Fire behavior of mining vehicles in underground hard rock mines

This paper presents laboratory testing procedures and key results on the consolidation of tailings from hard rock mines under positive or negative pore-water pressures (PWP). Specific experimental protocols have been developed and applied to assess the behaviour of low-density tailings (slurry) using compression tests in instrumented columns. The testing results on saturated specimens with positive PWP are used to determine the primary and secondary compression (consolidation) parameters of the tailings, based on excess PWP and displacement measurements. The compression tests with controlled negative PWP were conducted using two stress paths: vertical loading with a constant (imposed) suction and with a progressively increasing suction. The results from these tests illustrate specifically, for the first time, the combined effects of the net vertical stress and suction on tailings compressibility parameters, and on the evolution of PWP. The experimental procedures and related experimental results presented here can be quite useful for the analysis of tailings consolidation in the field, where both positive and negative PWP can occur.

Download Full-text

Predicting Hard Rock Pillar Stability Using GBDT, XGBoost, and LightGBM Algorithms

Mathematics ◽

10.3390/math8050765 ◽

2020 ◽

Vol 8 (5) ◽

pp. 765 ◽

Cited By ~ 6

Author(s):

Weizhang Liang ◽

Suizhi Luo ◽

Guoyan Zhao ◽

Hao Wu

Keyword(s):

Large Scale ◽

Prediction Models ◽

Hard Rock ◽

Gradient Boosting ◽

Pillar Stability ◽

Rock Pillar ◽

Light Gradient ◽

Gradient Boosting Machine ◽

Extreme Gradient Boosting ◽

Hard Rock Mines

Predicting pillar stability is a vital task in hard rock mines as pillar instability can cause large-scale collapse hazards. However, it is challenging because the pillar stability is affected by many factors. With the accumulation of pillar stability cases, machine learning (ML) has shown great potential to predict pillar stability. This study aims to predict hard rock pillar stability using gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM) algorithms. First, 236 cases with five indicators were collected from seven hard rock mines. Afterwards, the hyperparameters of each model were tuned using a five-fold cross validation (CV) approach. Based on the optimal hyperparameters configuration, prediction models were constructed using training set (70% of the data). Finally, the test set (30% of the data) was adopted to evaluate the performance of each model. The precision, recall, and F1 indexes were utilized to analyze prediction results of each level, and the accuracy and their macro average values were used to assess the overall prediction performance. Based on the sensitivity analysis of indicators, the relative importance of each indicator was obtained. In addition, the safety factor approach and other ML algorithms were adopted as comparisons. The results showed that GBDT, XGBoost, and LightGBM algorithms achieved a better comprehensive performance, and their prediction accuracies were 0.8310, 0.8310, and 0.8169, respectively. The average pillar stress and ratio of pillar width to pillar height had the most important influences on prediction results. The proposed methodology can provide a reliable reference for pillar design and stability risk management.

Download Full-text

LESSONS LEARNT FROM OPEN PIT WALL INSTABILITIES: CASE STUDIES OF BC OPEN PIT HARD ROCK MINES

Физико-технические проблемы разработки полезных ископаемых ◽

10.15372/ftprpi20180511 ◽

2018 ◽

Keyword(s):

Case Studies ◽

Hard Rock ◽

Open Pit ◽

Lessons Learnt ◽

Hard Rock Mines

Download Full-text