Search

Wertvolles Wissen wird in zahlreichen Prozessen auf dem Shopfloor schriftlich festgehalten. Dies geschieht in formalen Prozessen wie dem Shopfloor Management oder in informeller, direkter Kommunikation, die verstärkt über Chats abläuft. Dieser Beitrag zeigt, wie diese Daten wertschöpfend genutzt werden können, wie Unternehmen und Beschäftigte auf die Analyse von Wissenselementen aus Chat-Applikationen reagieren und wie Unternehmen sich in die Ausgestaltung der Anwendungen einbringen können. Valuable knowledge is written down in numerous processes on the shop floor. This takes place in formal processes such as shop floor management or in informal, direct communication, which is increasingly going on via chats. This article shows how this data can be used to add value, how companies and employees react to the analysis of knowledge elements from chat applications and how companies can get involved in the design of the applications.

This paper aims to develop concepts how digital shop floor management (dSFM) can be further enhanced by natural language processing (NLP) to bring a higher value to the shop floor team and decision makers. Based on the literature review on these two fields several valuable application of NLP in dSFM are theorized: recommender engines to improve knowledge management, text clustering to identify frequent problems, voice assistants to ease the interaction with the data base, chat log extraction to fill the database with unstructured written text from chats and spellcheck as well as auto fill to improve data quality. To show the feasibility for NLP in dSFM in industry, a case study for the document clustering is presented: A digital ticket system for shop floor issues used for two years and containing 2,735 entries is analysed with the “Graph”-feature from Elasticsearch to find the most frequent terms and intersections in the described problems. The approach is accurate, quick and detailed and will be established in the company and performed monthly.

The functionalities of BiFeO3-based magnetoelectric multiferroic heterostructures rely on the controlled manipulation of their ferroelectric domains and of the corresponding net in-plane polarization, as this aspect guides the voltage-controlled magnetic switching. Chemical substitution has emerged as a key to push the energy dissipation of the BiFeO3 into the attojoule range but appears to result in a disordered domain configuration. Using non-invasive optical second-harmonic generation on heavily La-substituted BiFeO3 films, it is shown that a weak net in-plane polarization remains imprinted in the pristine films despite the apparent domain disorder. It is found that this ingrained net in-plane polarization can be trained with out-of-plane electric fields compatible with applications. Operando studies on capacitor heterostructures treated in this way show the full restoration of the domain configuration of pristine BiFeO3 along with a giant net in-plane polarization enhancement. Thus, the experiments reveal a surprising robustness of the net in-plane polarization of BiFeO3 against chemical modification, an important criterion in ongoing attempts to integrate magnetoelectric materials into energy-efficient devices., Advanced Materials, 33 (52), ISSN:0935-9648, ISSN:1521-4095

Even with digital shop floor management systems on the rise the knowledge about previously solved problems in production is not shared and used valuably. This paper aims to evaluate if recommender engines can be utilized in digital shop floor management systems to overcome this gap. Therefore, in a first step interviews are conducted to identify requirements from an industry perspective. Based on those, a system for problem solving management with an integrated content-based recommender engine to enhance knowledge management on the shop floor is designed, implemented and tested for its functionality. The evaluation of the quality of the recommendations as well as the quantified industry feedback give promising results and indicate future research and development steps.

This paper explores how Japanese automotive manufacturers, whose production systems are characterised by the lean principle, address digital transformation. We conducted case studies of seven Japanese car makers and suppliers to investigate the interplay between lean production and digitalisation. We found that the firms selectively adopted digital technologies to enhance the existing lean production system. We labelled this type of digitalisation 'lean augmentation'. Further, we developed theoretical hypotheses regarding the potential of digitalisation to limit kaizen, the roles of human involvement and organisational coordination in digitalised manufacturing, and the potential risk of lean augmentation being caught by what we term the 'lean trap'.