Abstract: A method for training a machine-learning module of a computer-implemented prediction model for predicting product quality parameter values for one or more quality parameters of a chemical product produced by a chemical production plant. The production plant includes a plurality of sensors, each of which is configured to acquire process parameter values for one or more process parameters of a chemical process carried out by the production plant for producing the chemical product during operation of the production plant. A priori information about the production plant and the process carried out by the production plant is used, including chronological sequence information about a chronological sequence of the process carried out within the production plant, for which sensors sensor-specific time shifts between an acquisition time of training process parameter values and a production time of a product unit, during the production of which the corresponding training process parameter value was acquired.

Abstract: Disclosed is a method for producing a titanium containing catalyst, wherein the catalyst includes one or more titanium alpha-hydroxy carboxylate species, e.g., titanium citrate, and one or more titanium oxide species, e.g., TiOx, wherein x is greater than 0 and less than or equal to 2, wherein the sum of all of the above titanium oxide species relative to the sum of all titanium alpha-hydroxy carboxylate species in the titanium containing catalyst is greater than 0 but less than 1.00 mol.-%. The method of production involves, for example, reacting tetraisopropyl orthotitanate with an aqueous solution of citric acid, and removing the byproduct of 2-propanol by distillation. Also disclosed is a method for the production of polyesters by the use of the catalyst.

Abstract: The present invention is directed to a method for the production of a titanium containing catalyst, wherein a titanium-(IV)-alkoxide of high purity is reacted with an alpha-hydroxy carboxylic acid. Furthermore the invention concerns a titanium containing catalyst allowing for the production of high viscosity polyesters with high thermal stability. In addition, the invention is directed to a method for the production of polyesters and polyesters themselves.

Abstract: Provided are a catalyst mixture and also a method for the production of a polyester melt with high viscosity, the granulate obtained therefrom having an intrinsic viscosity of >0.70 dl/g and an L* color >70 and the b* color being between ?5 and +5. The catalysts being used during the production are not based on heavy metals but on titanium compounds. Also no components of catalysts based on heavy metal are added. The granulate can be processed further in any way, e.g. to form bottles, containers, films, foils or fibers.

Abstract: Provided are a catalyst mixture and also a method for the production of a polyester melt with high viscosity, the granulate obtained therefrom having an intrinsic viscosity of >0.70 dl/g and an L* colour >70 and the b* colour being between ?5 and +5. The catalysts being used during the production are not based on heavy metals but on titanium compounds. Also no components of catalysts based on heavy metal are added. The granulate can be processed further in any way, e.g. to form bottles, containers, films, foils or fibres.

Abstract: The invention relates to a polymerization catalyst for preparing polyesters. The catalyst contains aluminium hydroxide and/or aluminium acetate as a first component and at least one phosphoric or phosphonic ester as a second component. The invention also relates to a polymerization process for preparing polyethylene terephthalate from dimethyl terephthalate and ethylene glycol or terephthalic acid and ethylene glycol by transesterification and polycondensation respectively. The invention further relates to the use of aluminium hydroxide and/or aluminium acetate in combination with at least one phosphoric or phosphonic ester as polymerization catalyst when preparing polyesters by polycondensation or transesterification.