Refine
Document Type
Language
- English (3)
Is part of the Bibliography
- no (3)
Keywords
- data analytics (3) (remove)
Institute
Manufacturing companies are facing an increasingly turbulent market – a market defined by products growing in complexity and shrinking product life cycles. This leads to a boost in planning complexity accompanied by higher error sensitivity. In practice, IT systems and sensors integrated into the shop floor in the context of Industry 4.0 are used to deal with these challenges. However, while existing research provides solutions in the field of pattern recognition or recommended actions, a combination of the two approaches is neglected. This leads to an overwhelming amount of data without contributing to an improvement of processes. To address this problem, this study presents a new platform-based concept to collect and analyze the high-resolution data with the use of self-learning algorithms. Herby, patterns can be identified and reproduced, allowing an exact prediction of the future system behavior. Artificial intelligence maximizes the automation of the reduction and compensation of disruptive factors.
Real-time data analytics methods are key elements to overcome the currently rigid planning and improve manufacturing processes by analysing historical data, detecting patterns and deriving measures to counteract the issues.
The key element to improve, assist and optimize the process flow builds a virtual representation of a product on the shop-floor - called the digital twin or digital shadow. Using the collected data requires a high data quality, therefore measures to verify the correctness of the data are needed. Based on the described issues the paper presents a real-time reference architecture for the order processing.
This reference architecture consists of different layers and integrates real-time data from different sources as well as measures to improve the data quality. Based on this reference architecture, deviations between plan data and feedback data can be measured in real-time and countermeasures to reschedule operations can be applied.
Today, machine manufacturers generate a significant share of their revenues with the provision of services. At the same time, they are confronted with the challenge of adopting of Industrie 4.0.
One of the most important Industrie 4.0 concepts is the idea of the digital shadow, which contributes to the comprehensive structuring of different kinds of data from different data sources. It can be defined as the sufficiently precise, digital representation of reality in real-time.
Thus, it also functions as a database of the considered area of a company that can be used for numerous applications. It serves as a central platform for the aggregation and distribution of data. Thereby, it helps to open isolated data silos. A system architecture that enables extraction of data from various sources and the aggregation of that data is an important prerequisite for the digital shadow.
In addition, the merger of data from different sources requires a model of the part of the company to be mapped digitally. In this paper, we focus on maintenance, repair and overhaul (MRO) services of machine manufacturers. The scope comprises the whole order processing of a service including the utilized resources and the obtained results.
MRO services and their single elements are mapped and structured using a case study research in a first step. Those elements provide a basis for designing the digital shadow. A second contribution of this paper is a data model for the digital shadow of MRO services that entails a comprehensive representation of that department.