Table 6 An evaluation of the accuracy of z (t) using NDsolve and ANN-PSO-NNA for case 1, with \({\varvec{\sigma}}\) = 0.1, R = 0.2 and B = 0.3.

From: Neuro-computing solution for Lorenz differential equations through artificial neural networks integrated with PSO-NNA hybrid meta-heuristic algorithms: a comparative study

t

\({x(t)}_{Numerical}\)

\({\widehat{x}(t)}_{ANN}\)

\({AE(z(t))}_{ANN}\)

0

0

− 4.85E−06

4.8524E−06

0.1

0.000446736

0.000476715

2.99791E−05

0.2

0.001598645

0.001635725

3.70799E−05

0.3

0.003222261

0.003233088

1.08268E−05

0.4

0.0051386

0.005132109

6.49118E−06

0.5

0.007211748

0.007215832

4.08402E−06

0.6

0.009340018

0.009372364

3.2346E−05

0.7

0.011448536

0.011502689

5.41535E−05

0.8

0.013483495

0.013534246

5.07514E−05

0.9

0.015407483

0.015433005

2.55217E−05

1

0.017195735

0.017209134

1.33988E−05