Search

Underwater cracks are difficult to detect and observe, posing a major challenge to crack detection. Currently, deep learning-based underwater crack detection methods rely heavily on a large number of crack images that are difficult to collect due to their complex and hazardous underwater environments. This study proposes a new underwater image-processing method that combines a novel white balance method and bilateral filtering denoising method to transform underwater crack images into high-quality above-water images with original crack features. Crack detection is then performed based on an improved YOLOv9-OREPA model. Through experiments, it is found that the new image-processing method proposed in this study significantly improves the evaluation indicators of new images, compared with other methods. The improved YOLOv9-OREPA also exhibits a significantly improved performance. The experimental results demonstrate that the method proposed in this study is a new approach suitable for detecting underwater cracks in dams and achieves the goal of transforming underwater images into above-water images.

Gas turbines are widely used as important equipment for electricity generation on islands and offshore platforms. During the operation of a gas turbine, the flame shape in the combustion chamber undergoes variations in response to changes in parameters such as gas turbine load, fuel distribution, and burner structure. These alterations in flame shape exert influence on combustion instability, emissions, and load characteristics. This study explores the variations in flame transition, emissions, and operating parameters among three distinct center stage structures: namely, the non-premix center stage (NPCS), premix center stage (PCS), and enhanced premix center stage (PCSE). The investigation is conducted using a heavy-duty gas turbine hybrid burner on a full temperature, full pressure, and full-size single burner experimental bench. Simultaneously, a multi-parameter numerical simulation regarding the influence of the central fuel split on flame shape analysis was conducted using the PCS burner under the design point for a more in-depth understanding of the mechanisms and for influencing factors associated with flame transition. The findings indicate that variations in flame transition loads among different central stage structures: for the NPCS burner, the transition occurs between 45% and 50% load; for the PCS burners, it takes place between 60% and 65% load; for the PCSE burners, it shifts between 55% and 60% load. Additionally, a reduction in NOx emissions is observed during the flame transition process. Furthermore, it was found that decreasing the central stage fuel results in a decline in flame angle for the same burner structure. As the central stage fuel diminishes to a specific value, the flame shape undergoes a sudden change. Further reduction in central stage fuel does not significantly affect the flame shape and temperature distribution.

In this study, large eddy simulation (LES) was used to investigate the dynamic characteristics of diffusion flames in a swirl combustion chamber at an oxygen content of 11–23 wt% and temperature of 770 K. The proper orthogonal decomposition (POD) method was employed to obtain flame dynamic modes. The results indicate that oxygen content has a significant impact on the downstream flow and flame combustion characteristics of the swirl combustion chamber. With oxygen content increasing, the size of the recirculation zone is reduced, and the flame field fluctuations are intensified. The pressure and heat release fluctuations under different oxygen contents were analyzed using frequency spectrum analysis. Finally, the flame modes were analyzed using the POD method, and it was found that the coherent structures are asymmetric relative to the local coordinate system. At an oxygen content of 11 wt%, they exhibit larger coherent structures, while at an oxygen content of 23 wt%, they exhibit numerous turbulent structures.

Insulator defect detection of transmission line insulators is an important task for unmanned aerial vehicle (UAV) inspection, which is of immense importance in ensuring the stable operation of transmission lines. Transmission line insulators exist in complex weather scenarios, with small and inconsistent shapes. These insulators under various weather conditions could result in low-quality images captured, limited data numbers, and imbalanced sample problems. Traditional detection methods often struggle to accurately identify defect information, resulting in missed or false detections in real-world scenarios. In this paper, we propose a weather domain synthesis network for extracting cross-modality discriminative information on multi-domain insulator defect detection and classification tasks. Firstly, we design a novel weather domain synthesis (WDSt) module to convert various weather-conditioned insulator images to the uniform weather domain to decrease the existing domain gap. To further improve the detection performance, we leverage the attention mechanism to construct the Cross-modality Information Attention YOLO (CIA-YOLO) model to improve the detection capability for insulator defects. Here, we fuse both shallow and deep feature maps by adding the extra object detection layer, increasing the accuracy for detecting small targets. The experimental results prove the proposed Cross-modality Information Attention YOLO with the weather domain synthesis algorithm can achieve superior performance in multi-domain insulator datasets (MD-Insulator). Moreover, the proposed algorithm also gives a new perspective for decreasing the multi-domain insulator modality gap with weather-domain transfer, which can inspire more researchers to focus on the field.

Regular inspection of the insulator operating status is essential to ensure the safe and stable operation of the power system. Unmanned aerial vehicle (UAV) inspection has played an important role in transmission line inspection, replacing former manual inspection. With the development of deep learning technologies, deep learning-based insulator defect detection methods have drawn more and more attention and gained great improvement. However, former insulator defect detection methods mostly focus on designing complex refined network architecture, which will increase inference complexity in real applications. In this paper, we propose a novel efficient cross-modality insulator augmentation algorithm for multi-domain insulator defect detection to mimic real complex scenarios. It also alleviates the overfitting problem without adding the inference resources. The high-resolution insulator cross-modality translation (HICT) module is designed to generate multi-modality insulator images with rich texture information to eliminate the adverse effects of existing modality discrepancy. We propose the multi-domain insulator multi-scale spatial augmentation (MMA) module to simultaneously augment multi-domain insulator images with different spatial scales and leverage these fused images and location information to help the target model locate defects with various scales more accurately. Experimental results prove that the proposed cross-modality insulator augmentation algorithm can achieve superior performance in public UPID and SFID insulator defect datasets. Moreover, the proposed algorithm also gives a new perspective for improving insulator defect detection precision without adding inference resources, which is of great significance for advancing the detection of transmission lines.

Different types of surface defects will occur during the production of strip steel. To ensure production quality, it is essential to classify these defects. Our research indicates that two main problems exist in the existing strip steel surface defect classification methods: (1) they cannot solve the problem of unbalanced data using few-shot in reality, (2) they cannot meet the requirement of online real-time classification. To solve the aforementioned problems, a relational knowledge distillation self-adaptive residual shrinkage network (RKD-SARSN) is presented in this work. First, the data enhancement strategy of Cycle GAN defective sample migration is designed. Second, the self-adaptive residual shrinkage network (SARSN) is intended as the backbone network for feature extraction. An adaptive loss function based on accuracy and geometric mean (Gmean) is proposed to solve the problem of unbalanced samples. Finally, a relational knowledge distillation model (RKD) is proposed, and the functions of GUI operation interface encapsulation are designed by combining image processing technology. SARSN is used as a teacher model, its generalization performance is transferred to the lightweight network ResNet34, and it is conveniently deployed as a student model. The results show that the proposed method can improve the deployment efficiency of the model and ensure the real-time performance of the classification algorithms. It is superior to other mainstream algorithms for fine-grained images with unbalanced data classification.

Transmission line fittings have been exposed to complex environments for a long time. Due to the interference of haze and other environmental factors, it is often difficult for the camera to obtain high quality on-site images, and the traditional image processing technology and convolution neural networks find it difficult to effectively deal with the dense detection task of small targets with occlusion interference. Therefore, an image processing method based on an improved dark channel defogging algorithm, the fusion channel spatial attention mechanism, Vision Transformer, and the GhostNet model compression method is proposed in this paper. Based on the global receptive field of the saliency region capture and enhancement model, a small target detection network Double-attention YOLO for complex environments is constructed. The experimental results show that embedding a multi-head self-attention component into a convolutional neural network can help the model to better interpret the multi-scale global semantic information of images. In this way, the model learns more easily the distinguishable features in the image representation. Embedding an attention mechanism module can make the neural network pay more attention to the salient region of image. Dual attention fusion can balance the global and local characteristics of the model, to improve the performance of model detection.

In the production and manufacturing industry, factors such as rolling equipment and processes may cause various defects on the surface of the steel plate, which greatly affect the performance and subsequent machining accuracy. Therefore, it is essential to identify defects in time and improve the quality of production. An intelligent detection system was constructed, and some improved algorithms such as dataset enhancement, annotation and lightweight convolution neural network are proposed in this paper. (1) Compared with the original YOLOV5 (You Only Look Once), the precision is 0.924, and the inference time is 29.8 ms, which is 13.8 ms faster than the original model. Additionally, the parameters and calculations are also far less than YOLOV5. (2) Ablation experiments were designed to verify the effectiveness of the proposed algorithms. The overall accuracy was improved by 0.062; meanwhile, the inference time was reduced by 21.7 ms. (3) Compared with other detection models, although RetinaNet has the highest accuracy, it takes the longest time. The overall performance of the proposed method is better than other methods. This research can better meet the requirements of the industry for precision and real-time performance. It can also provide ideas for industrial detection and lay the foundation for industrial automation.

In view of the settlement problem of transmission tower foundation, the vibration characteristics of transmission towers under wind force are measured experimentally. In this paper, the 110 kV cat head transmission tower of Xi’an Polytechnic University is measured and analyzed. Firstly, the acceleration sensor and meteorological sensor are installed on the tower to collect the vibration response and environment parameters of the tower in real time. Then, an experiment platform is built to simulate the tower settlement, and the vibration response of the tower after settlement is measured in time. Finally, the low-order modal frequencies of the transmission tower before and after settlement under wind force load are extracted by stochastic subspace identification (SSI), and the relationship between modal frequencies of different modes is analyzed via temperature correction. By comparison and analysis, it is obvious that the X-direction modal frequencies before and after settlement under natural wind load are changed, and the change rate increases with the increase of settlement displacement, which can be used as effective evidence for judging the settlement of transmission tower foundation.

The capacitive method is considered to be a suitable icing-detection technology, but the lack of fundamental parameters restricts the development of icing-detection sensors. In this paper, an artificial icing laboratory, a capacitive sensor, and some simulation conductors have been designed for obtaining the artificial icing samples. Subsequently, the same characteristic values of artificial icing have been measured by an LCR device, under a selected frequency. This research found that the value of the icing dielectric constant closely correlated with its density, internal sublayer, and the test temperature. Finally, a fitting formula has been presented for calculating the relative dielectric constant, which may provide some important reference value for the design of icing-detection sensors.

Transmission lines are affected by Aeolian vibration, which causes strands to break and eventually causes an entire line to break. In this paper, a method for monitoring strand breaking based on modal identification is proposed. First, the natural frequency variation of a conductor caused by strand breakage is analyzed, and a modal experiment of the LGJ-95/15 conductor is conducted. The measurement results show that the natural frequencies of the conductor decrease with an increasing number of broken strands. Next, a monitoring system incorporating a fiber Bragg grating (FBG)-based accelerometer is designed in detail. The FBG sensor is mounted on the conductor to measure the vibration signal. A wind speed sensor is used to measure the wind speed signal and is installed on the tower. An analyzer is also installed on the tower to calculate the natural frequencies, and the data are sent to the monitoring center via 3G. Finally, a monitoring system is tested on a 110 kV experimental transmission line, and the short-time Fourier transform (STFT) method and stochastic subspace identification (SSI) method are used to identify the natural frequencies of the conductor vibration. The experimental results show that SSI analysis provides a higher precision than does STFT and can extract the natural frequency under various wind speeds as an effective basis for discriminating between broken strands.

Conductor galloping may cause flashovers and even tower collapses. The available conductor galloping monitoring methods often employ acceleration sensors to measure the conductor translations without considering the conductor twist. In this paper, a new sensor for monitoring conductor galloping of transmission lines based on an inertial measurement unit and wireless communication is proposed. An inertial measurement unit is used for collecting the accelerations and angular rates of a conductor, which are further transformed into the corresponding geographic coordinate frame using a quaternion transformation to reconstruct the galloping of the conductor. Both the hardware design and the software design are described in details. The corresponding test platforms are established, and the experiments show the feasibility and accuracy of the proposed monitoring sensor. The field operation of the proposed sensor in a conductor spanning 734 m also shows its effectiveness.