Table 5 Utilized DNN parameters.

From: UAV propeller fault diagnosis using deep learning of non-traditional χ2-selected Taguchi method-tested Lempel–Ziv complexity and Teager–Kaiser energy features

Parameter

Value

Number of hidden layers

3

Number of neurons in first hidden layer

100

Number of neurons in second hidden layer

50

Number of neurons in third hidden layer

25

Activation function

Hyperbolic Tangent (tanh)

Solver

Adam (adaptive moment estimation)

Number of iterations

1000

Learning rate

0.001

Batch size

32

Loss function

Cross-entropy

Regularization technique

L2 regularization

Initialization method

He initialization

Back to article page