Decomposition of wide‐angle X‐ray diffraction curves into crystalline peaks and amorphous components is one of the most difficult nonlinear optimization problems. For this reason, the elaboration of a reliable method that provides fast unambiguous solutions remains an important and topical task. This work presents a hybrid system dedicated to this aim, combining two methods of artificial intelligence – evolution strategies and an immune algorithm – with the classical method of Rosenbrock. A combination of the mechanisms of these three methods has given a very effective and convergent algorithm that performs very well a multicriterial optimization. Tests have shown that it is faster to converge and less ambiguous than the genetic algorithm.

No abstract

This paper describes how a combination of two methods of artificial intelligence, an immune algorithm and a genetic algorithm, can be used to recognize a polymer by the shape of its X-ray diffraction curve. To this end, the hybrid algorithm uses a database which contains theoretical functions describing wideangle X-ray diffraction curves of different polymers. These curves are compared by the algorithm with the experimental diffraction curve and the most similar are chosen. Such theoretical curves are kept in the immunological memory, and their parameters can be set as the starting ones in the optimization methods used for decomposition of the experimental curve into crystalline peaks and amorphous component. Using this algorithm, the preparation of the starting parameters is much easier and faster. Decomposition is the most important step in polymer crystallinity determination.

No abstract

No abstract