DWT and Hilbert Transform for Broken Rotor Bar Fault Diagnosis in Induction Machine at Low Load

Abstract

In this paper a new technique for broken rotor bars diagnosis in induction machine at low load and non stationary state is proposed. The technique is used in order to remedy the problem from using the classical signal-processing technique FFT by analysis of stator current envelope. The proposed method is based from using discrete wavelet transform (DWT) and Hilbert transform. The Hilbert transform is used to extract the stator current envelope. Then this signal is processed via DWT. The efficiency of the proposed method is verified by simulation tests.

Convolutional Neural Network and Motor Current Signature Analysis during the Transient State for Detection of Broken Rotor Bars in Induction Motors

“…Table 3 summarizes the results obtained by using the proposed methodology and previous works recently reported in the literature, where the methods employed, the evaluated damage level, and the obtained effectiveness percentage are presented. According to Table 3 , the proposed method presents effectiveness of 100% for detecting a partially-BRB fault as well as the consolidated state (1BRB and 2BRB), unlike other methods presented in the literature [ 10 , 12 , 43 ], which are focused mainly on evaluating IMs with one or more BRBs. In particular, promising results were also obtained using pre-trained CNNs such as the VGG-16 architecture [ 43 ]; however, although the design is easy, it keeps the complexity of a CNN for general applications, which in some cases is neither necessary nor justified, mainly if the task is not a large-scale image recognition problem.…”

“…MCSA is employed for identifying the frequency components associated with specific faults; in particular, the MCSA attempts to identify the frequency components around the fundamental component (e.g., 50 or 60 Hz), which are related to the BRB fault [ 9 ]. In this sense, diverse works have focused on evaluating one or multiple BRBs, a consolidated fault (one or more bars completely segmented or cracked in two parts) [ 10 , 11 , 12 ]; however, few works have investigated a partially cracked bar, an initial condition of the BRB fault [ 9 , 13 ], because this condition alters slightly the monitored physical magnitudes, which increases the detection difficulty [ 14 ].…”

Fault Diagnosis of HTS–SLIM Based on 3D Finite Element Method and Hilbert–Huang Transform

“…With considering the literature of fault diagnosis methods, they could classified in three important parts as signal processing, machine learning, and artificial intelligent algorithms, which the first method is widely used in the fault detection of electrical machines. The recent signal processing methods such as acoustic signals analysis [4,10,11], the vector space decomposition approach [12], KF based approaches [9,13], various Fourier Transforms (FTs) [14][15][16], the HT [3,17], the Hilbert-Huang Transform (HHT) [18][19][20][21], space pattern recognition [22], various Wavelet Transforms (WT) [5,7,23] or combined methods [24][25][26], etc., the machine learning based approaches such as Random Forest (RF) algorithm [27], fuzzy-Bayesian [28], Support Vector Machine (SVM) [29], etc., and artificial intelligent algorithms such as Artificial Neural Network (ANN) methods [30,31] have been proposed and used in the RIM fault detection problems. The above researches are based on the methods that needs several tests and to verify the results, even though the method is robust.…”

Broken rotor bar fault detection using Hilbert transform and neural networks applied to direct torque control of induction motor drive

“…It is used to analyse non‐linear and non‐stationary signals [28]. Nowadays this adaptive method is one of the most desirable signal processing tools in fault diagnosis [29]. It allows producing a meaningful representation of signals from non‐linear and non‐stationary signals.…”