Research on Prediction Technology of Safety Index of Power Supply System Based on Deep Learning

doi:10.3778/j.issn.1002-8331.2202-0132

Abstract

Abstract: The safety index of high-speed railway power supply system reflects the occurrence trend of failures and accidents in the system, and the regular verification and prediction of the index are of very important practical significance for the comprehensive evaluation and pre-warning of the power supply system. Based on the data of the safety index over ten years, a time series predictive model is proposed, which combines time series statistics and deep learning methods. Firstly, ARIMA（autoregressive integrated moving average model） is used to model the time series of the safety index, and the adjust-R2 of the ARIMA model is improved by introducing the seasonal characteristic variable, verifying the seasonal law of the time series. Secondly, the GRU（gated recurrent unit） neural network is used to predict the time series. Finally, the Pearson coefficient is used to evaluate the effectiveness of the predictive model. The results show that the Pearson coefficients on the training set and test set are respectively 0.71 and 0.74, which proves the effectiveness of the predictive model.

Key words: safety index of power supply system, deep learning, gated recurrent unit, time series prediction

摘要： 高速铁路供电专业安全指数反映了高铁供电故障与事故的发生趋势，对其进行规律验证与预测对于高速铁路现场供电专业安全的综合评估与预警具有非常重要的现实意义。基于高铁十周年供电安全指数数据，提出了一种时间序列深度学习预测模型。该模型结合了时间序列统计建模与深度学习方法。首先利用ARIMA（autoregressive integrated moving average model）方法对安全指数时序数据进行建模，通过引入季节性特征变量，提高模型的修正拟合优度，验证了供电安全指数的季节性规律；然后利用深度学习门控递归单元神经网络对供电安全指数进行预测；最后利用皮尔森系数评价预测模型的有效性。结果表明，利用门控递归单元对供电安全指数的预测值在训练集和测试集上的皮尔森系数分别达到0.71和0.74，可有效拟合安全指数变化趋势。

关键词: 供电安全指数, 深度学习, 门控递归单元, 时间序列预测

PENG Nan, GUO Jianfeng, ZHANG Wenxuan, WANG Jing, TAO Kai, HOU Senquan. Research on Prediction Technology of Safety Index of Power Supply System Based on Deep Learning[J]. Computer Engineering and Applications, 2023, 59(10): 314-320.

彭楠, 郭剑峰, 张文轩, 王婧, 陶凯, 侯森泉. 基于深度学习的供电安全指数预测技术研究[J]. 计算机工程与应用, 2023, 59(10): 314-320.

References

[1] 中华人民共和国交通运输部.2020年铁道统计公报[R/OL].（2021）[2022-01-10].https：//www.mot.gov.cn/tongjishuju/tielu/202104/P020210419530519499260.pdf.
Ministry of Transport of the People’s Republic of China. 2020 railway statistical bulletin[R/OL].（2021）[2022-01-10].https：//www.mot.gov.cn/tongjishuju/tielu/202104/P02021041
9530519499260.pdf.
[2] 程亮.高速铁路牵引供电典型故障分析及对策[J].中国新技术新产品，2017（6）：33-34.
CHENG L.Typical fault analysis and countermeasures of high-speed railway traction power supply[J].China New Technology and New Products，2017（6）：33-34.
[3] 王芳.浅析高铁牵引供电系统常见故障及处理[J].科技创新与应用，2014（9）：136.
WANG F.Analysis of common faults and solutions of high-speed railway traction power supply system[J].Science and Technology Innovation and Application，2014（9）：136.
[4] 高锋，高强，马涛.旋转机械振动状态监测与故障诊断管理[C]//第十届全国设备监测与诊断技术学术会议，2000：273-277.
GAO F，GAO Q，MA T.Rotating machinery vibration condition monitoring and fault diagnosis management[C]//10th National Conference on Equipment Monitoring and Diagnosis Technology，2000：273-277.
[5] 张铭坤，王昕.基于GRU-RNN模型的城市主干道交通时间预测[J].北京信息科技大学学报（自然科学版），2019，34（4）：30-35.
ZHANG M K，WANG X.Traffic time prediction of urban arterial roads based on GRU-RNN model[J].Journal of Beijing Information Science and Technology University（Natural Science Edition），2019，34（4）：30-35.
[6] 许国艳，周星熠，司存友，等.基于GRU和LightGBM特征选择的水位时间序列预测模型[J].计算机应用与软件，2020，37（2）：25-31.
XU G Y，ZHOU X Y，SI C Y，et al.Water level time series prediction model based on GRU and LightGBM feature selection[J].Computer Applications and Software，2020，37（2）：25-31.
[7] 吴肃.基于GRU的柴油发电机组故障诊断与预测的研究[D].苏州：苏州大学，2020.
WU S.Research on fault diagnosis and prediction of diesel generator set based on GRU[D].Suzhou：Suzhou University，2020.
[8] BECERRA-RICO J，ACEVES-FERNANDEZ M A，ESQUIVEL-ESCALANTE K，et al.Airborne particle pollution predictive model using gated recurrent unit（GRU） deep neural networks[J].Earth Science Informatics，2020，13（3）：821-834.
[9] DUTTA A，KUMAR S，BASU M.A gated recurrent unit approach to bitcoin price prediction[J].Journal of Risk and Financial Management，2020，13（2）：23.
[10] UNGUREAN L，MICEA M V，CARSTOIU G.Online state of health prediction method for lithiumion batteries based on gated recurrent unit neural networks[J].International Journal of Energy Research，2020，44（8）：6767-6777.
[11] 何正友，程宏波.高速铁路牵引供电系统健康管理及故障预警体系研究[J].电网技术，2012，36（10）：258-264.
HE Z Y，CHENG H B.Research on health management and fault early warning system of high-speed railway traction power supply system[J].Power Grid Technology，2012，36（10）：258-264.
[12] 郭剑峰，柯在田，王卫东，等.基于数据建模的高速铁路供电故障指数计算方法[J].中国铁路，2020（5）：39-45.
GUO J F，KE Z T，WANG W D，et al.Calculation method of failure index of high-speed railway power supply system based on data modeling[J].China Railway，2020（5）：39-45.
[13] 白玉新.接触网常见故障及对策研究[J].中国铁路，2009，（3）：62-64.
BAI Y X.Research on common faults and countermeasures of catenary[J].China Railway，2009（3）：62-64.
[14] 莫达隆.利用ADF检验对时间序列进行建模[J].时代金融，2010（4）：46-48.
MO D L.Using ADF test to model time series[J].Times Finance，2010（4）：46-48.
[15] BOX G，JENKINS G.Time series analysis：forecasting and control[M].San Francisco：Holden-Day，1970.
[16] 黎维，陶蔚，周星宇，等.时空序列预测方法综述[J].计算机应用研究，2020，37（10）：2881-2888.
LI W，TAO W，ZHOU X Y，et al.Survey of spatiotemporal sequence prediction methods[J].Application Research of Computers，2020，37（10）：2881-2888.
[17] RUMELHART D E，HINTON G E，WILLIAMS R J.Learning representations by back-propagating errors[J].Nature，1986，323（6088）：533-536.
[18] HOCHREITER S，SCHMIDHUBER J.Long short-term memory[J].Neural Computation，1997，9（8）：1735-1780.
[19] CHO K，MERRIENBOER B V，GULCEHRE C，et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing，Doha，2014：1724-1734.
[20] CHUNG J，GULCEHRE C，CHO K，et al.Empirical evaluation of gated recurrent neural networks on sequence modeling[J].arXiv：1412.3555，2014.
[21] GRUBER N，JOCKISCH A.Are GRU cells more specific and LSTM cells more sensitive in motive classification of text?[J].Frontiers in Artificial Intelligence，2020，3：40-48.
[22] 费致根，吴志营，肖艳秋，等.基于Adam优化算法的双目机器人手眼标定方法[J].机床与液压，2021，49（11）：26-30.
FEI Z G，WU Z Y，XIAO Y Q，et al.Hand-eye calibration method of binocular robot based on Adam optimization algorithm[J].Machine Tool and Hydraulics，2021，49（11）：26-30.