System modeling based on machine learning for anomaly detection and predictive maintenance in industrial plants

Abstract

Electricity, water or air are some Industrial energy carriers which are struggling under the prices of primary energy carriers. The European Union for example used more 20.000.000 GWh electricity in 2011 based on the IEA Report [1]. Cyber Physical Production Systems (CPPS) are able to reduce this amount, but they also help to increase the efficiency of machines above expectations which results in a more cost efficient production. Especially in the field of improving industrial plants, one of the challenges is the implementation of anomaly detection systems. For example as wear-level detection, which improves maintenance cycles and thus leads to a better energy usage. This paper presents an approach that uses timed hybrid automata of the machines normal behavior for a predictive maintenance of industrial plants. This hybrid model reduces discrete and continuous signals (e.g. energy data) to individual states, which refer to either the present condition of the machines. This allows an effective anomaly detection by implementing a combined data acquisition and anomaly detection approach, and the outlook for other applications, such as a predictive maintenance planning. Finally, this methodology is verified by three different industrial applications

Konzeptualisierung als Kernfrage des Maschinellen Lernens in der Produktion

“…In (Kroll et al 2014) wird ein Erkennungssystem für Anomalien des Energieverbrauches beschrieben, welches drei Produktionsmodule analysiert. EtherCAT und Profinet werden für Schnittstelle 1, und OPC UA für Schnittstelle 2 verwendet.…”

Business Model Innovation of Industry 4.0 Solution Providers Towards Customer Process Innovation

“…Some of the services proposed in the questionnaire, such as intelligent products, open source, availability on demand, and other options, can be traced back to Kaufmann [32]. Other services, such as needs-based maintenance and traceability, were explained in Kroll et al [40] and Aiello et al [35]. Further descriptions of service offerings that were used to develop this question can be found in Bischoff et al [41] or Schröder [42].…”

Towards Integration of Heterogeneous Controllers in an IOT-based Automation System

“…It is also can be fed to a machine learning algorithm to get meaningful insight that is useful for prediction (e.g. predictive maintenance for devices in a factory [2]). Currently, this research only provide a mechanism to collect data from heterogenous devices, store them in a database system, and visualize them to help system operators.…”