Search

The bearing vibration of wind turbines is nonlinear and non-stationary. To effectively extract bearing vibration signal features for fault diagnosis, a method of feature vector extraction based on variational mode decomposition (VMD) and energy entropy is proposed. In addition, the support vector machine (SVM) classifier is used to identify the types of vibration faults. VMD transforms the constrained variational objective function into the unconstrained one to optimize solution. Compared with the VMD and empirical mode decomposition (EMD), the modal decomposition layer of VMD is less than EMD, no found false modality, and truly reflecting signal components. After the Hilbert transformation, double logarithmic coordinates show that the VMD-based spectral characteristics are significant. VMD is performed on the different types of vibration signals of wind turbines. Therefore, VMD is not that affected by noise and has few decomposition levels. The energy entropy of the normalized four modal components is considered the eigenvalue and classified by SVM, and compared with EMD-based and wavelet db4-based energy entropy eigenvalue extraction methods. Experimental results indicate that the accuracy of the method is higher than those based on EMD and wavelet db4, under the limited sample condition. Thus, a referential diagnostic method is provided for practical applications. • A method of feature vector extraction based on variational mode decomposition (VMD) and energy entropy is proposed. • The time-frequency energy spectrum obtained by VMD is compared with that by empirical mode decomposition (EMD). • Different types of bearing vibration signals of wind turbine are analyzed. • The fault diagnostic identification of the proposed method is compared with EMD-based and wavelet db4-based methods. [ABSTRACT FROM AUTHOR]

Despite the rapid technical advancement of augmented reality (AR) and mixed reality (MR) in minimally invasive surgery (MIS) in recent years, monocular-based 2D/3D reconstruction still remains technically challenging in AR/MR guided surgery navigation nowadays. In principle, soft tissue surface is smooth and watery with sparse texture, specular reflection, and frequent deformation. As a result, we frequently obtain only sparse feature points that give rise to incorrect matching results with conventional image processing methods. To ameliorate, in this paper we enunciate an accurate and robust description and matching method for dense feature points in endoscopic videos. Our new method first extracts contours of the low-rank image sequences based on the adaptive robust principal component analysis (RPCA) decomposition. Then we propose a multi-scale dense geometric feature description approach, which simultaneously extracts dense feature descriptors of the contours in the original Euclidean coordinate space, the accompanying 3D color coordinate space, and the derived curvature-gradient coordinate space. Finally, we devise a new algorithm for both global and local point-wise matching based on feature fusion. For global matching, we employ the fast Fourier transform (FFT) to reduce the dimension of the dense feature descriptors. For local feature point matching, in order to enhance the robustness and accuracy of the matching, we cluster multiple contour points to form "super-point" based on dense feature descriptors and their spatio-temporal continuity. The comprehensive experimental results confirm that our novel approach can overcome the highlight influence, and robustly describe contours from image sequences of soft tissue surfaces. Compared with the state-of-the-art feature point description and matching methods, our analysis framework shows the key advantages of both robustness and accuracy in dense point-wise matching, even when the severe soft tissue deformation occurs. Our new approach is expected to have high potential in 2D/3D reconstruction in endoscopy. [Display omitted] • Accurate and robust contour description for soft tissue. • Multi-scale, dense, and hybrid geometric feature descriptors in endoscopic images. • Global and local point-wise feature point matching. • Our method overcomes the problems of highlight and sparse texture in feature extraction, and demonstrates its potential applications in 2D/3D reconstruction for endoscopy. [ABSTRACT FROM AUTHOR]

• This paper proposes a method called 2DWT-CNN for identifying DC bias magnetism conditions in transformers by studying the magnetostrictive effect of ferromagnetic materials and analyzing the dynamic process of core deformation. • A DC bias vibration test platform was built and vibration signals were collected from the core and shell of the transformer. • A two-dimensional transformation method of vibration signal is proposed to extract magnetic bias features by analyzing the magnetostrictive characteristics of transformer core under DC bias magnetic. • This paper successfully applies the microscopic process of magnetostriction to the macroscopic and practical testing of transformer bias conditions. Abnormal vibration of transformers under DC bias magnetism may cause permanent damage to its mechanical structure. Considering the magnetostrictive effect of the core is the main source of vibration in transformers, this paper proposes a method called 2DWT-CNN for identifying DC bias magnetism conditions in transformers by studying the magnetostrictive effect of ferromagnetic materials and analyzing the dynamic process of core deformation. Specifically, the electromagnetic vibration signals of the core and the shell of the transformer were acquired separately on the experimental platform. Then, based on the expansion and contraction characteristics of the core under DC bias magnetism conditions, the magnetic vibration features were extracted using the 2D wavelet transform. Finally, a bias magnetism recognition method called two-dimensional wavelet-convolutional neural network (2DWT-CNN) was established by combining convolutional neural networks as the classifier. The experimental results show that the recognition model has a classification accuracy of almost 100% for the core test points and a prediction accuracy of around 97% for the points located in the transformer's shell. Therefore, the 2DWT-CNN, which takes magnetostrictive effects into account, is an effective method for identifying bias magnetic conditions and can successfully apply the microscopic process of magnetostriction to the macroscopic and practical detection of transformer bias magnetic conditions. [ABSTRACT FROM AUTHOR]