基于频域盲解卷积的机械设备状态监测与故障诊断

在介绍频域盲解卷积（FDBD）模型的基础上，重点论述了其在工程信号特征提取中的关键技术：抑制循环—部分卷积误差的方法、次序不确定性的消除方法以及复数域盲分离算法的原理和应用。针对复杂环境或复杂机械设备结构中声、振信号的特征提取，全面综述了频域盲解卷积技术在机械设备状态监测和故障诊断中的研究现状，利用声学实验验证了其实际应用价值。论文最后指出了未来需要进一步研究的主要问题。

Mechanical equipment condition monitoring and fault diagnosis based on frequency-domain blind deconvolution

basis of introducing the model of Frequency-Domain Blind Deconvolution (FDBD), key techniques in engineering signal feature extraction were comprehensively related and analyzed in this paper, which include the methods of suppressing difference between circular and partial convolution, the methods of removing permutation indeterminacy, the applications of Complex-Domain Blind Separation Algorithms. Aimed at vibration and acoustic signal feature extraction in complex environment and equipment with complex mechanical structures, and the application values of FDBD and its research status in machinery condition monitoring and fault diagnosis were reviewed and summarized, the practical application value was verified by acoustics experiment. Finally, the main problems which need to be studied further in this area were pointed out.