A mixture of experts network structure construction algorithm for modelling and control

This paper introduces a new fast, effective and practical model structure construction algorithm for a mixture of experts network system utilising only process data. The algorithm is based on a novel forward constrained regression procedure. Given a full set of the experts as potential model bases, the structure construction algorithm, formed on the forward constrained regression procedure, selects the most significant model base one by one so as to minimise the overall system approximation error at each iteration, while the gate parameters in the mixture of experts network system are accordingly adjusted so as to satisfy the convex constraints required in the derivation of the forward constrained regression procedure. The procedure continues until a proper system model is constructed that utilises some or all of the experts. A pruning algorithm of the consequent mixture of experts network system is also derived to generate an overall parsimonious construction algorithm. Numerical examples are provided to demonstrate the effectiveness of the new algorithms. The mixture of experts network framework can be applied to a wide variety of applications ranging from multiple model controller synthesis to multi-sensor data fusion.

Modelling and control of Hammerstein system using B-spline approximation and the inverse of De Boor algorithm

In this article a simple and effective controller design is introduced for the Hammerstein systems that are identified based on observational input/output data. The nonlinear static function in the Hammerstein system is modelled using a B-spline neural network. The controller is composed by computing the inverse of the B-spline approximated nonlinear static function, and a linear pole assignment controller. The contribution of this article is the inverse of De Boor algorithm that computes the inverse efficiently. Mathematical analysis is provided to prove the convergence of the proposed algorithm. Numerical examples are utilised to demonstrate the efficacy of the proposed approach.

π-dimerization of pleiadiene radical cations at low temperatures revealed by UV–vis spectroelectrochemistry and quantum theory

One-electron oxidation of the non-alternant polycyclic aromatic hydrocarbon pleiadiene and related cyclohepta[ c,d]pyrene and cyclohepta[c,d]fluoranthene in THF produces corresponding radical cations detectable in the temperature range of 293–263 K only on the subsecond time scale of cyclic voltammetry. Although the EPR-active red-coloured pleiadiene radical cation is stable according to the literature in concentrated sulfuric acid, spectroelectrochemical measurements reported in this study provide convincing evidence for its facile conversion into the green-coloured, formally closed shell and, hence, EPRsilent π-bound dimer dication stable in THF at 253 K. The unexpected formation of the thermally unstable dimeric product featuring a characteristic intense low-energy absorption band at 673 nm (1.84 eV; logεmax=4.0) is substantiated by ab initio calculations on the parent pleiadiene molecule and the PF6 − salts of the corresponding radical cation and dimer dication. The latter is stabilized with respect to the radical cation by 14.40 kcal mol−1 (DFT B3LYP) [37.64 kcal mol−1 (CASPT2/DFT B3LYP)]. An excellent match has been obtained between the experimental and TDDFT- calculated UV–vis spectra of the PF6 − salt of the pleiadiene dimer dication, considering solvent (THF) effects.