-
Date submitted2023-11-10
-
Date accepted2024-06-03
-
Date published2025-02-25
Enhancing the interpretability of electricity consumption forecasting models for mining enterprises using SHapley Additive exPlanations
- Authors:
- Pavel V. Matrenin
- Alina I. Stepanova
The objective of this study is to enhance user trust in electricity consumption forecasting systems for mining enterprises by applying explainable artificial intelligence methods that provide not only forecasts but also their justifications. The research object comprises a complex of mines and ore processing plants of a company purchasing electricity on the wholesale electricity and power market. Hourly electricity consumption data for two years, schedules of planned repairs and equipment shutdowns, and meteorological data were utilized. Ensemble decision trees were applied for time series forecasting, and an analysis of the impact of various factors on forecasting accuracy was conducted. An algorithm for interpreting forecast results using the SHapley Additive exPlanation method was proposed. The mean absolute percentage error was 7.84 % with consideration of meteorological factors, 7.41 % with consideration of meteorological factors and a load plan formulated by an expert, and the expert's forecast error was 9.85 %. The results indicate that the increased accuracy of electricity consumption forecasting, considering additional factors, further improves when combining machine learning methods with expert evaluation. The development of such a system is only feasible using explainable artificial intelligence models.
-
Date submitted2022-05-11
-
Date accepted2023-02-20
-
Date published2023-08-28
Application of the support vector machine for processing the results of tin ores enrichment by the centrifugal concentration method
The relevance of the research is due to the acquisition of new knowledge about the features of the applicability of the support vector machine, related to machine learning tools, for solving problems of mathematical modeling of mining and processing equipment. The purpose of the research is a statistical analysis of the results of semi-industrial tests of the Knelson CVD technology on tin raw materials using the support vector machine method and the development of mathematical models suitable for further optimization of the technological parameters of the equipment. The objects of research were the products obtained as a result of the operation of hydro-cyclones, as well as the technological parameters of the operation of centrifugal concentrators. The work uses classical methods of mathematical statistics, the least squares method for constructing a linear regression model, the support vector machine implemented on the basis of the Scikit-learn library, as well as the method of verifying the resulting models based on the ShuffleSplit library. A general description of the process of testing the Knelson concentrator with continuous controlled unloading in relation to the enrichment of tin ores is presented. The results obtained were processed using the support vector machine. Regression models are obtained in the form of polynomials of the second degree and in the form of radial basis functions. A significant non-linearity is shown in the dependence between the content of the valuable component in the tailings and the values of the technological parameters of the apparatus.
-
Date submitted2020-05-18
-
Date accepted2020-06-16
-
Date published2021-04-26
Traction asynchronous electric drive of mine electric locomotivesimulation model structure improvement
The article discusses the solution to the problem of underground railway transport slipping in dynamic modes, which occurs when there is a significant difference in the speeds of the driving and driven pairs of wheels. The state of the rail surfaces largely determines the coefficient of adhesion, therefore, using a mathematical model, the condition for the dependence of the magnitude of slipping and tractive effort is selected. For effective acceleration and deceleration of an electric locomotive, it is necessary to control the coefficient of adhesion at a certain level. A simulation model of rolling stock has been created, which for the first time takes into account a mechanical system with distributed parameters. In the structural diagram of the automatic control system of traction electric drives with frequency regulation, such factors as the volume of goods being moved, rolling friction, slope (rise) levels and the state of the rail track are taken into account. The simulation results show the features of the movement and stops of the freight train not only by the diagrams of speed and forces in the modes of acceleration-deceleration and uniform movement, but also the positions of the plungers and tractive forces on the couplings of the electric locomotive and all trolleys involved in the movement of goods. The practical application of the proposed method lies in the possibility of starting a heavily laden train from its place on the ascent section in conditions of insufficient adhesion coefficient with contaminated roads.
-
Date submitted2019-03-11
-
Date accepted2019-05-06
-
Date published2019-08-23
Estimation Method for Vector Field Divergence of Earth Crust Deformations in the Process of Mineral Deposits Development
- Authors:
- B. T. Mazurov
- M. G. Mustafin
- A. A. Panzhin
An essential requirement for effective and safe deposit development is good geomechanical software. Nowadays software packages based on finite element method are used extensively to estimate stress-strain state of the rock mass. Their quality use can only be assured if boundary conditions and integral mechanical properties of the rock mass are known. In mining engineering this objective has always been achieved by means of experimental observations. The main source of information on initial and man-induced stress-strain state of the rock mass is natural measurement of displacement characteristics. Measurement of geodetic data (coordinates, heights, directions) in the period between alteration cycles allows to plot a field of displacement vectors for the points in question. Taken together, displacement vectors provide information on the objective stress-strain state of the Earth crust. Basing on it, strain tensors, displacement components, directions and rates of compression and tension can be calculated in the examined area. However, differential characteristics of any physical vector field – namely, curl and divergence – need to be taken into account. Divergence is a single value (scalar) associated with a single point. Vector field as a whole can be described with divergence scalar field. Divergence indicates the sign (positive or negative) of volume changes in the infinitesimal region of space and characterizes vector flux in the nearest proximity and in all directions from a given point. In the paper authors propose a method to estimate divergence using discrete geodetic observations of displacement occurring on the surface of examined territory. It requires construction of formulas that model vector field for any point of the area. It is proposed to use power polynomials that describe displacement in three directions (x, y, z). These formulas allow to estimate field vectors in any given point, i.e. to form vector tubes. Then areas of input and output cross-section, as well as divergence values are calculated. This increases the quality of geodetic observation and provides opportunities for more precise modeling of the rock mass disrupted by mining operations, using modern software packages.
-
Date submitted2017-09-03
-
Date accepted2017-11-04
-
Date published2018-02-22
Development of sensorless vector control system for permanent magnet synchronous motor in Matlab Simulink
- Authors:
- V. Ya. Frolov
- R. I. Zhiligotov
In last 20 years segment of electric drives with permanent magnet synchronous motors has increased. This type of motors has better technical characteristics compared to induction motors, but has problems in actual implementation, one of which is the requirement of rotor position data. It is possible to implement with use of sensors or without them by means of motor state observer. The paper describes problems of sensorless vector control system for permanent magnet synchronous motors. The vector control system with state observer for permanent magnet synchronous motors is described. Synthesis of sliding mode observer for rotor speed and position is presented. The algorithm is implemented by development of model in Matlab Simulink environment with support by Texas Instruments processors support blocks. Experimental comparison of results of rotor angle state calculation and the data obtained by rotor position sensors was conducted. Research objective is a development of control algorithm, which has required precision for calculation of rotor start angle, high range of speed regulation and resistance to drift of motor parameters.
-
Date submitted2010-07-29
-
Date accepted2010-09-02
-
Date published2011-03-21
The depth estimation of 2D conductive isometrical bodies by singular points at the tipper frequency characteristic
- Authors:
- E. Yu. Ermolin
- O. Ingerov
The relation between parameters of 2D anomaly body and features of vertical sections of tipper amplitude are considered in this paper. According to investigations the depth of center, top and bottom of conductive body is connected with geometrical distance between two symmetrically located positive extremes in tipper pseudo-sections. In addition the tipper amplitude in extremes decreases on account of increasing depth of anomalous body. The described regularities can be used for MT projects planning and quantitative estimation of anomalous body parameters using tipper pseudo-section constructed from field data.
-
Date submitted1907-12-20
-
Date accepted1908-02-25
-
Date published1908-06-01
Sketches on the geometry of spheres Spherocollineation; reciprocal transformations; megaspheres of vectorial and ordinary spheres. Megaspheres of parallel vectors. Polar relations of megaspheres
- Authors:
- Ye. S. Fedorov
I will provide the additional theorems on linear collections of the geometry of vectorial spheres and quadratic collections of ordinary spheres. For a detailed description, as well as a comparison of megaspheres of vectorial and ordinary spheres and an overview of the system of parallel vectors, see the article.