Pretreatment of turbine operation data based on wavelet transform

Blast furnace top gas recovery turbine unit, TRT for short, is an energy saving system. Turbine is the key equipment in TRT system. The normal operation of turbine is directly related to the capacity of TRT system and the benefit of enterprises. The turbine operation data collected from production scene contain large amounts of noise which will affect the analysis and process of turbine fault information. Therefore, this paper adopted wavelet transform to filter the noise in turbine operation data, and used the soft and hard threshold compromise algorithm to process wavelet coefficient in the simulation experiment. The result shows that this algorithm specializes in noise filtering and signal extraction, and applies to the pretreatment of turbine operation data in TRT system.