Seismic damage identification of moment frames based on random forest algorithm and enhanced gray wolf optimization

The present study aims to identify damage in two-dimensional (2-D) moment frames using seismic responses by combining the random forest (RF) machine classifier and the enhanced gray wolf optimizer (EGWO) metaheuristic algorithm. First, a 2-D moment frame for the dynamic analysis is simulated using the finite element method (FEM). Then, the placement of sensors is optimized using a proposed optimal sensor placement (POSP) method, which is a combination of the iterated improved reduced system (IIRS) and the binary differential evolution (BDE) optimization algorithm. The acceleration responses of the moment frame having damaged elements under 1995 Kobe earthquake are measured at the optimal sensor placement. Then, the natural frequencies and mode shapes of the structure are extracted using the auto-regressive model with exogenous input method (ARX) as a system identification method. The natural frequencies are exploited to train an RF machine learning network that can find the damaged story of the moment frame. Then, EGWO is employed to accurately locate and quantify the damaged elements of the structure. The efficiency of the proposed method is assessed through considering a six-story frame with 18 elements, a seven-story frame with 49 elements, and the experimental data of an eight-story frame for various conditions. The results show that the RF algorithm has an outstanding performance to correctly find a damaged story. Furthermore, the location and severity of damaged elements are precisely determined by EGWO algorithm. As a final outcome, it is demonstrated that the two-step proposed method is very effective in seismically identifying damage to such structures.