Detecting change-points and anomalies on sequential data is common in various domains such as fraud detection for credit cards, intrusion detection for cyber-security or military surveillance [1]. This study is motivated by the predictive maintenance of pneumatic doors in transit buses. For this purpose, buses are instrumented and data are collected through embedded sensors. Inspired by the CUSUM and GLR approaches, this paper deals with on-line change-point detection on sequential data where each observation consists in a bivariate curve. The system is considered out of control when a change occurs in the curves probability distribution. A specific regression model is used to describe the curves. The unknown parameters of this model are estimated using the maximum likelihood principle. Experimental studies performed on realistic data demonstrate the promising behavior of the proposed method.