Two-level fuzzy inference system for aircraft's structural health monitoring

Structural health monitoring is the process of detecting damages in an engineering structure and identifying location and type of the damage. This paper focuses on the development and implementation of clustering and classification software system for monitoring aircraft structure health status. The integrated software system was broken down into three modules namely; feature extraction, clustering and classification, and decision-fusion module. The feature extraction module was used to extract frequency features from the structural vibration data. The clustering and classification module was used to group the extracted sets of features into homogeneous classes of similar features. Finally, the decision-fusion module was used to fuse decisions made by multiple monitoring systems and produce more trustworthy decisions than the decisions made by a single clustering and classification module. The software system was developed based on fuzzy system with multiple inference engines. Finally, the developed health monitoring system was tested on data collected from experimental setup conducted on a simple structure with four bolts and four sensors. The test results of the developed software system will be reported and presented in this paper.