Analytics

Efficient operation and maintenance (O&M) processes are important success factors to reduce the operating costs in the operation phase of industrial assets. Therefore, companies use different maintenance strategies that are well known from literature. Due to uncertainties in occurrence of faults and the duration of process fulfilment, strategies even supported by new technologies do often not fit to the specific real-world challenges. The focus of this paper is to discuss a new concept where operation data analysis is used to support decisions for logistics maintenance processes.

The implementation of industry 4.0 concepts requires a new understanding of data processing and analysis. Data Science integrates approaches of mathematical modelling and performant implementation to analyse data of specific application areas. Within this first article, the basics of Data Science are presented and perspectives for a data-driven production and logistics are discussed. Within a second article in a following edition, the process steps for structured data analysis will be explained and illustrated by means of application examples.

Designing a road layout for automated guided vehicles (AGV) can be a very laborious process that is based in big parts upon the knowledge of experienced system planers. Up until now, it is not possible to save that knowledge in a form that makes it usable in an automated layout process for AGV-roadmaps. The research project aims to integrate the knowledge of the system planers in an artificial intelligence, so in the future an automated process of designing AGV roadmaps is achievable. The knowledge is implemented within a fuzzy-logic and can be used as a controller for the planning process.

One of the main purposes of the „Smart Virtual Worker“-project is the application of a digital human model for the simulation of industrial work tasks. This contribution focuses on the implementation of an autonomic action selection, such that a virtual agent is able to solve tasks under certain optimization criteria. To realize the autonomic action selection, we use the Q-Learning algorithm with different extensions. In this article, we describe these different learning algorithms and we briefly describe the performance of their implementation with regard to the industrial field.

As a result of continuously increasing economic constraints for the producing sector in Germany due to competitors from low-wage countries, production paradigms are changing substantially. This paradigm shift is characterized by rapidly advancing automation processes. Hence, highly complex Cyber-Physical Production Systems (CPPS) are developed and put into practice. In combination with decreasing numbers of staff and the resulting loss of knowledge, this leads to a deficit of competence required to handle the increasing complexity of CPPS. As a result, a need for innovative assistance systems arises for the support of the remaining employees. The given article describes the challenges and problems and drafts a potential technical solution as well as challenges concerning organization and staff.

Customers in online shops return at least half of the placed orders. This huge amount of return shipments results in high costs e.g. from a logistic point of view. To predict the return rate based on customer data and order information, machine learning techniques can be applied which are able to learn a powerful model for return prediction based on historical order data. This article introduces a hands-on approach for successfully applying machine learning in real world processes and shows a case study to predict the return shipment probability in an e-commerce scenario.

Traditional productivity analysis has emerged in mass production and cannot be adopted one-to-one on One-of-a-kind production (OKP). Due to the non-repetitive character of the processes in OKP, productivity improvements do not reproduce like in mass production. In addition, preparatory activities such as orientation, material handling and positioning usually consume a lot more time than the actual value-adding activities in OKP. Therefore, OKP requires analysis methods that deliver: 1) a generic working cycle to enable repetitive productivity improvements; 2) activities of personnel in production processes, which include the preparatory activities. We introduce a state-oriented approach for productivity measurement in OKP. With a case study we show how to capture, visualize and evaluate state data of an OKP.

The networking between companies in a supply chain becomes tighter. This applies for manufacturing plants and the supply with manufacturing equipment as well. Hence, the complexity of the flow of information, in particular for tool management, increases. Currently the exchange of information is mostly paper-based and tool data is not available continuously along the supply chain. By using a digital and cloud-based tool management system, breaks in the flow of information along the supply chain for machining tools can be overcome. Herewith tool data can be called and updated ongoing and location-independent. Furthermore, after clearly identifying a tool, required tool data can automatically be transferred into the control system of the machine.

The competitiveness of manufacturing companies producing in high-wage countries is strongly depending on labour productivity. In the course of Germany’s demographic change, companies with manual production need to compare the heterogeneous impact factors on labour productivity to develop goal-oriented measures for productivity improvements. The integral productivity analysis enables the user to identify the various impacts on labour productivity and to prioritise fields for process optimisation. The approach is based on the state-oriented modelling of worker activities.

Today’s standard information technologies in production logistics allow the storage of large data sets that have a huge variety of different parameters. The also increased complexity of production processes leads to complex dependencies between different decisions variables. Therefore, this paper deals with the application of computer-based methods of analysis for the efficient evaluation of multi-criteria dependencies.