Abstract
Structures are exceptionally helpless against impacts like natural effects, earthquakes, and typhoons. Along these lines, the organizer must know the damage and quality status of the structures in time so that essential maintenance is performed. More imaginative auxiliary damage identification systems connected to the current structures for Structural Strength Monitoring (SSM), particularly substantial scale structures, and many testing strategies are nondestructive. Considerations are attracted to how to utilize the present estimation information to create an outcome with less vulnerability, paying little intelligence to estimate clamors and natural assortments, such as evolving temperature, humidity, and load condition. This work presents two contributions. The role of sensors utilizes the Wireless Sensor Systems for diagnostic faults in the building. So Structural Strength Monitoring System (SSMS) utilizing Wireless Sensor Systems has considered as predominant research area because of its capacity to decrease the expenses related to the establishment and maintenance of SSMS frameworks and provides an extensive study of SSMS utilizing WSNs, drafting the calculations utilized in risk discovery and confinement, laying out system configuration difficulties. Another novel hybrid classification method which combines the features of Rough set (RS) with support vector machine (RS-SVM) and also with artificial neural network (RS-ANN). RS-SVM is used to classify the structures, and RS-ANN is used to predict the damage levels. The experiment results compared with the new SVM classifiers and identified that our approach got higher accuracy.
