Dimensionality reduction method based on multiple feature-space collaborative discriminative projection for rotor fault diagnosis

Abstract

At present, the trend of complex and intelligent rotating machinery and equipment is becoming more and more obvious, which generates a large amount of high-dimensional and nonlinear fault monitoring data that is difficult to handle. This makes the traditional dimensionality reduction algorithms based on point-to-point metrics or a small number of graph embedding structures lose their utility. To solve this problem, a multiple feature-spaces collaborative discriminative projection (MFSCDP) algorithm for rotor fault dataset dimensionality reduction is proposed. The algorithm first improves the projection metric from sample point to feature space into the median metric in order to achieve the effect of weakening the extrapolation error of the algorithm, and based on this, we propose a sample point-to-point guided nearest-neighbor feature space selection method to improve the construction efficiency of the feature space embedding graph. Then, by using Relief F to indirectly construct the reduced dimensional projection matrix with multiple feature spaces of collaboration. Finally, the proposed MFSCDP algorithm is used for the dimensionality reduction process of the rotor fault dataset. The algorithm's performance was verified using experimental information from rotor failure simulations of two different structural types. The result shows that the algorithm can reduce the difficulty of fault classification and improve the accuracy of identification.

Dimensionality reduction of rotor fault dataset based on joint embedding of multi-class graphs

“…However, in the case of the projection metric |𝑋 𝑖 𝑃 12 | < |𝑋 𝑖 𝑃 34 | , this error results in the scattering matrix not reflecting the local topology of the sample in a real and effective way. Therefore, the literature [5] proposes to improve the projection metric to the median point metric, i.e., take the midpoint of the sample point…”

“…In this scenario, the sample point 𝑥 𝑖 calculates the distance to all six feature lines and then sorts them to identify the two nearest feature lines. Therefore, literature [5] proposes the nearest neighbor selection in the feature space guided by P2S as shown in Fig. 2…”

“…However, there is a nearest-neighbor selection error during the computation process when employing the P2S metric. To tackle this issue, Dong [5] introduced an enhancement to the P2S projection metric, replacing it with the median metric. This modification aims to minimize the adverse effects of nearest neighbor selection errors on the algorithm.…”

Visual cue-aided human supervised robot navigation guidance in photometrically challenging environments using adaptive spatial-feature kernel-guided bilateral LPP

“…Cai et al [17] used twodimensional LPP in target recognition problems from inverse synthetic-aperture radar images. Improving the discriminability property [18] in LPP helps it perform better in fault diagnosis problems [19].…”