Case ID detection based on time series data -- the mining use case
This work addresses a specific data preprocessing bottleneck for process mining in industrial settings, enabling analysis where case IDs are not explicitly provided.
The paper tackles the problem of converting time series sensor data into event logs for process mining by proposing a rule-based algorithm to detect case IDs based on significant changes in short-term mean values. The algorithm achieves F1 scores of 96.8% and 97% on mining datasets with and without outliers, and 92.6% on a manufacturing dataset.
Process mining gains increasing popularity in business process analysis, also in heavy industry. It requires a specific data format called an event log, with the basic structure including a case identifier (case ID), activity (event) name, and timestamp. In the case of industrial processes, data is very often provided by a monitoring system as time series of low level sensor readings. This data cannot be directly used for process mining since there is no explicit marking of activities in the event log, and sometimes, case ID is not provided. We propose a novel rule-based algorithm for identification patterns, based on the identification of significant changes in short-term mean values of selected variable to detect case ID. We present our solution on the mining use case. We compare computed results (identified patterns) with expert labels of the same dataset. Experiments show that the developed algorithm in the most of the cases correctly detects IDs in datasets with and without outliers reaching F1 score values: 96.8% and 97% respectively. We also evaluate our algorithm on dataset from manufacturing domain reaching value 92.6% for F1 score.