An Ant Foraging Behavior Approach to Condition Monitoring of Power Generation Plants

摘要

In this paper, a novel approach based on ant foraging behavior is proposed for condition monitoring of power generation plants. Large systems can be considered as a collection of interconnected elements that communicate with each other through physical interactions. Thus, the behavior of an element can be seen in the behavior of other elements. In this work, we propose a condition monitoring approach based on ant foraging behavior and apply it to a power generation plant. First, the algorithm extracts the intrinsic communication topology of the system. The structure of this communication topology reflects the behavior of the system's elements as well as environmental effects and thus captures aspects of the system's operational state. We then employ graph similarity measures to quantify changes in the communication topology which is used for identifying the operational state of the power plant and detecting the change points in plant's state.