Refine
Year of publication
- 2020 (5) (remove)
Document Type
Is part of the Bibliography
- no (5)
Keywords
- Adherence To Delivery Dates (1)
- Assembly (1)
- Assistance Systems (1)
- Auftragsabwicklung (1)
- Datenqualität (3)
- Decision Support (2)
- Deviation Detection (1)
- Discrete Event Simulation (1)
- Disruption Management (1)
- Disturbance Management (1)
- ERP-Systeme (1)
- Entscheidungsunterstützung (1)
- Machine Learning (1)
- Mixed-Model Assembly (1)
- Process-Mining (3)
- Production Control (2)
- Produktionsplanung und -steuerung (1)
- Produktionsprozess (1)
- Prozessanalyse (2)
- Prozesse (1)
- Prozessmanagement (1)
- Prozessmodell (1)
- SV7289 (1)
- SV7315 (1)
- Similarity Analysis (1)
- Visual Analytics (1)
Institute
In diesem Whitepaper stellen wir Ihnen die Technologie Process-Mining vor und zeigen auf, welche enormen Potenziale in ihrer Anwendung liegen. Auch mit einer neuen Technologie ist jedoch ohne kompetente Anwendung
kein Erfolg erzielbar. Unser vorliegendes Whitepaper soll Ihnen dazu verhelfen, zu erkennen, welche Hürden Sie überwinden müssen, um das Potenzial von Process-Mining für sich zu heben, und wie wir vom FIR an der RWTH Aachen Ihnen bei der Umsetzung helfen können.
Process-Mining
(2020)
In manufacturing, adherence to delivery dates is one of the main logistic goals. The production control department has to cope with short-term deviations from the planned route sheets. Because of unforeseen disruptions, e.g. machine breakdowns or shortage of material or personnel, in some situations, the promised delivery date to the customer is at stake. In practice, a fast and reasonable decision on how to deal with the delayed order is required. This decision process is often based on a qualitative analysis relying on the planner’s subjective assessment of a complex situation. To improve the quality of possible countermeasures this paper presents an application, which supports the decision process through a quantified analysis using real-time data from business application systems in combination with a simulation of the value stream. The developed app is part of the decision process and estimates the effect of selected countermeasures to accelerate a delayed order. Performance indicators illustrate the effect of the countermeasures on the specific order as well as the whole system. This approach empowers the planner to assess unforeseen situations and aims to improve the quality of the decision-making process. This paper describes the architecture of the application, its simulation ecosystem, the relevant data and the decision process to select the most effective countermeasures.
Changing customer demands lead to increasing product varieties and decreasing delivery times, which in turn pose great challenges for production companies. Combined with high market volatility, they lead to increasingly complex and diverse production processes. Thus, the susceptibility to disruptions in manufacturing rises, turning the task of Production Planning and Control (PPC) into a complex, dynamic and multidimensional problem. Addressing PPC challenges such as disruption management in an efficient and timely manner requires a high level of manual human intervention. In times of digitization and Industry 4.0, companies strive to find ways to guide their workers in this process of disruption management or automate it to eliminate human intervention altogether. This paper presents one possible application of Machine Learning (ML) in disruption management on a real-life use case in mixed model continuous production, specifically in the final assembly. The aim is to ensure high-quality online decision support for PPC tasks. This paper will therefore discuss the use of ML to anticipate production disruptions, solutions to efficiently highlight and convey the relevant information, as well as the generation of possible reaction strategies. Additionally, the necessary preparatory work and fundamentals are covered in the discussion, providing guidelines for production companies towards consistent and efficient disruption management.