论文部分内容阅读
电容型设备介质损耗因数(tanδ)的在线监测会受到环境因素(温度、湿度、污秽等)的影响,对其进行合理修正非常必要。根据人工气候室内变压器套管tanδ的在线测量试验结果,分析了环境因素对电容型设备tanδ的影响情况,提出了基于最小二乘支持向量机的主要环境因素对tanδ影响的修正模型,并采用遗传算法优化了支持向量机的参数。该模型可用于将非标准大气条件下电容型设备的tanδ测量值修正为标准大气条件下的值,排除环境因素影响,增加在线监测结果的可比性,实际的修正结果验证了该方法的有效性。
Capacitive device dielectric loss tangent (tan δ) on-line monitoring will be affected by environmental factors (temperature, humidity, contamination, etc.), it is necessary to make a reasonable correction. According to the on-line measurement results of indoor tanδ of indoor transformer casing in artificial climate, the influence of environmental factors on tanδ of capacitive equipment is analyzed, and the correction model of main environmental factors affecting tanδ based on least squares support vector machine is proposed. The algorithm optimizes the parameters of SVM. This model can be used to correct the measured value of tanδ in capacitance-type equipment under non-standard atmospheric conditions to standard atmospheric conditions to exclude the influence of environmental factors and increase the comparability of on-line monitoring results. The actual correction results verify the effectiveness of the method .