Sensors used in structural health monitoring (SHM) are key units for data collection. However, their performance cannot be easily confirmed in situ for the absence of proper excitation sources. We present a calibrating method by which the load combination by traffic vehicles is recommended as an excitation source. We then demonstrate the stability of calibrating results under a random excitation source, i.e., random frequency and random amplitude. The stability experiment is performed with a simply supported beam bridge model under random excitation simulated by a programmable linear module. We conduct a dependency analysis by two-way ANOVA, which shows that the frequency and the amplitude of excitation source have no significant effect on calibrating results of sensors.