In this paper, we construct a one-dimensional convolutional neural network (1DCNN), which directly takes as the input the vibration signal in the mechanical operation process. It can realize intelligent mechanical fault diagnosis and ensure the authenticity of signal samples. Moreover, due to the excellent interpretability of the 1DCNN, we can explain the feature extraction mechanism of convolution and the synergistic work ability of the convolution kernel by analyzing convolution kernels and their output results in the time-domain, frequency-domain. What’s more, we propose a novel network parameter-optimization method by matching the features of the convolution kernel with those of the original signal. A large number of experiments proved that, this optimization method improve the diagnostic accuracy and the operational efficiency greatly.

Traffic sign detection systems provide important road control information for unmanned driving systems or auxiliary driving. In this paper, the Faster region with a convolutional neural network (R-CNN) for traffic sign detection in real traffic situations has been systematically improved. First, a first step region proposal algorithm based on simplified Gabor wavelets (SGWs) and maximally stable extremal regions (MSERs) is proposed. In this way, the region proposal a priori information is obtained and will be used for improving the Faster R-CNN. This part of our method is named as the highly possible regions proposal network (HP-RPN). Second, in order to solve the problem that the Faster R-CNN cannot effectively detect small targets, a method that combines the features of the third, fourth, and fifth layers of VGG16 to enrich the features of small targets is proposed. Third, the secondary region of interest method to enhance the feature of detection objects and improve the classification capability of the Faster R-CNN is proposed. Finally, a method of merging the German traffic sign detection benchmark (GTSDB) and Chinese traffic sign dataset (CTSD) databases into one larger database to increase the number of database samples is proposed. Experimental results show that our method improves the detection performance, especially for small targets.

This paper constructs a novel network structure (SVD-1DCNN) based on singular value decomposition (SVD) and one-dimensional convolutional neural network (1DCNN), which takes the original signal as input to realize intelligent diagnosis of bearing faults. The output of the first convolution layer was also analyzed from the perspectives of time domain and time-frequency domain in the simulation experiment. Through qualitative analysis and quantitative analysis, it was found that the convolution kernel not only extracted the classification features of signals but also gradually highlighted the learned features in the network training process. Moreover, applying this network in fault diagnosis of bearing date provided by the Case Western Reserve University (CWRU) Bearing Data Center, it was found that the convolution kernel could also achieve the above operation. The novel network of this paper achieved a good classification effect on both the simulated signals and the measured signals.

Effective intelligent fault diagnosis of bearings is important for improving safety and reliability of machine. Benefiting from the training advantages, deep learning method can automatically and adaptively learn more abstract and high-level features without much priori knowledge. To realize representative features mining and automatic recognition of bearing health condition, a diagnostic model of stacked sparse denoising autoencoder (SSDAE) which combines sparse autoencoder (SAE) and denoising autoencoder (DAE) is proposed in this paper. The sparse criterion in SAE, corrupting operation in DAE and reasonable designing of the stack order of autoencoders help to mine essential information of the input and improve fault pattern classification robustness. In order to provide better input features for the constructed network, the raw non-stationary and nonlinear vibration signals are processed with ensemble empirical mode decomposition (EEMD) and multiscale permutation entropy (MPE). MPE features which are extracted based on both the selected characteristic frequency-related intrinsic mode function components (IMFs) and the raw signal, are used as low-level feature for the input of the proposed diagnostic model for health condition recognition and classification. Two experiments based on the Case Western Reserve University (CWRU) dataset and the measurement dataset from laboratory were conducted, and results demonstrate the effectiveness of the proposed method and highlight its excellent performance relative to existing methods.

The conventional pooling method for processing one-dimensional vibration signals may lead to certain issues, such as weakening and loss of feature information. The present study proposes the cubic spline interpolation pooling method. The method is appropriate for processing one-dimensional signals. The proposed method can transform the pooling problem into a linear fitting problem, use the cubic spline interpolation method with outstanding fitting effects, and calculate the fitting function of the input signals. Moreover, the values of the interpolation points are sequentially taken as the feature value output. Furthermore, the network using the conventional pooling method and the pooling network model proposed in the present study are compared, tested, and analyzed on the constructed simulation signals and the measured bearing dataset. It is concluded that the proposed pooling method can reduce the data dimension while improving the network feature extraction capability and is more appropriate for pooling one-dimensional signals.

Maritime remote sensing ship detection has long been plagued by two major issues: the failure of geometric priors due to the extreme length-to-width ratio of ships; and the sharp drop in edge signal-to-noise ratio caused by the overlapping chromaticity domain between ships and seawater, which leads to unsatisfactory accuracy of existing detectors in such scenarios. Therefore, this paper proposes an optical remote sensing ship detection model combining channel shuffling and bilinear interpolation, named CSBI-YOLO. The core innovations include three aspects: First, a group shuffling feature enhancement module is designed, embedding parallel group bottlenecks and channel shuffling mechanisms into the interface between the YOLOv8 backbone and neck to achieve multi-scale semantic information coupling with a small number of parameters. Second, an edge-gated upsampling unit is constructed, using separable Sobel magnitude as structural prior and a learnable gating mechanism to suppress low-contrast noise on the sea surface. Third, an R-IoU-Focal loss function is proposed, introducing logarithmic curvature penalty and adaptive weights to achieve joint optimization in three dimensions: location, shape, and scale. Dual validation was conducted on the self-built SlewSea-RS dataset and the public DOTA-ship dataset. The results show that on the SlewSea-RS dataset, the mAP₅₀ and mAP_50–95 values of the CSBI-YOLO model increased by 6% and 5.4%, respectively. On the DOTA-ship dataset, comparisons with various models demonstrate that the proposed model outperforms others, proving the excellent performance of the CSBI-YOLO model in detecting maritime ship targets.