The Fault Diagnosis of Rolling Bearings Is Conducted by Employing a Dual-Branch Convolutional Capsule Neural Network.

Currently, many fault diagnosis methods for rolling bearings based on deep learning are facing two main challenges. Firstly, the deep learning model exhibits poor diagnostic performance and limited generalization ability in the presence of noise signals and varying loads. Secondly, there is incomplete utilization of fault information and inadequate extraction of fault features, leading to the low diagnostic accuracy of the model. To address these problems, this paper proposes an improved dual-branch convolutional capsule neural network for rolling bearing fault diagnosis. This method converts the collected bearing vibration signals into grayscale images to construct a grayscale image dataset. By fully considering the types of bearing faults and damage diameters, the data are labeled using a dual-label format. A multi-scale convolution module is introduced to extract features from the data and maximize feature information extraction. Additionally, a coordinate attention mechanism is incorporated into this module to better extract useful channel features and enhance feature extraction capability. Based on adaptive fusion between fault type (damage diameter) features and labels, a dual-branch convolutional capsule neural network model for rolling bearing fault diagnosis is established. The model was experimentally validated using both Case Western Reserve University's bearing dataset and self-made datasets. The experimental results demonstrate that the fault type branch of the model achieves an accuracy rate of 99.88%, while the damage diameter branch attains an accuracy rate of 99.72%. Both branches exhibit excellent classification performance and display robustness against noise interference and variable working conditions. In comparison with other algorithm models cited in the reference literature, the diagnostic capability of the model proposed in this study surpasses them. Furthermore, the generalization ability of the model is validated using a self-constructed laboratory dataset, yielding an average accuracy rate of 94.25% for both branches.

Accuracy improvement of quantitative analysis in spatially resolved fiber-optic laser-induced breakdown spectroscopy.

Fiber-optic laser-induced breakdown spectroscopy (FO-LIBS) has been employed in many applications because of the flexibility of optical fiber cable. However, the inhomogeneous elemental distribution of plasmas can cause a self-absorption effect and, hence, significantly hinder the determination of FO-LIBS. Here, to solve this flaw, we took iron (Fe), magnesium (Mg), and zinc (Zn) elements in aluminum alloy as examples to investigate the self-absorption reduction and accuracy improvement using spatially resolved FO-LIBS. Spatially resolved FO-LIBS means the spectra were collected at different positions along the direction parallel to the surface of the sample rather than at the center of the plasma. With this method, the self-absorption effect could be improved by selecting different acquisition positions along the X-axis. The root mean square error of cross-validations (RMSECV) for Fe, Mg, and Zn were reduced from 0.388, 0.348, and 0.097 wt. % to 0.172, 0.224, and 0.024 wt. %, respectively. Generally, spatial resolution is an effective method of self-absorption reduction and accuracy improvement in FO-LIBS.