说明：  针对矿井主通风机振动信号的非平稳性导致故障特征准确提取困难的问题，提出 依据转速变化幅度分工况进行特征提取的思路，将非平稳工况分为转速波动和变转速 两种。针对转速波动工况，采用小波包分解提取不同故障下振动信号频带能量作为故障 特征;针对变转速工况，采用阶次分析将时域非平稳信号转为角域伪平稳信号，对比不 同故障信号角域特征得到故障特征参量。通过两种方法的结合，实现非平稳工况下矿井 主通风机的振动故障特征精确提取。
(Aiming at the problem that it is difficult to extract fault features accurately due to the non-stationary vibration signal of mine main fan, this paper puts forward a new method The non-stationary condition is divided into speed fluctuation and variable speed Two. According to the condition of speed fluctuation, wavelet packet decomposition is used to extract the frequency band energy of vibration signal under different faults as fault The order analysis is used to transform the time domain non-stationary signal into the angle domain pseudo-stationary signal under the condition of variable speed The fault characteristic parameters are obtained from the angle domain characteristics of the fault signal. Through the combination of the two methods, the mine under non-stationary working conditions is realized The vibration fault feature of main fan is extracted accurately.)