Improved Algorithm of Correlation Dimension Estimation and its Application in Fault Diagnosis for Industrial Fan

In this paper an automatic method for the correlation dimension estimation was introduced, which can improve the precision and speed of the correlation dimension compared with traditional Grassberger and Procaccia algorithm. This improvement is carried out by choosing appropriates key parameter and optimization of calculation process. The effectiveness of this automatic method was tested by means of the calculation of well-know models as logistic attractor and Henon attractor. As a typical example, we applied above method to real vibration signals of fan bearing condition monitoring. Analysis result demonstrates the applicability of this method in distinguishing the bearing status with normal status, local fault and disturbing fault.