Feature Extraction Based on Adaptive Multiwavelets and LTSA for Rotating Machinery Fault Diagnosis

Abstract

Feature extraction is a key procedure in the fault diagnosis of rotating machinery. To obtain fault features with lower dimensionality and higher sensitivity, a feature extraction method based on adaptive multiwavelets transform (AMWT) and local tangent space alignment (LTSA) is proposed in this paper. AMWT is first used to obtain multiple features from the vibration signals of the machine under test to form a high-dimensional feature set. en, in order to avoid the adverse effect of the irrelevant features in this high-dimensional feature set on the fault diagnosis result, a detection index (DI) is investigated to evaluate the sensitivity of the features and those with lower sensitivity are removed. After that, LTSA is applied for feature fusion to reduce the redundant features in the high-dimensional feature set. To validate the proposed method, performance of four feature extraction schemes based on (i) wavelet and LTSA, (ii) Geronimo, Hardin, and Massopust (GHM) multiwavelets and LTSA, (iii) AMWT and principal component analysis (PCA), and (iv) AMWT and multidimensional scaling (MDS) is compared with the proposed method. e feature extraction results by these methods are then fed into K-medoids classifier to discriminate the faults. e results show that the proposed method can improve the sensitivity of the extracted features and obtain higher fault recognition rate.

The Flame-Retardant Mechanisms and Preparation of Polymer Composites and Their Potential Application in Construction Engineering

“…In recent years, with the gradual development of the field of construction engineering, many researchers have devoted themselves to this field and developed a large number of flame-retardant polymer materials that can be used in construction engineering [ 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 ]. According to the material composition, they can be divided into intrinsic-type and doped-type flame-retardant polymer materials.…”

Multi-Filter Clustering Fusion for Feature Selection in Rotating Machinery Fault Classification

“…Feature selection can be divided into wrapper, hybrid, and embedded methods. Filter methods include methods determining the ranks of features by evaluating close relationships or similarity of features, based on information theory and statistics [ 17 ]. They evaluate the relative importance of features, but there is no absolute criterion for selecting them [ 21 ], so it is difficult to distinguish between necessary and unnecessary features [ 22 ].…”

“…Up to four features are used (considering the computational time), but a larger number of features can be used. The set of all features is defined as Equation (17), and the number of feature combinations is calculated using Equation (18):…”

“…An optimal combination of features has been derived using filter methods such as relief, chi-square, and information gain [ 13 ], or by using Pareto optimization [ 14 ] or a binary particle swarm optimization method [ 15 ] after using a filter method. A wrapper-based embedded method, using a support vector machine (SVM) [ 16 ], and a method of deriving optimal features using the sensitivity of features [ 17 ] or a genetic algorithm [ 18 ] have been proposed. Although these methods have shown results in improving classification accuracy, each method has been applied to specific classification problems, which is insufficient to show the universality and robustness of the proposed methods.…”

Weighted K-NN Classification Method of Bearings Fault Diagnosis With Multi-Dimensional Sensitive Features

“…In practical applications, due to the different bearing models and operating conditions, different types of features also have different sensitivity [7]. The study the extraction, screening and feature fusion methods of fault characteristic signals to reduce redundant features that have little contribution to fault diagnosis and obtain lowdimensional, high-sensitivity fault feature subsets is of great significance for improving the accuracy of fault diagnosis results and reducing the complexity of corresponding algorithms [8]. Liu et al [9] used 3-layer wavelet packet decomposition to extract 56-dimensional features, and used kernel principal component analysis (KPCA) to reduce feature dimension and extract the main features, as well as a support vector machine (SVM) for fault identification.…”