access icon openaccess Application of improved grey model residual modified fusion algorithm in dissolved gas forecasting

This is an open access article published by the IET under the Creative Commons Attribution -NonCommercial License (http://creativecommons.org/licenses/by-nc/3.0/)
Received 17/10/2018, Accepted 09/01/2019, Published 25/03/2019

The power transformer directly affects whether the power system can operate safely and reliably, and the prediction of the dissolved gas content in the transformer oil is an effective means to discover transformer defects and latent faults, which helps to better carry out state maintenance work. This study extracts the time series data in transformer oil and analyses the interactions and effects between various gas components in the oil. Then, combined with the changing trend of the content of each component, the original sequence was processed using an accumulated method to extract the intrinsic characteristics of the sequence, thus establishing the MGM(1,n)(grey multivariate model). As the grey prediction model can reduce the prediction accuracy of the sequence with longer time span, this study combines the adaptive regression and Markov correction models to optimise the grey prediction model from the perspective of residual correction. Finally, the accuracy and effectiveness of the model are verified by comparing with the original prediction method.

Inspec keywords: grey systems; Markov processes; transformer oil; regression analysis; time series; power transformers

Other keywords: transformer defects; grey prediction model; time series data; original sequence; original prediction method; dissolved gas content; dissolved gas forecasting; residual correction; latent faults; Markov correction models; longer time span; state maintenance work; prediction accuracy; gas components; improved grey model residual modified fusion algorithm; power transformer; power system; transformer oil

Subjects: Organic insulation; Transformers and reactors; Combinatorial mathematics; Other topics in statistics; Knowledge engineering techniques; Other topics in statistics

References

    1. 1)
      • 3. Sergejs, Z., Poiss, G.: ‘Power transformer mechanical condition assessment with a vibration-based diagnostic method’. Int. Scientific Conf. on Power and Electrical Engineering of Riga Technical University IEEE, Riga, Latvia, October 2015, pp. 1–4.
    2. 2)
      • 1. Borucki, S.: ‘Diagnosis of technical condition of power transformers based on the analysis of vibroacoustic signals measured in transient operating conditions’, IEEE Trans. Power Deliv., 2012, 27, (2), pp. 670–676.
    3. 3)
      • 9. Gao, J., He, J.: ‘Quantum genetic neural network in the analysis of dissolved gas in transformer oil’. Proc. CSEE, 2010, 30, (30), pp. 121–127.
    4. 4)
      • 5. Sima, L., Shu, N., Zuo, J., et al: ‘Prediction of dissolved gas concentration in transformer oil based on grey correlation and fuzzy support vector machine’, Power Syst. Prot. Control, 2012, 40, (19), pp. 41–46.
    5. 5)
      • 11. Luo, Y., Yu, P., Song, B., et al: ‘Predicting the content of dissolved gas in transformer oil by grey model’. Proc. CSEE, 2001, 21, (3), pp. 65–69.
    6. 6)
      • 12. Li, M., Sha, X.: ‘Improvement and application of grey prediction model based on GM(1, 1)’, Comput. Eng. Applic., 2016, 52, (4), pp. 24–30.
    7. 7)
      • 13. Truong, D.Q, Ahn, K.K.: ‘Wave prediction based on a modified grey model MGM(1, 1) for real-time control of wave energy converters in irregular waves’, Renew. Energ., 2012, 43, pp. 242–245.
    8. 8)
      • 14. Tang, Y., Gui, W., Peng, T.: ‘Multinuclear principal component regression prediction model for gas in transformer oil’, Electr. Mach. Control, 2012, 16, (11), pp. 92–99.
    9. 9)
      • 10. Yang, T., Zhou, L., Li, J., et al: ‘Diagnosis of transformer faults based on combination model of optimal weights’, Power Syst. Technol., 2013, 37, (1), pp. 190–194.
    10. 10)
      • 15. Zhai, J., Sheng, J.: ‘MGM(1, n) and its application’, Syst. Eng. Theory Pract., 1997, 17, (5), pp. 109–113.
    11. 11)
      • 8. Liu, W.: ‘Forecasting the semiconductor industry cycles by bootstrap prediction intervals’, Appl. Econ., 2007, 39, (13), pp. 1731–1742.
    12. 12)
      • 4. Sica, F.C., Guimarães, F.G., Duarte, R.O., et al: ‘A cognitive system for fault prognosis in power transformers’, Electric. Power Syst. Res., 2015, 127, pp. 109–117.
    13. 13)
      • 7. Khosravi, A., Nahavandi, S., Creighton, D.: ‘Construction of optimal prediction intervals for load forecasting problems’, IEEE Trans. Power Syst., 2010, 25, (3), pp. 1496–1503.
    14. 14)
      • 2. Suurmond, C.: ‘Design and implementation of vibration on-line monitoring system of power transformer’. Power and Energy Society General Meeting, Vancouver, Canada, July, 2013, pp. 1–5.
    15. 15)
      • 6. Wang, K., Li, J., Zhang, S., et al: ‘New characteristic parameters of dissolved gas in transformer fault diagnosis oil’. Proc. CSEE, 2016, 36, (23), pp. 6570–6578.
http://iet.metastore.ingenta.com/content/journals/10.1049/joe.2018.9200
Loading

Related content

content/journals/10.1049/joe.2018.9200
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading