Force identification in bolts of flange connections for structural health monitoring and failure prevention

摘要

Force identification in bolts of flange connection is not only important to preserve the structure integrity but also to understand how does it works or even improve code procedures. Due to the relaxation phenomenon it becomes even more important in case of compressed bolts. In this paper a bolted flange connection was examined during static tensile test. Four of six bolts were equipped with washer load cells. Alternatively some bolts were equipped with piezoelectric transducers (actuator and sensor) in order to measure signals of elastic waves. It was noted that the load increasing causes changes in the signals measured. Principal components analysis was used for dimensionality reduction of measured signals. The aim of this study was to investigate the use of elastic waves and artificial neural networks for the purpose of force identification. Examples of preliminary results have shown that force in each bolt may be estimated with relatively good accuracy.