Improved Hybrid Response Surface Method Based on Double Weighted Regression and Vector Projection

In order to increase the accuracy and stability of the classical response surface method and relevant method, a new improved response surface method based on the idea of double weighting factors and vector projection method is proposed. The response surface is fitted by the weighted regression technique, which allows the sampling points to be weighted by their distance from the true failure surface and that from the estimated design point. It uses the vector of the gradient projection method to get new sampling points in the process of iteration, in order to make the sampling points closer to the design point, and the value of deviation coefficient is constantly adjusted. To some extent, these strategies increase the accuracy and stability of the response surface method, while the calculation time is decreased. At last, the rationality and efficiency of the proposed method are demonstrated through five examples. Besides, as revealed from this investigation, compared with other conventional algorithms, this method has a few obvious advantages; this algorithm not only has high precision and efficiency, but also has solid stability.