Environment has significant impacts on the structure performance and will change features of sensor measurements on the monitored structure. The effect of varying environment needs to be considered and eliminated while conducting structural health monitoring. In order to achieve this purpose, a baseline model based structural health monitoring method is proposed in this paper. The relationship between signal features and varying environment, known as a baseline model, is first established. Then, a tolerance range of the signal feature is evaluated via a data based statistical analysis. Furthermore, the health indicator, which is defined as the proportion of signal features within the tolerance range, is used to judge whether the structural system is in normal working condition or not so as to implement the structural health monitoring. Finally, experimental data analysis for an operating wind turbine is conducted and the results demonstrate the performance of the proposed new technique. (C) 2019 Elsevier Ltd. All rights reserved.