts at intersections. Such simulation models typically require very detailed and accurate models of the underlying road networks. The manual creation of such networks constitutes a high effort, limiting the simulated area in practical applications to the absolutely necessary. With the increased availability of satellite based geographical data we investigate, if and how such data can be automatically transformed into route networks with adequate level of detail for microscopic traffic simulation models. We further outline the design of data structures for an extensible simulation framework for microscopic traffic simulation which is capable of including different types of publically available data sources.



http://dx.doi.org/10.1109/WSC.2014.7020126
Feldkamp, Niclas;
Automatische Generierung von Routennetzen für die mikroskopische Verkehrssimulation. - 111 S. : Ilmenau, Techn. Univ., Masterarbeit, 2014

Im Rahmen der Modellerstellung für mikroskopische Verkehrssimulationen ist die exakte Abbildung der geographischen und topologischen Eigenschaften des Routennetzwerks mit Aufwand und Kosten verbunden. Ein möglicher Ansatz zur Reduzierung dieses Aufwands liegt in der automatischen Modellgenerierung durch die Nutzung digitaler Karten. Diese Arbeit untersucht am Beispiel von OpenStreetMap, inwiefern offene, frei verfügbare Datenquellen für die automatische Routennetzgenerierung herangezogen werden können. Hierzu wurden Methoden und Algorithmen entwickelt, um OpenStreetMap-Daten in geeignete Datenstrukturen für ein Routennetz zu überführen. Weiter wurden diese Datenstrukturen in ein ganzheitliches und erweiterbares Framework für die mikroskopische Verkehrssimulation eingebettet. Dieses umfasst die Konfiguration der Simulation, Datenstrukturen für dynamische Simulationsentitäten sowie die Anbindung an einen Simulator. Zudem wurde mit Hilfe des konzeptionellen Ansatzes ein Prototyp entwickelt, anhand dessen gezeigt werden kann, welche Potenziale und Einschränkungen die Nutzung von OpenStreetMap-Daten hinsichtlich der Routennetzgenerierung bietet.