Casing Vibration Fault Diagnosis Based on Variational Mode Decomposition, Local Linear Embedding, and Support Vector Machine

Abstract

To diagnose mechanical faults of rotor-bearing-casing system by analyzing its casing vibration signal, this paper proposes a training procedure of a fault classifier based on variational mode decomposition (VMD), local linear embedding (LLE), and support vector machine (SVM). VMD is used first to decompose the casing signal into several modes, which are subsignals usually modulated by fault frequencies. Vibrational features are extracted from both VMD subsignals and the original one. LLE is employed here to reduce the dimensionality of these extracted features and make the samples more separable. Then low-dimensional data sets are used to train the multiclass SVM whose accuracy is tested by classifying the test samples. When the parameters of LLE and SVM are well optimized, this proposed method performs well on experimental data, showing its capacity of diagnosing casing vibration faults.

A Comparative Study of Four Kinds of Adaptive Decomposition Algorithms and Their Applications

“…Similar to EWT, as the fault diagnosis of machinery is a popular issue of dynamic analysis, a great amount of research regarding application and improvement has been undertaken for VMD in this domain [ 89 , 90 , 91 , 92 , 93 , 94 , 95 , 96 , 97 , 98 , 99 , 100 , 101 , 102 , 103 , 104 , 105 , 106 , 107 , 108 , 109 , 110 , 111 ]. After decomposition of signals by using VMD, signal characteristics of fault are obtained by some other methods.…”

“…An [ 100 ] also used the K nearest neighbor algorithm to extract energy characteristic parameters from components carrying defect information decomposed by VMD to obtain fault diagnosis of rolling bearings of a wind turbine. Yang [ 101 ] employed local linear embedding to reduce the dimensionality of these extracted features extracted from both VMD sub-signals and the original one and made the samples more separable. Then, multiclass support vector machine was used to diagnose mechanical faults of a rotor-bearing-casing system.…”

A novel deep learning-based method for damage identification of smart building structures

“…After extracting the signal feature, we need to select features sensitive to damage patterns and remove the features with useless information, thus decreasing the dimension of features for the purpose of calculation efficiency. The feature-selection methods for structural DI include local linear embedding (LLE), 10–12 independent component analysis (ICA), 13–15 principal component analysis (PCA), 16–18 isometric mapping algorithm 19 and so on. With optimal features chosen from vibration signals, the final step is to identify the signal patterns via machine learning (ML) methods, such as artificial neural networks (ANNs), 20–22 support vector machine (SVM), 23–25 extreme learning machine (ELM), 26 adaptive neuro-fuzzy inference system (ANFIS) 27 and so on.…”

Bearing Fault Diagnosis with Kernel Sparse Representation Classification Based on Adaptive Local Iterative Filtering‐Enhanced Multiscale Entropy Features

“…Li et al [4] utilized local mean decomposition (LMD) [5] for preprocessing, improved multiscale fuzzy entropy as features, Laplacian scores for feature selection, and improved support vector machine based binary tree for bearing fault diagnosis. Yang et al [6] combined variational mode decomposition (VMD) [7], local linear embedding (LLE) with support vector machine (SVM) to diagnose mechanical faults of the rotor-bearing-casing system. Good effects in bearing fault diagnosis have been realized to some extent from the above description; however, some problems still exist and need to be investigated further.…”

“…Before classification, feature selection like LS or dimensionality reduction like PCA and LLE should be performed. In the following, classifiers such as HMM [1], ANN [2], SVM [6], and multiclass relevance vector machine [20] are carried out for identification of the fault type. Though theories of them are well established, the inherent limitations have confined them to some extent.…”