Pyro-metallurgy of copper production is characterized by the output of copper slag, which is regarded as a kind of solid waste. Moreover, this slag is identified as hazardous because it contains impurities, like Pb, As, and Cu. Obtaining dump slags in autogenous processes does not always meet the requirements of effective technologies, most often slags contain more than 1.0% of copper and need to be depleted. This work is presented a brief analysis of existing technologies used for copper slag depletion. The analysis of the existing technologies for the depletion of autogenous smelting dump slags showed that the most promising option seems to be the depletion of copper slags in one PV unit since by improving the process itself, by changing the unit design, it is possible to achieve technologically complete production of matte and dump slag with low copper content. There were proposed two technologies of improvement: electro-heating of slag siphon using the graphite electrodes and depletion process in two-zone PV furnace.

The growing environmental impact of copper production necessitates innovative approaches for optimizing metallurgical processes and minimizing waste. This study addresses this challenge by leveraging advanced machine learning (ML) techniques to enhance the efficiency of pyrometallurgical operations such as slag optimization, composition prediction, and waste minimization. Using a combination of real-world and synthetic data, we developed models capable of both forward prediction, estimating slag and matte compositions from ore characteristics, and backward prediction, inferring ore compositions from output characteristics. Five ML algorithms were evaluated, with Gradient Boosting and Support Vector Regression demonstrating superior performance in capturing complex, non-linear relationships. Forward prediction achieved near-perfect accuracy, while backward prediction highlighted the inherent complexity of inverse modeling. This backward-driven strategy proposed in this research aims to determine optimal ore compositions to achieve desired outputs, reducing waste and energy consumption. By integrating ML models with a systematic hyperparameter optimization approach, this work advances the potential for sustainable and precise metallurgical processes. While challenges remain in refining backward predictions, the findings demonstrate the transformative potential of data-driven strategies in industrial metallurgy, paving the way for environmentally sustainable and economically efficient copper production practices.

The purpose of this work is to determine the regularities of reducing the losses of valuable metals with waste slag of copper smelting in the conditions of the Balkhash copper smelter. The change in the raw material base, the introduction of low-quality copper concentrates in the Balkhash copper smelter (BCS) on the VF-1 and VF-2 (Vanyukov furnaces), are accompanied by the production of waste slag containing increased copper content, which requires additional technological operations for their depletion. Smelting in optimal conditions can exclude the organization of separate processing waste slag. Ways to improve the autogenous smelting of copper concentrates at BCS are the following: strict adjustment of the charge composition by basic metals and silicon dioxide, temperature regime, maintaining the heat balance with the possibility of using fuel, optimal operation of the electric mixer. A study of the dependences between the copper content in charge and slag on furnaces VF-1 and VF-2 of BCS allows establishing that the amount of slag increases 1.5-2 times with a decrease of the copper content in the charge 2 times. Reducing the copper content in the feed increases the losses of copper in the slag. The dependences of the copper content in waste slag on content of magnetite and zinc indicate that an increase of the magnetite content from 8 up to 11 % leads to an increase of the copper content in the slag for 0.4-0.5 %. An increase of the zinc content from 4 up to 6 % leads to increase for 0.3-0.5 % of copper content in the slag. Thermal studying of samples of dump slag, produced on furnaces VF-1 and VF-2 showed that the temperature of the slag at the outlet of the electric mixer should be at least 1300 °C. This temperature is difficult to reach by autogenous smelting regime. To solve the problem of complete separation of slag and matte, it is necessary to overheat slag for 70-80 0С, which will realise at electric energy consumption 80 kWt·h/t of slag and allows obtaining waste slag of the optimal composition.

This work is devoted to the investigation of the possibilities of processing oxidized copper ore and sulfide copper concentrate of the Aktogay deposit by pyrometallurgical methods at the operating metallurgical units of the largest copper producer in Kazakhstan, Kazakhmys Smelting Ltd. The chemical, phase compositions and thermal properties of the samples of the Aktogay ore and concentrate were investigated. To test the possibility of using oxidized copper ore of the Aktogay deposit as quartz flux for autogenous smelting in Vanyukov furnaces (VF) with copper sulphide concentrates laboratory experiments were carried out. They made it possible to establish that the replacement of quartz flux on the oxidized ore of the Aktogay deposit is entirely permissible in consideration of the satisfactory composition of slags and mattes obtained in the smelting, even when the content of silica in the ore is 64.56 %. With a higher content of silica in the ore, its use as a flux will be even more effective. The available capacities of the two Vanyukov furnaces are not sufficient for processing all available high-sulfur raw materials, including the Aktogay sulphide copper concentrate, using autogenous melting. Therefore, in the laboratory and in an industrial scale, a preliminary test was carried out on the possibility of processing a part of the copper poor and high-sulfur Aktogay concentrates on the electric furnaces of the Zhezkazgan Copper Smelting Plant (ZCS). The results of laboratory studies and preliminary industrial tests have shown the possibility of such processing with the production of mattes containing no less than 47 % of copper and suitable for converting on existing equipment of ZCS.