What are the dampers in the transmission line?

Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ( https://creativecommons.org/licenses/by/4.0/ ).

huaneng Product Page

The vibration dampers can eliminate the galloping phenomenon of transmission lines caused by the wind. The detection of vibration dampers based on visual technology is an important issue. Current CNN-based methods struggle to meet the requirements of real-time detection. Therefore, the current vibration damper detection work has mainly been carried out manually. In view of the above situation, we propose a vibration damper detection-image generation model called DamperGAN based on multi-granularity Conditional Generative Adversarial Nets. DamperGAN first generates a low-resolution detection result image based on a coarse-grained module, then uses Monte Carlo search to mine the latent information in the low-resolution image, and finally injects this information into a fine-grained module through an attention mechanism to output high-resolution images and penalize poor intermediate information. At the same time, we propose a multi-level discriminator based on the multi-task learning mechanism to improve the discriminator&#;s discriminative ability and promote the generator to output better images. Finally, experiments on the self-built DamperGenSet dataset show that the images generated by our model are superior to the current mainstream baselines in both resolution and quality.

1. Introduction

The galloping phenomenon is prone to occur when high-voltage transmission lines are subjected to wind forces. Long-term vibration leads to metal fatigue damage at the suspension, which leads to serious accidents such as wire breakage and tower collapse. The use of vibration dampers on high-voltage transmission lines can reduce the vibration of the wires caused by the wind, thereby reducing the probability of accidents. The aim of a vibration damper detection task is to provide the position of the vibration damper in the image. It is the basis for other tasks such as vibration damper corrosion inspection and mobile inspection. At present, this problem has attracted the attention of researchers studying smart grids and other fields [1,2].

In recent years, UAV-related technology has become one of the fastest developing directions in the field of science and technology. UAVs have the advantages of simple operation, easy portability, and low use cost that other aircraft such as helicopters do not have [3]. The UAV array network composed of sensor networks [4] can quickly complete tasks such as object recognition [5] and crop yield estimation [6]. While drones bring convenience to human activities, they also bring some negative effects [7]. Examples include the communication security issues of UAVs [8] and the noise pollution generated during flight, which threatens the safety of birds [9]. Current transmission line inspection tasks are still mainly performed manually. Therefore, the use of UAVs for power line inspection is an issue worth researching, and there have been a number of relevant studies [10]. This paper focuses on the detection of line vibration dampers using aerial images obtained by UAVs.

In early work, the use of image processing algorithms to improve the visual perception of vibration dampers in images was the most common method. Usually, researchers use an appropriate feature extraction operator to detect vibration dampers [11]. In addition, there are studies that combine machine learning algorithms to improve the level of automation [1], and such methods were also the main direction of early research. However, traditional methods generally have the problem of a low detection accuracy.

In recent years, with the renewed popularity of deep learning technology, multiple algorithms represented by convolutional neural networks (CNNs) have emerged, providing new energy to the task of vibration damper detection. Such methods can obtain an end-to-end model through iterative training on the dataset, and only one input is required to obtain an output with excellent detection accuracy in subsequent use. Although CNN-like algorithms have high detection accuracy, they still have the problem of a long training time, and the effect is limited by the size of the dataset. We hope to obtain a method with low resource requirements and a high detection effect.

Benefiting from the rapid development of deep learning, image generation algorithms represented by GAN [12] have become one of the research hotspots in the field of computer vision. CGAN [13] through additional auxiliary conditions and the use of common data annotations in the field of object detection can generate vibration damper detection images.

In view of the research status of the field of vibration damper detection, as shown in , we proposed a model for line vibration damper detection image generation that is based on a conditional generative adversarial network. The main contributions of this paper are as follows:

• On the basis of an improved conditional generative adversarial network, we proposed a framework for vibration damper detection image generation named DamperGAN. The framework contains a two-stage generator and a multi-scale discriminator.

• In order to generate high-resolution vibration damper detection images, we used a coarse-to-fine generation method. At the same time, an attention mechanism and a penalty mechanism based on Monte Carlo search were introduced into the generator to provide enough semantic information for image generation to improve the edge information of the image.

• In order to improve the high-resolution images generated by the discriminator, we proposed a multi-level discriminator structure based on the parameter sharing mechanism, so that the entire discriminator pays attention to both semantic information and underlying feature information.

• Aiming to address the problem of no public dataset in the field of vibration damper detection, we established a dataset named DamperGenSet that is based on real optical images from UAV aerial photography. Through comparison with the experimental results of multiple state-of-the-art models on the DamperGenSet dataset, we prove that our proposed DamperGAN has certain advantages.

  Want more information on transmission line dampers? Feel free to contact us.

The remainder of this article is organized as follows. Section 2 briefly introduces related work on vibration damper detection and image generation. Section 3 introduces the basic knowledge used in this article. In Section 4, we introduce the details of DamperGAN. In Section 5, we introduce the dataset, experimental details, and a series of comparative experiments. Section 6 provides a brief summary of the work in this article.

Dampers

Dampers used in transmission lines for aviod oscillations in overhead transmission lines.Due to laminar wind, overhead transmission lines will be excited to vibrations and oscillations that can lead to damage on the conductor of the overhead transmission line, single parts or the pole. In order to reduce these vibrations and oscillations to an uncritical dimension, damping systems will have to be installed in the overhead transmission lines.

Types Of Dampers

Dampers used in transmission lines are of following types.

Stockbridge dampers

A Stockbridge damper is a tuned mass damper used to suppress wind-induced vibrations on slender structures such as overhead power lines and long cantilevered signs.The dumbbell-shaped device consists of two masses at the ends of a short length of cable or flexible rod, which is clamped at its middle to the main cable. The damper is designed to dissipate the energy of oscillations in the main cable to an acceptable level. Its distinctive shape gives it the nickname &#;dog-bone damper&#;.These dampers are used to counteract vibrations excited by wind, so-called Karman vibrations. Depending on the type of the the conductor of the overhead transmission line, several damper types with many different models are available. The name of the damper is due to the scientist H. Stockbridge, who advanced the development of the damper in the &#;s. The functional mode has not changed up to now and is one of the methods for reducing vibrations on overhead transmission lines that are spread most.

Spacer dampers

Spacers serve to establish a distance between the partial conductors of a bundle line in order to prevent the conductors from knocking together or tilting and thus avoid damage done to conductors. Spacer dampers will be used if vibrations excited by wind need to be expected. Thanks to use of damping elements between the frame and the conductor clamps, the vibration amplitudes of the conductor can be reduced to an uncritical dimension. In this context, many different models of the spacers are available for different bundle arrangements.

For more active damping vs passive dampinginformation, please contact us. We will provide professional answers.