No abstract

No abstract

No abstract

No abstract

As a noncontact and non-intrusive technique, infrared image analysis becomes promising for machinery defect diagnosis. However, the insignificant information and strong noise in infrared image limit its performance. To address this issue, this paper presents an image segmentation approach to enhance the feature extraction in infrared image analysis. A region selection criterion named dispersion degree is also formulated to discriminate fault representative regions from unrelated background information. Feature extraction and fusion methods are then applied to obtain features from selected regions for further diagnosis. Experimental studies on a rotor fault simulator demonstrate that the presented segmented feature enhancement approach outperforms the one from the original image using both Naï ve Bayes classifier and support vector machine.

Vibration signal analysis is one of the most effective approaches for detecting faults in bearings. A bearing compound-fault signal always consists of multiple signatures and stochastic noise. The separation of multi-fault signals from them is not only crucial but also very challenging. In order to solve this issue, a novel multiple faults detecting technique has been developed based on tensor factorization. The original multi-channel vibration signals are formulated as a 3-way tensor via the temporal signal, spectra, and channel information in a high-dimensional space. The PARAFAC decomposition is used to analyze the tensor model, and then, principal component analysis (PCA) is introduced to find the numbers of the rankone tensor. Finally, the tensor model is solved by alternating least squares (ALSs) approach combined with PCA technique. The performance of the detection method has been proven by simulation analysis of the multi-channel compound faults signals. The experimental results obtained using the developed technique also demonstrated that compound-fault signatures can be effectively and clearly identified.INDEX TERMS PARAFAC, compound-fault, rolling element bearing, fault identification, tensor.

The detection of rail surface defects is an important tool to ensure the safe operation of rail transit. Due to the complex diversity of track surface defect features and the small size of the defect area, it is difficult to obtain satisfying detection results by traditional machine vision methods. The existing deep learning-based methods have the problems of large model sizes, excessive parameters, low accuracy and slow speed. Therefore, this paper proposes a new method based on an improved YOLOv4 (You Only Look Once, YOLO) for railway surface defect detection. In this method, MobileNetv3 is used as the backbone network of YOLOv4 to extract image features, and at the same time, deep separable convolution is applied on the PANet layer in YOLOv4, which realizes the lightweight network and real-time detection of the railway surface. The test results show that, compared with YOLOv4, the study can reduce the amount of the parameters by 78.04%, speed up the detection by 10.36 frames per second and decrease the model volume by 78%. Compared with other methods, the proposed method can achieve a higher detection accuracy, making it suitable for the fast and accurate detection of railway surface defects.

Gearbox diagnosis under stationary operating conditions has been extensively investigated; however, variable operating conditions such as load and speed changes play important roles in affecting the accuracy of gearbox diagnosis. This article presents an integrative approach of intrinsic time-scale decomposition and hierarchical temporal memory for gearbox diagnosis under variable operating conditions. A total of two modules are emphasized including a feature extraction method and an integrative feature fusion and classification model. Intrinsic time-scale decomposition method is investigated to extract the gearbox features which are insensitive to variable operating conditions, and its performance overcomes the commonly used empirical mode decomposition in terms of decomposition result and computational efficiency. Hierarchical temporal memory integrates feature fusion and pattern classification in one model to autonomously diagnose gearbox defect. Performance comparison among the presented method, back-propagation neural network, support vector machine, and fuzzy c-means clustering using experimental data demonstrate the effectiveness of the presented method.