The sensitivity functions are calculated along with the state variables and the bound of the region of parametric sensitivity is drawn by the maximum of the sensitivity of the particle temperature at the hot spot.
The robust controller, for his part, is then applied to adaptively estimate an unknown upper bound of the time-varying parametric uncertainties, external disturbances and approximation error of the neural network system.
Amini et al. [6, 7] introduced new IPMs based on parametric versions of kernel functions in [3] and obtained the better iteration bounds than the bound of the algorithm in [3] with numerical tests.
Thus, a non-parametric upper bound of the ICER is 334.
An ad hoc identification procedure is presented which allows estimating not only a nominal parametric process model, but also a bound of the model uncertainty (i.e. modelling errors).
To this aim, two fundamental concepts parametric bound of convergence (PBoC) and parametric convergence margin (PCM) are proposed, which are related to the conditions, under which a given NARX model can be approximated by a convergent Volterra series, in terms of system characteristic parameters including model parameters (of interest), input magnitude, and frequency.
In this algorithm, a new parametric linearized technique is proposed for generating parametric linear relaxation programming (PLRP) of the NQP, which can be used to determine the lower bound of global minimum value of the NQP.
The asymptotic information and lower bound for estimating the parametric regression parameter are calculated based on the effective score, which is obtained by determining the component of the parametric score orthogonal to the space generated by the infinite-dimensional nuisance parameter.
The results of the parametric studies are discussed below.
Because of the parametric resampling of the link weights, this method formally falls under parametric bootstrapping.
The results of the non-parametric Mann-Whitney U test were consistent with those of the parametric analyses.
