Location

Grand Wailea, Hawaii

Event Website

https://hicss.hawaii.edu/

Start Date

7-1-2020 12:00 AM

End Date

10-1-2020 12:00 AM

Description

The analysis of events with spatio-temporal context and their interdependencies is a crucial task in the manufacturing domain. In general, understanding this context, for example investigating error messages or alerts is important to take corrective actions. In the manufacturing domain, comprehending the relations of errors is often based on the technicians' experience. Validation of cause-effect relations is necessary to understand if an effect has a preceding causality, e.g., if an error is the result of multiple issues from previous working steps. We present an approach to investigate spatio-temporal relations between such events. Based on a time-sensitive correlation measure, we provide multiple coordinated views to analyze and filter the data. In collaboration with an industry partner, we developed a visual analytics approach for error logs reported by machines that covers a multitude of analysis tasks. We present a case study based on real-world event logs of an assembly line with feedback from our industry partner's domain experts. The findings show that experts can effectively identify error dependencies that impair the overall assembly line productivity using our technique. Furthermore, we discuss how our approach is applicable in other domains.

Share

COinS
 
Jan 7th, 12:00 AM Jan 10th, 12:00 AM

Visual analysis for spatio-temporal event correlation in manufacturing

Grand Wailea, Hawaii

The analysis of events with spatio-temporal context and their interdependencies is a crucial task in the manufacturing domain. In general, understanding this context, for example investigating error messages or alerts is important to take corrective actions. In the manufacturing domain, comprehending the relations of errors is often based on the technicians' experience. Validation of cause-effect relations is necessary to understand if an effect has a preceding causality, e.g., if an error is the result of multiple issues from previous working steps. We present an approach to investigate spatio-temporal relations between such events. Based on a time-sensitive correlation measure, we provide multiple coordinated views to analyze and filter the data. In collaboration with an industry partner, we developed a visual analytics approach for error logs reported by machines that covers a multitude of analysis tasks. We present a case study based on real-world event logs of an assembly line with feedback from our industry partner's domain experts. The findings show that experts can effectively identify error dependencies that impair the overall assembly line productivity using our technique. Furthermore, we discuss how our approach is applicable in other domains.

https://aisel.aisnet.org/hicss-53/da/visual_analytics/3