A complete error calibration model with 12 independent parameters is established by analyzing the three-axis magnetometer error mechanism. The said model conforms to an ellipsoid restriction, the parameters of the ellipsoid equation are estimated, and the ellipsoid coefficient matrix is derived. However, the calibration matrix cannot be determined completely, as there are fewer ellipsoid parameters than calibration model parameters. Mathematically, the calibration matrix derived from the ellipsoid coefficient matrix by a different matrix decomposition method is not unique, and there exists an unknown rotation matrix R between them. This paper puts forward a constant intersection angle method (angles between the geomagnetic field and gravitational field are fixed) to estimate R. The Tikhonov method is adopted to solve the problem that rounding errors or other errors may seriously affect the calculation results of R when the condition number of the matrix is very large. The geomagnetic field vector and heading error are further corrected by R. The constant intersection angle method is convenient and practical, as it is free from any additional calibration procedure or coordinate transformation. In addition, the simulation experiment indicates that the heading error declines from ±1° calibrated by classical ellipsoid fitting to ±0.2° calibrated by a constant intersection angle method, and the signal-to-noise ratio is 50 dB. The actual experiment exhibits that the heading error is further corrected from ±0.8° calibrated by the classical ellipsoid fitting to ±0.3° calibrated by a constant intersection angle method.

Due to the large-scale changes of different forms of traffic signs and the rapid speed of vehicles, the detection accuracy and real-time performance of general object detectors are greatly challenged, especially the detection accuracy of small objects. In order to solve this problem, a multi-scale traffic sign detection model CR-YOLOv8 is proposed based on the latest YOLOv8. In the feature extraction stage, the attention module is introduced to enhance the channel and spatial features, so that the network can learn the key information of the small objects more easily. The RFB module is introduced in the feature fusion stage, which improves the feature diversity with less computational overhead and improves the network’s ability to detect multi-scale objects. By improving the loss function to enable the model to effectively balance multi-scale objectives during training, the model generalization ability is improved.The experimental results on TT100k dataset show that compared with the baseline network, the average detection accuracy of the improved method is increased by 2.3 %, and the detection accuracy of small objects is increased by 1.6 %, which effectively reduces the detection accuracy gap among different scales.

Industrial product quality inspection, a crucial procedure in industrial production, is crucial in assuring product yield. Product safety and quality inspections on industrial assembly lines are predominantly manual, and there is currently a dearth of safe and dependable inspection techniques. An improved surface defect detection approach based on YOLOv5 is proposed for the problem of surface flaws in industrial components in order to improve the quality detection effect of industrial production parts. To improve the effect of dense object detection, the image features are extracted by the convolutional network and enhanced by coordinate attention. BiFPN is utilized to fuse multi-scale features in order to lower the rate of missed detection and false detection for small target samples. The detectors from the Transformer structure are added to the complex problem of fine-grained detection to improve the predictability of challenging occurrences. According to the experimental findings, on the dataset for industrial parts defects, the proposed network increases the recall of the original algorithm in abnormal classes by 5.3%, reaching 91.6%. Its inference speed can approach 95FPS, indicating an improved real-time detection performance.

Ensuring the promptly removal of foreign objects from transmission lines is crucial for electricity safety. However, the existing object detection algorithms exhibit low precision and recall due to factors such as uncertainty in the type of foreign objects, imbalance of positive and negative samples, and the complexity of aerial photography backgrounds. Therefore, in this paper, an algorithm called DF-YOLO (Deformable Faster-You Only Look Once) for transmission line foreign object detection is proposed to resolve these problems. The algorithm is based on YOLOv7-Tiny and tailored to the dataset’s characteristics to achieve high precision along with excellent recall. The Focal-DIoU loss function is utilized to balance positive and negative sample proportions during training. Additionally, the algorithm incorporates the deformable convolution (DCN) module and the SimAM attention mechanism to enhance model performance, particularly in terms of foreign object recall and detection accuracy. Moreover, we optimized the network inference speed with the improved SPPCSPC_S-F module. Experimental results demonstrate that the improved DF-YOLO network achieves a 2.04% increase in mAP@.5 compared to the original YOLOv7-Tiny network. The recall rate also improves from 89% to 91.51%. Additionally, the inference speed of the network rises from 130 to 140 FPS, which enhances detection effectiveness and reduces the frequency of transmission line leaks triggered by foreign object incursion.

Oil impregnated paper bushing is the key equipment connecting a transformer and a power grid. Insulation deterioration may cause partial discharge, which poses a great threat to the safe operation of power systems. In order to realize the online diagnosis for partial discharge and automatic identification of insulation defects of transformer bushings, an ultra-micro-convolutional neural network with only more than 3000 parameters is designed, which adaptively extracts partial discharge characteristics based on small samples, so as to judge the defect category and the reasons. The accuracy rate can reach 97.1%, the computational complexity is lower, the real-time performance is stronger, and it can be easily deployed on various embedded platforms.

Optimizing travel routes in urban transportation networks is essential for enhancing traffic efficiency in major cities. This study focuses on optimizing the combined subway and taxi travel routes from Beijing Union University to Beijing South Railway Station, a critical route for students and staff in Beijing. To address this, we propose three genetic algorithms: the Standard Genetic Algorithm (SGA), the Multipoint Crossover and Elitist Selection Genetic Algorithm (MPEGA), and the Improved Dynamic Crossover and Mutation Rate Genetic Algorithm (IDCMGA). Experimental results indicate that MPEGA reduces the mean travel cost by 15.21%, the variance by 81.72%, and the standard deviation by 57.25% compared to SGA. Additionally, IDCMGA reduces the average by 1.76%, the variance by 63.16%, and the standard deviation by 39.30% compared to MPEGA. The improved IDCMGA algorithm demonstrates significant advantages over the other two algorithms in terms of global optimization capability, convergence speed, and stability, and is more adept at adapting to new traffic conditions to identify the optimal route. Optimizing this route not only reduces commuting time and costs but also alleviates traffic congestion, thereby enhancing the overall efficiency of the urban transportation system.