In this paper, crosstalk sensitivity analysis of a microwave coupled-line structure due to the fabrication imperfections is investigated using Least Square-Support Vector Machine (LS-SVM) method. Since LS-SVM uses a set of linear equations instead of a convex quadratic programming problem, the computational cost is extremely reduced compared to that of the well-known Monte Carlo (MC) analysis or even Support Vector Machine (SVM) without decreasing the accuracy. Using this method, the geometrical parameters of the coupled-line are assumed to be randomly distributed using the Latin Hypercube function and the variation range of each parameter is set to± 50% around its central value. The frequency response of the coupled-line is estimated and compared with those of the measured and simulation ones for a few well-known practical case studies. The results show that the LS-SVM procedure quickly predicts the worst-case crosstalk expectation values and accurately anticipates the probability of obtaining various outcomes of the coupled-line for the specifed parameter variation over a wide frequency range.

Keywords