Process mining on machine event logs for profiling abnormal behaviour and root cause analysis
- PDF / 1,350,232 Bytes
- 10 Pages / 595.224 x 790.955 pts Page_size
- 78 Downloads / 218 Views
Process mining on machine event logs for profiling abnormal behaviour and root cause analysis Jonas Maeyens1 · Annemie Vorstermans1 · Mathias Verbeke2 Received: 11 November 2019 / Accepted: 27 August 2020 / Published online: 16 September 2020 © Institut Mines-T´el´ecom and Springer Nature Switzerland AG 2020
Abstract Process mining is a set of techniques in the field of process management that have primarily been used to analyse business processes, for example for the optimisation of enterprise resources. In this research, the feasibility of using process mining techniques for the analysis of event data from machine logs is investigated. A novel methodology, based on process mining, for profiling abnormal machine behaviour is proposed. Firstly, a process model is constructed from the event logs of the healthy machines. This model can subsequently be used as a benchmark to compare process models of other machines by means of conformance checking. This comparison results in a set of conformance scores related to the structure of the model and other more complex aspects such as the differences in duration of particular traces, the time spent in individual events, and the relative path frequency. The identified differences can subsequently be used as a basis for root cause analysis. The proposed approach is evaluated on a real-world industrial data set from the renewable energy domain, more specifically event logs of a fleet of inverters from several solar plants. Keywords Process mining · Event logs · Industrial machinery · Irregular behaviour · Profiling · Root cause analysis
1 Introduction Internet-of-Things (IoT) technology increasingly finds its way to the industrial domain, and as most IT-related phenomena, the growth of (event) data complies with Moore’s Law [3]. Many organisations now realise that the goal is not to collect as much data as possible, but to use the gathered data to gain valuable insights, to improve current processes and to enhance overall efficiency. Furthermore, industrial machines are being equipped with sensors, capturing the machine’s states in the form of raw data, which are then sent to information systems. Mathias Verbeke
[email protected] Jonas Maeyens [email protected] Annemie Vorstermans [email protected] 1
KU Leuven - Technology Campus Ghent, Gebroeders de Smetstraat 1, B-9000, Ghent, Belgium
2
Sirris - Data and AI Competence Lab, Bd. A. Reyerslaan 80, B-1030, Brussels, Belgium
These sensor data are then stored in data logs that allow the monitoring and the analysis of the functioning of the machines. However, it is possible that not only raw time series data but also events are being logged. These events are often correlated to a certain pattern in the sensor data. A process is a set of discrete activities or events that are performed in order to achieve a particular goal. Process mining is a family of techniques used for extracting insights from these processes by the means of analysing the event data that is generated during the execution of th
Data Loading...
