Wyniki wyszukiwania - Biblioteka Nauki

Ten serwis zostanie wyłączony 2025-02-11.

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

2 Archives of Mining Sciences

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Study on the stability evolution law of expansive soft rock roadway affected by seasonal wet-dry cycle

100%

Jing H. , Qu F. , Liu X. , Zhang G. , Zhang X. , Ma X.

Archives of Mining Sciences

2023

tom Vol. 68, no. 1

165--182

Many open-pit mines are gradually converted to underground mining, the problem of roadway surrounding rock damage caused by expansive soft rock is becoming increasingly problematic. To study the seasonal evolution of expansive rock mass containing clay minerals, an underground mine transferred from an open-pit was selected as the experimental mine. The experimental results of SEM electron microscopy and X-ray diffraction confirmed that the surrounding rock of the main haulage roadway contains a large number of expansive clay minerals. The expansive grade of the main transport roadway’s surrounding rock could then be identified as the medium expansive rock mass, which has a large amount of exchangeable cation and strong water absorption capacity, based on the combined test results of dry saturated water absorption and free expansion deformation. The water swelling can cause the roadway to considerably deform, and then the surrounding rock will have strong rheological characteristics. From the research results in the text, the seasonal evolution law of the main haulage roadway in the experimental mine was obtained, and the deformation law of the expansive rock mass under different dry and wet conditions was revealed. The research results provide a reference for studying the stability evolution law of expansive soft rocks in underground mines.

Research on ore fragmentation recognition method based on deep learning

84%

Jing H. , He W. , Yu M. , Li X. , Zhang X. , Liu X. , Cui Y. , Wang Z.

Archives of Mining Sciences

2024

tom Vol. 69, no. 3

447--459

The degree of ore fragmentation in mining sites is closely related to crushing efficiency, equipment safety, beneficiation efficiency, and mining costs. Aiming to address the challenges of high labour intensity and low accuracy during manual ore fragmentation measurement at the mine site, this paper proposes a method for ore fragmentation recognition based on deep learning. This method not only uses the residual neural network structure to form the backbone feature extraction network of CSPDarkNet21 under the Darknet framework but also selects the simple two-way fusion feature PANet as the feature extraction network under the condition of only needing to identify large ore. PANet is simplified from three feature layers to one feature layer, which speeds up model training and prediction. The research results show that with a 6% decrease in accuracy, the model training time is reduced by 13 times, and the model running efficiency is improved by 21.2 times, significantly shortening the model development time. At the same time, CIOU calculates the loss value to make model training more stable. After the ore identification is completed, the real size of the ore can be obtained by calculating the pixel area of the prediction frame using the ore fragmentation judgement method.