|
|
|
| Application of Kernel Principal Component Analysis Based on Geodesic Distance in Pattern Recognition of Gear Pump |
| (Department of Equipment Management Engineering, The Second Artillery Engineering College, Xi’an 710025, China) |
|
|
|
|
Abstract As traditional Gauss radial basis kernel which adopts the method of calculating Euclidean distances can not describe completely the relationship between the nonlinear vibration sample data, an improved kernel principal component analytic method was proposed. The method substitutes geodesic distance for Euclidean distance in Gauss radial basis kernel, establishes an appraisement function based on scatter of the sort and space between different sorts, and then uses genetic algorithm (GA) to optimize the k parameter within geodesic distance and delta parameter within Gauss radial basis kernel. The gear pump vibration output signals are decomposed into a number of intrinsic mode function (IMF) components and a residue component, and the method calculates ten nondimensional parameters of each IMF and residue component, then using the optimized kernel function to analyze original parameters. The condition recognition result of gear pump vibration signals in different conditions shows that the novel method is effective.
|
|
Received: 01 December 2010
Published: 30 November 2011
|
|
|
|
|
|
|
|
|
