Необходимость вовлечения в переработку техногенных отходов-железистых песков Павлодарского алюминиевого завода-связана не только с охраной окружающей среды, но и с потребностью увеличения производства глинозема, комплексной утилизаций отходов и нормализации процесса спекания. Для эффективного использования высокожелезистых бокситов на ранней стадии процесса проводят максимальное отделение железистых соединений от основной массы боксита. Поток железистых песков, направляемых в отвал, составляет примерно 10 % от общего потока боксита, поступающего в процесс, в данном случае-50 т/ч. В нем содержится до 60 % оксида железа и 17 % оксида алюминия, который безвозвратно теряется, снижая общее извлечение глинозема из боксита. Для вовлечения техногенных отходов в производственный процесс были проведены детальные физико-химические исследования состава железистого песка: рентгенографический, оптический, термический и химический анализы фракций от +1 до-0,15 мм.

The article describes the use of digital twins in socio-economic processes using the example of predictive asset maintenance management. For this, the architecture of a distributed forecasting information system is proposed that collects data from digital twins and provides them with a pre-trained neural network model to obtain forecasts about the need for predictive maintenance. The article discusses two types of forecasts - about the remaining useful life and the possible failure of an asset in the considered time window. Computational experiments have been carried out, confirming that the proposed neural network model allows, due to the simultaneous training of solving two problems, to obtain more accurate forecasts than models trained to solve one problem.

In this work the task is formulated and the method of reconfiguration of systems of organizational management on the basis of synthesis of the functional structure having an impact on an appearance of all system considerably defining an order of its functioning, integrating in a whole of means of technical and mathematical, program and information support is offered. The research objective consists in need of increase in effective management of organizational systems on the basis of complex development, implementation and application of funds of automated management of its elements. Expert systems on the basis of declarative programming languages are applied to synthesis of similar structures. Research methods. As the tool for definition of the knowledge base about the field of restructuring of structure of management calculation of expressions and language of a predicate logic, that is a logic theory of first order is used. Then, the problem of reconfiguration of hierarchical structure of management system can be presented doubly. First, as a problem of definition of the changes of the known rational hierarchical structure providing minimum loss from the arisen functional failures. Secondly, as a problem of creation of new rational structure which provides optimum use of the resources used in the course of achievement of definite purposes in the changing conditions. Results. As a result of a research, on the basis of de Morgan's law the factors influencing a system status of organizational management in general are defined. The necessary structure of solvable tasks of all hierarchical structure is defined by extent of influence of different factors on characteristics of structure of management. Conclusion. Work of the received expert system consists in consecutive execution or failure to follow rules and transition from one status to another. In case of an impasse the expert system gives the report in the form of requirements of alternative change of these or those rules (factors). New rules are remembered. Thus, the system of knowledge is increased.