作者: Junaid Ali Khan , Muhammad Asif Zahoor Raja , Ijaz Mansoor Qureshi
DOI: 10.1088/0256-307X/28/11/110205
关键词: Statistical analyses 、 Reliability (statistics) 、 Van der Pol oscillator 、 Algorithm 、 Computer science 、 Simulated annealing 、 Artificial neural network 、 Time domain
摘要: We investigate the continuous time domain numerical treatment of a van der Pol oscillator, applying trial solution as an artificial feed-forward neural network model containing unknown adjustable parameters. The optimization is performed by simulated annealing in unsupervised method. proposed scheme tested successfully its application both non-stiff and stiff conditions. Its reliability effectiveness validated through comprehensive statistical analyses. obtained results are good agreement with classical RK45