Mixed-signal extraction and recognition of wind turbine blade multiple-area damage based on improved Fast-ICA

Abstract In order to use fewer sensors to achieve more detection information caused by wind turbine blade multiple-area damage, the improved Fast-ICA is studied in this paper. In theory, the Kendall rank correlation coefficient is introduced to improve Fast-ICA and solve the sequence identification issue of the separated original signal. To confirm the data extraction capability of the improved Fast-ICA, simulation experiment and validation experiment are all carried out. Data analyses results of simulation experiment and validation experiment confirm that the improved Fast-ICA can achieve the mixed-signal extraction and recognition, and solve the sequence identification issue of the separated original signal. So, the improved Fast-ICA proposed in this paper can not only reduce the number of sensors and the cost of damage detection system, but also provide effective data support for accurate determination of wind turbine blade multiple-area damage location.