Fault Diagnosis of Rotating Machinery Based on Multisensor Information Fusion Using SVM and Time-Domain Features

Table 1

The statistic features in time domain.

Code name	Feature	Equation
𝑓1	Mean (𝑥)	1𝑥=𝑛∑|𝑥𝑖|
𝑓2	Peak (𝑥𝑝)	𝑥𝑝=max(|𝑥𝑖|)
𝑓3	Amplitude square (𝑥𝑒)	𝑥𝑒=∑^𝑛𝑖=1𝑥𝑖^2
𝑓4	Root mean square (𝑥rms)	𝑥rms=1𝑛^𝑛𝑖∑=1𝑥𝑖^21/2
𝑓5	Root amplitude (𝑥𝑟)	𝑥𝑟=1𝑛^𝑛𝑖∑=1|𝑥𝑖|^1/22
𝑓6	Standard deviation (𝑥std)	𝑥std=1𝑛−1^𝑛𝑖∑=1(𝑥𝑖−𝑥)^21/2
𝑓7	Skewness (𝑥ske)	𝑥ske=∑^𝑛𝑖=1(𝑥𝑖−𝑥)^3(𝑛−1)𝑥std^3
𝑓8	Kurtosis (𝑥kur)	𝑥kur=∑^𝑛𝑖=1(𝑥𝑖−𝑥)^4(𝑛−1)𝑥std^4
𝑓9	Waveform factor (SF)	𝑥SF=^rms𝑥
𝑓10	Peak factor (CF)	𝑥CF=^𝑝𝑥rms
𝑓11	Pulse factor (IF)	𝑥IF=^𝑝𝑥
𝑓12	Margin factor (CIF)	𝑥CIF=^𝑝𝑥𝑟

𝑥_𝑖 in the table is discrete time series signal.