Refine
Document Type
- Conference Proceeding (2)
- Master's Thesis (1)
Is part of the Bibliography
- no (3)
Keywords
- Machine learning (3) (remove)
Institute
Forecasting-based skills management, which is oriented to the respective corporate goals, is gaining enormous importance as a central management tool. The aim is to predict future skills requirements and match them with existing interorganizational skills. Companies are required to anticipate changes in markets, industries, and technologies at an early stage as well as to identify changes in job profiles within an occupational profile by tapping into and evaluating various data sources. Based on these findings, they can then make informed decisions regarding skill gaps, for example, to implement targeted further training measures. Forecasting-based skills management offers the opportunity to optimally qualify employees for constantly changing tasks. At the same time, however, the targeted development of such skills requires a high level of time, financial and personnel resources, which small and medium-sized enterprises (SMEs) generally do not have at their disposal. In addition, many SMEs are not yet aware of the importance of this issue. Within the framework of research and industrial projects of the Smart Work department at the FIR (Institute for Industrial Management) at the RWTH Aachen University, an AI-based skills forecasting tool will be developed. The goal of the paper is to conceptualize the future machine learning method, that is able to generate individualized skills forecasts and recommendations for SMEs. This is achieved by linking societal forecasts and sector trends with company-specific conditions and skills. In order to generate a corresponding database, the derivation system is made available to various companies (large companies and SMEs) in order to obtain as many data sets as possible. The data sets obtained via the derivation system are then used as training data sets for the machine learning method, with the help of which an automatic derivation of competencies depending on new trends is to be made possible.
The acquisition, processing and analysis of internal and external data is one of the key competitive factors for corporate innovation and competitive advantage. Many firms invest a significant amount of resources to take advantage of advanced analytics methods. Machine learning methods are used to identify patterns in structured and unstructured data and increase predictive capabilities. The related methods are of particular interest when previously undiscovered and unknown structures are discovered in comprehensive data sets in order to more accurately predict the outcome of manufacturing or production processes based on a multitude of parameter settings. So far, this knowledge is often part of the individual or collective knowledge of experts and expert teams, but rarely explicit and therefore not replicable for future applications. On the one hand, it is demonstrated in this paper how different machine learning algorithms have been applied to better predict the output quality in the process industry. On the other hand, it is explained how the application of machine learning methods could contribute to making previously not accessible process knowledge explicit. In order to increase the prognostic accuracy of the model diferrent methods were combined, later on compared and evaluated within an industrial case. In this paper a comprehensive approach to knowledge-based process engineering is being presented.
Industrie 4.0 bietet produzierenden Unternehmen die Möglichkeit, unternehmerische Entscheidungs- und Anpassungsprozesse durch neue organisatorische Ansätze und technische Veränderungen entscheidend zu beschleunigen. Um zielführende Maßnahmen ergreifen und konkreten Nutzen aus der digitalen Transformation ziehen zu können, ist eine gesamtheitliche Betrachtung aller wesentlichen Aspekte essentiell. Diese sind neben der Organisationsgestaltung und der Kulturausprägung eines Unternehmens die Anwendung verschiedener Technologien. Unter anderem wird Machine Learning (ML) dafür eingesetzt, um entscheidungsrelevante Informationen mit geringer Analyselatenz bereitzustellen. ML-Anwendungsfälle sowie deren erforderliche Maßnahmen zur Realisierung hängen dabei stark von dem individuellen Transformationsgrad des betrachteten Unternehmens ab.
In dieser wissenschaftlichen Arbeit werden strukturierte Umsetzungsmaßnahmen für ML-Anwendungsfälle produzierender Unternehmen mittels des Industrie 4.0-Reifegradmodells abgeleitet. Dafür werden relevante ML-Anwendungsfälle, maßgeblich aus den Bereichen Produktion und Logistik, zunächst beschrieben und kategorisiert. Anschließend wird erörtert, welche Ansätze und Methoden bei der Umsetzung der Anwendungsfälle eingesetzt werden und welcher Nutzen sich für produzierende Unternehmen ergibt. Aufbauend darauf werden Umsetzungsmaßnahmen abgeleitet und den vier Industrie 4.0-Stufen des Reifegradmodells zugeordnet. Mit Hilfe der Implementierung eines realen ML-Anwendungsfalls werden Umsetzungsmaßnahmen abschließend validiert.