Home | deutsch  | Legals | Data Protection | Sitemap | KIT

Fabio Echsler Minguillon, M.Sc.

Team leader production system planning
department: production systems
office hours: To be agreed
room: 110, Geb. 50.36
phone: +49 1523 9502572
Fabio EchslerSph0∂kit edu

Campus Süd

Fabio Echsler Minguillon, M. Sc.

Area of Research:

  • Robust Production Planning and Control
  • Artificial Intelligence in Production Control
  • Industry 4.0 Applications


General Tasks:

  • Coordination of lecture „Integrierte Produktionsplanung im Zeitalter von industrie 4.0“
    • Lecture: Fördersysteme und Lagertechnik
  • Coordination of lecture „Integrative Strategien und deren Umsetzung in Produktion und Entwicklung von Sportwagen“
  • Learning Factory „Scalable Automation“



  • BMWi SmartBodySynergy


Curriculum Vitae:

since 11/2015 Research Associate at the Institute of Production Sci-ence (wbk) at the KIT
10/2009 - 09/2015 Study of industrial engineering an management (KIT)
23/11/1989 Born in Stuttgart




[ 1 ] Greinacher, S.; Echsler Minguillon, F.; Häfner, B.; Stricker, N. & Lanza, G. (2016), "Skalierbare Automatisierung und Industrie 4.0", wt Werkstattstechnik online, no. 9, pp. 659-665.
Industrie 4.0 ist ein Enabler für wandlungsfähige Montagesysteme. Am Beispiel der skalierbaren Automatisierung eines Montagesystems für Elektromotoren wird der effektive Einsatz von Industrie 4.0-Konzepten und -Komponenten aufgezeigt. Exemplarisch werden die Applikation einer dezentralen Steuerung sowie ein integriertes Robotiksystem vorgestellt. Erst die Kombination der Industrie 4.0-Elemente erlaubt ein plug&produce-fähiges Montagesystem, das auf veränderte Anforderungen reagieren kann.

[ 2 ] Bürgin, J.; Echsler Minguillon, F.; Wehrle, F.; Häfner, B. & Lanza, G. (2017), "Demonstration of a Concept for Scalable Automation of Assembly Systems in a Learning Factory". 7th Conference on Learning Factories, CLF 2017, eds. Procedia Manufacturing, pp. 111-118.
Companies operating assembly systems in global production networks constantly have to deal with change drivers. For the design of adaptable assembly systems, change drivers can be considered as fluctuating KPIs, such as labor costs, as well as changing KPI targets, such as rising quality requirements. In this paper, a concept for the design of changeable assembly lines with scalable automation is introduced and applied to the Learning Factory Global Production at KIT. The change of the automation level over time is based on an ex ante evaluation and ex post performance assessment of the impact of change drivers.

[ 3 ] Stricker, N.; Echsler Minguillon, F. & Lanza, G. (2017), "Selecting key performance indicators for production with a linear programming approach", International Journal of Production Research, pp. 5537-5549. https://doi.org/10.1080/00207543.2017.1287444
Modern production systems are prone to disruptions due to shorter product life cycles, growing variant diversity and progressively distributed production. At the same time, reduced time and capacity buffers diminish mitigation opportunities, requiring better tools for production control. Performance measurement with key performance indicators (KPIs) is a widely used instrument to detect changes in production system performance in order to coordinate appropriate countermeasures. The main challenge in planning KPI systems consists in determining relevant KPIs. On the one hand, enough KPIs must be selected for a sufficiently high information content. On the other hand, the cognitive abilities of users are not to be overstrained by selecting too many KPIs. This tradeoff is addressed in a proposed selection process using an integer linear programme for objective KPI selection. In order to achieve this goal, crucial facets of the information content requirement are formalised mathematically. The developed method is validated using a practical application example, showing the influence of model parameter selection on optimisation results. The formalisation of the information content is shown to be a novel and promising approach.

[ 4 ] Echsler Minguillon, F. & Lanza, G. (2017), "Maschinelles Lernen in der PPS", wt Werkstattstechnik online, pp. 630-634.
Für die variantenreiche Serienproduktion werden neue Produktionskonzepte wie die Matrix-Produktion untersucht, um künftigen Flexibilitätsanforderungen gerecht werden zu können. Die zentrale Planung stößt dort aufgrund der Komplexität häufig an ihre Grenzen, während die Leistungsfähigkeit einer dezentralen Planung oft nicht vorhersagbar ist. Maschinelles Lernen kann dazu eingesetzt werden, die dezentrale Steuerung zu verbessern und so Freiheitsgrade in der zentralen Planung zu schaffen.

[ 5 ] Echsler Minguillon, F.; Schömer, J.; Stricker, N.; Lanza, G. & Duffie, N. (2019), "Planning for changeability and flexibility using a frequency perspective", CIRP Annals - Manufacturing Technology, vol. 1, pp. 427-430. https://doi.org/10.1016/j.cirp.2019.03.006
Changeability and flexibility are increasingly important features of production in today’s global environment. The influences of change drivers (e.g. fluctuating demand) lead to pressure for change in production systems, and various types of change can be applied. An approach for determining a cost-efficient plan for types of change by analyzing the demand from a frequency perspective is presented in this paper. The approach iteratively optimizes the allocation of types of change in the frequency domain and evaluates the obtained solution in the time domain. The result is improved decision support and increased transparency for planners in obtaining cost-efficiency and agility.

[ 6 ] Echsler Minguillon, F. & Lanza, G. (2019), "Coupling of centralized and decentralized scheduling for robust production in agile production systems". 12th CIRP Conference on Intelligent Computation in Manufacturing Engineering, 18-20 July 2018, Gulf of Naples, Italy, eds. Roberto Teti, pp. 385-390.
Individualized products and timely delivery require agile just-in-time manufacturing operations. Scheduling needs to deliver a robust performance with high and stable results even when facing disruptions such as machine failures. Existing approaches often generate predictive schedules and adjust them reactively as disturbances occur. However, the effectiveness of rescheduling approaches highly depends on the available degrees of freedom in the predictive schedule. In the proposed approach, a centralized robust scheduling procedure is coupled with a decentralized reinforcement learning algorithm in order to adjust the required degrees of freedom for a maximally efficient production control in real-time.