Aiming at the problem of poor fault diagnosis performance of rolling bearings under small sample conditions, a novel method based on self-calibrated coordinate attention mechanism and multi-scale convolutional neural network (SC-MSCNN) is proposed in this paper. Firstly, Markov transition field (MTF) is used to convert the original vibration signals into MTF images with temporal correlation. Then, the self-calibrated coordinate attention mechanism is presented, which obtains feature location information and feature channel information from two directions, and locates useful features more accurately. Finally, the SC-MSCNN model is built, and the MTF images are input into the model to complete the classification. The SC-MSCNN model simplifies the structure of the model by adding jump connections, which greatly reduces the number of learnable parameters and thus alleviates the overfitting problem. The approach is demonstrated using two bearing datasets, and the results show that SC-MSCNN can accurately diagnose different fault modes using small samples under given and variable working conditions, which is superior to other popular CNNs.
30 August 2022 in Measurement Science and Technology
Safe and reliable operation of mechanical equipment depends on timely and accurate fault diagnosis. When the actual working conditions are complex and variable and the available sample data set is small, recognition accuracy of the rolling bearing fault diagnosis model is low. To solve this problem, a novel method based on Markov transition field (MTF) and multi-dimension convolutional neural network (MDCNN) is proposed in this paper. Firstly, the original vibration signals are converted into two-dimensional images containing temporal correlation by MTF. Then, a neural network model is constructed by using multi-dimension attention and E-rectified linear units (E-Relu) activation function to fully extract fault feature information. Finally, the MTF images are input into the model and the data is normalized using the group normalization method. The MDCNN model is validated on two different data sets, and the results show that compared with other intelligent fault diagnosis methods, the MDCNN has higher fault diagnosis accuracy and stronger robustness under both variable working conditions and small sample data sets conditions.
8 December 2023 in Measurement Science and Technology
A rolling bearing fault diagnosis method based on the Markov transition field (MTF) and multi-scale feature aggregation convolutional neural network (MFACNN) is proposed to address the problems of excessive parameter number, slow training speed, and insufficient generalization of traditional CNNs. Firstly, the original vibration signal is input into the MTF and converted into two-dimensional images with time correlation. Then, in order to effectively aggregate feature information at different scales and levels, a MFA module is presented to capture rich information from feature maps at different scales and assign different weights to these features for fusion. Secondly, while ensuring the lightweight of the model, utilizing feature information of different resolutions, a lightweight feature fusion module is put forward to fuse multiple feature maps together to improve the performance and efficiency of the model. On this basis, an MFACNN model is constructed. Finally, the two-dimensional images are input into MTF-MFACNN and experimentally validated using two different datasets. The results show that the proposed method has faster calculation speed, higher fault recognition accuracy, and stronger generalization performance compared to other methods.
In this work, the distribution and evolution of micro-defect in single crystal γ-TiAl alloy during nanometer cutting is studied by means of molecular dynamics simulation. Nanometer cutting is performed along two typical crystal directions: and . A machined surface, system potential energy, amorphous layer, lattice deformation and the formation mechanism of chip are discussed. The results indicate that the intrinsic stacking fault, dislocation loop and atomic cluster are generated below the machined surface along the cutting crystal directions. In particular, the Stacking Fault Tetrahedron (SFT) is generated inside the workpiece when the cutting crystal direction is along . However, a “V”-shape dislocation loop is formed in the workpiece along . Furthermore, atomic distribution of the machined surface indicates that the surface quality along is better than that along . In a certain range, the thickness of the amorphous layer increases gradually with the rise of cutting force during nanometric cutting process.
21 September 2023 in Measurement Science and Technology
In order to address the problem that one- dimensional convolutional neural networks is difficult to extract the local correlation information and mine multi-scale information of rolling bearing fault signals under variable working conditions, a novel fault diagnosis method for rolling bearings based on Markov transition field (MTF) and multi-scale Runge–Kutta residual attention network (MRKRA-Net) is proposed in this paper. Firstly, the original signal is encoded into a two-dimensional image using the MTF method. Then, a multi-scale network is constructed using pre-activation Runge–Kutta residual blocks to extract multi-level features. Secondly, a feature-guided attention mechanism is designed and embedded into the network model to enhance its generalization ability. Finally, the MRKRA-Net model is validated on two different bearing datasets, and the results show that compared with other popular intelligent fault diagnosis methods, MRKRA-Net has higher fault diagnosis accuracy and stronger robustness under both given and variable working conditions.
31 July 2023 in Measurement Science and Technology
Aiming at the problems of traditional fault diagnosis methods that do not represent the time correlation between signals, low recognition accuracy under complex working conditions and noise interference and too many parameters, a bearing fault diagnosis method based on mixed attention mechanism (MAM) and deep separable dilated convolution neural network (DSDCNN) is proposed. Firstly, a Markov transfer field encoding method is used to transform the original one-dimensional vibration signal into a two-dimensional feature image with temporal correlation. Secondly, a deep separable convolution algorithm is presented by taking advantage of the low computational complexity of deep separable convolution and the ability of dilated convolution to expand the receptive field under the condition of invariable number of parameters. Then, the MAM is designed to make the model capture the feature dependency of the feature map in spatial and channel dimensions, and the MAM-DSDCNN model is constructed. Finally, the fault diagnosis performance of the proposed model is verified with two different data sets. The results show that the average recognition accuracy of MAM-DSDCNN reaches 99.63% under variable load conditions, 99.42% under variable speed conditions, 94.26% under noisy environment with the signal-to-noise of 0 dB, which prove that the model has higher recognition accuracy, stronger generalization and noise immunity performance than other deep learning algorithms.