Synthetic Data Generation Using GAN for RUL Prediction of Supercapacitors

다국어 초록 (Multilingual Abstract)

The remaining useful life (RUL) prediction of supercapacitors is an important part of supercapacitors management system. To accurately predict the RUL of supercapacitor, a large amount of capacity data is required which can be difficult to acquire due to privacy restrictions and limited access. Previous works have employed the use of deep learning models to synthetically generate data. However, a prerequisite ensuring the success of these models depends on their ability to preserve the temporal dynamics of the data. This paper presents a generative adversarial network (GAN) for synthetic data generation and a long short-term memory (LSTM) network for accurate RUL prediction. Firstly, the GAN model is employed for synthetic data generation and LSTM for RUL prediction. We show that the GAN model is capable of preserving the temporal dynamics of the original data and also prove that the generated data can be used to accurately carry out RUL prediction. Our proposed GAN model was able to achieve an accuracy of 85% after 500 epochs.
The performance of the generated data set with the LSTM model achieved an RMSE of 0.29. The overall results show that synthetic data can be used to achieve excellent performance for RUL prediction.

참고문헌 (Reference)

1 최경준 ; 최세영 ; 염성관 ; 조영식, "무인항공기의 비행시간 향상을 위한 배터리 관리 회로 구현" 한국통신학회 45 (45): 285-288, 2020

2 Z. Wan, "Variational autoencoder based synthetic data generation for imbalanced learning" 10 (10): 1-7, 2017

3 K. Vulrilehto, "Supercapacitors-basics and applications" 23 : 2014

4 D. Eroldi, "Sizing for fuel cell/supercapacitor hybrid vehicles based on stochastic driving cycles" 183 (183): 45-50, 2016

5 S. Liu, "Review on reliability of supercapacitors in energy storage applications" 278 (278): 54-36, 2020

6 W. -S. Si, "Remaining useful life estimation—A review on the statistical data driven approaches" 213 (213): 1-14, 2011

7 J. F. Sun, "Recent progresses in high energy density all pseudocapacitive-electrodematerials-based asymmetric supercapacitors" 5 (5): 9443-9464, 2017

8 J. Chen, "Probabilistic analysis of hybrid energy systems using synthetic renewable and load data" Bournemouth Int. Centre Labour 4723-4728, 2017

9 최경준 ; 최세영 ; 오장훈, "IoT 센서 노드 충전용 RF 에너지 하베스팅 회로 구현" 한국통신학회 44 (44): 755-758, 2019

10 C. Zhang, "Generative adversarial network for synthetic time series data generation in smart grids" 1-6, 2018

11 M. Pyne, "Generation of synthetic battery data with capacity variation" 476-480, 2019

12 M. Lakshminarayanan, "Generating high-fidelity synthetic battery parameter data : solving sparse dataset challenges" 41-47, 2021

13 T. Ma, "Development of hybrid batterysupercapacitor energy storage for remote area renewable energy systems" 10 (10): 58-63, 2014

14 AU. Chokwitthaya, "Applying the Gaussian mixture model to generate large synthetic data from a small data set" 7 (7): 34-38, 2019

15 M. Aszczur, "An optimisation and sizing of photovoltaic system with supercapacitor for improving selfconsumption" 3 (3): 26-19, 2020

16 Y. Roh, "A survey on data collection for machine learning : A big data-ai integration perspective" 33 (33): 1328-1347, 2021

17 R. Gu, "A novel battery/Ultracapacitor hybrid energy storage system analysis based on physics-based lithium-ion battery modelling" 1-6, 2015

18 C. Hu, "A new remaining useful life estimation method for equipment subjected to intervention of imperfect maintenance activities" 31 (31): 514-528, 2018

19 J. Liu, "A multi-step predictor with a variable input pattern for system state forecasting" 23 (23): 1586-1599, 2009

20 Z. S. Iro, "A brief review on electrode materials for supercapacitor" 11 (11): 10628-10643, 2016