Место работы автора, адрес/электронная почта: ФИЦ "Якутский научный центр СО РАН", Институт горного дела Севера им. Н. В. Черского ; 677000, г. Якутск, пр-т Ленина, 43 ; e-mail: igds@ysn.ru ; http://igds.ysn.ru
ID Автора: SPIN-код: 9842-9280, РИНЦ AuthorID: 1231853677980
Количество страниц: 6 с.
Cracks in the rock mass significantly affect the physical and mechanical properties of rocks, and they, in turn,must be taken into account in the planning of mining operations and construction of mining structures. There arevarious techniques for detecting cracks in the rock mass using GPR data. However, the application of these techniquesis limited by the productivity of geophysical operators, as the GPR data are mainly interpreted by them manually. Tostudy the fracturing of frozen rocks from GPR data, it is possible to use artificial neural networks (ANN), which willmake it possible to analyze GPR radarograms in order to detect discontinuities and shifts of in-phase axes of GPRsignals. A significant problem in the application of ANN is the preparation of data for training (training sample). It ispossible to create a training data set using a model of GPR section of frozen rock massif with a fracture. However,the practice of using synthetic radarograms based on the model of GPR section of frozen rock massif with a crack hasshown the need for its improvement in terms of increasing the number of rock layers, the possibility of setting inclinedboundaries, taking into account the presence of syn- and antiforms. The article describes the stages of neural networkmodel development, including the creation of a training data set, selection of architecture, training and testing of theneural network model. The validation of the ANN model showed high performance of the ANN model. Nevertheless,some drawbacks are observed in the performance of the model. The developed system will significantly reduce the timecost of GPR data interpretation. Further research will be related to improving the prediction accuracy associated withthe expansion of the training data set and development of an additional ANN model.
Соколов, К. О. Распознавание волновых образов трещин массива горных пород на основе нейронных сетей по данным георадиолокациям / Соколов К. О., Шамаев С. Д. ; Институт горного дела Севера им. Н. В. Черского // Успехи современного естествознания. - 2023, N 7. - С. 109-114. - DOI: 10.17513/use.38079
DOI: 10.17513/use.38079
Количество страниц: 16 с.
- Общий отдел > Информационные технологии. Вычислительная техника,
- Математика. Естественные науки > Геология. Геологические и геофизические науки,
- НАУКА ЯКУТИИ > МАТЕМАТИКА. ЕСТЕСТВЕННЫЕ НАУКИ > Геология. Геологические и геофизические науки,
- НАУКА ЯКУТИИ > ОБЩИЙ ОТДЕЛ > Информационные технологии. Вычислительная техника.
Relevance. Rock mass cracks are fracture surfaces in rocks with no signs of shifting. They significantly affect the physical and mechanical properties of rocks, and they, in turn, must be taken into account when planning mining operations and constructing mining structures. This problem can be solved by applying artificial intelligence (AI) methods, as they are able to process large amounts of data. The purpose of the work: choice of artificial intelligence method for detecting rock mass cracks from GPR data based on an analytical review of the applied artificial intelligence methods in the processing and interpretation of geophysical measurement data. Research methodology: analytical review of the application of artificial intelligence methods in the processing of geophysical methods data. The results of the work and their scope. As a result of the study, a table has been formed showing the qualitative assessments of the four characteristics of AI methods, which make it possible to make a reasonable choice of a method for detecting rock mass cracks from GPR data. The resulting estimates of the characteristics of AI methods will be useful to a wide range of geophysicists involved in data processing and interpretation and those who want to improve the efficiency of their work. Conclusions. The review showed that artificial intelligence methods are widely used in the processing of geophysical methods data. Among the methods used, one can single out artificial neural networks, support and relevance vector machines, genetic algorithms, etc. A convolutional neural network was chosen as an artificial intelligence method for detecting rock mass cracks from GPR data, since it is most sensitive to that data type and has a high noise immunity.
Шамаев, С. Д. Применение методов искусственного интеллекта при обработке и интерпретации данных геофизических методов / С. Д. Шамаев ; Институт горного дела Севера им. Н. В. Черского // Известия Уральского государственного горного университета. - 2022, N 1 (65). - С. 86-101. - DOI: 10.21440/2307-2091-2022-1-86-101
DOI: 10.21440/2307-2091-2022-1-86-101