Environmental and operational changes, make the continuous monitoring of the health of civil engineering structures inaccurate and unreliable. The local unsupervised learning method based on double data clustering can help to solve this challenge. The main purpose is to extract the most relevant information insensitive to environmental and operational variations. The Local Density Peak Clustering under Minimum Spanning Tree (LDPC-MST) divides all available data points into main clusters. Using the representative sub-clusters of all main clusters, a damage detection indicator based on the Mahalanobis-squared distance is defined to detect any abnormal change caused by damage. Then, a steel arch bridge and a concrete box-girder bridge under strong environmental variations are investigated. Several comparative analyses are also performed to indicate the superiority of this method. The main innovation of this research is to develop a novel locally unsupervised learning method by using the process of double clustering and LDPC-MST. Results show that the proposed method is highly able to minimize the environmental and operational effects and provide reliable results.