Fan vibration abnormal detection method and device

Abstract

The invention discloses a draught fan vibration anomaly detection method and device. The method comprises: collecting draught fan operation data within a certain time period; extracting working condition features and vibration features from the fan operation data to obtain a test data set; predicting vibration characteristics in the test data set by using a pre-established working condition-vibration model to obtain a predicted value corresponding to the vibration characteristics; calculating a vibration characteristic residual error according to the vibration characteristics in the test dataset and a predicted value thereof to obtain a residual error matrix; calculating the distance of the vibration characteristic residual error of each working condition point in the test data set according to the residual error matrix; and if the distances of the vibration characteristic residual errors of the continuous set number of working condition points are all larger than a predetermined distance threshold value, determining that vibration of the draught fan is abnormal in the time period. By means of the scheme, under the condition that the high-frequency vibration signal of the draughtfan component cannot be obtained, effective detection of draught fan vibration abnormity can also be achieved.

Description

technical field [0001] The invention relates to the field of data processing, in particular to a method and device for detecting abnormal vibration of a fan. Background technique [0002] Existing wind turbine condition monitoring systems include fan vibration anomaly detection based on high-frequency vibration signals, such as fault diagnosis through Fourier transform and envelope spectrum analysis. This detection requires specific sensors to collect High frequency vibration signal. However, for abnormal vibration detection of components such as wind turbine towers and nacelles, usually only low-frequency vibration signal data from the SCADA (Supervisory Control And Data Acquisition, data acquisition and monitoring control) system can be collected. If the existing high-frequency vibration signal Anomaly detection method, it is impossible to obtain effective fault characteristic frequency from these low-frequency vibration signal data, especially for new wind turbines or un...

AI Technical Summary

Problems solved by technology

However, for abnormal vibration detection of components such as wind turbine towers and nacelles, usually only low-frequency vibration signal data from the SCADA (Supervisory Control And Data Acquisition, data acquisition and monitoring control) system can be collected. If the existing high-frequency vibration signal However, if the abnormal detection method is used, the effective fault characteristic frequency cannot be obtained from these low-frequency vibration signal data, especially for newly-built wind turbines or units with a short effective running time, and effective abnormal vibration detection of wind turbines cannot be carried out.

Images