Detecting the changes of bike sharing demands, which are evoked by event disturbances, is critical to evaluating the event impacts on a bike sharing system. Although there has been a proliferation of studies that investigate the problem of demand change detection, most, if not all, of them focus exclusively on the short-term changes lasting for hours or few days. In this research, we propose to detect the abrupt, substantial and persistent changes in the changing regularity of daily demands. We develop a Bayesian hierarchical model, where the upper layer captures the state sequence using a Dirichlet process, and the lower layer captures the state-specific changing regularity of daily demands using linear regression. We estimate the parameters of our model based on the Markov Chain Monte Carlo method. We conduct numerical experiments using the publicly available bike sharing records collected in New York. Results show that our model identifies the demand changes evoked by three bike sharing system expansions and significantly improves the average log marginal likelihood per region.