- Research Article
- 10.31721/2306-5435-2024-1-112-23-29
Інтелектуальні засоби у процесах подрібнення як потужний інструмент автоматизації
- Jan 01, 2024
- Mining Journal of Kryvyi Rih National University
- V.G Liashok + 1 more +1
Purpose of the study: The purpose of this study is to achieve improvement of the mineral grinding process in the context of the production needs of PJSC "Northern GOK" using intelligent methods, in particular neural networks. The use of intelligent tools, such as neural networks, is aimed at improving the quality, accuracy and efficiency of the grinding process. The research is expected to result in the development and implementation of new algorithms and methods that will ensure optimal use of resources, reduce costs and increase the overall productivity of the grinding process in the mining industry. Research methods. The following methods were used: study of scientific research and literature in the field of application of intelligent methods in the processes of grinding materials, analysis of technological schemes and grinding processes at PJSC "Northern GOK", development and modelling of systems for optimisation of grinding parameters. Scientific novelty. The study introduces the latest methods of data mining, including the use of artificial neural networks, to optimise the process of grinding minerals. The use of neural networks in the mining industry is a new and rapidly growing area of research and opens up great opportunities for improving the efficiency and accuracy of ore processing in the mining and processing sector. Practical significance. Implementation of the developed methods and models into the practice of grinding minerals at PJSC Northern Mining can lead to an increase in the quality and efficiency of the process, a reduction in downtime and optimisation of energy consumption. This can have a significant positive impact on the economic efficiency of the enterprise and the overall level of mineral production. Results. This paper has demonstrated how dynamic modelling can be used to evaluate the effects of process modifications and predict actual performance. Despite the complexity of dynamic modelling, it has a higher potential for predicting actual performance. The developed systems used in this paper will be useful tools for further research in the field of automation to improve performance
Read more