The seam tracking operation is essential for extracting welding seam characteristics which can instruct the motion of a welding robot along the welding seam path. The chief tasks for seam tracking would be divided into three partitions. First, starting and ending points detection, then, weld edge detection, followed by joint width measurement, and, lastly, welding path position determination with respect to welding robot co-ordinate frame. A novel seam tracking technique with a four-step method is introduced. A laser sensor is used to scan grooves to obtain profile data, and the data are processed by a filtering algorithm to smooth the noise. The second derivative algorithm is proposed to initially position the feature points, and then linear fitting is performed to achieve precise positioning. The groove data are transformed into the robot’s welding path through sensor pose calibration, which could realize real-time seam tracking. Experimental demonstration was carried out to verify the tracking effect of both straight and curved welding seams. Results show that the average deviations in the X direction are about 0.628 mm and 0.736 mm during the initial positioning of feature points. After precise positioning, the average deviations are reduced to 0.387 mm and 0.429 mm. These promising results show that the tracking errors are decreased by up to 38.38% and 41.71%, respectively. Moreover, the average deviations in both X and Z direction of both straight and curved welding seams are no more than 0.5 mm, after precise positioning. Therefore, the proposed seam tracking method with four steps is feasible and effective, and provides a reference for future seam tracking research.

The welding seam tracking operation ensures that the welding torch of the welding robot can go with the welding seam during the whole symmetrical robotic welding procession. To achieve three-dimensional complex welding seams tracking, a four-step welding seam tracking system is suggested based on segmented scanning, combined filtering, feature-point extraction, and welding path planning. From using the laser sensor installed at the end of welding robot, the welding seam data was continuously collected in multiple segments by segmented scanning. For the purpose of improving seam tracking accuracy, a combined filtering technique was used to correct the data to reduce the effects of burrs, data distortion, and noise on the surface of the weldment. Then, the feature points were collected so that the coordinate system will be calibrated to identify the welding points. Finally, a spatial welding path was obtained by welding path planning. Experimental investigations of the two-dimensional (2D) symmetrical S-shaped and three-dimensional (3D) curved welding seams were conducted. The obtained results demonstrate the proposed method can form a complete welding path. The average errors of the two weldments are about 0.296 mm and 0.292 mm, respectively. This shows that the proposed tracking method is effective and can provide a reference for the research of high-precision seam tracking and automatic welding.

Subway vehicle roofs must be inspected when entering and exiting the depot to ensure safe subway vehicle operations. This paper presents an improved method for detecting foreign objects on subway vehicle roofs based on the YOLOv7 algorithm. First, we capture images of foreign objects using a line-scan camera at the depot entrance and exit, creating a dataset of foreign roof objects. Subsequently, we address the shortcomings of the YOLOv7 algorithm by introducing the Ghost module, an improved weighted bidirectional feature pyramid network (WBiFPN), and the Wise intersection over union (WIoU) bounding-box regression loss function. These enhancements are incorporated to build the subway vehicle roof foreign object detection model based on the improved YOLOv7, which we refer to as YOLOv7-GBW. The experimental results demonstrate the practicality and usability of the proposed method. The analysis of the experimental results indicates that the YOLOv7-GBW algorithm achieves a detection accuracy of 90.29% at a speed of 54.3 frames per second (fps) with a parameter count of 15.51 million. The improved YOLOv7 model outperforms mainstream detection algorithms in terms of detection accuracy, speed, and parameter count. This finding confirms that the proposed method meets the requirements for detecting foreign objects on subway vehicle roofs.

In this paper, the asymptotic consensus control of multi-agent systems with general linear agent dynamics is investigated. A neighbor-based adaptive event-triggering strategy with a dynamic triggering threshold is proposed, which leads to a fully distributed control of the multi-agent system, depending only on the states of the neighboring agents at triggering moments. By using the Lyapunov method, we prove that the states of the agents converge asymptotically. In addition, the proposed event-triggering strategy is proven to exclude Zeno behavior. The numerical simulation results illustrate that the agent states achieve consensus in sense of asymptotic convergence. Furthermore, the proposed strategy is shown to be scalable in case of variable agent numbers.

Calligraphy works have high artistic value, but there is the rampant problem of forgery. Indeed, the authentication of traditional calligraphy heavily relies on calligraphers’ subjective judgment. Therefore, spurred by the recent development of neural networks, this paper proposes a method for authenticating calligraphy works based on an improved EfficientNet network. Specifically, the developed method utilizes the character box algorithm to efficiently extract individual calligraphy characters, which are then augmented and used as the training set for the model. The training process employs CBAM and Self-Attention modules to enhance the attention mechanism of the EfficientNet network. The trained network model is used to judge the calligraphy works’ similarity; tested on authentic works, imitated works, and works from other calligraphers; and compared with other networks. The experimental results demonstrate that the proposed method effectively achieves the authentication of calligraphy works, and the improved CBAM-EfficientNet network and SA-EfficientNet network achieve better authentication performance.

Phase-sensitive optical time-domain reflectometry (φ-OTDR) is capable of detecting acoustic emission induced small strain with high sensitivity. However, there is a tradeoff between sensitivity, bandwidth and detection range, which makes the detection of a transient weak signal challenging. In this work, we focus on transient weak signal detection using φ-OTDR. To achieve this aim, we propose a cascaded statistics-based signal-processing framework in a φ-OTDR system to fetch the transient weak signal from a noisy background. Our framework is based on two key elements, including an estimator that is derived based on the probability characteristic of the Rayleigh backscattered light, and a time-frequency feature extraction process that maps the signal to the time-frequency domain. Using our statistics-based signal processing φ-OTDR, we demonstrate experimentally the detections of, firstly a weak persistent signal with a magnitude down to 4 nϵ and a frequency up to 40 kHz, and then a weak transient acoustic tone-burst signal. Our proposed scheme is promising for φ-OTDR performance improvement particularly in weak signal detections, and it will find new applications in the future systems.