-
Date submitted2023-03-14
-
Date accepted2023-06-20
-
Date published2023-07-19
Forecasting planned electricity consumption for the united power system using machine learning
The paper presents the results of studies of the predictive models development based on retrospective data on planned electricity consumption in the region with a significant share of enterprises in the mineral resource complex. Since the energy intensity of the industry remains quite high, the task of rationalizing the consumption of electricity is relevant. One of the ways to improve control accuracy when planning energy costs is to forecast electrical loads. Despite the large number of scientific papers on the topic of electricity consumption forecasting, this problem remains relevant due to the changing requirements of the wholesale electricity and power market to the accuracy of forecasts. Therefore, the purpose of this study is to support management decisions in the process of planning the volume of electricity consumption. To realize this, it is necessary to create a predictive model and determine the prospective power consumption of the power system. For this purpose, the collection and analysis of initial data, their preprocessing, selection of features, creation of models, and their optimization were carried out. The created models are based on historical data on planned power consumption, power system performance (frequency), as well as meteorological data. The research methods were: ensemble methods of machine learning (random forest, gradient boosting algorithms, such as XGBoost and CatBoost) and a long short-term memory recurrent neural network model (LSTM). The models obtained as a result of the conducted studies allow creating short-term forecasts of power consumption with a fairly high precision (for a period from one day to a week). The use of models based on gradient boosting algorithms and neural network models made it possible to obtain a forecast with an error of less than 1 %, which makes it possible to recommend the models described in the paper for use in forecasting the planned electricity power consumption of united power systems.
-
Date submitted2022-10-26
-
Date accepted2023-02-13
-
Date published2023-07-19
Determination of the grid impedance in power consumption modes with harmonics
The paper investigates the harmonic impedance determination of the power supply system of a mining enterprise. This parameter is important when calculating modes with voltage distortions, since the determined parameters of harmonic currents and voltages significantly depend on its value, which allow the most accurate modeling of processes in the presence of distortions in voltage and current. The power supply system of subsurface mining is considered, which is characterized by a significant branching of the electrical network and the presence of powerful nonlinear loads leading to a decrease in the power quality at a production site. The modernization of the mining process, the integration of automated electrical drive systems, renewable energy sources, energy-saving technologies lead to an increase in the energy efficiency of production, but also to a decrease in the power quality, in particular, to an increase in the level of voltage harmonics. The problem of determining the grid harmonic impedance is solved in order to improve the quality of design and operation of power supply systems for mining enterprises, taking into account the peculiarities of their workload in the extraction of solid minerals by underground method. The paper considers the possibility of determining the grid impedance based on the measurement of non-characteristic harmonics generated by a special nonlinear load. A thyristor power controller based on phase regulation of the output voltage is considered as such a load. Simulation computer modeling and experimental studies on a laboratory test bench are used to confirm the proposed method. The recommendations for selecting load parameters and measuring device connection nodes have been developed.
-
Date submitted2021-05-13
-
Date accepted2022-11-28
-
Date published2022-12-29
Reproduction of reservoir pressure by machine learning methods and study of its influence on the cracks formation process in hydraulic fracturing
Hydraulic fracturing is an effective way to stimulate oil production, which is currently widely used in various conditions, including complex carbonate reservoirs. In the conditions of the considered field, hydraulic fracturing leads to a significant differentiation of technological efficiency indicators, which makes it expedient to study in detail the crack formation patterns. For all affected wells, the assessment of the resulting fractures spatial orientation was performed using the developed indirect technique, the reliability of which was confirmed by geophysical methods. In the course of the analysis, it was found that in all cases the fracture is oriented in the direction of the development system element area, which is characterized by the maximum reservoir pressure. At the same time, reservoir pressure values for all wells were determined at one point in time (at the beginning of hydraulic fracturing) using machine learning methods. The reliability of the used machine learning methods is confirmed by high convergence with the actual (historical) reservoir pressures obtained during hydrodynamic studies of wells. The obtained conclusion about the influence of the formation pressure on the patterns of fracturing should be taken into account when planning hydraulic fracturing in the considered conditions.
-
Date submitted2022-03-17
-
Date accepted2022-10-04
-
Date published2022-11-10
Improving the reliability of 3D modelling of a landslide slope based on engineering geophysics data
Landslides are among the most dangerous geological processes, posing a threat to all engineering structures. In order to assess the stability of slopes, complex engineering surveys are used, the results of which are necessary to perform computations of the stability of soil masses and assess the risks of landslide development. The results of integ-rated geological and geophysical studies of a typical landslide slope in the North-Western Caucasus spurs, composed of clayey soils, are presented. The purpose of the work is to increase the reliability of assessing the stability of a landslide mass by constructing a 3D model of the slope, including its main structural elements, identified using modern methods of engineering geophysics. Accounting for geophysical data in the formation of the computed 3D model of the slope made it possible to identify important structural elements of the landslide, which significantly affected the correct computation of its stability.
-
Date submitted2021-09-22
-
Date accepted2022-03-24
-
Date published2022-04-29
Predicting dynamic formation pressure using artificial intelligence methods
Determining formation pressure in the well extraction zones is a key task in monitoring the development of hydrocarbon fields. Direct measurements of formation pressure require prolonged well shutdowns, resulting in underproduction and the possibility of technical problems with the subsequent start-up of wells. The impossibility of simultaneous shutdown of all wells of the pool makes it difficult to assess the real energy state of the deposit. This article presents research aimed at developing an indirect method for determining the formation pressure without shutting down the wells for investigation, which enables to determine its value at any time. As a mathematical basis, two artificial intelligence methods are used – multidimensional regression analysis and a neural network. The technique based on the construction of multiple regression equations shows sufficient performance, but high sensitivity to the input data. This technique enables to study the process of formation pressure establishment during different periods of deposit development. Its application is expedient in case of regular actual determinations of indicators used as input data. The technique based on the artificial neural network enables to reliably determine formation pressure even with a minimal set of input data and is implemented as a specially designed software product. The relevant task of continuing the research is to evaluate promising prognostic features of artificial intelligence methods for assessing the energy state of deposits in hydrocarbon extraction zones.
-
Date submitted2019-05-07
-
Date accepted2019-07-11
-
Date published2019-10-23
Operation of a Single-phase Autonomous Inverter as a Part of a Low-power Wind Complex
- Authors:
- A. A. Belsky
- V. S. Dobush
- Shaiban Fuad Haikal
The article discusses the experience of operating a wind power complex with a low-power wind power installa- tion (5 kW), the use of which is promising for powering remote oil production facilities, exploration and other types of mining operations. The structure of the studied complex and its characteristics, technical problems that have arisen during operation for 6 years are given. The elements of the wind energy complex – the battery charge regulator and the inverter-converter are considered. The consequences of the mechanical regulator failure of battery charge are con- sidered and recommendations for its replacement are presented. The issues of diagnostics and repair of one of the main elements of the complex – the inverter-converter, its component – DC link are highlighted in detail. Oscil- lograms of the output voltage of the inverter-converter are presented for different capacities of the DC link and the images of the repaired inverter-converter are given. Recommendations are given on choosing an inverter-converter and setting up the operating modes of the wind energycomplex.
-
Date submitted2018-12-25
-
Date accepted2019-03-02
-
Date published2019-06-25
Non-linear electrical load location identification
- Authors:
- S. Pirog
- Ya. E. Shklyarskiy
- A. N. Skamyin
The article discusses the issues of identifying the location of non-linear loads in electrical networks which makes the main contribution to the distortion of the non-sinusoidal voltage and current in the distribution network of an industrial enterprise, including mining enterprises. The existing methods for determining the location of the source of higher harmonic components in voltage and current are considered, their advantages and disadvantages are revealed. The main disadvantages of the methods used include the low accuracy and incorrectness of their use in existing enterprises. When developing a new method, the authors were faced with the task of simplicity of its use in the conditions of industrial operation of electrical equipment and the absolute correctness of the results obtained. The proposed method of identifying the source of higher harmonics is based on the variation of the parameters of the power system, in particular, the change in resistance of power transformers taking into account their transformation ratio. It is shown that by varying the transformation ratio during regulation under load, the total coefficient of the harmonic components of the voltage changes. Based on the constructed dependencies, the variation of the derivative of this function with different variations of the parameters of sources of higher harmonics is analyzed and a method is developed that allows determining the share contribution of consumers to the total harmonic component of the voltage.
-
Date submitted2018-09-08
-
Date accepted2018-11-01
-
Date published2019-02-22
Complexation of telecommunications and electrical systems in mines and under-ground facilities
- Authors:
- V. A. Shpenst
The possible options for the integration of telecommunications and electrical systems of mining enterprises are considered. Based on an analysis of the current state and prospects for the development of telecommunications systems, various technical solutions are proposed for sharing the power supply networks available in mines and underground structures in order to solve the problems of telecommunication, automate process control and ensure the safety of operations. The analysis of the possibilities of applying the PLC technology in underground structures and mines for solving specific telecommunication problems has been carried out, and examples of their possible technical and hardware implementation are given.
-
Date submitted2017-12-29
-
Date accepted2018-03-06
-
Date published2018-06-22
Evaluation of signal properties when searching for cavities in soil under concrete slabs by radio detection stations of subsurface investigation
- Authors:
- G. V. Rudianov
- E. I. Krapivskii
- S. M. Danilev
A method of localization of concealed cavities on the basis of studying of the reflected electromagnetic impulses is considered in the paper. An issue of early detecting of concealed cavities in engineering facilities is a critical one due to a significant influence on further serviceability of a structure. Problems of localization of concealed cavities in the soil body under the concrete slabs of hydropower stations were studied; the results of ground radar detecting investigations of the cavities, physical simulation of a cavity as well as a mathematical modeling of a reflected signal are presented. Modern subsurface radar detection provides methods which allow to reliably detect concealed cavities in the soil. However, it is possible only in case of a clear boundary between the adjacent layers that conditions a jump of dielectric permeability. In the result of an abrupt change of dielectric permeability a reflected wave occurred; the existence of subsurface heterogeneity is conditioned by the properties of this wave. Moreover, the greater is the difference between the values of dielectric permeability in the adjacent layers, the larger amplitude the reflected wave will have. If the cavity is at the stage of forming, i.e. it is filled with the soil of reduced density, then there is no clear boundary at the border of the layers which will condition a gradual change of dielectric permeability with depth. In this case an amplitude of a reflected wave will be minimal and a formation signal will be masked out by jamming signals reflected from various heterogeneities. In such case to determine a cavity at the stage of forming seems to be impossible. To determine poor signals an analysis of a phase of a reflected signal may be used; phase alters in compliance with the reflection coefficient change pattern. The article contains information about signals reflected from the heterogeneities and a conclusion regarding a possibility of detecting cavities in the soil on the basis of a method of coherent processing of signals is made.
-
Date submitted2017-09-14
-
Date accepted2017-11-23
-
Date published2018-02-22
Providing energy decoupling of electric drive and electric grids for industrial electrical installations
Subjects of the research are industrial electric drives, witch maintain the operation of main actuating units of production machines and installations during the development of mineral resource deposits. The goal is to research the possibility to ensure the energy decoupling of industrial electric drives and electric grid by means of structural implementation of active rectifiers into frequency converters. The main purpose of energy decoupling is to eliminate the negative impact of low quality electric energy and changes in energy parameters on electric drive operation. In order to accomplish energy decoupling of electric drive with active rectifier, methods of mathematical and simulation modeling with mathematical application software package were used. The integrated simulation model with two electric drives, including active rectifier (energy decoupled electric drive) and diode rectifier (standard type electric drive), were created. Simulation model is provided with tools for oscillographic testing and analysis of the impact of power quality parameters on frequency converters and drive motors operation. The analysis of effectiveness of energy decoupling by means of active rectifier of frequency converter shows that drive motor completely retains the stability and controllability of rotation frequency and torque during the changes of power quality parameters in electric grid. The use of active rectifier allows to ensure the operation of electric drive in required mode in case of voltage decrease by 30 % with normative value of 5-10 %, i.e. energy decoupling provides high stability margin for voltage. Electric drive with active rectifier ensures energy decoupling in case of asymmetry of supply voltage. The control of mechanical variables of induction motor during offsets in amplitude and frequency in all phases of electric grid is ensured to be on required level.
-
Date submitted2017-09-17
-
Date accepted2017-11-06
-
Date published2018-02-22
Collaborative interpretation of the data obtained by resistivity and ground penetrating radar methods for assessing the permeability of sandy clay soils
- Authors:
- D. A. Lalomov
- V. V. Glazunov
A method for estimating the filtration factor of sandy clay soils is considered on the basis of a joint interpretation of the data of a set of methods of engineering electrical exploration, including electrical resistivity tomography and ground penetrating radar studies. The solution of this problem is based on the use of known empirical connections between the imaginary and real parts of the complex dielectric permittivity, specific electrical resistance, and Q factor. An example of the effective joint use of the ground penetrating radar and non-contact electrical resistivity tomography shows how to obtain qualitative and quantitative estimates of a changing filtration factor in a draining road layer. It is necessary to use precise engineering geological information in order to provide the required estimates. The proposed approach makes it possible to describe continuous profiles of a pavement and underlying layers by ground penetrating radar and electrical resistivity tomography, as well as to assess soil properties when conducting an electrical survey from the surface of asphalt concrete pavement. Recommendations for the implementation of the developed methods of complex engineering and geophysical research are given for solving issues of repair work design, supervision, and quality control of road construction.
-
Date submitted2014-09-27
-
Date accepted2014-11-11
-
Date published2015-06-26
Electric network equivalenting in the presence of high harmonics
The article deals with equivalenting of complex electrical networks of industrial enterprises. In the article the different methods of averaging equivalenting elements in power systems are compared, specifically, the method of moments, the equivalent section method, and the average value method. The current value of the capacitor bank as part of the electrotechnical complex of the enterprise is the main criterion for determining the equivalenting error of the electric network. The equivalenting in the presence of high harmonics in electrical networks of the enterprise is considered by applying the methods under discussion. Comparison of these equivalenting methods in the presence of high harmonics shows that the error in the calculation of capacitor bank current ranges from 3,8 to 14,7 %. In addition, the most accurate method for determining the capacitor bank overload is the method of moments.
-
Date submitted2010-07-29
-
Date accepted2010-09-27
-
Date published2011-03-21
Efficiency increasing of condenser batteries operation in mining enterprise`s electric circuits
- Authors:
- A. N. Skamin
This work contains the method of effective reactive power compensation at the expense of high harmonics reduction. The decrease of condenser batteries overloading from the high harmonics is based on variation of condenser power depending on current and voltage spectral structure, electric network parameters and load power.
-
Date submitted2009-08-01
-
Date accepted2009-10-08
-
Date published2010-02-01
Advance of the metallurgical limestone shaft kilning process control system
- Authors:
- N. I. Koteleva
Today at management system engineering by metallurgical processes used to special methods of the control theory such as optimal, neuro-fuzzy and adaptive methods. First of all, it is connected with increase of problems complexity maintained in control process. In article possibility of application of neural networks is considered at improvement of a control system by process of mine roasting of limestone, are described the neural network scheme controls and the basic stages of its construction.
-
Date submitted2008-10-10
-
Date accepted2008-12-13
-
Date published2009-12-11
Magnetotelluric evidence of deep geodynamic settings at the junction zone of the Southern Tien Shan and Tarim basin
Detailed magnetotelluric and magnetovariation profiling was conducted (40 broadband stations) at the southern 140 km segment of geophysical transect MANAS with the help of MT instruments: MTU-5 (produced by «Phoenix Geophysics Ltd») and MT-24 (produced by EMI Center). MANAS transect extended from south of Kashgar, China, to just south of Bishkek, Kyrgyzstan and crossing the whole Tien Shan orogenic belt in transverse direction of its main ranges strike. We constructed 2D geoelectric model to characterize block-fracture structure at the junction zone of the Southern Tien Shan. There is low resistive inclined zone in the obtained cross-section imaging the underthrusting process of Tarim tectonic sheets under the Tien Shan mountains. Also there are some electrical heterogeneities as indications that young deformations inside Tarim lithospheric block have the whole crust scale.