Refine
Document Type
Is part of the Bibliography
- no (4)
Keywords
- Machine Learning (4) (remove)
Institute
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.
Methods of machine learning (ML) are notoriously difficult for enterprises to employ productively. Data science is not a core skill of most companies, and acquiring external talent is expensive. Automated machine learning (Auto-ML) aims to alleviate this, democratising machine learning by introducing elements such as low-code / no-code functionalities into its model creation process. Multiple applications are possible for Auto-ML, such as Natural Language Processing (NLP), predictive modelling and optimization. However, employing Auto-ML still proves difficult for companies due to the dynamic vendor market: The solutions vary in scope and functionality while providers do little to delineate their offerings from related solutions like industrial IoT-Platforms. Additionally, the current research on Auto-ML focuses on mathematical optimization of the underlying algorithms, with diminishing returns for end users. The aim of this paper is to provide an overview over available, user-friendly ML technology through a descriptive model of the functions of current Auto-ML solutions. The model was created based on case studies of available solutions and an analysis of relevant literature. This method yielded a comprehensive function tree for Auto-ML solutions along with a methodology to update the descriptive model in case the dynamic provider market changes. Thus, the paper catalyses the use of ML in companies by providing companies and stakeholders with a framework to assess the functional scope of Auto-ML solutions.
Methods of machine learning (ML) are difficult for manufacturing companies to employ productively. Data science is not their core skill, and acquiring talent is expensive. Automated machine learning (Auto-ML) aims to alleviate this, democratizing machine learning by introducing elements such as low-code or no-code functionalities into its model creation process. Due to the dynamic vendor market of Auto-ML, it is difficult for manufacturing companies to successfully implement this technology. Different solutions as well as constantly changing requirements and functional scopes make a correct software selection difficult. This paper aims to alleviate said challenge by providing a longlist of requirements that companies should pay attention to when selecting a solution for their use case. The paper is part of a larger research effort, in which a structured selection process for Auto-ML solutions in manufacturing companies is designed. The longlist itself is the result of six case studies of different manufacturing companies, following the method of case study research by Eisenhardt. A total of 75 distinct requirements were identified, spanning the entire machine learning and modeling pipeline.
Die sich ständig ändernden Kundenanforderungen sorgen für eine immer komplexere und dynamischer werdende Produktionsumgebung. In diesem Umfeld ist es die Aufgabe der Produktionssteuerung, die Erfüllung der Nachfrage des Kunden in der richtigen Qualität zum richtigen Zeitpunkt und mit möglichst geringen Kosten sicherzustellen. Abweichungen vom Soll-Zustand sollen dabei im Rahmen des Störungsmanagements möglichst früh erkannt und schnell durch die Wahl der richtigen Gegenmaßnahme beseitigt werden. In der Praxis stehen dem Entscheider dafür jedoch nur selten entsprechende Tools zur Verfügung, sodass Entscheidungen häufig auf Basis der Erfahrung der Mitarbeiter getroffen werden. Daher wird im Folgenden ein Referenzmodell für die Entwicklung eines Decision-Support-Systems, das eine schnelle Erkennung potenzieller Störungen und eine datenbasierte Entscheidung bezüglich einzuleitender Gegenmaßnahmen ermöglicht, vorgestellt.