论文部分内容阅读
针对反应堆堆芯吊篮破裂和吊篮紧固件部分脱落故障信号难以获取问题,提出一种小波包能量特征提取和不确定理论DSm T故障决策的融合方法。测试3种吊篮故障工况的振动信号,利用小波包变换对信号进行分解-重构,提取频段能量构建子带能量特征向量,归一化处理后赋值给DSm T信度函数,使用DSm T信息融合方法在决策层对故障模式进行识别及验证。实验结果表明该方法能够有效辨识吊篮故障模式,具有较高的准确性及泛化能力。
In order to solve the problem that the reactor core basket is broken and the part of the basket fastener detachment failure signal is difficult to obtain, a fusion method of wavelet packet energy feature extraction and DSM T fault decision based on uncertainty theory is proposed. The vibration signal of the three kinds of baskets in fault condition was tested, the signal was decomposed and reconstructed by wavelet packet transform, the energy of the frequency band was extracted to build the sub-band energy eigenvector, normalized and assigned to the DSm T reliability function, and DSm T Information fusion method at the decision-making layer to identify and verify the failure mode. The experimental results show that this method can effectively identify the basket failure mode, with high accuracy and generalization ability.