KEYWORDS: Transformers, Energy efficiency, Standards development, Sensors, Power grids, Equipment, Inspection equipment, Resistance, Power consumption, Iron
Reducing consumption and increasing efficiency is an important task in building a new type of power system to achieve the target of dual carbon. 40% of losses in the power system come from transformers. However, due to limitations in current testing techniques, lack of regulatory measures, and human factors, there is still a certain distance to achieve the expected goals. Clarifying the relationship between offline measurement values of transformer losses and actual operating losses, controlling transformer loss indicators well, and researching new technologies for improving transformer energy efficiency urgently require new breakthroughs in online testing technology for transformer losses. This article summarizes the mechanism of transformer losses and related technical parameter indicators, proposes online detection technology for transformer losses and methods to improve measurement accuracy. The practical application cases have verified that this method can achieve good results, laying the foundation for improving the energy efficiency of transformer operation in the future.
The capacitive voltage transformer is an important metering device in power systems, the principal element analysis method has certain limitations in the error evaluation of capacitive voltage transformer (CVT), and this paper proposes an adaptive evaluation method based on moving window-weighted principal component analysis (PCA). This method combines the ideas of moving window PCA and exponential weighted PCA, which can adaptively update the evaluation model and achieve state evaluation of CVT. The moving window-weighted PCA method can effectively identify abrupt and gradual errors, which is more suitable for long-term CVT error monitoring.
Aiming at the problem that it is difficult to obtain the core parameters of the current transformer simulation model, a genetic simulated annealing algorithm is proposed in this paper. This method combines simulated annealing algorithm with genetic algorithm to overcome the premature phenomenon of traditional genetic algorithm. It realizes the fast fitting of core specific parameters of current transformer J-A model, and can quickly build the current transformer simulation model. The effectiveness of the algorithm is verified by example simulation.
A Convolutional Neural Network (CNN) for theoretical station area line loss is proposed in this paper. Considering that CNN has strong nonlinear fitting ability, it is often used to predict the station area line loss. We analyze case, and select appropriate number of input features to verify proposed method’s availability. Meanwhile, the station area line loss is calculated under the most appropriate number of feature inputs. The results show that the station area classification and key factors are identified as the subsequent station area loss calculation model, which optimizes the input variables and improves efficiency and accuracy for station area line loss calculation.
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.