► SVM for the determination of classification of long-term rockburst is proposed. ► The SVMs is used into classification technique with (RBF) kernel function. ► The heuristic algorithms of GA and PSO ...are adopted to SVMs. ► The heuristic algorithms of GA & PSO can speed up SVMs parameter optimization search.
Rockburst possibility prediction is an important activity in many underground openings design and construction as well as mining production. Due to the complex features of rockburst hazard assessment systems, such as multivariables, strong coupling and strong interference, this study employs support vector machines (SVMs) for the determination of classification of long-term rockburst for underground openings. SVMs is firmly based on the theory of statistical learning algorithms, uses classification technique by introducing radial basis function (RBF) kernel function. The inputs of models are buried depth H, rocks’ maximum tangential stress σθ, rocks’ uniaxial compressive strength σc, rocks’ uniaxial tensile strength σt, stress coefficient σθ/σc, rock brittleness coefficient σc/σt and elastic energy index Wet. In order to improve predictive accuracy and generalization ability, the heuristic algorithms of genetic algorithm (GA) and particle swarm optimization algorithm (PSO) are adopted to automatically determine the optimal hyper-parameters for SVMs. The performance of hybrid models (GA+SVMs=GA-SVMs) and (PSO+SVMs=PSO-SVMs) have been compared with the grid search method of support vector machines (GSM-SVMs) model and the experimental values. It also gives variance of predicted data. A rockburst dataset, which consists of 132 samples, was employed to evaluate the current method for predicting rockburst grade, and the good results of overall success rate were obtained. The results indicated that the heuristic algorithms of GA and PSO can speed up SVMs parameter optimization search, the proposed method is robust model and might hold a high potential to become a useful tool in rockburst prediction research.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
•A novel prediction method that utilizes the gradient boosting machine (GBM) method to analyze slope stability.•221 different actual slope cases between 1994 and 2011 with circular mode failure are ...examined using GBM method.•Three performance metrics, the AUC, classification accuracy rate and Cohen’s Kappa coefficient are employed.•The GBM model has high credibility for the prediction of slope stability.•Geometrical slope design parameters (γ, C and H) are the most influential on the stability of slope.
Prediction of slope stability is one of the most crucial tasks in mining and geotechnical engineering projects. The accuracy of the prediction is very important for mitigating the risk of slope instability and enhancing mine safety in preliminary design. However, existing methods such as traditional statistical learning models are unable to provide accurate results for slope instability due to the complexity and uncertainties of multiple related factors with small unbalanced data samples thus requiring complex data processing algorithms. To address this limitation, this paper presents a novel prediction method that utilizes the gradient boosting machine (GBM) method to analyze slope stability. The GBM-based model is developed by the freely available R Environment software, trained and tested with the parameters obtained from the detailed investigation of 221 different actual slope cases between 1994 and 2011 with circular mode failure available in the literature. The stability of the circular slope accounts for the unit weight (γ), cohesion (c), angle of internal friction (φ), slope angle (β), slope height (H) and pore water pressure coefficient (ru). A fivefold cross-validation procedure is implemented to determine the optimal parameter values during the GBM modeling and an external testing set is employed to validate the prediction performance of models. Area under the curve (AUC), classification accuracy rate and Cohen’s Kappa coefficient have been employed for measuring the performance of the proposed model. The analysis of AUC, accuracy together with kappa for the dataset demonstrate that the GBM model has high credibility as it achieves a comparable AUC, classification accuracy rate and Cohen’s kappa values of 0.900, 0.8654 and 0.7324, respectively for the prediction of slope stability. Also, variable importance and partial dependence plots are used to interpret the complex relationships between the GBM predictive results and predictor variables.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
To test the impact of different mixture ratios on backfilling strength in Fankou lead–zinc mine, various mixture ratio designs have been conducted. Meanwhile, to improve the strength of ultra-fine ...tailings-based cement paste backfill (CPB), two kinds of fibers were utilized in this study, namely polypropylene (PP) fibers and straw fibers. To achieve these, a total of 144 CPB backfilling scenarios with different combinations of influenced factors were tested by uniaxial compressive tests. The test results indicated that polypropylene fibers improve the strength of CPB, while in some scenarios the addition of straw fibers decreases the strength of CPB. In this research, the support vector machine (SVM) technique coupled with three heuristic algorithms, namely genetic algorithms, particle swarm optimization and salp swarm algorithm (SSA), was developed to predict the strength of fiber-reinforced CPB. Also, the optimal performance of metaheuristic algorithms was compared with one fundamental search method, i.e., grid search (GS). The overall performance of four optimal algorithms was calculated by the ranking system. It can be found that these four approaches all presented satisfactory predictive capability. But the metaheuristic algorithms can capture better hyper-parameters for SVM prediction models compared with GS-SVM method. The robustness and generalization of SSA-SVM methods were the most prominent with the
R
2
values of 0.9245 and 0.9475 for training sets and testing sets. Therefore, SSA-SVM will be recommended to model the complexity of interactions for fiber-reinforced CPB and predict fiber-reinforced CPB strength.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
Display omitted
•Three metaheuristic algorithms were proposed to improve the performance the CCS;•Metaheuristic algorithms converges quickly and has high accuracy in CCS problems;•The single location ...time of the MFO-CCS model is 0.28 s;•The errors of the MFO-CCS model inside and outside the array are 36 m and 155 m.
Microseismic location systems tend to be high-speed and precise. However, the requirement of high precision tends to slow down the calculation speed. Fortunately, metaheuristics are able to alleviate this problem. In this research, metaheuristic algorithms are used to improve the performance of cross-correlation stacking (CCS). CCS has able to provide excellent location accuracy as it uses more information in the entire waveform for location. However, this method often requires more calculation time due to its complex mathematical modeling. To overcome this problem, various metaheuristic algorithms (i.e. moth flame optimization (MFO), ant lion optimization (ALO) and grey wolf optimization (GWO)) have been used to improve CCS. It has been found that appropriate control parameters can improve the metaheuristic algorithm performance manyfold. So, these control parameters have been adjusted based on three different perspectives, i.e. success rate (SR), computational efficiency and convergence performance. The results show that these models are able to provide better location efficiency compared to the full grid search (FGS) and particle swarm optimization (PSO) based on ensuring good location accuracy. It is also found that MFO is significantly better than the other metaheuristic algorithms. In addition, the superiority of CCS over traditional location methods is verified through comprehensive tests, and the influence of the speed model and the number of sensors on the location performance of CCS was tested.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
In order to reduce the undesired phenomenon including brow damage, over crushing and bulking yield in the ring blasting which are owning to the unreasonable distribution of blasting energy, a new ...optimization method is proposed to improve the charge scheme based on the Scaled Heelan (SH) model. First, the traversal algorithm for an arrangement of regular holes (holes charged to the collar) is proposed based on the analysis of the current interval charge design method in ring blasting. Second, a new developed mathematical model based on the SH model is introduced to predict the fragment size of the column charge. Then, the optimization method according to two key parameters of the blasted fragment prediction, D50 and D90−D10, is discussed. Finally, a case study is introduced to illustrate the usage and optimization procedure of the program. Sixty trial blasts were conducted in the Tonglvshan copper mine to verify the feasibility and effectiveness of the optimization algorithm. The frequency of occurrence of brow damage was reduced from 36.7% to 16.7% using the proposed method in our sixty field tests, and the loading efficiency was also improved by 11.3% due to the more uniform distribution of muck pile fragment size.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
AbstractEarthquakes have always attracted civil and geotechnical engineers’ attention, especially when it comes to the liquefaction potential of soil. This paper investigates the feasibility of ...classifier based on stochastic gradient boosting (SGB) to explore the liquefaction potential from actual cone penetration test (CPT) and standard penetration test (SPT) field data. SGB is composed of many classification and regression trees which meet the mechanism of ensemble learning and show strong predictive power compared with conventional statistical learning models in several engineering applications. The binary classifier was built by the database gathered from CPT and SPT filed data for predicting the non-liquefaction or liquefaction of soil, the SGB hyperparameters are optimized by grid search method with tenfolds cross validation methods. Three performance metric, namely Cohen’s Kappa coefficient, classification accuracy rate and receiver operating characteristic curve, are used to evaluate the predictive performance of SGB approaches. With CPT and SPT test sets, highest classification accuracy rate of 88.62% and 95.45%, respectively, are achieved with SGB. It is confirmed that the SGB can be applied to characterize the complex relationship between the liquefaction potential and different soil and seismic parameters with great efficiency. Further, relative importance of influencing variables for each model are investigated and demonstrated that the SGB predictor is more sensitive to the indicators of initial soil friction angle for SPT data whereas cone tip resistance for CPT data.
To mitigate the level of blast-induced vibrations, the time-delay experiments involved 5 delay intervals, 8 holes and 11 monitoring stations, were undertaken in a newly constructed underground mine. ...The method of instantaneous energy based on the empirical mode decomposition (EMD) was adopted to identify the actual delay times from the near-field accelerations. Then the Theil-Sen regression was adopted to analyze the vibration attenuation. Based on the drawbacks of the field experiments due to various unpredictable factors, the blast damage model was further employed to make a comprehensive understanding of the effects of delay times. The signature invoked the average waveform of multiple holes in the experimental 75 ms case, then a group of fluctuating signature waveforms were generated from the Monte Carlo scheme based on waveform comparison between the measured and the signature. Upon completion of the model verification, the number of delays was examined within four delay intervals, and 25 delays were selected to figure out the effects of delay times and delay errors. The results state that the peak particle velocity (PPV) and average frequency (AF) are insensitive to delay times irrespective of delay errors, except short delay times. The vibration dominant frequency (DF) is mainly contributed by idea delay times and delay errors, and the optimal delay interval is half of the dominant period, which is only effective to improve DFs at a target location. The commonly used pyrotechnic detonator is competent in most blasts unless structures need to be protected from their resonances.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
The indirect and accurate determination of blast-induced rock movement has important significance in the reduction of ore loss and dilution and in the protection of environment. The present paper ...aims to predict blast-induced rock movement resulting from the Husab Uranium Mine, Namibia, the Coeur Rochester Mine, USA, and the Phoenix Mine, USA, and three new hybrid models using a genetic algorithm (GA), an artificial bee colony algorithm (ABC), a cuckoo search algorithm (CS) and support vector regression (SVR), namely the GA-SVR, ABC-SVR and CS-SVR models, are proposed. Eight typical blasting parameters rock type, number of free faces, first centerline distance, hole diameter, power factor, spacing, subdrill and initial depth of monitoring were chosen as the input variables to establish the intelligent model, and horizontal blast-induced rock movement (
M
H
) was the output variable after conducting the available analyses of the database. Three performance metrics, including the correlation coefficient (
R
2
), mean square error and variance account for, were used to assess the predictive performances of the aforementioned models. Based on the obtained results, the performance metrics show that the GA-SVR, ABC-SVR and CS-SVR model can provide satisfactory performance in estimating blast-induced rock movement, and GA-SVR model can achieve better results than the GWO-SVR, CS-SVR and ANN models when considering both predictive performance and calculation speed.
Article Highlights
Three new hybrid predictive models are proposed (GA-SVR, ABC-SVR and CS-SVR).
An more convenient, easily operable and higher accuracy predictive method for blast-induced rock movement determination is presented.
The GA-SVR model can provide a higher performance capacity when considering both the predictive performance and the calculation speed.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
Most mines choose the drilling and blasting method which has the characteristics of being a cheap and efficient method to fragment rock mass, but blast-induced ground vibration damages the ...surrounding rock mass and structure and is a drawback. To predict, analyze and control the blast-induced ground vibration, the random forest (RF) model, Harris hawks optimization (HHO) algorithm and Monte Carlo simulation approach were utilized. A database consisting of 137 datasets was collected at different locations around the Tonglvshan open-cast mine, China. Seven variables were selected and collected as the input variables, and peak particle velocity was chosen as the output variable. At first, an RF model and a hybrid model, namely a HHO-RF model, were developed, and the prediction results checked by 3 performance indices to show that the proposed HHO-RF model can provide higher prediction performance. Then blast-induced ground vibration was simulated by using the Monte Carlo simulation approach and the developed HHO-RF model. After analyzing, the mean peak particle velocity value was 0.98 cm/s, and the peak particle velocity value did not exceed 1.95 cm/s with a probability of 90%. The research results of this study provided a simple, accurate method and basis for predicting, evaluating blast-induced ground vibration and optimizing the blast design before blast operation.
For maximum metal recovery, considering the movement of ore and waste during the blasting process in loading design is meaningful for reducing ore loss and ore dilution in an open-pit mine. The ...blast-induced rock movement (BIRM) can be directly measured; nevertheless, it is time-consuming and relative expensive. To solve this problem, a novel intelligent prediction model was proposed by using dimensional analysis and optimized artificial neural network technique in this paper based on the BIRM monitoring test in Husab Uranium Mine, Namibia and Phoenix Mine, USA. After using dimensional analysis, five input variables and one output variable were determined with both considering the dimension and physical meaning of each dimensionless variable. Then, artificial neural network technique (ANN) technique was utilized to develop an accurate prediction model, and a metaheuristic algorithm namely the Equilibrium Optimizer (EO) algorithm was applied to search the optimal hyper-parameter combination. For comparison aims, a linear model and a non-linear regression model were also performed, and the comparison results show that the provided hybrid ANN-based model can yield better prediction performance. As a result, it can be concluded that the developed intelligent model in this article has the potential to predict BIRM during bench blasting, and the analysis method and modeling process in this paper can provide a reference for solving other engineering problems.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP