Jianmin Zhou

Aiming at the problem that the surface defects of blAister tablets are difficult to detect correctly, this paper proposes a detection method based on the improved U2Net. First, the features extracted from the RSU module of U2Net are enhanced and adjusted using the large kernel attention mechanism, so that the U2Net model strengthens its ability to extract defective features. Second, a loss function combining the Gaussian Laplace operator and the cross-entropy function is designed to make the model strengthen its ability to detect edge defects on the surface of blister tablets. Finally, thresholds are adaptively determined using the local mean and OTSU(an adaptive threshold segmentation method) method to improve accuracy. The experimental results show that the method proposed in this paper can reach an average accuracy of 99% and an average precision rate of 96.3%; the model test only takes 50 ms per image, which can meet the rapid detection requirements. Minor surface defects can also be accurately detected, which is better than other algorithmic models of the same type, proving the effectiveness of this method.

In fault diagnosis, broad learning systems (BLS) have been applied in recent years. However, the best fault diagnosis cannot be guaranteed by width node extension alone, so a stacked broad learning system (stacked BLS) was proposed. Most of the methods for choosing the number of depth layers used optimization algorithms that tend to increase computation time. In addition, the data under single feature selection are not sufficiently representative, and effective features are easily lost. To solve these problems, this article proposes an infrared fault diagnosis model for rolling bearings based on integration of principal component analysis and singular value decomposition (IPS) and the stacked BLS with self-selected depth model (SSDStacked-BLS). First, 72 second-order statistical features are extracted from the pre-processed infrared images of rolling bearings. Next, feature selection is performed using IPS. he IPS feature selection module consists of principal component analysis (PCA) and singular value decomposition (SVD). The feature selection is performed by PCA and SVD separately, which are then stitched together to form a new feature. This ensures a comprehensive coverage of infrared image features. Finally, the acquired features are input into SSDStacked-BLS. This model establishes a data storage group for the residual training characteristics of stacked BLS, adding one block at a time. The accuracy rate of each newly added block is output and saved to the data storage group. If the diagnostic rate fails to increase three consecutive times, the block stacking is stopped and the results are output. IPS-SSDStacked-BLS achieved an accuracy of 0.9667 in 0.1775 s. This is almost five times faster than stacked BLS optimized using the grid search method. Compared with the original BLS, its accuracy was 0.0445 higher and the time was approximated. Compared with IPS-SVM, IPS-RF, IPS-1DCNN and 2DCNN, IPS-SSDStacked-BLS was more advantageous in terms of accuracy and time consumption.

To overcome the problems of low machine learning fault diagnosis rate and long consumption time of deep learning in rolling bearing fault diagnosis, an RFR-GA-BLS model is proposed. The model is validated by infrared images of rolling bearings to find the most representative features, the most suitable parameters and the best diagnostic rate. Based on the pre-processed infrared thermal images of the faulty bearing, 72 second-order statistical features were obtained as information for fault diagnosis. RFR considered the robustness of the features, and new sequences were obtained. BLS was optimized by GA for fault diagnosis. New sequence features were added to the model sequentially, one at a time. After satisfying the model conditions, the most appropriate number of features was selected as the first 20. The search results for the number of feature nodes, the number of feature node windows and the number of enhancement nodes for the BLS were 24, 19 and 544, respectively, and the fault diagnosis rate of 98.8889% was achieved. According to a comparison with CFR-GA-BLS, BLS, PSO-BLS and Grdy-BLS, our proposed model is more advantageous in the search for the best performance. The fault diagnosis accuracy is higher compared to SVM and RF. The speed of our proposed model is 207 times faster than 1DCNN and 10,147 times faster than 2DCNN.

The Bayesian support vector regression (BSVR) metamodel is widely used in various engineering fields to analyze the uncertainty arising from uncertain parameters. However, the accuracy of the BSVR metamodel based on the traditional one-shot sampling method fails to meet the requirements of the uncertainty analysis of complex systems. To this end, an error-pursing adaptive uncertainty analysis method based on the BSVR metamodel is presented by combining a new adaptive sampling scheme. This new sampling scheme was improved by a new error-pursuing active learning function that is named, herein, adjusted mean square error (AMSE), which guides the adaptive sampling of the BSVR metamodel’s design of experiments (DoE). During the sampling process, AMSE combines mean square error and leave-one-out cross-validation error to estimate the prediction error of the metamodel in the entire design space. Stepwise refinement of the metamodel was achieved by placing the sampled regions at locations with large prediction errors. Six benchmark analytical functions featuring different dimensions were used to validate the proposed method. The effectiveness of the method was then further illustrated by a more realistic application of an overhung rotor system.

Bearings are essential components of rotating machinery used in mechanical systems, and fault diagnosis of bearings is of great significance to the operation and maintenance of mechanical equipment. Deep learning is a popular method for bearing fault diagnosis, which can effectively extract the in-depth information of fault signals, thus achieving high fault diagnosis accuracy. However, due to the complex deep structure of deep learning, most deep learning methods require more time and resources for bearing fault diagnosis. This paper proposes a bearing fault diagnosis method combining feature engineering and fuzzy broad learning. First, time domain, frequency domain, and time-frequency domain features are extracted from the bearing signals. Then the stability and robustness indexes of these features are evaluated to complete the feature engineering. The features obtained by feature engineering are used as the input of the fault diagnosis model, and three sets of experimental data validate the model. The experimental results show that the proposed method can achieve the bearing fault diagnosis accuracy of 96.43% on the experimental bench data, 100% on the Case Western Reserve University dataset, and 100% on the centrifugal pump bearing fault dataset, with a time of approximately 0.28 s. The results show that this method has the advantages of accuracy, rapidity, and stability of bearing fault diagnosis.

Deep learning-based fault diagnosis usually requires a rich supply of data, but fault samples are scarce in practice, posing a considerable challenge for existing diagnosis approaches to achieve highly accurate fault detection in real applications. This paper proposes an imbalanced fault diagnosis of rotatory machinery that combines time-frequency feature oversampling (TFFO) with a convolutional neural network (CNN). First, the sliding segmentation sampling method is employed to primarily increase the number of fault samples in the form of one-dimensional signals. Immediately after, the signals are converted into two-dimensional time-frequency feature maps by continuous wavelet transform (CWT). Subsequently, the minority samples are expanded again using the synthetic minority oversampling technique (SMOTE) to realize TFFO. After such two-fold data expansion, a balanced data set is obtained and imported to an improved 2dCNN based on the LeNet-5 to implement fault diagnosis. In order to verify the proposed method, two experiments involving single and compound faults are conducted on locomotive wheel-set bearings and a gearbox, resulting in several datasets with different imbalanced degrees and various signal-to-noise ratios. The results demonstrate the advantages of the proposed method in terms of classification accuracy and stability as well as noise robustness in imbalanced fault diagnosis, and the fault classification accuracy is over 97%.

Fault diagnosis of rolling bearings is significant for mechanical equipment operation and maintenance. Presently, the deep convolutional neural network (CNN) is increasingly used for fault diagnosis of rolling bearings, but CNN has challenges with incomplete training and lengthy training times. This paper proposes a residual network combined with the transfer learning (ResNet-TL) based diagnosis method for rolling bearing, which can preprocess the one-dimensional data of vibration signals into image data. Then, the transfer learning theory in parameter transfer is applied to the training of the network model, and the ResNet34 network is pre-trained and re-trained; the image data are selected to be the inputs of the fault diagnosis model. The experimental validation of the rolling bearing fault dataset collected from the practical bench and Case Western Reserve University shows the superiority of the ResNet34-TL model compared with other classification models.

At present, high-speed serial transmission technology is gradually replacing parallel transmission as the mainstream. Due to the influence of power supply noise, inter symbol crosstalk and transmission channel, various jitters will occur in the process of data transmission, which will have a significant impact on the whole system. It is more and more important to improve the jitter tolerance and clock data recovery ability of the receiver of high-speed serial communication system. In order to effectively test the jitter tolerance and clock data recovery of high-speed serial communication system, the serial signal source needs to have the function of controllable jitter injection. After comparing various jitter injection methods, a jitter injection method using phase interpolation to change the edge position of code pattern is introduced in this paper. Through the dynamic reconfiguration function of FPGA, the phase of serders output sampling clock edge is dynamically and periodically changed to realize the jitter control of output data edge, so as to realize the jitter injection of high-speed data. Through this method, the jitter injection of sine wave and square wave with amplitude of 0 ∼ 2ui and frequency of 0 ∼ 12.5mhz is verified on 0.5 ∼ 32gbps serial signal. It can provide controllable jitter signal for testing jitter tolerance and clock data recovery ability of high-speed serial communication system.

To extract the time‐series characteristics of the original bearing signals and predict the remaining useful life (RUL) more effectively, a parallel multichannel recurrent convolutional neural network (PMCRCNN) is proposed for the prediction of RUL. Firstly, the time domain, frequency domain, and time‐frequency domain features are extracted from the original signal. Then, the PMCRCNN model is constructed. The front of the model is the parallel multichannel convolution unit to learn and integrate the global and local features from the time‐series data. The back of the model is the recurrent convolution layer to model the temporal dependence relationship under different degradation features. Normalized life values are used as labels to train the prediction model. Finally, the RUL was predicted by the trained neural network. The proposed method is verified by full life tests of bearing. The comparison with the existing prognostics approaches of convolutional neural network (CNN) and the recurrent convolutional neural network (RCNN) models proves that the proposed method (PMCRCNN) is effective and superior in improving the accuracy of RUL prediction.