基于牵引网的电参数波形异常识别方法、装置、设备
By integrating autoencoders and discriminators in the network to perform similarity discrimination and prediction probability normalization on electrical parameter waveform data, the problem of false detection of abnormal electrical phenomena in the traction network of electrified railways is solved, and efficient and accurate anomaly identification is achieved.
CN122413221APending Publication Date: 2026-07-17SHUOHUANG RAILWAY DEV +1
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHUOHUANG RAILWAY DEV
- Filing Date
- 2026-04-22
- Publication Date
- 2026-07-17
Smart Images
Figure CN122413221A_ABST
Abstract
本申请涉及一种基于牵引网的电参数波形异常识别方法、装置、设备。方法包括：获取列车牵引网的电参数波形数据集；将电参数波形数据集中所包括的电参数波形数据，分别输入到集成网络中多个不同子网络中，得到各子网络各自输出的预测概率；对各子网络各自输出的预测概率进行归一化处理，得到集成网络的输出概率，并确定输出概率的可信度；在可信度超过预设阈值的情况下，根据预测概率得到电参数波形数据的异常识别结果。采用本方法能够减少误检测、提高检测准确性。
Need to check novelty before this filing date? Find Prior Art