Insulation Diagnosis of Service Aged XLPE Power Cables Using Statistical Analysis and Fuzzy Inference  

作　　者：LIU Fei JIANG Pingkai LEI Qingquan ZHANG Li SU Wenqun 

机构地区：[1]Shanghai Key Laboratory of Electrical Insulation and Thermal Aging, Department of Polymer Science and Engineering,Shanghai Jiao Tong University, Shanghai 200240, China [2]Shanghai Electric Power Company, Shanghai 200122, China

出　　处：《高电压技术》2013年第8期1932-1940,共9页High Voltage Engineering

基　　金：Project supported by National Natural Science Foundation of China（51277117）, Shang- hai Science and Technology Comrmssion（11 DZ2283000）.

摘　　要：Cables that have been in service for over 20 years in Shanghai, a city with abundant surface water, failed more frequently and induced different cable accidents. This necessitates researches on the insulation aging state of cables working in special circumstances. We performed multi-parameter tests with samples from about 300 cable lines in Shanghai. The tests included water tree investigation, tensile test, dielectric spectroscopy test, thermogravimetric analysis (TGA), fourier transform infrared spectroscopy (FTIR), and electrical aging test. Then, we carried out regression analysis between every two test parameters. Moreover, through two-sample t-Test and analysis of va- riance (ANOVA) of each test parameter, we analyzed the influences of cable-laying method and sampling section on the degradation of cable insulation respectively. Furthermore, the test parameters which have strong correlation in the regression analysis or significant differ- ences in the t-Test or ANOVA analysis were determined to be the ones identifying the XLPE cable insulation aging state. The thresholds for distinguishing insulation aging states had been also obtained with the aid of statistical analysis and fuzzy clustering. Based on the fuzzy in- ference, we established a cable insulation aging diagnosis model using the intensity transfer method. The results of regression analysis indicate that the degradation of cable insulation accelerates as the degree of in-service aging increases. This validates the rule that the in- crease of microscopic imperfections in solid material enhances the dielectric breakdown strength. The results of the two-sample t-Test and the ANOVA indicate that the direct-buried cables are more sensitive to insulation degradation than duct cables. This confirms that the tensile strength and breakdown strength are reliable functional parameters in cable insulation evaluations. A case study further indicates that the proposed diagnosis model based on the fuzzy inference can reflect the comprehensive aging state of cablCables that have been in service for over 20 years in Shanghai, a city with abundant surface water, failed more frequently and induced different cable accidents. This necessitates researches on the insulation aging state of cables working in special circumstances. We performed multi-parameter tests with samples from about 300 cable lines in Shanghai. The tests included water tree investigation, tensile test, dielectric spectroscopy test, thermogravimetric analysis （TGA）, fourier transform infrared spectroscopy （FTIR）, and electrical aging test. Then, we carried out regression analysis between every two test parameters. Moreover, through two-sample t-Test and analysis of va- riance （ANOVA） of each test parameter, we analyzed the influences of cable-laying method and sampling section on the degradation of cable insulation respectively. Furthermore, the test parameters which have strong correlation in the regression analysis or significant differ- ences in the t-Test or ANOVA analysis were determined to be the ones identifying the XLPE cable insulation aging state. The thresholds for distinguishing insulation aging states had been also obtained with the aid of statistical analysis and fuzzy clustering. Based on the fuzzy in- ference, we established a cable insulation aging diagnosis model using the intensity transfer method. The results of regression analysis indicate that the degradation of cable insulation accelerates as the degree of in-service aging increases. This validates the rule that the in- crease of microscopic imperfections in solid material enhances the dielectric breakdown strength. The results of the two-sample t-Test and the ANOVA indicate that the direct-buffed cables are more sensitive to insulation degradation than duct cables. This confirms that the tensile strength and breakdown strength are reliable functional parameters in cable insulation evaluations. A case study further indicates that the proposed diagnosis model based on the fuzzy inference can reflect the comprehensive aging s

关 键 词：交联聚乙烯绝缘电力电缆 模糊推理 统计分析 诊断服务 傅立叶变换红外光谱 电缆绝缘层 老化状态 电击穿强度 

分 类 号：TM247.1[一般工业技术—材料科学与工程] TP18[电气工程—电工理论与新技术]