Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Suddenly expanded flow field [1, 2].

More »

Fig 1 Expand

Fig 2.

Test jet apparatus [8].

More »

Fig 2 Expand

Fig 3.

Schematic of the experimental set up [16].

More »

Fig 3 Expand

Table 1.

Details of operating conditions for the ANN model.

More »

Table 1 Expand

Fig 4.

ANN model with input, hidden, and output layers.

More »

Fig 4 Expand

Fig 5.

Flowchart for ANN training.

More »

Fig 5 Expand

Fig 6.

Variation of β w.r.t M without control (WC) and with control (WC) for different η = 1.2, 1.5, and 1.8 for fixed α = 4.75 and γ = 8.

More »

Fig 6 Expand

Fig 7.

Variation of β w.r.t M without control (WC) and with control (WC) for different γ = 2, 6, and 10 for fixed α = 4.75 and η = 1.5.

More »

Fig 7 Expand

Fig 8.

Variation of β w.r.t α for without control (WC) and with control (WC) for different M = 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, and 0.9 for fixed γ = 8 and η = 1.5.

More »

Fig 8 Expand

Fig 9.

Variation of ω w.r.t δ for M = 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, and 0.9 for constant η = 1.5, α = 4.75 for (a) γ = 7, (b) γ = 4.

More »

Fig 9 Expand

Fig 10.

Variation of ω with respect to δ without control (WC) and with control (WC) for different η = 1.2, 1.5, and 1.8 at constant M = 0.6, α = 4.75 for (a) γ = 6, (b) γ = 10.

More »

Fig 10 Expand

Fig 11.

Variation of ω with respect to δ without control (WC) and with control (WC) for different α = 3.25, 4.75, and 6.25 at constant M = 0.6, η = 1.5, and γ = 8.

More »

Fig 11 Expand

Fig 12.

Network of input and outputs used in the study.

More »

Fig 12 Expand

Table 2.

ANN model parameters for training.

More »

Table 2 Expand

Fig 13.

ANN testing and training result for (β) based on the 6-5-1 network architecture.

More »

Fig 13 Expand

Fig 14.

ANN testing and training result for (ω) based on the 6-4-1 network architecture.

More »

Fig 14 Expand

Fig 15.

Gradient plot for the (β) network output.

More »

Fig 15 Expand

Fig 16.

Gradient plot for the (ω) network output.

More »

Fig 16 Expand

Table 3.

ANN performance results for β and ω.

More »

Table 3 Expand

Fig 17.

Regression coefficient (R2) for (β)—(a) Training data, (b) Testing data.

More »

Fig 17 Expand

Fig 18.

Regression coefficient (R2) for (ω)—(a) Training data, (b) Testing data.

More »

Fig 18 Expand

Fig 19.

Comparison of experimental and ANN predicted results for (β).

More »

Fig 19 Expand

Fig 20.

Comparison of experimental and ANN predicted results for (ω).

More »

Fig 20 Expand

Table 4.

Experimental and ANN predicted result comparison for β and ω.

More »

Table 4 Expand

Table 5.

Comparison the literature with the present study.

More »

Table 5 Expand

Fig 21.

Sensitivity of input variable for (a) β and (b) ω.

More »

Fig 21 Expand

Table 6.

Weights and biases for the ANN model (β).

More »

Table 6 Expand

Table 7.

Weights and biases for the ANN model (ω).

More »

Table 7 Expand

Fig 22.

Histogram plot of the β for the case of (a)WoC, (b) WC, and (c) ω (WoC).

More »

Fig 22 Expand