China
Africa
Explore chapters and articles related to this topic
Introducing process mining for AECFM: Three experimental case studies
Published in Symeon E. Christodoulou, Raimar Scherer, eWork and eBusiness in Architecture, Engineering and Construction, 2017
S. van Schaijk, L.A.H.M. van Berlo
The second type of mining is conformance. This method compares reality with an existing process model using event logs of the process. In addition conformance checking can be used to detect, locate and explain deviations, and to measure the value of these deviations.
Adapting process models via an automated planning approach
Published in Journal of Decision Systems, 2020
Bernd Heinrich, Alexander Schiller, Dominik Schön, Michael Szubartowicz
Finally, the research field of process mining comprises the areas of conformance checking and process enhancement (Leemans et al., 2018; van der Aalst, 2015) that are also part of the process monitoring and controlling phase. Conformance checking is used to detect differences between the traces of a process execution (e.g. found in event logs) and a given process model (Garcia-Bañuelos et al., 2017; Leoni & Marrella, 2017). In process enhancement (which deals with tasks such as ‘model extension’ or ‘model repair’), the goal is to change or extend an already existing process model by taking information about the process instances from event logs into account (cf., e.g. Fahland & van der Aalst, 2012). The focus of process enhancement, analyzing an existing, already instantiated and enacted process with respect to deviations from an existing process model, however, is different to ours. Therefore, these works do not aim to provide an approach for adapting process models to so far unconsidered changes such as new requirements in advance as they rely on event logs. In contrast, we aim to model a desired process which is not yet realized and thus to adapt to needs for change in advance (cf. (C1)).
Towards data-driven approaches in manufacturing: an architecture to collect sequences of operations
Published in International Journal of Production Research, 2020
Ashfaq Farooqui, Kristofer Bengtsson, Petter Falkman, Martin Fabian
Conformance checking is the process of investigating if a given log of a process is allowed by a model defining the same process. Broadly speaking, there are two approaches towards performing conformance checking. Footprint Comparison and Token Replay (van der Aalst 2011). In the Footprint Comparison method, the given model and the collected sequences of operations are converted to footprint tables that describe the relationship between the events. These tables are then compared to find discrepancies. However, in this paper, we use the Token Replay method and hence will not give further details about Footprint Comparison.
Integration of Industry 4.0 technologies into Lean Six Sigma DMAIC: a systematic review
Published in Production Planning & Control, 2023
Tanawadee Pongboonchai-Empl, Jiju Antony, Jose Arturo Garza-Reyes, Tim Komkowski, Guilherme Luz Tortorella
Studies reviewed have shown that Process Mining tools qualify for supporting LSS. Process Mining is an analytical approach situated between data science and process science and aims to build an exhaustive and objective vision of processes based on data from event logs delivered by IT systems (van der Aalst 2016, 18, 31–33). In contrast to the other I4.0 approaches described above, Process Mining finds a broader application outside manufacturing. The existing case studies are not primarily concerned with manufacturing processes optimization (Shin et al. 2019; Kregel et al. 2021) but also with administrative processes, such as invoicing (Graafmans et al. 2021) or procurement (Ramires and Sampaio 2022), or with processes in healthcare, such as resource planning for eye surgeries (Singh, Verma, and Koul 2022). Besides Shin et al. (2019), all authors mapped Process Mining functions to LSS or Six Sigma, albeit with slight variations. Singh, Verma, and Koul (2022) applied a Plan, Do, Study, Act (PDSA) approach instead of DMAIC. In contrast, Kregel et al. (2021) implemented Process Mining for Six Sigma using an ‘Agile’ DMAIC methodology, i.e. the team re-iterated between the DMAIC phases instead of performing one phase after the other like in a waterfall approach. The studies by Graafmans et al. (2021), Kregel et al. (2021), and Ramires and Sampaio (2022) show that Process Mining functions can support all DMAIC phases. The ‘Exploration’ function provides an overview of existing process flows (Kregel et al. 2021) and thus can enhance or replace process mapping. Also, it can assist in analyzing root causes for process related issues and identifying bottlenecks and idle time (Kregel et al. 2021). ‘Conformance checking’ detects unwanted process deviations and thus provides input for process improvements or a new process model (Kregel et al. 2021). ‘Enhancement’, a function for autonomously improving processes, has unfortunately been little researched so far. Some Process Mining applications also offer dashboards that enable process monitoring (Graafmans et al. 2021; Ramires and Sampaio 2022). The articles by Shin et al. (2019) and by Singh, Verma, and Koul (2022), on the other hand, are more focussed on finding improvement opportunities by identifying idle times, redundant steps, and bottlenecks to improve the process flow and do not fully leverage the potential of a Process Mining integration with LSS like the other authors. What all the studies have in common, however, is that they used standard process mining software for the implementation (see Appendix B).