Using behavior models for anomaly detection in hybrid systems

Abstract

The importance of safety and reliability in today's real-world complex hybrid systems, such as process plants, led to the development of various anomaly detection and diagnosis techniques. Model-based approaches established themselves among the most successful ones in the field. However, they depend on a model of a system, which usually needs to be derived manually. Manual modeling requires a lot of efforts and resources.This paper gives a procedure for anomaly detection in hybrid systems that uses automatically generated behavior models. The model is learned from logged system's measurements in a hybrid automaton framework. The presented anomaly detection algorithm utilizes the model to predict the system behavior, and to compare it with the observed behavior in an online manner. Alarms are raised whenever a discrepancy is found between these two. The effectiveness of this approach is demonstrated in detecting several types of anomalies in a real-world running production system.

A stochastic method for the detection of anomalous energy consumption in hybrid industrial systems

“…This evaluation platform is described in detail in [4] and [21]. The LMF represents a plant for storing, transporting, processing and packing raw material (corn).…”

“…There has been some research on anomaly detection for hybrid systems with timed hybrid automata (see e.g. [3]- [8]). The learning of discrete event systems which form the basis of hybrid automata has been investigated extensively (see e.g.…”

“…The learning of discrete event systems which form the basis of hybrid automata has been investigated extensively (see e.g. [5], [6], [8]). However, there seems to be potential with respect to the modeling of the continuous energy consumption in the particular modes of the hybrid automaton.…”

“…However, there seems to be potential with respect to the modeling of the continuous energy consumption in the particular modes of the hybrid automaton. Initial research on modeling the continuous energy behavior was conducted in [5], [7], [8]. In these approaches, regression based methods and neural networks are employed to model the trajectory of the continuous process variables for each system mode as a function of time.…”

Genetic Re-planning Strategy of Wormhole Model using Neural Learned Vibration Behavior in Robotic Assembly

“…Due to their large representation in the real-world, especially in the process and the automotive industries, the significance of hybrid systems cannot be overemphasized [18].…”