Defect detection based on two different algorithms of analysis and comparison

Conventional techniques for feature extraction are based on the stationary process and linear theory, so they are unsuited for processing the non-stationary signals. Hilbert-Huang transform (HHT) has been proposed recently and is specially fit to explore the non-stationary signals. The paper utilizes HHT to analyze the signals from the WZ12-1 platform. First, we employ a simulation signal to measure the performance of empirical mode decomposition (EMD), which is the core of HHT. Next, the HHT method is applied to extract the fault feature from the signals collected from the WZ12-1 platform and successfully reveals the reason causing the excessive vibration of the WZ12-1 platform. The results indicate that HHT could be a helpful method for the fault feature extraction of mechanical systems.Keywordsfeature extractionHilbert-Huang transform (HHT)empirical mode decomposition (EMD)offshore platform

Fluctuating pressure is an important feature of the bottom of a stilling basin with step-down floor. To analyze the frequency domain characteristics and energy distribution of this fluctuating pressure, the Hilbert–Huang transform (HHT) method is used. First, empirical mode decomposition is performed on the pressure fluctuation signal to obtain a number of intrinsic mode functions (IMFs), and then the Hilbert transformation is performed on each IMF to obtain the Hilbert spectrum and marginal spectrum for characterizing the pressure fluctuation signal. The results show that the fluctuating pressure signal of the stilling basin with step-down floor has obvious characteristics of low frequency and large amplitude. The dominant frequencies of the head and tail of the stilling basin are very prominent, and most of the energy is concentrated below 5.0 Hz; with the increase in the relative position of the measuring point, the energy distribution in stilling basin with step-down floor changes from high-frequency component to low-frequency component. The fluctuating pressure signal of the stilling basin with step-down floor has random amplitude modulation and frequency modulation. The marginal spectrum obtained by the HHT method can obtain the local characteristics of the signal more accurately and is more suitable for processing nonlinear and nonstationary signals.

In this paper, one fabric defect detection and classification system based on 2D Gabor wavelet transform and Elman neural network is introduced. In the proposed scheme, the texture features of the textile fabric are extracted by using an optimal 2D Gabor filter. A new modified Elman network is proposed to classify the type of fabric defects which have a proportional (P), integral (I) and derivative (D) properties. The proposed inspecting system in this study is more feasible and applicable in fabric defect detection and classification.

Atomic clock difference (errors) contains various kinds of noise and it can be characterized to as non-stationary. Hilbert-Huang Transform (HHT), a new adaptive method based on empirical mode decomposition (EMD) and Hilbert spectral analysis, was used to analyze and process atomic clock difference. Taking real data for discussion, the results show that HHT method is practical and versatile to handle noisy data and characterize the clock behavior.

This paper explores the possibility of using a combination of the empirical mode decomposition (EMD) and the Hilbert transform (HT), termed the Hilbert-Huang transform (HHT) method, to identify the modal damping ratios of the structure with closely spaced modal frequencies. The principle of the HHT method and the procedure of using the HHT method for modal damping ratio identification are briefly introduced first. The dynamic response of a two-degrees-of-freedom (2DOF) system under an impact load is then computed for a wide range of dynamic properties from well-separated modal frequencies to very closely spaced modal frequencies. The natural frequencies and modal damping ratios identified by the HHT method are compared with the theoretical values and those identified using the fast Fourier transform (FFT) method. The results show that the HHT method is superior to the FFT method in the identification of modal damping ratios of the structure with closely spaced modes of vibration. Finally, a 36-storey shear building with a 4-storey light appendage, having closely spaced modal frequencies and subjected to an ambient ground motion, is analyzed. The modal damping ratios identified by the HHT method in conjunction with the random decrement technique (RDT) are much better than those obtained by the FFT method. The HHT method performing in the frequency-time domain seems to be a promising tool for system identification of civil engineering structures.

本文提出了基于希尔伯特–黄变换(Hilbert-Huang Transform, HHT)与Teager能量算子(Teager Energy Operator, TEO)相融合的谐振接地选线新方法。首先对零序电流信号进行经验模态分解法(Empirical Mode De-composition, EMD)分解，然后将TEO合理的引入选线算法中，并与HHT极性判别法相融合，实现了HHT与TEO两者融合的优势互补。通过仿真分析，验证了所提方法的可行性和有效性。 The combination method of Hilbert-Huang Transform (HHT) and Teager Energy Operator (TEO) for fault line selection with resonance grounding is proposed in this paper. The zero sequence current signals are decomposed using Empirical Mode Decomposition (EMD). The TEO is reasonable introduced into algorithm of fault line selection. The TEO is combined with the method of HHT polarity estimate. The complementary advantage for combination method of HHT and TEO is implemented. The feasibility and effectiveness of the proposed method is verified by simulation results.

The features extraction is the main step in a Brain-Computer Interface (BCI) design. Its goal is to create features easy to be interpreted in order to produce the most accurate control commands. For this end, these features must include all the original signal characteristics. The generated brain's signals' non-stationary and nonlinearity constitute a limitation to the improvement of the performances of systems based on traditional signal processing such as Fourier Transform. This work deals with the comparison of features extraction between Hilbert-Huang Transform (HHT) and Welch's method for Power Spectral Density estimation (PSD) then on the creation of an adaptive method combining the two. The parameters optimization of each method is firstly performed to reach the best classification accuracy rate. The study shows that the PSD estimation is sensitive to the parametric variation whereas the HHT method is mainly robust. The classification results show that an adaptive joint method can reach 90% of accuracy rate for a mental activity period of 1s.

Improved MobileNetV2-SSDLite for automatic fabric defect detection system based on cloud-edge computing

Hilbert-Huang Transform (HHT) is a kind of signal analysis method suitable for non-stationary signal, and the combination of HHT and vector signal processing is called vector HHT, by which the instantaneous azimuth of the target can be estimated. In vector HHT signal processing method, the existence of intermittent signal and noise leads to mode mixing in the results of empirical mode decomposition (EMD). Mode mixing influences exact extraction of vibration mode, which causes that the signal which should be in the same order of intrinsic mode function (IMF) distributes in different IMFs. In vector HHT signal processing method, the two vibration speed components need to be multiplied by sound pressure respectively, so mode mixing will lead to great error in the estimation of azimuth of the target. To overcome the influence of mode mixing on vector HHT, this paper proposes a kind of vector HHT signal processing method based on scale filtering. The new method can effectively eliminate mode mixing resulting from intermittent signal and noise, and exact decomposition results can be achieved. The improved vector HHT method is used in processing acoustic vector signal, and the data obtained from a certain sea experiment in Dalian city is analyzed by the new method. The waterfall plot accurately shows the azimuth of the target ship, which proves the validity of the method.

Low-complexity sinusoidal-assisted EMD (SAEMD) algorithms for solving mode-mixing problems in HHT

As an essential step in quality control, fabric defect detection plays an important role in the textile manufacturing industry. The traditional manual detection method is inaccurate and incurs a high cost; as a result, it is gradually being replaced by deep learning algorithms based on cloud computing. However, a high data transmission latency between end devices and the cloud has a significant impact on textile production efficiency. In contrast, edge computing, which provides services near end devices by deploying network, computing and storage facilities at the edge of the Internet, can effectively solve the above-mentioned problem. In this article, we propose a deep-learning-based fabric defect detection method for edge computing scenarios. First, this article modifies the structure of DenseNet to better suit a resource-constrained edge computing scenario. To better assess the proposed model, an optimized cross-entropy loss function is also formulated. Afterward, six feasible expansion schemes are utilized to enhance the data set according to the characteristics of various defects in fabric samples. To balance the distribution of samples, proportions of various defect types are used to determine the number of enhancements. Finally, a fabric defect detection system is established to test the performance of the optimized model used on edge devices in a real-world textile industry scenario. Experimental results demonstrate that compared with the conventional convolutional neural network (CNN), the proposed optimized model attains an average improvement of 18% in the area under the curve (AUC) metric for 11 defects. Data transmission is reduced by approximately 50% and latency is reduced by 32% in the Cambricon 1H8 platform compared with a cloud platform.

Novel and efficient computation of Hilbert–Huang transform on surfaces

Traditional modal parameter identification methods have many disadvantages, especially when used for processing nonlinear and non-stationary signals. In addition, they are usually not able to accurately identify the damping ratio and damage. In this study, methods based on the Hilbert-Huang transform (HHT) are investigated for structural modal parameter identification and damage diagnosis. First, mirror extension and prediction via a radial basis function (RBF) neural network are used to restrain the troublesome end-effect issue in empirical mode decomposition (EMD), which is a crucial part of HHT. Then, the approaches based on HHT combined with other techniques, such as the random decrement technique (RDT), natural excitation technique (NExT) and stochastic subspace identification (SSI), are proposed to identify modal parameters of structures. Furthermore, a damage diagnosis method based on the HHT is also proposed. Time-varying instantaneous frequency and instantaneous energy are used to identify the damage evolution of the structure. The relative amplitude of the Hilbert marginal spectrum is used to identify the damage location of the structure. Finally, acceleration records at gauge points from shaking table testing of a 12-story reinforced concrete frame model are taken to validate the proposed approaches. The results show that the proposed approaches based on HHT for modal parameter identification and damage diagnosis are reliable and practical.

This paper presents recent time-frequency analysis technique called Hilbert Huang Transform (HHT) used for non-stationary and nonlinear signals. This technique is applied in combination with a pattern recognition method to detect defects in induction motor. Studied defects in our case are one broken rotor bar, two broken rotor bars and broken ring on the rotor. The aim of this study is to improve the classification results of these different rotor faults. The classification results obtained by using the HHT method and those obtained by using the temporal signals are compared.

Abnormal vibration signals of tramcar are mostly nonstationary and nonlinear signals. This study applied the Hilbert–Huang transform (HHT) to analyze abnormal vibration of the tramcar, aiming to overcome the limitations of some traditional time-frequency analysis methods, such as Fourier transform, in dealing with nonstationary and nonlinear signals. Additionally, to address mode aliasing produced during empirical mode decomposition (EMD) used in classical HHT, this study proposed to first use complete EMD with adaptive noise for the decomposition of original vibration data, then eliminate the trend-term components with the calculated correlation coefficients, and finally perform denoising on high-frequency noisy components using the wavelet threshold method. After weighted reconstruction using denoised high-frequency components and low-frequency information components, data processing was finally optimized via HHT. Taking a tramcar as an example, the Hilbert spectra of the vertical acceleration of axle box were plotted via HHT, and the time-instantaneous, frequency-instantaneous energy 3D relations were obtained for the location of impact points. Further, the vibration characteristics were analyzed and quality indexes were calculated in combination with the marginal spectra so as to judge the reasons for abnormal vibration and failure modes of the tramcar. The results revealed that the proposed method was feasible and effective in vibration feature extraction and vibration impact analysis for tramcars.