变压器油中颗粒污染物的中红外光谱检测

陈彬; 韩超; 刘阁

doi:doi:10.3788/gzxb20164505.0530002

光子学报, 2016, 45 (5): 0530002, 网络出版: 2016-06-06

变压器油中颗粒污染物的中红外光谱检测

Detection on Particulate PollutantinTransformer oil Based on the Mid-Infrared Spectrum

论文大纲

陈彬 ^*韩超刘阁

作者单位

重庆工商大学废油资源化技术与装备工程研究中心, 重庆 400067

摘要

配制了含不同颗粒污染等级的变压器油样, 利用中红外光谱扫描获得油样的红外光谱数据, 再采用连续投影算法提取油样红外光谱的有效波长变量, 分别应用偏最小二乘法和支持向量机法方法建立了颗粒污染等级与中红外光谱有效波长的模型.所配置的油样红外光谱经过连续投影算法提取的有效波长具有特定颗粒污染物特征波长的特点, 所建两种模型的预测效果均优于全谱的偏最小二乘法和支持向量机法模型, 对验证集样本数据预测的决定系数分别为0.892 9、0.934 3, 均方根误差为6.372×10－3、3.07×10－3, 获得了较好的预测效果, 为变压器油中颗粒物的检测提供了借鉴.

Abstract

The different particle pollution degree in transformer oil samples were made up, the infrared spectrum data of the oil samples were acquired by using the infrared spectrum scanning. Using the successive projections algorithm, the effective wavelength variables of the oil samples were extracted. Based on the extracted wavelength variables, two models of both the effective wavelength of the infrared spectrum and the particle contamination pollution degree were established by using partial least squares and support vector machine method. The effective wavelength of successive projections algorithm extracted from the infrared spectrum of transformer oil samples has the characteristics of the wavelength of specific particle contamination, and the prediction effects of the models are better than partial least squares model and support vector machine model using the full infrared spectrum data of the oil samples. Besides, the determination coefficient of the prediction set of oil samples are 0.892 9, 0.934 3 respectively with the two models, and the root mean square error are 6.372×10－3、3.07×10－3 respectively, thereby the satisfactory prediction results has achieved, these provide a reference for the detection of the particle contamination in transformer oil.

参考文献

[1] RODRIGUEZD M , AGUILAR FJA, WROBEL K, et al. Spectrophotometric assay for copper and iron in transformer oil using partial least squares regression (PLS2)［J］. IEEE Transactions on Dielectrics & Electrical Insulation, 2007, 13(6): 1272-1277.

[2] YANG D W, WU J J, YUAN D,et al.Determination of micro copper in transformer oil by FAAS［J］. Chinese Journal of Spectroscopy Laboratory, 2013, 30(1): 216-219.

[3] AKSHATHAA, KUMAR R, SUNDARA R J, et al. Copper corrosion phenomenon in transformers due to DBDS in mineral transformer oil［C］. Electrical Insulation and Dielectric Phenomena (CEIDP) 2013 IEEE Conference, 2013: 826-829.

[4] WU D, HE Y, SHI J H, et al. Exploring near and mid-infrared spectroscopy to predict trace iron and zinc contents in powdered milk ［J］. Journal of Agricultural and Food Chemistry, 2009, 57(5): 1697-1704.

[5] WU D, CHEN X J, SHI P Y,et al. Determination of alpha-linoleic acid and linoleic acid in edible oils using near-infrared spectroscopy improved by wavelet transform and uninformative variable elimination［J］.Analytical Chimica Acta, 2009, 634(2): 166-171.

[6] 严衍禄,赵龙莲,韩东海,等.近红外光谱分析基础与应用［M］.北京: 中国轻工业出版社,2005.

YAN Yan-lu,ZHAO Long-lian.HAN Dong-hai,et al.Basic and application of near infrared spectrum analysis［M］. China Light Industry Press,Beijing, 2005

[7] VANF R, SEDMAN J, YAYLAYAN V, et al. Determination of acid number and base number in lubricants by Fourier transform infrared spectroscopy.［J］. Applied Spectroscopy, 2003, 57(11): 1425-1431.

[8] CANECA A R, PIMENTEL M F, MATTA C E D,et al. Assessment of infrared spectroscopy and multivariate techniques for monitoring the service condition of diesel-engine lubricating oils.［J］. Talanta, 2006, 70(2): 344-352.

[9] JEREMY A, INGELA P. Quantifying colocalization by correlation: the pearson correlation coefficient is superior to the mander's overlap coefficient［J］.International Society for Advancement of Cytometry, 2010, 77a(8): 733-742.

[10] 陈彬,武宏阳,韩超,等.用中红外光谱法分析含微水绝缘油的粘度［J］.光子学报,2015, 44(6): 119-124.

CHEN Bin, WU Hong-yang, HAN Chao, et al. Viscosity of insulating oil with trace water based on the mid-infrared spectral analysis ［J］. Acta Photonica Sinica, 2015, 44(6): 119-124.

[11] 陈彬,刘阁.基于近红外光谱的润滑油中含水量T-S模糊辨识［J］.光子学报,2014, 43(2): 0230001.

CHEN Bin, LIU Ge. Analysis on near infrared spectroscopy of water content in oil using t-s fuzzy identifying model［J］.Acta Photonica Sinica, 2014, 43(2): 0230001.

[12] 张瑜,吴迪,何勇,等.基于可见-近红外光谱技术的润滑油酸值无损检测方法研究［J］.红外,2011, 32(12): 39-44.

ZHANG Yu, WU Di, HE Yong,et al. Non-invasive measurement of acidvalue of lubricant using visible and near infrared spectroscopy ［J］. Infrared, 2011, 32(12): 39-44.

[13] LANGSHOLT M, ZARRUK G A. Particle transport in semi-dilute turbulent pipe flow［J］. Journal of Dispersion Science and Technology, 2015, 36(10): 1513-1526.

[14] 陈彬,刘阁,张贤明.连续投影算法的润滑油中含水量的近红外光谱分析［J］.红外与激光工程,2013, 42(12): 3168-3174.

CHEN Bin, LIU Ge, ZHANG Xian-ming.Analysis on near infrared spectroscopy of water content in lubricating oil using successive projections algorithm［J］.Infrared & Laser Engineering, 2013, 42(12): 3168-3174.

[15] 陈彬,武宏阳,刘阁,等.含绝缘油表面张力的中红外光谱检测［J］.光学精密工程,2015, 23(9): 2452-2458.

Foundation item: The National Natural Science Foundation of China (No.51375516), Chongqing Research Program of Basic Research and Frontier Technology (Nos.cstc2014jcyjA90015, cstc2013jcyjA90021)

CHEN Bin, WU Hong-yang, LIU Ge,et al.Detection on interfacial tension of insulating oil with trace water based on mid-infrared spectroscopy［J］. Optics and Precision Engineering, 2015, 23(9): 2452-2458.

陈彬, 韩超, 刘阁. 变压器油中颗粒污染物的中红外光谱检测[J]. 光子学报, 2016, 45(5): 0530002. CHEN Bin, HAN Chao, LIU Ge. Detection on Particulate PollutantinTransformer oil Based on the Mid-Infrared Spectrum[J]. ACTA PHOTONICA SINICA, 2016, 45(5): 0530002.

变压器油中颗粒污染物的中红外光谱检测

关于本站 Cookie 的使用提示

全站搜索

变压器油中颗粒污染物的中红外光谱检测

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索