为了快速准确定位脑电图在较多种类干扰下的故障特征,本文提出一种基于Hilbert-Huang时频谱特征提取的脑电图机干扰故障检测方法.运用信号采集技术进行脑电图机的诊断数据采集并进行信号拟合,采用二阶自适应IIR陷波器进行脑电图机采集信号的干扰滤波提纯处理,对提纯输出的信号进行时频分析,通过经验模态分解将复杂的脑电图机故障分析信号分解成若干个固有模态函数,对每个固有模态分量作Hilbert-Huang变换,实现Hilbert-Huang时频谱特征提取,以提取的特征量作为训练样本,实现脑电图机中的干扰故障检测.仿真结果表明,采用该方法进行脑电图机中的干扰故障检测的准确性较好,抗干扰能力较强,具有较好的故障诊断能力.%To locate the malfunction characteristics of the electroencephalogram (EEG) quickly and accurately under many kinds of interference, the present study proposed an EEG detection method based on the spectrum feature of hilbert-huang. The signal collection technology was used for the diagnosis of EEG machine data acquisition and signal fitting.The second-order adaptive IIR trapper collection was applied to perform the EEG signal interference filter purification processing, and the time-frequency analysis was carried out on the purification of the output signal. EEG machine fault signal was decomposed into several intrinsic mode functions through the empirical mode decomposition analysis, and each intrinsic mode components was conducted a Hilbert Huang transform to realize the Hilbert Huang-spectrum feature extraction. The interference of EEG machine fault detection was finally realized by using the extracted characteristic as the training sample. The results of simulation showed that using this method to interfere with the accuracy of the fault detection of EEG machine was good, which had a strong anti-jamming capability and good ability of fault diagnosis.
展开▼
