Simultaneous Process Mining of Process Events and Operator Actions for Alarm Management

Abstract

Alarm management is an important task to ensure the safety of industrial process technologies. A well-designed alarm system can reduce the workload of operators parallel with the support of the production, which is in line with the approach of Industry 5.0. Using Process Mining tools to explore the operator-related event scenarios requires a goal-oriented log file format that contains the start and the end of the alarms along with the triggered operator actions. The key contribution of the work is that a method is presented that transforms the historical event data of control systems into goal-oriented log files used as inputs of process mining algorithms. The applicability of the proposed process mining-based method is presented concerning the analysis of a hydrofluoric acid alkylation plant. The detailed application examples illustrate how the extracted process models can be interpreted and utilized. The results confirm that applying the tools of process mining in alarm management requires a goal-oriented log-file design.

Sequence Compression and Alignment-Based Process Alarm Prediction

“…A well-designed log file is essential for in-depth process analysis tasks. 21 An alarm represents a state of the system where a process variable exceeds the warning or alarm limits. 22 To predict potential alarm escalation scenarios, typical alarm sequence patterns have to be explored.…”

“…An alarm management database contains E = { e 1 , ···, e i , ···, e w } alarms stored with some attributes, like a timestamp, the ID of the sensor, the ID of the equipment, etc., forming a D T log file. A well-designed log file is essential for in-depth process analysis tasks . An alarm represents a state of the system where a process variable exceeds the warning or alarm limits .…”

“…In this section, the analysis of historical alarm data of a delayed-coker plant at the Danube Refinery of the MOL Group is presented alongside the algorithm used to predict the next element of an online sequence opening up the possibility to the creation of numerous data-driven Decision Support Systems (DSSs). A detailed description of the plant is provided in ref , and the process flow diagram of the analyzed technology can be seen in Figure . The analyzed alarm log contains more than 2,000 process tag names on the level of sensors and actuators recorded in almost 400 units (equipment, vessel), located in 19 production units (subparts of the plant), so our example of application can be considered a realistic and challenging case study.…”