Discovering Actionable Knowledge for Industry 4.0: From Data Mining to Predictive and Prescriptive Analytics

Autoren
C. Schütz, M. Selway, S. Thalmann, M. Schrefl
Paper
Schu23b (2023)
Zitat
Buchkapitel. Digital Transformation - Core Technologies and Emerging Topics from a Computer Science Perspective. Editoren: Birgit Vogel-Heuser, Manuel Wimmer, Springer Vieweg Berlin, Heidelberg, ISBN: 978-3-662-65003-5, DOI: https://doi.org/10.1007/978-3-662-65004-2_14, pp. 337-362, 2023.
Ressourcen
Kopie  (Senden Sie ein Email mit  Schu23b  als Betreff an dke.win@jku.at um diese Kopie zu erhalten)

Kurzfassung (Englisch)

Making sense of the vast amounts of data generated by modern production operations - and thus realizing the full potential of digitization - requires adequate means of data analysis. In this regard, data mining represents the employment of statistical methods to look for patterns in data. Predictive analytics then puts the thus gathered knowledge to good use by making predictions about future events, e.g., equipment failure in process industries and manufacturing or animal illness in farming operations. Finally, prescriptive analytics derives from the predicted events suggestions for action, e.g., optimized production plans or ideal animal feed composition. In this chapter, we provide an overview of common techniques for data mining as well as predictive and prescriptive analytics, with a specific focus on applications in production. In particular, we focus on association and correlation, classification, cluster analysis and outlier detection. We illustrate selected methods of data analysis using examples inspired from real-world settings in process industries, manufacturing, and precision farming.

Keywords: Data mining • Data analytics • Predictive maintenance • Predictive quality control