We propose a CUSUM-based testing procedure to sequentially monitor structural changes in Autoregressive Distributed Lag (ARDL) models using a penalized algorithm. Initially, this approach leverages historical panel data to simultaneously perform variable selection and estimation through a penalization method applied to the ARDL model. To detect any change point when new data is introduced, we conduct tests based on the CUSUM statistics. The consistency of this method, along with the oracle property of the resulting regularized estimators, is thoroughly examined. Additionally, we establish the asymptotic properties of the test statistics under both the null and alternative hypotheses. Simulations are carried out to demonstrate the effectiveness of the proposed method, and a real data application is presented to illustrate the detection procedure.