Search

A noise suppression method for feature frequency extraction that is supplemented with multi-point data fusion was investigated in consideration of issues involving wind turbine vibration signals subject to high noise disturbance. The difficulty of extracting early weak fault features was examined as well. First, a de-noising and feature extraction method that uses EMD-Correlation was developed by adding empirical mode decomposition (EMD) and autocorrelation de-noising to the wavelet package transform under the effects of white noise and short-term disturbance noise in wind turbine vibration signals. Second, an EMD-Correlation analysis model for feature frequency extraction supplemented with multi-point data fusion was established with reference to adaptive resonance theory-2 to highlight the feature frequency of a possible early weak fault. Third, the results obtained with the actual and simulated fault vibration signals of wind turbine bearing faults and the outcomes of comparing the different feature frequency extraction methods show that the proposed method of EMD-Correlation that is supplemented with multi-point data fusion can not only effectively reduce white noise and short-term disturbance noise but can also extract the feature frequency of early weak faults. Finally, prototype hardware and software were developed for a wind turbine condition monitoring system based on the aforementioned fault feature extraction algorithms and tested in an actual wind turbine generation system. [ABSTRACT FROM AUTHOR]

• A lightweight and efficient BLS-based crack detection model is proposed to automatically classify and identify crack images. • The bottleneck structure of MobileNetV3 is introduced as the convolution module of the proposed broad learning system for feature extraction. • By training and validating with public and realistic crack image datasets, the proposed model achieves fast and efficient incremental learning as training samples increase. • The sliding window algorithm is introduced to efficiently recognize and locate cracks in the large-size image. Concrete surface crack detection is an important means to ensure infrastructure security, including bridges and tunnels. In recent years, computer vision has been widely adopted for concrete surface crack detection, and the intelligent crack detection method based on computer vision has achieved good results with the breakthrough of the deep learning algorithm. However, there are also some challenges, such as complex architecture, high computing burden, and time-consuming training. In this paper, a lightweight broad learning system detection method called MobileNetV3-BLS is proposed. First, the inverted residual structure with the linear bottleneck of MobileNetV3 is introduced as the convolution module of the proposed broad learning system for feature extraction. Then the extracted features are employed to randomly generate both mapping and enhancement nodes in a broad learning system, which are used to train the crack detection model. The proposed MobileNetV3-BLS can improve crack detection accuracy and training speed compared with other classical deep learning networks. On the other hand, the proposed method is a dynamic network of which the weights can be updated quickly to achieve incremental learning by adding new nodes and samples. [ABSTRACT FROM AUTHOR]

Abstract: The singular points of fingerprints, namely core and delta, play an important role in fingerprint recognition and classification systems. Several traditional methods have been proposed; however, these methods cannot achieve the reliable and accurate detection of poor-quality fingerprints. In this paper, an algorithm is proposed which combines improved Poincaré index and multi-resolution analysis to detect singular points. Conventional Poincaré index method is improved on the basis of the Zero-pole Model analysis to detect singular points with different resolutions. A model is presented to extract the multi-resolution information of the fingerprint pattern; this model divides fingerprint image into nonoverlapping blocks corresponding to different block sizes on the basis of wavelet functions to compute multiple resolution directional fields, and block position shifting is performed on these resolution levels to capture the features of the ridge direction patterns, where the corresponding shifting intervals are based on Sampling theorem. The relationship of singularities detected by improved Poincaré index in different resolution directional fields is used to confirm singular points accurately and reliably. The combination of local and global information makes our algorithm more robust to noise than methods that use local information only, and the existence of this algorithm increases the insight into the nature of singular points extraction. The accuracy and reliability of the method are demonstrated by experiment on database NIST-4, public fingerprint databases FVC02 DB1 and DB2. [Copyright &y& Elsevier]