Alexander Puchta, M.Sc.

Especially in the context of Artifcial Intelligence (AI) applications and increasing Overall Equipment Effectiveness (OEE) requirements, the use of data in production is gaining in importance. Applications in the feld of process or condition monitoring use, for example, machine component parameters such as motor currents, travel speeds and position information. However, as the data is usually only accessible in the machine control systems in non-standard structures and semantics, while having a large number of potential variables, the identifcation and use of these parameters and data sources represents a signifcant challenge. This paper therefore presents an approach to automatically identify and assign machine parameters on the basis of time series data. For the identifcation, feature- and deep learning-based classifcation approaches are used and compared. Classifcation results show a general usability of the approaches for the identifcation of machine parameters.

In machine tools, existing solutions for process monitoring and condition monitoring rely on additional sensors or the machine control system as data sources. For a higher level of autonomy, it becomes necessary to combine several data sources, which may be within or outside of the machine. Another requirement for autonomy is additional computing power, which may be hosted on edge devices or in the cloud. A seamless and modular architecture, where sensors are integrated in smart machine components or smart sensors, which are in turn connected to edge devices and cloud platforms, provides a good basis for the incremental realisation of autonomy in all phases of the machine life cycle.

The increasing automation level of processes in production systems leads to new technical challenges, especially in the implementation and maintenance of software architectures. New requirements arise regarding the interface between Programmable Logic Controllers (PLC), robots, Human Machine Interfaces (HMI) and superordinate information systems (e.g. ERP). Industry 4.0 demands, among other things, an increase in flexibility, adaptability and transparency to achieve vertical and horizontal interoperability and a continuous integration. The innovative automation middleware is capable of replacing the heterogeneous interface landscape, which currently exists in many companies and institutions. The basic idea is the implementation of a modular and standardized middleware. Due to relevant characteristics, such as dataflow orientation and graphical programming interface, using LabVIEW as a programming language turned out to be the most suitable solution. The system deploys OPC Unified Architecture (OPC UA) to connect all required components across multiple enterprise levels. Moreover, the software solution controls the workflow and collects process data for further analysis. In contrast to software products available on the market, which usually come along with manufacturer dependencies, the established middleware based on the combination LabVIEW and OPC UA is transparent, extensible and independent.