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 article, we consider the solution of adaptive control problems by developing a unified algorithm for regulator tuning. The task of adaptive control of dynamic processes in real time, today plays a key role in the development of modern control systems. Existing adaptive management development assumes, as a rule, an unchanged structure of the technological process, where only the parameters of the process under investigation are subject to change. To create such systems, detailed modeling of the technological process is necessary, while the typical management model after identification becomes unique for a particular enterprise due to the parameters found. This system is designed for operating objects that allows you to take into account the dynamic change of parameters in the process of object identification while the stage of mathematical modeling is replaced by a standard approximating model.

This article describes an approach of mathematical processing of signals (seismograms) from five blasthole charges from experimental blasting, each 3 m deep, with equal explosive weight (1 kg), and equidistant (3 m) from one other. The seismic explosive waves were measured at a 13 to 25 m distance. This article provides spectral analysis, wavelet analysis, and fractal analysis results. It defines the dependence of dominant frequency and amplitude on the distance to the blast center. According to the experimental data, the dominant frequency is calculated as y = 1.0262x0.2622 and the amplitude dependency as y = 18.139x−2.276. Furthermore, the analysis shows that 80% of the entire signal is concentrated in half the area of frequency range, i.e., the low frequency zone is of the most interest. This research defines the dependence of distance on the energy value of signal wavelet analysis. It is demonstrated that, according to the experimental data, the 12th frequency range is closely correlated with the distance values. This article gives the definitions of entropy, correlation dimension, and predictability time. This experiment shows that entropy and correlation dimension decrease but predictability time increases when the distance to the blast center increases. This article also describes the method for determining optimal drilling and blasting parameters, and concludes with the possibility of applying the analytical results to predicting and enhancing drilling and blast-ing operations.