In this paper, the nonlinear or rather transient relationship between the air temperature and the building temperature is simulated by a machine learning model. Based on this modelling, different use cases for the application of machine learning regression methods to monitoring data are presented, which resulted from practical questions. Basic knowledge of neural networks will be given and for the calculations, long-term monitoring data of valley bridges from VDE 8 are used. It is shown, for example, that these methods can be used to detect and compensate measurement errors or to predict the behaviour of structures. The results show that these methods, have a great potential for the evaluation of large amounts of data since no physical models are required. The paper focuses more on the application of AI methods rather than on the mathematical or theoretical background of the methods.
|Number of pages||10|
|Publication status||Published - 4 Nov 2020|
- bridge, monitoring, temperature behaviour, machine learning, prediction, Bridge engineering, New Processes, Experimental Techniques, Maintenance and Repair