基于熵权模糊物元和主元分析的变压器状态评价

摘要

Aiming at the problem of the transformer condition assessment of each index in the uncertainty, fuzziness and too many transformer on-line monitoring state information, this paper puts forward a new method of transformer condition assessment based on entropy fuzzy matter-element and principal component analysis. Citing the information entropy which reflects value of the data itself to compute the weight coefficient of index, setting up the model of entropy fuzzy matter-element, and employing principal component analysis method to extract the main components in the information data which effectively solves the difficulty of weight allocation and on-line monitoring state quantity too much. Finally, combined with examples, the validity and practicability of the method is verified.%针对变压器状态评价中各指标的不确定性、模糊性以及变压器在线监测状态量信息过多的问题，提出一种基于熵权模糊物元和主元分析的变压器状态评估新方法。引用信息熵反映数据本身的效用值来计算指标的权重系数，建立了基于熵权模糊物元模型。并采用主元分析法提取了信息数据中的主成分，有效解决了权重分配困难和在线监测状态量过多的问题。最后结合实例分析，验证了所提方法的有效性和实用性。