论文部分内容阅读
随着变压器状态监测技术的发展,获得的变压器状态信息种类也越来越多。为此,提出了多信息融合的变压器健康状态评估方法。该方法通过融合粗糙集、神经网络和D-S证据理论,解决了因变压器信息参数繁多而造成的网络结构复杂和庞大等一系列问题,也为D-S证据理论中的基本可信度分配提供了有效的依据。实例表明,该方法具有较高的诊断准确性和可靠性。
With the development of transformer condition monitoring technology, more and more types of transformer status information are obtained. To this end, proposed multi-information fusion transformer health assessment. This method solves a series of problems caused by complicated and huge network parameters due to the variety of information parameters of the transformer through the fusion of rough sets, neural networks and DS evidence theory. It also provides an effective method for the basic credibility distribution in DS evidence theory in accordance with. The example shows that the method has high diagnostic accuracy and reliability.