Abstract: Disclosed herein is a computer-implemented method for training a data-driven model for predicting properties of a chemical mixture. The method includes the steps of obtaining data including history and/or calibration data of a plurality of chemical mixture recipes and properties of each chemical mixture recipe, with each chemical mixture recipe including two or more ingredients, assigning at least one ingredient in each chemical mixture recipe to one of pre-defined substance clusters, each pre-defined substance cluster representing one ingredient or a group of ingredients having similar chemistry, revising each chemical mixture recipe by replacing the at least one ingredient with the assigned pre-defined substance cluster, and providing the revised chemical mixture recipes, together with the properties of the chemical mixture recipes, to a machine learning process in order to train a data-driven model, which is usable for predicting characteristics of properties of a new chemical mixture.

Abstract: Described herein is a process for producing an effect pigment paste including at least steps (1) and (2), namely producing a mixture including at least one effect pigment (a) and at least one polymer (b) in a liquid medium (c) (step (1)), and dispersing the mixture obtained after step (1) to obtain the effect pigment paste (step (2)), where step (2) is performed using a shaker and the effect pigment paste obtained after the performance of step (2) has ended is free of grinding media. Also described herein are an effect pigment paste producible by this process, containing an amount of effect pigment of at least 5% by weight, based on the total weight of the effect pigment paste, and a method of using a shaker for dispersing of effect pigments for production of an effect pigment paste.

Abstract: Method of analyzing and optimizing a multistage manufacturing process which includes a number of standard steps that are carried out identically and which are followed by tuning steps that are carried out in order to achieve predefined product properties, their type, number and exit being variable. The individual steps relate to at least one production-specific property an are recorded quantitatively in an electronic database. The property can be, for example, a proportion of the quantities, a proportion of the costs, or the effects of an individual step on a product property to be achieved. Examples of a multistage manufacturing process are the manufacture of a coating from a plurality of individual components and additives. With the aid of the information compiled in a database, individual steps can be reduced in terms of their number and their extent.