A Fault Identification Method for Electric Submersible Pumps Based on DAE-SVM

Table 3

.Parameters’ selection.

No.	Parameter	Scope
1	Optimization algorithm	SGD, Adagrad, AdaDelta, RMSProp, and Adam
2	Learning rate	[0.01, 0.02, 0.03, 0.04, 0.05, 0.06]
3	Batch size	[4, 8, 16, 32, 64, 128]
4	Denoising parameter	[0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0]