Kompleksnoe Ispolzovanie Mineralnogo Syra = Complex use of mineral resources

Predicting Copper Production Cycles in Hydrometallurgy with Interpretable Machine Learning

2025-10-06T07:51:33+00:00

Accurate production forecasting in industrial hydrometallurgy is essential for process optimization yet is often hindered by the scarcity of extensive historical data. This study demonstrates the effectiveness of classical machine learning models as a data-efficient and interpretable alternative to complex deep learning methods for predicting total copper mass. We evaluated four models—Random Forest, Gradient Boosting, Decision Tree, and Linear Regression—using a methodology centered on two key strategies: synthetically expanding a limited 150-day dataset into 10,000 simulated cycles (approximately 1.5 million data points) via data augmentation, and engineering 10-day lag features to provide the models with a temporal perspective for a 10-step-ahead forecasting task. The results revealed exceptional predictive accuracy, with ensemble techniques proving superior. The Random Forest model emerged as the top performer, achieving an R² of 0.974, an MAE of 0.088, and an RMSE of 0.111, closely followed by Gradient Boosting (R² of 0.971). All models successfully captured the distinct 150-day cyclical dynamics of the production process, showing a near-zero phase lag (0.00 ± ≤0.05 days). While performance on new, independent data requires further validation, this work establishes a robust and transparent framework for developing reliable forecasting tools in data-limited industrial environments.

Use of Industrial By-products from Metallurgical Production for the Development of Heat-Resistant Building Mixes and their Molding in an Improved Device

2025-08-25T05:44:51+00:00

In the context of the increasing volume of industrial waste and stricter environmental requirements, the urgent task is to efficiently process them to produce products with high added value. In this work, the composition of industrial products of vanadium production formed during the hydrometallurgical processing of rare metals is investigated, and the possibility of their use for the production of heat-resistant building mixes is substantiated. A comprehensive analysis, including X-ray, X-ray fluorescence, and scanning electron microscopic methods, revealed a high content of silica, aluminum oxides, and refractory minerals that determine the heat resistance of the material. Optimal compositions of building mixes based on Portland cement, liquid glass, and chamotte have been developed, providing compressive strength up to 45 MPa and resistance to thermal cycling at temperatures up to 1800 ° C. The design of a device for forming building blocks based on industrial waste from metallurgical production by vibration pressing is proposed, designed to ensure high density and geometric stability of products. The results obtained confirm the possibility of complex industrial waste disposal with the simultaneous creation of environmentally safe, durable, and heat-resistant building materials used in energy, metallurgy, the chemical industry, and civil engineering.

Artificial graphite from Shubarkol coal obtained by sublimation of carbon atoms into the gas phase followed by desublimation into high-purity graphite

2025-10-17T11:17:30+00:00

This article discusses a plasma-chemical method for producing high-purity graphite from an air suspension of low-ash coal particles from the Shubarkol deposit in Kazakhstan. The technological process is based on the ability of carbon to transform from a solid to a gaseous state, bypassing the liquid state. This means it sublimes at high temperatures and desublimes as the temperature of the gaseous medium in the reactor zone decreases. The use of a graphite catalyst allows for controlled formation of the graphitized material. Atomic carbon graphitization occurs over a wide temperature range. It was established that graphite obtained in high-temperature reactor zones is purer than graphite obtained in reactor zones close to 500°C. This feature of the graphitization process enables product classification by quality. The design of a reactor based on sublimation and desublimation processes for graphite production is discussed. The use of a high-frequency electromagnetic zone in the plasma-chemical reactor design allows for controlled graphitization of atomic carbon, intensifying desublimation processes over a graphite powder catalyst. The plasma-chemical apparatus design includes a dust collection system and carbon monoxide neutralization, which can occur due to variations in the component proportions in the feedstock, which includes carbon powder, graphite powder catalyst, and carbon dioxide. The developed apparatus can be used to produce a sorbent – thermochemically expanded graphite – from graphite by varying the operating mode. The aim of this research is to develop a plasma-chemical technology for producing graphite from coal based on sublimation and desublimation processes in a single reactor, with the separation of impurities during the graphitization of carbon atoms over a graphite catalyst.

Redistribution of rock pressure and deformation of the rock mass in the Karaganda coal basin

2025-09-26T06:17:53+00:00

The study examines the redistribution of rock pressure and associated deformation processes in the Karaganda Coal Basin. It focuses on the geometry and parameters of the abutment, unloading, and disintegration zones around underground workings, and on their influence on gas-dynamic phenomena. The methodological basis combines a critical review of current geomechanical models, calculation–graphic nomograms for estimating zone width as a function of mining depth and seam thickness, and schematic construction of high-stress regions from the boundaries of the goaf at limiting angles of 75–90°. It is shown that, with increasing depth up to about 500 m, the zone configuration becomes wedge-shaped with a tendency to narrow downward, while increasing seam thickness expands the affected areas. Lithology controls the localization of hazardous zones: weakly bedded argillites and siltstones accelerate loosening and loss of stiffness, whereas stronger sandstones form dome-like stress concentrations with elevated likelihood of sudden outbursts and rockbursts. As a verification case, an episode of a sudden coal-and-gas outburst was analyzed. The observed failure boundaries are consistent with the calculated wedge-shaped high-stress zone, supporting the validity of the chosen approach within the stated assumptions. The practical significance lies in refining threshold conditions that trigger mandatory comprehensive forecasting at depths exceeding ~400 m, justifying regular instrumental monitoring to validate calculations, and adjusting barrier-pillar parameters about seam thickness and depth. The findings can be applied to the planning and safe execution of longwall and development operations under outburst-prone conditions.

Innovative technologies for paraffin deposit removal in oil tubing to enhance oil recovery: a mechanical approach

2025-08-05T03:52:22+00:00

Asphaltene - resin - paraffin deposits (ARPD) on the inner wall of production tubing shorten service intervals, elevate operating expenditures, and frequently induce downtime at mature fields. This paper presents the design and field performance of a rod-driven in-well scraper that provides continuous tubing cleaning during routine sucker-rod operation without chemical dosing or surface interventions. The scraper sub is inserted into the rod string and is compatible with Ø73 - 89 mm tubing and Ø19 - 22 mm rods. Performance was evaluated on a before/after basis using the inter-cleaning period (ICP), downtime, and annual cleaning costs, with extrapolation to multi-well programs. Field deployments of model CP TP ST 01KZ achieved an ICP of 144 - 280 days with zero cleaning-induced downtime (0 days yr⁻¹). Annual cleaning costs were ~0.265 million KZT per well (scheduled service only), which is ≈31× lower than hot-wash budgets on the same asset. The implied per-well saving is ≈7.94 million KZT yr⁻¹; for a 50-well program, this corresponds to ≥397 million KZT yr⁻¹ in avoided expenditure. Continuous in-well action of the reciprocating toothed head on each rod stroke disrupts the boundary wax layer and limits deposit regrowth between services, eliminating periodic thermal/chemical treatments and their logistics. The subassembly mass (≈30 kg) permits installation with standard handling; the pump string configuration is unchanged apart from the insertion of the scraper section. Compared with thermal, chemical, and batch mechanical methods, the technology extends service intervals, removes cleaning-related shut-ins, and compresses the cleaning budget to a predictable, low annual service cost. The results support routine use of rod-driven scraping for ARPD control in wax-prone wells and provide quantitative guidance for field-scale rollout and further optimization (wear resistance, centralization tolerances, and application in deviated completions).