Applying Adaptive Neural Fuzzy Inference System to Improve Concrete Strength Estimation in Ultrasonic Pulse Velocity Tests

Table 1

Network model parameter setting.

Network parameters of the project	Explanation
Internet usage examples model	Backpropagation neural network
Sample selection (exemplars)	Training group	232 set of data
	Cross validation group	20 set of data
	Test group	60 set of data
The number (hidden layers)	Layer 1 and layer 2
Transfer	Tanh Axon
Learning rule	Levenberg Marqua
Maximum epochs	The default value is 200, increased by the amount
Termination	(1) The minimum tolerable range (MSE)
	(2) The maximum training period (epochs)
Cumulative weights update method	Batch