This research is about a statistical diagnostic method for the structural health monitoring which is applicable to existing structures from the present moment. In this method, structural condition is statistically diagnosed by the change of the response surface. The response surface is a regression model of sensor's outputs. The change of the response surface is statistically tested with the F-test. In the F-test, a threshold of normal or fault condition is simply investigated with a theoretical F-probability distribution. Therefore, this diagnostic method only requires data of intact condition and does not require the complicated modeling and information of fault condition. Since the SI-F method is able to detect the damage in the structure by judging the deviation from the normal state, it is important to avoid the false positive detection for raising the reliability of the structure. In the present study, relationship between the condition of the false positive detection and the shape of the response surface is clarified. And several numerical simulations were carried out to declare the optimal condition of the damage detection for the structural health monitoring using the SI-F method.
