Performance Evaluation of an Entropy-Based Structural Health Monitoring System Utilizing Composite Multiscale Cross-Sample Entropy.

摘要: The aim of this study was to develop an entropy-based structural health monitoring system for solving the problem unstable entropy values observed when multiscale cross-sample (MSCE) is employed assess damage in real structures. Composite MSCE utilized enhance reliability on every scale. Additionally, first mode a structure extracted using ensemble empirical decomposition conduct analysis and evaluate accuracy assessment. A seven-story model created validate efficiency proposed method index. Subsequently, experiment conducted steel benchmark including 15 damaged cases compare numerical experimental models. confusion matrix applied classify results performance over three indices: accuracy, precision, recall. revealed feasibility modified demonstrated its potential field long-term monitoring.