Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Damage and stability analysis of sandstone-type uranium ore body under physical and chemical action of leaching solution

Liu Yulong, Huang Lei, He Guicheng, Hu Nan, Zhou Shuhui, Yu Qing, Ding Dexin

Archives of Mining Sciences

2023

Vol. 68, no. 3

409--423

In this paper, the typical sand-conglomerate uranium ore in north China was taken as the research object. The uniaxial compression and tensile tests of sand-conglomerate specimens under natural status and acidic solution status were used to research the compressive strength, tensile strength, Young’s modulus, cohesion and internal friction angle. Focusing on this type of uranium deposit, during the underground design of the in-situ leaching mining method, the three-dimensional finite element method was used to conduct a numerical simulation of the liquid collecting tunnel with different structural parameters of 10 m×2 m, 3 m×2 m, 2 m×2 m, and comprehensively analyse the vertical displacement, principal stress and plastic deformation zone changes of the tunnelbefore and after leaching. Based on the results, influenced by an acidic aqueous solution, the grain of the conglomerate became soft and secondary pores appeared, resulting in the superimposed effect of physical damage and chemical damage. Macroscopically, an obvious decrease was witnessed in mechanical property. Based on the stability and economy factor of three scenarios before and after leaching, the scenario was recommended as the experimental testing scenario, specifically, two longitudinal collecting tunnel were arranged along the strike of the orebody, with the size of 3 m×2 m and the width of the middle pillar of 4 m. The results of the numerical simulation are significant in guiding the design of underground in-situ leaching technology and determining the structural parameters of the deposit.

A fault detection method based on stacking the SAE-SRBM for nonstationary and stationary hybrid processes

Huang Lei, Ren Hao, Chai Yi, Qu Jianfeng

International Journal of Applied Mathematics and Computer Science

2021

Vol. 31, no. 1

29--43

This paper proposes a fault detection method by extracting nonlinear features for nonstationary and stationary hybrid industrial processes. The method is mainly built on the basis of a sparse auto-encoder and a sparse restricted Boltzmann machine (SAE-SRBM), so as to take advantages of their adaptive extraction and fusion on strong nonlinear symptoms. In the present work, SAEs are employed to reconstruct inputs and accomplish feature extraction by unsupervised mode, and their outputs present a knotty problem of an unknown probability distribution. In order to solve it, SRBMs are naturally used to fuse these unknown probability distribution features by transforming them into energy characteristics. The contribution of this method is the capability of further mining and learning of nonlinear features without considering the nonstationary problem. Also, this paper introduces a method of constructing labeled and unlabeled training samples while maintaining time series features. Unlabeled samples can be adopted to train the part for feature extraction and fusion, while labeled samples can be used to train the classification part. Finally, a simulation on the Tennessee Eastman process is carried out to demonstrate the effectiveness and excellent performance on fault detection for nonstationary and stationary hybrid industrial processes.