Chimp Optimization Algorithm with Fuzzy Cognitive Map for Vibration-based Damage Detection

In the past, Structural health monitoring (SHM) and vibration-oriented structural damage detection gain the great attention of mechanical, aerospace, and civil engineers. Initial and meticulous damage recognition has been one main aim of SHM applications. One key difficulty for structural damage detection utilizing observing dataset was to gain features that are delicate to damage but insensitive to noise (for example sensor measurement noise) along with the operational and environmental effects (for instance temperature effect). The performance of traditional damage detection techniques mainly relies upon the choice of the classifier and the features. Therefore, this study develops a Chimp optimization Algorithm with Fuzzy Cognitive Map for Vibration-based Damage Detection (COAFCM-VDD) technique. The presented COAFCM-VDD technique determines cross-correlation functions of vibration data as fundamental features as input. The proposed COAFCM-VDD technique intends to derive damage features from the field measurement under the impact of noisy uncertainty. For detecting the damages, the FCM model is exploited in this work. At last, the performance of the FCM model can be improvised by the COA. The experimental result analysis of the COAFCM-VDD technique is tested using vibration dataset and the obtained outcomes signify the improved performance of the COAFCM-VDD technique.