KEYWORDS: Data modeling, Data transmission, Binary data, Machine learning, Humidity, Ice, Support vector machines, Mathematical modeling, Education and training, Vibration
With the continuous expansion of power grid scale and the improvement of power grid informatization level, China has accumulated a certain amount of wire wind vibration data in years of transmission line operation, including structured and unstructured data such as text, statistical charts, images, videos, etc., providing strong data support for data-driven wire wind vibration disaster mechanism mining. Therefore, it is necessary to integrate multi-disciplinary knowledge such as computer, mathematics, information processing, mechanics, and biology based on data mining and digital machine learning techniques, effectively mine and deeply analyze the historical records of wind-induced vibration disasters on transmission lines, meteorological and geographical environmental parameter information, multi-source and wide-area wind-induced vibration monitoring information, and line structural parameters, in order to clarify the main influencing factors and disaster mechanisms of wind-induced vibration disasters on transmission lines, improve the prevention and control technology of wind-induced vibration disasters on transmission lines, enhance the identification level of wind-induced vibration disasters in power grids, and provide decision-making support for the safe operation of power grids.
The galloping of overhead transmission lines can cause damage to equipment such as conductors, drainage lines, insulators, and towers. In this paper, the loosening of bolts under vibration is studied, and it is found that the vibration frequency has a significant impact on bolt loosening. With the increase of vibration frequency, the risk of bolt loosening increases. At the same time, under quasi-static and different frequencies, the axial pre-tightening force of bolts decreases with the increase of cycle number. When the transverse vibration amplitude is less than a certain critical value, the bolts are basically not loose. When the transverse vibration amplitude is greater than a certain critical value, the larger the transverse vibration amplitude, the easier it is to loosen the bolts. In addition, the friction coefficient will also affect the loosening behavior of bolts. These results can provide reference for predicting the fatigue life of bolted connection structures. Therefore, in practice, attention should be paid to controlling the transverse vibration amplitude and friction coefficient to avoid bolt loosening.
In this study, a multi-layer perceptron based identification method is proposed for the identification of wind vibration hazards of conductors in power systems. First, the background and impact of conductor wind vibration hazards are introduced and analyzed, and the related theories are discussed. Further, a data set including several feature parameters is established, and a high-quality feature vector is obtained through feature engineering, and the degree of influence of each attribute on the occurrence of wind vibration is explored. Then, a multilayer perceptron model with multiple implicit layers is designed and trained for the automatic identification of wind vibration hazards in conductors. Finally, experimental validation shows that the proposed method has high accuracy and robustness in wire wind vibration hazard identification and can be effectively applied to the safe operation of power systems.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.