Pushing the Limits of Lean Thinking–Design and Management of Complex Production Systems

Linking data science to lean production: a model to support lean practices

“…In particular, the findings of this study agree with previous research on the use of DS in support of LP practices that considered the 'production planning and control' LP bundle (e.g. Stojanovic et al 2016;Deuse et al 2018;Kutschenreiter-Praszkiewicz 2018;Mayr et al 2018;Abd Rahman et al 2020;Ito et al 2020;Sarkar et al 2020;Shahin et al 2020;Valamede and Akkari 2020). However, differently from previous research, the results of this research demonstrate also that the application of the identified set of techniques and tools is not limited to the 'production planning and control' bundle but can potentially support all the LP bundles.…”

“…The cloud computing combines production data gathered from the field and results from an ant colony-based simulation serving as data generator, based on process rules and displays jobs and activity progresses. 'Pull production' is also addressed by Deuse et al (2018), who propose the improvement of traditional Kanban using machine learning methods. Clustering is used in the identification of product families with similar routing and work content to deal with value adding variables, discovering multivariate connections and patterns in manufacturing data.…”

“…DS can improve LP practices potential (Rosin et al 2020) by helping companies in achieving excellence through data-driven decision-making (Provost and Fawcett 2013;Wamba et al 2015;Akter et al 2016;Rejikumar et al 2020). For example, real-time data acquisition and data analytics are very useful in dynamic value stream mapping Meudt et al 2017;Deuse et al 2018;Phuong and Guidat 2018;Lugert, Batz and Winkler 2018). They improve employee commitment (Ciano et al 2020) and process transparency, and support improvement (i.e.…”