EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Estimasi Loss Of Life Tranformator Berdasarkan Loading dan Temperature Menggunakan LSTM di Gardu Induk 150KV Buduran

Anjar Novian Piyan

Impression : Jurnal Teknologi dan Informasi · 2023

DOI: 10.59086/jti.v2i2.312 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Impression : Jurnal Teknologi dan Informasi, 2023. Verfasst von Anjar Novian Piyan. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Transformers are crucial equipment in substations, performing important tasks such as voltage transformation, current adjustment, and power quality maintenance. However, various factors over time, such as increased operating temperature, loading conditions, and maintenance schedules, can impact transformer performance and lead to a reduction in its lifespan. This research focuses on the effective and accurate estimation of age loss employ the Long Short Term Memory (LSTM) skill. LSTM means a deep neural network that processes sequential data and retains historical information. Data utilized in this research is sourced from transformer 6 at the Buduran 150 kV substation, including load and oil temperature data for 2021 and 2022. The performance of LSTM is assessed using Mean Squared Error (MSE) cum Root Mean Squared Error (RMSE). The estimation results demonstrate the favorable performance of the LSTM method, with an MSE error value of 0.0002 and an RMSE of 0.014. The projected age loss for 2023 is estimated to be 17.89% or 0.1789 pu. Transformers are crucial equipment in substations, performing important tasks such as voltage transformation, current adjustment, and power quality maintenance. However, various factors over time, such as increased operating temperature, loading conditions, and maintenance schedules, can impact transformer performance and lead to a reduction in its lifespan. This research focuses on the effective and accurate estimation of age loss employ the Long Short Term Memory (LSTM) skill. LSTM means a deep neural network that processes sequential data and retains historical information. Data utilized in this research is sourced from transformer 6 at the Buduran 150 kV substation, including load and oil temperature data for 2021 and 2022. The performance of LSTM is assessed using Mean Squared Error (MSE) cum Root Mean Squared Error (RMSE). The estimation results demonstrate the favorable performance of the LSTM method, with an MSE error value of 0.0002 and an RMSE of 0.014. The projected age loss for 2023 is estimated to be 17.89% or 0.1789 pu.

Zitieren

APA

Piyan, A. N. (2023). Estimasi Loss Of Life Tranformator Berdasarkan Loading dan Temperature Menggunakan LSTM di Gardu Induk 150KV Buduran. Impression : Jurnal Teknologi dan Informasi. https://doi.org/10.59086/jti.v2i2.312

Vancouver

Piyan AN. Estimasi Loss Of Life Tranformator Berdasarkan Loading dan Temperature Menggunakan LSTM di Gardu Induk 150KV Buduran. Impression : Jurnal Teknologi dan Informasi. 2023. doi:10.59086/jti.v2i2.312

BibTeX
@article{Piyan2023,
  author = {Piyan, Anjar Novian},
  title = {Estimasi Loss Of Life Tranformator Berdasarkan Loading dan Temperature Menggunakan LSTM di Gardu Induk 150KV Buduran},
  journal = {Impression : Jurnal Teknologi dan Informasi},
  year = {2023},
  doi = {10.59086/jti.v2i2.312}
}
Kostenlos starten →