Fault diagnosis is one of the important applications of edge computing in the Industrial Internet of Things (IIoT). To address the issue that traditional fault diagnosis methods often struggle to effectively extract fault features, this paper proposes a novel rolling bearing fault diagnosis method that integrates Gramian Angular Field (GAF), Convolutional Neural Network (CNN), and Vision Transformer (ViT). First, GAF is used to convert one-dimensional vibration signals from sensors into two-dimensional images, effectively retaining the fault features of the vibration signal. Then, the CNN branch is used to extract the local features of the image, which are combined with the global features extracted by the ViT branch to diagnose the bearing fault. The effectiveness of this method is validated with two datasets. Experimental results show that the proposed method achieves average accuracies of 99.79% and 99.63% on the CWRU and XJTU-SY rolling bearing fault datasets, respectively. Compared with several widely used fault diagnosis methods, the proposed method achieves higher accuracy for different fault classifications, providing reliable technical support for performing complex fault diagnosis on edge devices.

The job shop scheduling problem (JSSP) is a classical NP-hard combinatorial optimization challenge that plays a crucial role in manufacturing systems. Deep reinforcement learning has shown great potential in solving this problem. However, it still has challenges in reward function design and state feature representation, which makes it suffer from slow policy convergence and low learning efficiency in complex production environments. Therefore, a human feedback-based large language model-assisted deep reinforcement learning (HFLLMDRL) framework is proposed to solve this problem, in which few-shot prompt engineering by human feedback is utilized to assist in designing instructive reward functions and guiding policy convergence. Additionally, a self-adaptation symbolic visualization Kolmogorov–Arnold Network (KAN) is integrated as the policy network in DRL to enhance state feature representation, thereby improving learning efficiency. Experimental results demonstrate that the proposed framework significantly boosts both learning performance and policy convergence, presenting a novel approach to the JSSP.

Having great impacts on machining precision, thermal error is one of the main error sources for heavy-duty computer numerical control machine tools. Thermal error compensation using prediction models with temperature field is an effective way to improve machining precision of computer numerical control machine tools. The accuracy and robustness of thermal error prediction models depend considerably on the selection of temperature measurement points. Too many temperature measurement points will increase the complexity of thermal error prediction models and incur over-fitting problems. To improve the complexity and performances of prediction models, a selection method of key temperature measurement points based on density peaks clustering is presented in this article. This method is able to cluster massive temperature measurement points quickly and select the key temperature measurement point which characterizes the common feature of each cluster automatically. It is verified on the ZK5540A heavy-duty computer numerical control gantry drilling machine tool. Six key temperature measurement points are selected from the total 222 temperature measurement points with this method. Then, the back propagation neural network optimized by genetic algorithm thermal error model with the six key temperature measurement points is built and the accuracy and robustness of the model are analyzed. The results show that the model has high prediction accuracy and strong robustness.

In urban logistics distribution, vehicle carbon emissions during the distribution process significantly contribute to environmental pollution. While developing green logistics is critical for the sustainable growth of the logistics industry, existing studies often overlook the potential benefits of depot sharing among enterprises. By enabling depots belonging to different enterprises to be shared, it would shorten the distance traveled by vehicles returning to depots and reduce carbon emissions. And it would also reduce the number of depots being built. Therefore, a green vehicle routing problem with depot sharing is presented in the paper. To solve this problem, an improved adaptive large neighborhood search algorithm is presented, in which the Split strategy and two new operators are proposed to enhance solution quality and computational efficiency. Extensive numerical experiments are conducted on instances of varying scales to evaluate this algorithm, and also demonstrate its effectiveness and efficiency. Furthermore, the experimental results demonstrate that depot sharing significantly reduces carbon emissions, achieving an average optimization rate of 10.1% across all instances compared to returning to the original depot.

With the rapid development of e-commerce, the importance of logistics distribution is becoming increasingly prominent. In particular, the last-mile delivery is particularly important because it serves customers directly. Improving customer satisfaction is one of the important factors to ensure the quality of service in delivery and also an important guarantee for improving the market competitiveness of logistics enterprises. In the process of last-mile delivery, flexible delivery locations and variable delivery times are effective means to improve customer satisfaction. Therefore, this paper introduces a Vehicle Routing Problem with flexible time windows and delivery locations, considering customer satisfaction (VRP-CS), which considers customer satisfaction by using prospect theory from two aspects: the flexibility of delivery time and delivery locations. This VRP-CS is formally modeled as a bi-objective optimization problem, which is an NP-hard problem. To solve this problem, a Multi-Strategy Adaptive Large Neighborhood Search (MSALNS) method is proposed. Operators guided by strategies such as backtracking and correlation are introduced to create different neighborhoods for ALNS, thereby enriching search diversity. In addition, an acceptance criterion inspired by simulated annealing is designed to balance exploration and exploitation, helping the algorithm avoid being trapped in local optima. Extensive numerical experiments on generated benchmark instances demonstrate the effectiveness of the VRP-CS model and the efficiency of the proposed MSALNS algorithm. The experiment results on the generated benchmark instances show that the total cost of the VRP-CS is reduced by an average of 14.22% when optional delivery locations are utilized compared to scenarios with single delivery locations.

Defect detection on Printed Circuit Boards (PCBs) constitutes a pivotal component of the quality control system in electronics manufacturing. However, owing to the intricate circuitry structures on PCB surfaces and the characteristics of defects—specifically their minute scale, irregular morphology, and susceptibility to background texture interference—existing generic deep learning models frequently fail to achieve an optimal equilibrium between detection accuracy and inference speed. To address these challenges, this study proposes MDEB-YOLO, a lightweight real-time detection network tailored for PCB micro-defects. First, to enhance the model’s perceptual capability regarding subtle geometric variations along conductive line edges, we designed the Efficient Multi-scale Deformable Attention (EMDA) module within the backbone network. By integrating parallel cross-spatial channel learning with deformable offset networks, this module achieves adaptive extraction of irregular concave–convex defect features while effectively suppressing background noise. Second, to mitigate feature loss of micro-defects during multi-scale transformations, a Bidirectional Residual Multi-scale Feature Pyramid Network (BRM-FPN) is proposed. Utilizing bidirectional weighted paths and residual attention mechanisms, this network facilitates the efficient fusion of multi-view features, significantly enhancing the representation of small targets. Finally, the detection head is reconstructed based on grouped convolution strategies to design the Lightweight Grouped Convolution Head (LGC-Head), which substantially reduces parameter volume and computational complexity while maintaining feature discriminability. The validation results on the PKU-Market-PCB dataset demonstrate that MDEB-YOLO achieves a mean Average Precision (mAP) of 95.9%, an inference speed of 80.6 FPS, and a parameter count of merely 7.11 M. Compared to baseline models, the mAP is improved by 1.5%, while inference speed and parameter efficiency are optimized by 26.5% and 24.5%, respectively; notably, detection accuracy for challenging mouse bite and spur defects increased by 3.7% and 4.0%, respectively. The experimental results confirm that the proposed method outperforms state-of-the-art approaches in both detection accuracy and real-time performance, possessing significant value for industrial applications.