ICACT20220383 Slide.16
[Big slide for presentation]
|
Chrome Text-to-Speach Click!! |
 |
Thank you so much for giving attentions on the presentation and the proposed preprocessing algorithm. Please let us know and feel free to contact through the following email addresses of the co-authors if you have any questions or comments.
|
|
ICACT20220383 Slide.15
[Big slide for presentation]
|
Chrome Text-to-Speach Click!! |
 |
In this paper, we proposed a preprocessing algorithm that is an essential component of the data-intensive smart factory operationalization process framework, and proved that the proposed algorithm works correctly on the dataset collected from a smart factory. We strongly believe that the proposed preprocessing algorithm can be expanded to the new concept of the data-intensive smart factory digital twin in the future.
|
|
ICACT20220383 Slide.14
[Big slide for presentation]
|
Chrome Text-to-Speach Click!! |
 |
In this slide, we present the preprocessing algorithm that is arranging the time-series inner-processes from the dataset. And, we show a captured screen visualizing a series of inner-processes and its IEEE-XES formatted dataset mined from the dataset by applying the preprocessing algorithm proposed in the paper. We won't explain the details of the proposed algorithm.
|
|
ICACT20220383 Slide.13
[Big slide for presentation]
|
Chrome Text-to-Speach Click!! |
 |
The figure illustrates the time-series smart factory operationalization process event log preprocessing framework and its preprocessing algorithms that support rearranging a series of time-driven temporal trace processes as well as a series of metrics-driven temporal trace processes from a time-series dataset collected from the production and operational event logs of the devices and sensors associated with a smart factory.
|
|
ICACT20220383 Slide.12
[Big slide for presentation]
|
Chrome Text-to-Speach Click!! |
 |
Now, we present the main contribution of the paper, which is the details of the proposed preprocessing algorithm in the data-intensive smart factory operationalization process framework.
|
|
ICACT20220383 Slide.11
[Big slide for presentation]
|
Chrome Text-to-Speach Click!! |
 |
The figure illustrates a data-intensive smart factory operationalization process framework that consists of a stepwise mining approach and a stepwise deep-learning approach. In this paper, we propose a preprocessing algorithm of the stepwise mining approach to be arranged for discovering temporal traces from the IEEE-XES formatted dataset.
|
|
ICACT20220383 Slide.10
[Big slide for presentation]
|
Chrome Text-to-Speach Click!! |
 |
The sensors' datasets in the data-intensive smart factory operationalization process are stored in a format of the IEEE-XES standardized event logs, which is depicted in the figure. The left-side part of the figure is the meta-data model in UML class diagram, and the right-side part of the figure is a sample of the XES-formatted event traces collected in a smart factory dataset.
|
|
ICACT20220383 Slide.09
[Big slide for presentation]
|
Chrome Text-to-Speach Click!! |
 |
The figure is captured from a data-intensive smart factory operationalization process monitoring system that has been successfully developed by the authors' research group. As we can see, it depicts the smart factory operationalization process model with its associated devices and their sensors' datasets collected. Each device is equipped by several specific sensors like temperature measurement, humidity measurement, pressure measurement, and others. Conclusively, all the devices and their status can be represented by a group of sensors' datasets, and we can discover, analyze, and predict the operationalization processes and their knowledge by the datasets.
|
|
ICACT20220383 Slide.08
[Big slide for presentation]
|
Chrome Text-to-Speach Click!! |
 |
Now, we explain the details of a conceptual approach of the data-intensive smart factory.
|
|
ICACT20220383 Slide.07
[Big slide for presentation]
|
Chrome Text-to-Speach Click!! |
 |
The technological scope of the paper is to propose, concretize, and deploy a new concept of data-intensive smart factory operationalization processes. The figure depicts a data-intensive smart factory operationalization process model that is representing the operationalization process of a nation-wide and very large-scale natural gas production smart factory by using the information control net process modeling approach. As annotated in the figure, the operationalization process model is built from the combinations of two types of operationalization process patterns, such as outer-process pattern and inner-process pattern. The preprocessing algorithm proposed in this paper is about discovering the inner-process patterns in a dataset of the operationalization process enactment event logs.
|
|
ICACT20220383 Slide.06
[Big slide for presentation]
|
Chrome Text-to-Speach Click!! |
 |
The theoretical background of the paper is on modeling the operationalization processes in smart factories. There are two main streams on the theoretical process modeling approaches. One is the Petri-net process modeling theory, and the other is the information control net process modeling theory. In this paper, we use the information control net process modeling approach for graphically and textually representing the smart factory operationalization processes.
Furthermore, the essential objective of the paper is aiming at concretizing and realizing the concept of proactive and predictive smart factory operationalization through the process mining and deep-learning techniques, and we named the new conceptual paradigm as data-intensive smart factory operationalization.
|
|
ICACT20220383 Slide.05
[Big slide for presentation]
|
Chrome Text-to-Speach Click!! |
 |
The next is about the related works that have been done in the smart factory operationalization process intelligence literature.
|
|
ICACT20220383 Slide.04
[Big slide for presentation]
|
Chrome Text-to-Speach Click!! |
 |
As we all know, the recent hot-issued technologies are bigdata mining and deep-learning technologies. The smart factory industry is also adopting them for implementing their operationalization intelligence and for eventually realizing the proactive operations of the smart factories. The figure gives a conceptual view of convergence of data-intensive process mining technology and deep-learning technology by using the smart factory operational process enactment event log datasets and realizing the proactive operationalization in the smart factories. In this paper, we proposed an algorithmic preprocessing approach to be used in mining the operationalization processes from a time-series smart factory big dataset collected from a smart factory.
|
|
ICACT20220383 Slide.03
[Big slide for presentation]
|
Chrome Text-to-Speach Click!! |
 |
The first of all is the introduction.
|
|
ICACT20220383 Slide.02
[Big slide for presentation]
|
Chrome Text-to-Speach Click!! |
 |
This presentation is going to be explaining the following order of the contents from the introduction to the conclusion through three consecutive sections of the related works, the proposed framework, and the proposed algorithm.
|
|
ICACT20220383 Slide.01
[Big slide for presentation]
[YouTube] |
Chrome Text-to-Speach Click!! |
 |
The title of the paper to be presented in this session is a time-series process event log preprocessing approach for data-intensive and predictive operationalization of smart factories. I am Professor Min-Jae Park from the Daelim University College, South Korea.
|
