В статье приведены результаты исследований применения фреймворка автоматического создания алгоритмов машинного обучения (AutoML) для решения задач диагностики и оценки технического состояния электродвигателей, применяемых в широком спектре в горнодобывающей промышленности. Представлена работа и функционирование AutoML Фреймворка – FedotIndustrial, разработанного автором. Предложен в качестве экспериментального и практического применения испытательный стенд, на котором при помощи электродвигателей переменного тока формируются условия изменения нагрузки и величины дефекта в виде несоосности. Выявлено, что более информативной является интерпретация данных в виде годографа Парка и диагностической кривой. Установлено что, при решении задача классификации данных с учителем, формируются разметка данных на классы, образующих в совокупности 6 классов технического состояния электродвигателя. Результаты исследований могут быть полезными при дальнейшей разработке предиктивных систем автоматизации и защиты электромеханического оборудования горнодобывающих предприятий.

In this paper, we consider the need to create an algorithmized digital platform for the development of electric charging networks of road transport and to optimize the load on the current power grid complex. In modern conditions, this platform can become an example of a mechanism for public-private partnerships and the development of environmentally friendly transport. The purpose of the platform is to provide users with up-to-date information about the state of the electric vehicle battery, reduce the cost of creating a network charging infrastructure for electric vehicle transport, automated resource accounting for power supply companies, and other services. The use of information technologies to combine the processes of economic relations in the field of energy sales services will attract funds for infrastructure development by increasing the load factor of generating capacities and unloading power centers. In the article, the authors propose a digital platform architecture using modern technologies such as IIoT, Vehicle to Grid (V2G), Machine learning, Big Data.

This article examines the development of deep and extensive potash deposits, focusing on the mandatory preservation of the waterprotective layer and the implementation of measures to minimize surface subsidence, which significantly affects the mineral extraction ratio. These requirements, along with the need for disposal of processing plant waste, can be addressed through backfilling of mined-out spaces. The main types and methods of backfilling are reviewed. It is noted that backfill costs can be reduced by using technologies that employ hardening mixtures, which enable the subsequent extraction of inter-chamber pillars and increase overall mineral extraction. However, the production and complete filling of chambers with hardening mixtures substantially raises costs, limiting widespread adoption and necessitating the development of more economical solutions. A technology for layer-by-layer mechanized backfilling, developed by the Institute of Comprehensive Exploitation of Mineral Resources (IPKON) Russian Academy of Sciences, is presented. This approach involves two stages: the primary stage uses dry transport of processing waste, and the secondary stage backfills the upper part of the chamber with a hardening mixture prepared directly near the chamber, achieving high strength characteristics in the backfill mass. A proposed equipment set, designed to fit within the actual dimensions of mine workings, can be assembled into a single mobile system through technical modifications. The potential for using mobile systems to prepare backfill mixtures in underwater mining of solid minerals is also discussed.