An Integrated Method of Rolling Bearing Fault Diagnosis Based on Convolutional Neural Network Optimized by Sparrow Optimization Algorithm

Table 2

Details of the sample sets.

Running state	Fault diameter	Training samples	Test samples	Status labels
Normal	//	19200	4800	1000000000
Inner race fault	0.1778 mm	19200	4800	0100000000
	0.3556 mm	19200	4800	0000100000
	0.5334 mm	19200	4800	0000000100
Ball fault	0.1778 mm	19200	4800	0010000000
	0.3556 mm	19200	4800	0000010000
	0.5334 mm	19200	4800	0000000010
Outer race fault	0.1778 mm	19200	4800	0001000000
	0.3556 mm	19200	4800	0000001000
	0.5334 mm	19200	4800	0000000001