Maintenance

The paper describes a modular, AR-based assistance system that guides the user through a maintenance task by displaying components and meta-information step by step. By supplementing a learning success control, the system can also be used for continuing education of service technicians and operating personnel. Special emphasis was placed on an integrated information system that allows maintenance information and training tasks to be created with little effort and at the same learning and work tasks to be teached on the systems used in practice.

Due to competitive pressure pharmaceutical companies are also driven to increase the efficiency of their processes. In this paper an approach for the predictive detection of malfunctions of filling systems for powdery pharmaceutical products using machine learning is presented. The focus is on the prediction of filling deviations with recurrent neural networks, with the objective to detect a drift in the process stability to intervene accordingly.

Solutions to increase the efficiency of industrial supply chains, such as vendor managed inventory or Kanban, are not new. But thanks to technologies such as the 0G network from Sigfox and blockchains, it is becoming ever easier to digitize these strategies and to add automatic delivery confirmations, invoicing and collection in one go. The cost of immutable digital twins is becoming more and more affordable.

In many industries, neutral data platforms are currently being developed for data acquisition, data preparation and processing and subsequent provision to commercial users, public authorities (e.g. statistical offices) or security agencies. Downstream and separated from the data platform, commercial services will then be developed on the corresponding service platforms. Examples of service platforms in the aviation environment are Aviatar, Skywise or AnalytX. The interaction of the platform and service entities, possibly even across industries and with public institutions, has not yet been conclusively researched and established both on the technical level with regard to data security, data quality, data classification and data assignment to categories such as personal, security-relevant, anonymous only etc. and on the legal level with regard to data sovereignty, intellectual property and observance of aviation-specific regulations.

Existing selective laser melting (SLM) machine tools are not equipped with analytics tools. This paper describes an approach to analyze offline data, based on machine learning algorithms, to identify clusters. Normal states and error cases can be identified. The results can be used to develop condition monitoring systems that provide predictive maintenance for SLM machine tools.

Wire ropes are used in different applications and human life often depend on their integrity. Therefore, technical personnel checks the tightropes on a regular basis but there are some difficulties in detecting damaged areas. Consequently, wire ropes are exchanged rather too early than too late causing avoidable extra costs. In this paper, the project MOBISTAR is presented that combines a magneto-inductive and an optical sensor to detect damages and a software based on Convolutional Neural Networks to evaluate those defects.

Industrial communication benefits from wireless systems, which is more flexible, easily scalable and low in maintenance compared to wired systems. Hence, wireless systems are of interest to many producing companies in various industries. However, industrial applications vary broadly in their requirements regarding a communication system. Thus, applications are categorized by their typical requirements, and suitable wireless systems are proposed. Based on these considerations, methods for comparing different wireless systems are reviewed and thereby, the decision making process is supported.

Technological changes related to Industry 4.0 generate new potentials. Hence, it is important to understand which dimensions of a business model to adapt. Industry 4.0 technologies enable a company to offer new products, new services or to achieve efficiency improvements. The Industry 4.0 business model decomposition allows visualising which goal the initiative has, what the value offering is and which processes, technologies and capabilities are needed. As connectivity is a key dimension of Industry 4.0, technologies and systems are needed to connect internal and external processes.

Standards are becoming more and more important in maintenance, particularly as a result of the changes in Industry 4.0. The vision of Smart Maintenance describes a predictive maintenance which, with the help of digital technologies, ensures the availability of the highly automated systems. The collaboration in maintenance of all actors within the asset life cycle (manufactures, operators, service providers, etc.) depends on agreed standards on technological and organizational aspects. And it’s only with a coordinated asset management that the idea of Industry 4.0 will fly.

The comprehensive digitalization of work environment constitutes major challenges in connection with new media and an extended human-computer interaction. In this context, service and maintenance proved to be an important field of application for this form of Industry 4.0. An adequate process execution and documentation has to be secured, even under challenging conditions, e.g. malfunctions on short notice, harsh working conditions or tight timeframes. These requirements as well as the increasing digitalization promote the application of Augmented Reality solutions in this area. With a focus on maintenance of wind energy turbines, this article describes the state of the art in relation to current solution approaches and development needs in connection with a process-oriented application of Augmented Reality. Therefore, current solutions that are already on the market are considered as well as results of the joint research project “AR Maintenance System”.