The present study investigates the prediction efficiency of nonlinear system-identification\nmodels, in assessing the behavior of a coupled structure-passive vibration controller. Two\nsystem-identification models, including Nonlinear AutoRegresive with eXogenous inputs (NARX)\nand adaptive neuro-fuzzy inference system (ANFIS), are used to model the behavior of an\nexperimentally scaled three-story building incorporated with a tuned mass damper (TMD) subjected\nto seismic loads. The experimental study is performed to generate the input and output data sets\nfor training and testing the designed models. The parameters of root-mean-squared error, mean\nabsolute error and determination coefficient statistics are used to compare the performance of the\naforementioned models. A TMD controller system works efficiently to mitigate the structural\nvibration. The results revealed that the NARX and ANFIS models could be used to identify the\nresponse of a controlled structure. The parameters of both two time-delays of the structure response\nand the seismic load were proven to be effective tools in identifying the performance of the models.\nA comparison based on the parametric evaluation of the two methods showed that the NARX model\noutperforms the ANFIS model in identifying structures response.
Loading....