Abstract
Due to the long-term operation of the transformer oil chromatographic online monitoring device, there will be chromatographic peak shifts and baseline jitter, which may cause chromatographic peak loss or misidentification. This study proposes a method for identifying chromatographic peaks of dissolved gas in transformer oil based on random forests. The peak position, peak height, peak width, and peak area were used as evaluation factors. While the evaluation factors subjected to factor analysis, public factors extracted and the random forest algorithm used for training as final. A random forest model based on factor analysis of the chromatographic peaks of dissolved gas in transformer oil was established. The results of a case study show that the chromatographic peak identification of the algorithm has high accuracy which can effectively avoid the misjudgment and missed detection of chromatographic peaks caused by peak position shift.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Faiz, J., Soleimani, M.: Dissolved gas analysis evaluation in electric power transformers using conventional methods a review. IEEE Trans. Dielectr. Electr. Insul. 24(2), 1239–1248 (2017). https://doi.org/10.1109/TDEI.2017.005959
Mirowski, P., LeCun, Y.: Statistical machine learning and dissolved gas analysis: a review. IEEE Trans. Power Delivery 27(4), 1791–1799 (2012). https://doi.org/10.1109/TPWRD.2012.2197868
Duval, M.: A review of faults detectable by gas-in-oil analysis in transformers. IEEE Electr. Insul. Mag. 18(3), 8–17 (2002). https://doi.org/10.1109/MEI.2002.1014963
Bakar, N.A., Abu-Siada, A., Islam, S.: A review of dissolved gas analysis measurement and interpretation techniques. IEEE Electr. Insul. Mag. 30(3), 39–49 (2014). https://doi.org/10.1109/MEI.2014.6804740
Hu, S., Zhu, J., Zhou, X.: Fast and intelligent chromatographic peak identification algorithm. Mod. Sci. Instrum. 1995(01), 19–21 (1995)
Liu, Z., Zou, H., Ye, M., Ni, J., Zhang, Y.: Effect of temperature and buffer on the migration time window of micellar electrokinetic capillary chromatography. Chin. J. Chromatogr. 17(02), 147–152 (1999)
Miao, H., Hu, S.: Chromatographic peak detecting algorithmcombining the first and second derivatives. Chin. J. Anal. Chem. 22(03), 247–250 (1994)
Hu, J., Bao, J., Zhou, F., Luo, Z.: Mode matching based transformer chromatogrampeaks identification algorithm. Autom. Electr. Power Syst. 29(21), 85–87 (2005). https://doi.org/10.3321/j.issn:1000-1026.2005.21.017
Cao, J., Fan, J., An, C.: Application of grey correlation analysis in chromatograph peak identification of transformer oil. Power Syst. Technol. 34(07), 206–210 (2010). https://doi.org/10.1109/CCECE.2010.5575154
Wang, W.: Research on transformer chromatographic peaks quantitative analysis based on wavelet filtering. In: Proceedings of 2011 International Conference on Electronics and Optoelectronics, vol. 1, V1-339–V1-342 (2011). https://doi.org/10.1109/ICEOE.2011.6013115
Hu, J., Zhou, F., Bao, J., Luo, Z.: Qualitative algorithm for fuzzy membership function based transformer chromatogramcomponents. Autom. Electr. Power Syst. 29(18), 70–72 (2005). https://doi.org/10.3321/j.issn:1000-1026.2005.18.014
Zhang, W., Jiang, L., Wu, Q., Deng, Y.: Chromatographic peak recognition technology for oil dissolved gas based on multi-parameter weight. Electr. Power Constr. 35(10), 43–46 (2014). https://doi.org/10.3969/j.issn.1000-7229.2014.10.009
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001). https://doi.org/10.1023/A:1010933404324
Meng, Z., Pan, J.-S., Huarong, Xu.: QUasi-Affine TRansformation Evolutionary (QUATRE) algorithm: a cooperative swarm based algorithm for global optimization. Knowl.-Based Syst. 109, 104–121 (2016)
Zhuang, J., Luo, J., Peng, Y., Huang, C., Wu, C.: Fault diagnosis method based on modified random forests. Comput. Integr. Manuf. Syst. 15(4), 777–785 (2009). https://doi.org/10.1007/978-3-642-02298-2_32
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, HM., Chang, CK., Pan, JS., Shan, J., Li, ZJ. (2021). Chromatographic Peaks of Dissolved Gases in Transformer Oil Identification by Random Forest. In: Pan, JS., Li, J., Ryu, K.H., Meng, Z., Klasnja-Milicevic, A. (eds) Advances in Intelligent Information Hiding and Multimedia Signal Processing. Smart Innovation, Systems and Technologies, vol 212. Springer, Singapore. https://doi.org/10.1007/978-981-33-6757-9_8
Download citation
DOI: https://doi.org/10.1007/978-981-33-6757-9_8
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-6756-2
Online ISBN: 978-981-33-6757-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)