With the widespread use of industrial Internet technology in intelligent production lines, the number of task requests generated by smart terminals is growing exponentially. Achieving rapid response to these massive tasks becomes crucial. In this paper we focus on the multi-objective task scheduling problem of intelligent production lines and propose a task scheduling strategy based on task priority. First, we set up a cloud-fog computing architecture for intelligent production lines and built the multi-objective function for task scheduling, which minimizes the service delay and energy consumption of the tasks. In addition, the improved hybrid monarch butterfly optimization and improved ant colony optimization algorithm (HMA) are used to search for the optimal task scheduling scheme. Finally, HMA is evaluated by rigorous simulation experiments, showing that HMA outperformed other algorithms in terms of task completion rate. When the number of nodes exceeds 10, the completion rate of all tasks is greater than 90%, which well meets the real-time requirements of the corresponding tasks in the intelligent production lines. In addition, the algorithm outperforms other algorithms in terms of maximum completion rate and power consumption.

Semantic segmentation of surface defects is essential to ensure product quality in intelligent manufacturing. However, due to the diversity and complexity of industrial scenarios and defects, existing defect semantic segmentation methods still suffer from inconsistent intraclass and indistinguishable interclass segmentation results. To overcome these problems, we propose a new dual-branch surface defect semantic segmentation network, DDSNet. First, we integrate semantic and border information to enrich the feature representation of defects and solve the problem of indistinguishable interclass segmentation results. Next, we introduce a global and local feature fusion (GLF) module based on similarity metrics to guide the network in further refining and highlighting the detail feature on defects to solve the problem of inconsistent intraclass segmentation results. In addition, to enrich the surface defect segmentation datasets, we collect datasets of steel foil surface defects, Ste-Seg, and aluminum block surface defects, Alu-Seg. Experimental results for five datasets of semantic segmentation of defects show that DDSNet outperforms the state-of-the-art methods in terms of mIoU (NEU-Seg: 85.12%, MT-Defect: 76.51%, MSD: 91.82%, Ste-Seg: 90.01%, and Alu-Seg: 84.77%). All our experiments were conducted on a NVIDIA GTX 3060Ti. The dataset and code are available at https://github.com/QinLi-STUDY/DDSNet .

Confronting the challenge of identifying unknown fault types in rolling bearing fault diagnosis, this study introduces a multi-scale bearing fault diagnosis method based on transfer learning. Initially, a multi-scale feature extraction network, MBDCNet, is constructed. This network, by integrating the features of vibration signals at multiple scales, is dedicated to capturing key information within bearing vibration signals. Innovatively, this study replaces traditional convolution with dynamic convolution in MBDCNet, aiming to enhance the model’s flexibility and adaptability. Furthermore, the study implements pre-training and transfer learning strategies to maximally extract latent knowledge from source domain data. By optimizing the loss function and fine-tuning the learning rate, the robustness and generalization ability of the model in the target domain are significantly improved. The proposed method is validated on bearing datasets provided by Case Western Reserve University and Jiangnan University. The experimental results demonstrate high accuracy in most diagnostic tasks, achieving optimal average accuracy on both datasets, thus verifying the stability and robustness of our approach in various diagnostic tasks. This offers a reliable research direction in terms of enhancing the reliability of industrial equipment, especially in the field of bearing fault diagnosis.

Rolling bearing fault diagnosis is of great significance to the safe and reliable operation of manufacturing equipment. In the actual complex environment, the collected bearing signals usually contain a large amount of noises from the resonances of the environment and other components, resulting in the nonlinear characteristics of the collected data. Existing deep-learning-based solutions for bearing fault diagnosis perform poorly in classification performance under noises. To address the above problems, this paper proposes an improved dilated-convolutional-neural network-based bearing fault diagnosis method in noisy environments named MAB-DrNet. First, a basic model called the dilated residual network (DrNet) was designed based on the residual block to enlarge the model’s perceptual field to better capture the features from bearing fault signals. Then, a max-average block (MAB) module was designed to improve the feature extraction capability of the model. In addition, the global residual block (GRB) module was introduced into MAB-DrNet to further improve the performance of the proposed model, enabling the model to better handle the global information of the input data and improve the classification accuracy of the model in noisy environments. Finally, the proposed method was tested on the CWRU dataset, and the results showed that the proposed method had good noise immunity; the accuracy was 95.57% when adding Gaussian white noises with a signal-to-noise ratio of −6 dB. The proposed method was also compared with existing advanced methods to further prove its high accuracy.

In recent years, self-supervised monocular depth estimation has gained popularity among researchers because it uses only a single camera at a much lower cost than the direct use of laser sensors to acquire depth. Although monocular self-supervised methods can obtain dense depths, the estimation accuracy needs to be further improved for better applications in scenarios such as autonomous driving and robot perception. In this paper, we innovatively combine soft attention and hard attention with two new ideas to improve self-supervised monocular depth estimation: (1) a soft attention module and (2) a hard attention strategy. We integrate the soft attention module in the model architecture to enhance feature extraction in both spatial and channel dimensions, adding only a small number of parameters. Unlike traditional fusion approaches, we use the hard attention strategy to enhance the fusion of generated multi-scale depth predictions. Further experiments demonstrate that our method can achieve the best self-supervised performance both on the standard KITTI benchmark and the Make3D dataset.