# Remanufacturing Decision-Making for Gas Insulated Switchgear with Remaining Useful Life Prediction

^{1}

^{2}

^{3}

^{4}

^{*}

## Abstract

**:**

## 1. Introduction

- To the best of our knowledge, this is the first attempt to propose a data-driven remanufacturing decision-making framework in GIS equipment. With the test R-squared 0.999, the RUL regression model shows state-of-the-art prediction performance.
- We acquire signal data from GIS with accelerated life testing by setting up a laboratory. The data consist of seven signal data crucially related to the degradation of GIS.
- The replacement simulation confirms that the proposed framework is valid for improving RUL economically.

## 2. Proposed Framework

#### 2.1. Data Collection

#### 2.2. Data Preprocessing

#### 2.3. Remaining Useful Life Regression

#### 2.4. Gis Parts Replacement Simulation

## 3. Results

## 4. Discussion

## 5. Conclusions

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## Abbreviations

GIS | Gas Insulated Switchgear. |

RUL | Remaining Useful Life. |

ALT | Accelerated Life Testing. |

## References

- Avtar, R.; Tripathi, S.; Aggarwal, A.K.; Kumar, P. Population–urbanization–energy nexus: A review. Resources
**2019**, 8, 136. [Google Scholar] [CrossRef] - Luo, Y.; Tang, J.; Pan, C.; Pan, Z.; Li, Y.; Cui, Z. Dynamics of surface charge and electric field distributions on basin-type insulator in GIS/GIL due to voltage polarity reversal. High Volt.
**2020**, 5, 151–159. [Google Scholar] [CrossRef] - Esposito, M.; Tse, T.; Soufani, K. Introducing a circular economy: New thinking with new managerial and policy implications. Calif. Manag. Rev.
**2018**, 60, 5–19. [Google Scholar] [CrossRef] - Kizilboga, G.; Mandil, G.; Genevois, M.E.; Zwolinski, P. Remanufacturing network design modeling: A case of diesel particulate filter. Procedia CIRP
**2013**, 11, 163–168. [Google Scholar] [CrossRef] - Fegade, V.; Shrivatsava, R.; Kale, A. Design for remanufacturing: Methods and their approaches. Mater. Today Proc.
**2015**, 2, 1849–1858. [Google Scholar] [CrossRef] - Jiang, Z.; Ding, Z.; Zhang, H.; Cai, W.; Liu, Y. Data-driven ecological performance evaluation for remanufacturing process. Energy Convers. Manag.
**2019**, 198, 111844. [Google Scholar] [CrossRef] - Ling, T.; He, Y. The remanufacturing evaluation for feasibility and comprehensive benefit of retired grinding machine. PLoS ONE
**2020**, 15, e0234603. [Google Scholar] [CrossRef] - Fofou, R.F.; Jiang, Z.; Wang, Y. A review on the lifecycle strategies enhancing remanufacturing. Appl. Sci.
**2021**, 11, 5937. [Google Scholar] [CrossRef] - Tahan, M.; Tsoutsanis, E.; Muhammad, M.; Karim, Z.A. Performance-based health monitoring, diagnostics and prognostics for condition-based maintenance of gas turbines: A review. Appl. Energy
**2017**, 198, 122–144. [Google Scholar] [CrossRef] - Wang, Y.; Zhao, Y.; Addepalli, S. Remaining useful life prediction using deep learning approaches: A review. Procedia Manuf.
**2020**, 49, 81–88. [Google Scholar] [CrossRef] - Ma, Z.; Guo, J.; Mao, S.; Gu, T. An interpretability research of the Xgboost algorithm in remaining useful life prediction. In Proceedings of the 2020 International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE), Bangkok, Thailand, 30 October–1 November 2020; pp. 433–438. [Google Scholar]
- Nguyen, M.T.; Nguyen, V.H.; Yun, S.J.; Kim, Y.H. Recurrent neural network for partial discharge diagnosis in gas-insulated switchgear. Energies
**2018**, 11, 1202. [Google Scholar] [CrossRef] - Khan, Q.; Refaat, S.S.; Abu-Rub, H.; Toliyat, H.A. Partial discharge detection and diagnosis in gas insulated switchgear: State of the art. IEEE Electr. Insul. Mag.
**2019**, 35, 16–33. [Google Scholar] [CrossRef] - Ni, J.; Zhang, C.; Yang, S.X. An adaptive approach based on KPCA and SVM for real-time fault diagnosis of HVCBs. IEEE Trans. Power Deliv.
**2011**, 26, 1960–1971. [Google Scholar] [CrossRef] - Ma, S.; Chen, M.; Wu, J.; Wang, Y.; Jia, B.; Jiang, Y. High-voltage circuit breaker fault diagnosis using a hybrid feature transformation approach based on random forest and stacked autoencoder. IEEE Trans. Ind. Electron.
**2018**, 66, 9777–9788. [Google Scholar] [CrossRef] - Yin, X.; Su, Y.; Xi, T.; Chen, B.; Zhang, L.; Zhang, X.; Liu, L.; Shao, X. Research progress on photoacoustic SF6 decomposition gas sensor in gas-insulated switchgear. J. Appl. Phys.
**2022**, 131, 130701. [Google Scholar] [CrossRef] - Okabe, S. Insulation properties and degradation mechanism of insulating spacers in gas insulated switchgear (GIS) for repeated/long voltage application. IEEE Trans. Dielectr. Electr. Insul.
**2007**, 14, 101–110. [Google Scholar] [CrossRef] - Zhang, Z.; Zhang, J.; Gockenbach, E.; Borsi, H. Life management of SF 6 circuit breakers based on monitoring and diagnosis. IEEE Electr. Insul. Mag.
**2009**, 25, 21–29. [Google Scholar] [CrossRef] - Qin, S.; Wang, B.X.; Wu, W.; Ma, C. The prediction intervals of remaining useful life based on constant stress accelerated life test data. Eur. J. Oper. Res.
**2022**, 301, 747–755. [Google Scholar] [CrossRef] - Han, D.; Bai, T. Design optimization of a simple step-stress accelerated life test–Contrast between continuous and interval inspections with non-uniform step durations. Reliab. Eng. Syst. Saf.
**2020**, 199, 106875. [Google Scholar] [CrossRef] - Mohamed, A.E.R.; Abu-Youssef, S.; Ali, N.S.; Abd El-Raheem, A. Inference on constant-stress accelerated life testing based on geometric process for extension of the exponential distribution under type-II progressive censoring. Pak. J. Stat. Oper. Res.
**2018**, 233–251. [Google Scholar] [CrossRef][Green Version] - Bhattacharjee, P.; Dey, V.; Mandal, U. Risk assessment by failure mode and effects analysis (FMEA) using an interval number based logistic regression model. Saf. Sci.
**2020**, 132, 104967. [Google Scholar] [CrossRef] - Fu, S.; Cheng, F.; Tjahjowidodo, T.; Zhou, Y.; Butler, D. A non-contact measuring system for in-situ surface characterization based on laser confocal microscopy. Sensors
**2018**, 18, 2657. [Google Scholar] [CrossRef] [PubMed] - Ren, L.; Zhao, L.; Hong, S.; Zhao, S.; Wang, H.; Zhang, L. Remaining useful life prediction for lithium-ion battery: A deep learning approach. IEEE Access
**2018**, 6, 50587–50598. [Google Scholar] [CrossRef] - Ge, X.; Fan, Y.; Li, J.; Wang, Y.; Deng, S. Noise reduction of nuclear magnetic resonance (NMR) transversal data using improved wavelet transform and exponentially weighted moving average (EWMA). J. Magn. Reson.
**2015**, 251, 71–83. [Google Scholar] [CrossRef] [PubMed] - Bartlett, P.L.; Long, P.M.; Lugosi, G.; Tsigler, A. Benign overfitting in linear regression. Proc. Natl. Acad. Sci. USA
**2020**, 117, 30063–30070. [Google Scholar] [CrossRef] - Hoerl, A.E.; Kennard, R.W. Ridge regression: Biased estimation for nonorthogonal problems. Technometrics
**1970**, 12, 55–67. [Google Scholar] [CrossRef] - Tibshirani, R. Regression shrinkage and selection via the lasso. J. R. Stat. Soc. Ser. (Methodol.)
**1996**, 58, 267–288. [Google Scholar] [CrossRef] - Zou, H.; Hastie, T. Regularization and variable selection via the elastic net. J. R. Stat. Soc. Ser. (Stat. Methodol.)
**2005**, 67, 301–320. [Google Scholar] [CrossRef] - Breiman, L. Random forests. Mach. Learn.
**2001**, 45, 5–32. [Google Scholar] [CrossRef][Green Version] - Chen, T.; Guestrin, C. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016; pp. 785–794. [Google Scholar]
- Zerveas, G.; Jayaraman, S.; Patel, D.; Bhamidipaty, A.; Eickhoff, C. A transformer-based framework for multivariate time series representation learning. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Virtual Event. Singapore, 14–18 August 2021; pp. 2114–2124. [Google Scholar]
- Pan, H.; He, X.; Tang, S.; Meng, F. An improved bearing fault diagnosis method using one-dimensional CNN and LSTM. Stroj. Vestn./J. Mech. Eng.
**2018**, 64, 443–452. [Google Scholar]

**Figure 3.**(

**a**) LD sensor for measuring stroke distance. (

**b**) DC CT sensor for measuring current of open/close trip coil and auxiliary coil.

**Figure 5.**(

**a**) is a sampled signal datum using 10,000 Hz sensor and represents 0.28 s duration per each operation. The stroke sensor is used as an example of visualization (

**a**), and the other sensors, including trip coil, auxiliary, and motor temperature, also have the same frequency and duration. (

**b**) is a sampled signal datum from motor sensor using a 1000 Hz sensor and represents 26 s duration per each operation. (

**c**) is a visualization of time interval between operations.

**Figure 6.**Visualization of splitting sensor signal data into ten to extract statistics during one open/close operation.

**Figure 10.**(

**left**) A graph of the corresponding motor current values when 1000, 7000, and 14,300 open/close operations are conducted. (

**right**) Zooming into the 0 to 11 second range and the 0 to 9 motor current value range.

No. | Sensing Position | Sensing Value | Sensor Type |
---|---|---|---|

1 | Simulated load | Distance | LD sensor |

2 | Open trip coil | Current | DC CT |

3 | Close trip coil | Current | DC CT |

4 | Auxiliary coil | Current | DC CT |

5 | Auxiliary contact | Contact signal | - |

6 | Motor | current | DC CT |

7 | Motor | temperature | Temperature detector |

**Table 2.**Comparisons of results using six regression algorithms, in terms of MSE, MAE, and R-Squared. The best performances are in bold and the mean and standard deviations are reported.

Model | MSE | MAE | ${\mathbf{R}}^{2}$ |
---|---|---|---|

Linear Regression | 46.824 (53.815) | 2.324 (0.101) | 0.940 (0.068) |

Ridge | 32.196 (40.842) | 2.351 (0.091) | 0.959 (0.051) |

Lasso | 87.764 (1.789) | 7.519 (0.091) | 0.887(0.002) |

Elastic Net | 85.772 (1.924) | 7.433 (0.101) | 0.890 (0.003) |

Random Forest | 0.463 (0.143) | 0.263 (0.014) | 0.999 (0.000) |

XGBoost | 0.765 (0.176) | 0.509 (0.018) | 0.999 (0.000) |

**Table 3.**List of parts that affect each sensor data. The RUL increment per cost is reported. mark means sensor and corresponding parts are closely related.

Sensor | Stroke | Open Trip Coil | Close Trip Coil | Auxiliary Coil | Motor Temperature | Motor Current | Cost Ratio | |
---|---|---|---|---|---|---|---|---|

Parts | ||||||||

Gear | ✓ | ✓ | 0.135 | |||||

Open/close hook | ✓ | ✓ | ✓ | 0.125 | ||||

Close shaft/spring | ✓ | ✓ | ✓ | 0.225 | ||||

Open shaft/spring | ✓ | 0.215 | ||||||

Dashpot | ✓ | 0.075 | ||||||

Link | ✓ | 0.014 | ||||||

Frame | ✓ | 0.211 | ||||||

Sum cost | 0.529 | 0.125 | 0.125 | 0.125 | 0.571 | 0.36 | 1 | |

RUL increment | 24.09 | 0.11 | 0.02 | 0.23 | 0.12 | 96.88 | - | |

RUL increment per cost | 45.53 | 0.88 | 0.16 | 1.84 | 0.21 | 269.11 | - |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2022 by the authors. 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/).

## Share and Cite

**MDPI and ACS Style**

Moon, S.; Cho, H.; Koh, E.; Cho, Y.S.; Oh, H.L.; Kim, Y.; Kim, S.B.
Remanufacturing Decision-Making for Gas Insulated Switchgear with Remaining Useful Life Prediction. *Sustainability* **2022**, *14*, 12357.
https://doi.org/10.3390/su141912357

**AMA Style**

Moon S, Cho H, Koh E, Cho YS, Oh HL, Kim Y, Kim SB.
Remanufacturing Decision-Making for Gas Insulated Switchgear with Remaining Useful Life Prediction. *Sustainability*. 2022; 14(19):12357.
https://doi.org/10.3390/su141912357

**Chicago/Turabian Style**

Moon, Seokho, Hansam Cho, Eunji Koh, Yong Sung Cho, Hyoung Lok Oh, Younghoon Kim, and Seoung Bum Kim.
2022. "Remanufacturing Decision-Making for Gas Insulated Switchgear with Remaining Useful Life Prediction" *Sustainability* 14, no. 19: 12357.
https://doi.org/10.3390/su141912357