A true triaxial strength criterion for rocks by gene expression programming
- Authors: Zhou, Jian , Zhang, Rui , Qiu, Yingui , Khandelwal, Manoj
- Date: 2023
- Type: Text , Journal article
- Relation: Journal of Rock Mechanics and Geotechnical Engineering Vol. 15, no. 10 (2023), p. 2508-2520
- Full Text:
- Reviewed:
- Description: Rock strength is a crucial factor to consider when designing and constructing underground projects. This study utilizes a gene expression programming (GEP) algorithm-based model to predict the true triaxial strength of rocks, taking into account the influence of rock genesis on their mechanical behavior during the model building process. A true triaxial strength criterion based on the GEP model for igneous, metamorphic and magmatic rocks was obtained by training the model using collected data. Compared to the modified Weibols-Cook criterion, the modified Mohr-Coulomb criterion, and the modified Lade criterion, the strength criterion based on the GEP model exhibits superior prediction accuracy performance. The strength criterion based on the GEP model has better performance in R2, RMSE and MAPE for the data set used in this study. Furthermore, the strength criterion based on the GEP model shows greater stability in predicting the true triaxial strength of rocks across different types. Compared to the existing strength criterion based on the genetic programming (GP) model, the proposed criterion based on GEP model achieves more accurate predictions of the variation of true triaxial strength (
Comparative evaluation of empirical approaches and artificial intelligence techniques for predicting uniaxial compressive strength of rock
- Authors: Li, Chuanqi , Zhou, Jian , Dias, Daniel , Du, Kun , Khandelwal, Manoj
- Date: 2023
- Type: Text , Journal article
- Relation: Geosciences (Switzerland) Vol. 13, no. 10 (2023), p.
- Full Text:
- Reviewed:
- Description: The uniaxial compressive strength (UCS) of rocks is one of the key parameters for evaluating the safety and stability of civil and mining structures. In this study, 386 rock samples containing four properties named the load strength (PLS), the porosity (Pn), the P-wave velocity (Vp), and the Schmidt hardness rebound number (SHR) are utilized to predict the UCS using several typical empirical equations (EA) and artificial intelligence (AI) methods, i.e., 16 single regression (SR) equations, 2 multiple regression (MR) equations, and the random forest (RF) models optimized by grey wolf optimization (GWO), moth flame optimization (MFO), lion swarm optimization (LSO), and sparrow search algorithm (SSA). The root mean square error (RMSE), determination coefficient (R2), Willmott’s index (WI), and variance accounted for (VAF) are used to evaluate the predictive performance of all developed models. The evaluation results show that the overall performance of AI models is superior to empirical approaches, especially the LSO-RF model. In addition, the most important input variable is the Pn for predicting the UCS. Therefore, AI techniques are considered as more efficient and accurate approaches to replace the empirical equations for predicting the UCS of these collected rock samples, which provides a reliable and effective idea to predict the rock UCS in the filed site. © 2023 by the authors.
Estimating the mean cutting force of conical picks using random forest with salp swarm algorithm
- Authors: Zhou, Jian , Dai, Yong , Tao, Ming , Khandelwal, Manoj , Zhao, Mingsheng , Li, Qiyue
- Date: 2023
- Type: Text , Journal article
- Relation: Results in Engineering Vol. 17, no. (2023), p.
- Full Text:
- Reviewed:
- Description: Conical picks are widely used as cutting tools in shearers and roadheaders, and the mean cutting force (MCF) is one of the important parameters affecting conical pick performance. As MCF depends on a number of parameters and due to that the existing empirical and theoretical formulas and numerical modelling are not sufficient enough and reliable to predict MCF in a proficient manner. So, in this research, a novel intelligent model based on a random forest algorithm (RF) and a heuristic algorithm called the salp swarm algorithm (SSA) have been applied to determine the optimal hyper-parameters in RF, and root mean square error is used as a fitness function. A total of 188 data samples including 50 rock types and seven parameters (tensile strength of the rock
Hybridizing five neural-metaheuristic paradigms to predict the pillar stress in bord and pillar method
- Authors: Zhou, Jian , Chen, Yuxin , Chen, Hui , Khandelwal, Manoj , Monjezi, Masoud , Peng, Kang
- Date: 2023
- Type: Text , Journal article
- Relation: Frontiers in Public Health Vol. 11, no. (2023), p.
- Full Text:
- Reviewed:
- Description: Pillar stability is an important condition for safe work in room-and-pillar mines. The instability of pillars will lead to large-scale collapse hazards, and the accurate estimation of induced stresses at different positions in the pillar is helpful for pillar design and guaranteeing pillar stability. There are many modeling methods to design pillars and evaluate their stability, including empirical and numerical method. However, empirical methods are difficult to be applied to places other than the original environmental characteristics, and numerical methods often simplify the boundary conditions and material properties, which cannot guarantee the stability of the design. Currently, machine learning (ML) algorithms have been successfully applied to pillar stability assessment with higher accuracy. Thus, the study adopted a back-propagation neural network (BPNN) and five elements including the sparrow search algorithm (SSA), gray wolf optimizer (GWO), butterfly optimization algorithm (BOA), tunicate swarm algorithm (TSA), and multi-verse optimizer (MVO). Combining metaheuristic algorithms, five hybrid models were developed to predict the induced stress within the pillar. The weight and threshold of the BPNN model are optimized by metaheuristic algorithms, in which the mean absolute error (MAE) is utilized as the fitness function. A database containing 149 data samples was established, where the input variables were the angle of goafline (A), depth of the working coal seam (H), specific gravity (G), distance of the point from the center of the pillar (C), and distance of the point from goafline (D), and the output variable was the induced stress. Furthermore, the predictive performance of the proposed model is evaluated by five metrics, namely coefficient of determination (R2), root mean squared error (RMSE), variance accounted for (VAF), mean absolute error (MAE), and mean absolute percentage error (MAPE). The results showed that the five hybrid models developed have good prediction performance, especially the GWO-BPNN model performed the best (Training set: R2 = 0.9991, RMSE = 0.1535, VAF = 99.91, MAE = 0.0884, MAPE = 0.6107; Test set: R2 = 0.9983, RMSE = 0.1783, VAF = 99.83, MAE = 0.1230, MAPE = 0.9253). Copyright © 2023 Zhou, Chen, Chen, Khandelwal, Monjezi and Peng.
Knowledge mapping of research progress in blast-induced ground vibration from 1990 to 2022 using CiteSpace-based scientometric analysis
- Authors: Zhang, Yulin , He, Haini , Khandelwal, Manoj , Du, Kun , Zhou, Jian
- Date: 2023
- Type: Text , Journal article , Review
- Relation: Environmental Science and Pollution Research Vol. 30, no. 47 (2023), p. 103534-103555
- Full Text: false
- Reviewed:
- Description: Blasting constitutes an essential component of the mining and construction industries. However, the associated nuisances, particularly blast vibration, have emerged as significant concerns that pose threats to operational stability and the safety of the surrounding areas. Given the increasing emphasis on sustainability, ecological responsibility, safety, and geo-environmental practices, the impact of blast vibration has garnered heightened attention and scrutiny. Nevertheless, the field still lacks comprehensive phase analysis studies. Therefore, it is imperative to elucidate the research progress on blast vibration and discern its current frontiers of investigation. To address this need, this study employs bibliometric methods and the CiteSpace 6.1.R2 software to analyze 3093 papers from the Web of Science database. Through this comprehensive analysis, the study aims to chronicle the developmental trajectory, assess the present research status, and identify future trends in the field of blast vibration. The findings of this study reveal that research on “blasting vibration” is advancing rapidly, with the number of citations exhibiting a J-shaped growth curve over time. China emerges as the leading contributor to this research, followed by India, and the foremost institution in this field is Central South University in China. Cluster analysis identifies the effects of ground vibration, numerical simulation, blast load, blasting vibration and rockburst hazard as the most prominent research areas presently. The primary research directions in this domain revolve around the rock fragmentation, compressive strength, particle swarm optimization, and ann. The emergence of these keywords underscores a dynamic shift towards a more holistic and multidisciplinary approach in the field of blasting-induced ground vibration. Furthermore, this study provides a concise overview of blast vibration, discusses prediction techniques, and proposes measures for its control. Additionally, the discussion delves into the social significance of intelligent blasting systems within the context of artificial intelligence, aiming to address the hazards associated with blast-induced ground vibrations. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
Performance evaluation of rockburst prediction based on PSO-SVM, HHO-SVM, and MFO-SVM hybrid models
- Authors: Zhou, Jian , Yang, Peixi , Peng, Pingan , Khandelwal, Manoj , Qiu, Yingui
- Date: 2023
- Type: Text , Journal article
- Relation: Mining, Metallurgy and Exploration Vol. 40, no. 2 (2023), p. 617-635
- Full Text: false
- Reviewed:
- Description: Rockburst prediction is crucial in deep hard rock mines and tunnels to make safer working conditions. Due to the complex interaction of many factors involved in rockburst prediction, such as multi-variable and multi-interference factors, three hybrid support vector machine (SVM) models optimized by particle swarm optimization (PSO), Harris hawk optimization (HHO), and moth flame optimization (MFO) are proposed to predict rockburst hazard level (RHL). The RHL is determined according to four kinds of microseismic characteristic parameters including angular frequency ratio, total energy, apparent stress, and convexity radius. Then, six types of microseismic characteristic parameters are taken as input variables in 343 sets of data, including angular frequency ratio and total energy, etc. And the RHL is taken as the output target of rockburst prediction. The classification performance of PSO-SVM, HHO-SVM, and MFO-SVM hybrid models is evaluated by accuracy (ACC), precision (PRE), and kappa coefficient. Findings reveal that the MFO-SVM model performs best in terms of accuracy, with ACC, PRE, and kappa coefficients reaching 0.9559, 0.9063, and 0.9094 respectively, while PSO-SVM and HHO-SVM have similar performances. However, the PSO-SVM, HHO-SVM, and MFO-SVM all perform better than the unoptimized SVM model. This confirms that the three optimization algorithms significantly enhance the rockburst prediction capacity of the SVM model to help mine practitioners apply machine learning methods to rockburst prediction problems appropriately. © 2023, Society for Mining, Metallurgy & Exploration Inc.
Stability prediction of underground entry-type excavations based on particle swarm optimization and gradient boosting decision tree
- Authors: Zhou, Jian , Huang, Shuai , Tao, Ming , Khandelwal, Manoj , Dai, Yong , Zhao, Mingsheng
- Date: 2023
- Type: Text , Journal article
- Relation: Underground Space (China) Vol. 9, no. (2023), p. 234-249
- Full Text:
- Reviewed:
- Description: The stability of underground entry-type excavations will directly affect the working environment and the safety of staff. Empirical critical span graphs and traditional statistics learning methods can not meet the requirements of high accuracy for stability assessment of entry-type excavations. Therefore, this study proposes a new prediction method based on machine learning to scientifically adjust the critical span graph. Accordingly, the particle swarm optimization (PSO) algorithm is used to optimize the core parameters of the gradient boosting decision tree (GBDT), abbreviated as PSO-GBDT. Moreover, the classification performance of eight other classifiers including GDBT, k-nearest neighbors (KNN), two kinds of support vector machines (SVM), Gaussian naive Bayes (GNB), logistic regression (LR) and linear discriminant analysis (LDA) are also applied to compare with the proposed model. Findings revealed that compared with the other eight models, the prediction performance of PSO-GBDT is undoubtedly the most reliable, and its classification accuracy is up to 0.93. Therefore, this model has great potential to provide a more scientific and accurate choice for the stability prediction of underground excavations. In addition, each classification model is used to predict the stability category of several grid points divided by the critical span graph, and the updated critical span graph of each model is discussed in combination with previous studies. The results show that the PSO-GBDT model has the advantages of being scientific, accurate and efficient in updating the critical span graph, and its output decision boundary has strict theoretical support, which can help mine operators make favorable economic decisions. © 2022
A hybrid metaheuristic approach using random forest and particle swarm optimization to study and evaluate backbreak in open-pit blasting
- Authors: Dai, Yong , Khandelwal, Manoj , Qiu, Yingui , Zhou, Jian , Monjezi, Monjezi , Yang, Peixi
- Date: 2022
- Type: Text , Journal article
- Relation: Neural Computing and Applications Vol. 34, no. 8 (2022), p. 6273-6288
- Full Text:
- Reviewed:
- Description: Backbreak is a rock fracture problem that exceeds the limits of the last row of holes in an explosion operation. Excessive backbreak increases operational costs and also poses a threat to mine safety. In this regard, a new hybrid intelligence approach based on random forest (RF) and particle swarm optimization (PSO) is proposed for predicting backbreak with high accuracy to reduce the unsolicited phenomenon induced by backbreak in open-pit blasting. A data set of 234 samples with six input parameters including special drilling (SD), spacing (S), burden (B), hole length (L), stemming (T) and powder factor (PF) and one output parameter backbreak (BB) is set up in this study. Seven input combinations (one with six parameters, six with five parameters) are built to generate the optimal prediction model. The PSO algorithm is integrated with the RF algorithm to find the optimal hyper-parameters of each model and the fitness function, which is the mean absolute error (MAE) of ten cross-validations. The performance capacities of the optimal models are assessed using MAE, root-mean-square error (RMSE), Pearson correlation coefficient (R2) and mean absolute percentage error (MAPE). Findings demonstrated that the PSO–RF model combining L–S–B–T–PF with MAE of 0.0132 and 0.0568, RMSE of 0.0811 and 0.1686, R2 of 0.9990 and 0.9961 and MAPE of 0.0027 and 0.0116 in training and testing phases, respectively, has optimal prediction performance. The optimal PSO–RF models were compared with the classical artificial neural network, RF, genetic programming, support vector machine and convolutional neural network models and show that the PSO–RF model has superiority in predicting backbreak. The Gini index of each input variable has also been calculated in the RF model, which was 31.2 (L), 23.1 (S), 27.4 (B), 36.6 (T), 23.4 (PF) and 16.9 (SD), respectively. © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.
COSMA-RF : new intelligent model based on chaos optimized slime mould algorithm and random forest for estimating the peak cutting force of conical picks
- Authors: Zhou, Jian , Dai, Yong , Du, Kun , Khandelwal, Manoj , Li, Chuanqi , Qiu, Yingui
- Date: 2022
- Type: Text , Journal article
- Relation: Transportation Geotechnics Vol. 36, no. (2022), p.
- Full Text: false
- Reviewed:
- Description: Since conical pick cutting is a complex process of multi-factor coupling effects, theoretical model construction for cutting force prediction is a quite difficult task. In this paper, various novel intelligent models based on chaos-optimized slime mould algorithm (COSMA) and random forest (RF) are proposed for this task. In the proposed COSMA-RF methods, the chaos algorithms with the ergodicity and randomness are introduced to chaotically determine the initial position to form a COSMA, and the SMA and COSMA are used to tune the hyperparameters of RF and mean square error are assigned as a fitness function. Consequently, 205 data samples having seven variables (tensile strength of the rock
Cross-correlation stacking-based microseismic source location using three metaheuristic optimization algorithms
- Authors: Zhou, Jian , Shen, Xiaojie , Qiu, Yingui , Shi, Xiuzhi , Khandelwal, Manoj
- Date: 2022
- Type: Text , Journal article
- Relation: Tunnelling and Underground Space Technology Vol. 126, no. (2022), p.
- Full Text: false
- Reviewed:
- Description: 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. © 2022 Elsevier Ltd
Experimental investigation and theoretical analysis of indentations on cuboid hard rock using a conical pick under uniaxial lateral stress
- Authors: Wang, Shaofeng , Sun, Licheng , Li, Xibing , Zhou, Jian , Du, Kun , Wang, Shanyong , Khandelwal, Manoj
- Date: 2022
- Type: Text , Journal article
- Relation: Geomechanics and Geophysics for Geo-Energy and Geo-Resources Vol. 8, no. 1 (2022), p.
- Full Text:
- Reviewed:
- Description: Abstract: Stress conditions are critical in deep hard rock mining and significantly influence hard rock cuttability. The peak cutting force (PCF), cutting work (CW), and specific energy (SE) can reflect rock cuttability and determine the feasibility and saving of mechanized mining to some extent. In this paper, the influence of uniaxial lateral stress on rock cuttability was investigated by an indentation experiment on cuboid rock using a conical pick, and a theoretical model was proposed to analyze the PCF and associated factors. The PCF, CW, and SE were used as indices to measure hard rock cuttability. The regression analyses show that rock cuttability presents as decreasing followed by increasing as uniaxial lateral stresses increases. The theoretical model was established by simplifying rock fragments into three-dimensional ellipse cones, and a formula was derived based on the elastic fracture mechanics theory. The error between the calculated and experimental values is 3.8%, which confirms the accuracy of the prediction formula. Finally, rock fragmentation by using conical picks was successfully applied on the field mining stope by inducing high geostresses to promote adjustments in stress and improve ore-rock cuttability. Highlights: (1)The influences of uniaxial lateral stress on rock cuttability have been investigated.(2)The peak cutting force, cutting work and specific energy can reflect the rock cuttability.(3)A new theoretical model has been proposed to analyze the peak cutting force.(4)The rock fragmentation using conical picks was successfully applied in deep hard rock mining. © 2022, The Author(s), under exclusive licence to Springer Nature Switzerland AG.
Investigating the slurry fluidity and strength characteristics of cemented backfill and strength prediction models by developing hybrid GA-SVR and PSO-SVR
- Authors: Du, Kun , Liu, Minghui , Zhou, Jian , Khandelwal, Manoj
- Date: 2022
- Type: Text , Journal article
- Relation: Mining, Metallurgy and Exploration Vol. 39, no. 2 (2022), p. 433-452
- Full Text: false
- Reviewed:
- Description: The waste rock and tailings backfill into the mined-out areas are the most effective method for solving the environmental pollution and surface disasters for nonferrous metals mines. In practice, the success and availability of backfill operations are dependent on the slurry fluidity and the strength properties of cement backfill. The transport of the slurry through the pipeline to the designated backfilling area relies on its eximious flow properties, while the appropriate strength of the filling body ensures the safe operation of the stope. In this paper, the effects of cement and aggregate types on the slurry fluidity and strength characteristics of cemented backfill are studied in detail, which are often ignored in other pieces of literature. Diffusivity is used as an indicator to evaluate the slurry fluidity. Various slurries whose concentrations ranging from 70%, 73%, 75%, 78%, and 80% are made with different aggregate ratios and cement-sand ratios are tested. It has been shown that slurry fluidity is inversely related to its concentration, but 78% is the “stopping point” for the deterioration of fluidity. The addition of rod-milled sand improves or worsens the cemented backfill (CB) strength depending on the amount of rob-milled sand. The uniaxial compression experiment results on 216 CB specimens produced by different combinations of influencing variables showed that CB specimens made from cement with superior mechanical properties have a higher uniaxial compressive strength (σucs). It has been also found that the effect of aggregate ratio on the CB strength is not singular, but works in conjunction with the curing time and the cement-sand ratio. The longer the curing time and the higher the cement content, the higher the CB’s σucs. To avoid the time-consuming and costly problem of obtaining the strength of the CB from indoor experiments, an SVR model capable of predicting the uniaxial compression strength of CB specimens is proposed, which is optimized by genetic algorithm (GA) and particle swarm optimization (PSO) algorithm. The results of the three performance indexes (MAPE, MSE, and R2) show the superior performance of the GA-SVR and PSO-SVR models and the agreement of the predicted results with the experimental results, which indicate that these two models can accurately predict the σucs of CB. © 2022, Society for Mining, Metallurgy & Exploration Inc.
Mineral composition and grain size effects on the fracture and Acoustic Emission (AE) characteristics of rocks under compressive and tensile stress
- Authors: Du, Kun , Sun, Yu , Zhou, Jian , Khandelwal, Manoj , Gong, Fengqiang
- Date: 2022
- Type: Text , Journal article
- Relation: Rock Mechanics and Rock Engineering Vol. 55, no. 10 (2022), p. 6445-6474
- Full Text:
- Reviewed:
- Description: The influence of rock mineral composition and mineral grain size on basic rock strength performance and AE characteristics have been studied, 13 different rocks microstructures are analyzed in an optical microscope thin section using petrographic image analysis, making it possible to determine the mineral composition and mineral texture characteristics of rocks. Then, the basic strength parameters of rock and AE signals generated during fracture propagation were obtained by UCT (uniaxial compression test) and BIT (Brazilian intension test). Finally, the relationship between basic strength parameters and AE characteristics of rock with mineral composition and grain size was analyzed. The results showed that different mineral constituents have significant effects on rock strength. The positive influence of plagioclase content on igneous strength was obtained. Sedimentary rocks strength increases initially and then decreases with the increase of plagioclase content. Besides, with the increase in quartz and K-feldspar content, the strength of the rock was weakened obviously. It is also found that the greater the dimensional deviation of mineral grain, the greater the strength of the rock. The strength of igneous rocks was inversely proportional to the mineral grain size, but there is no correlation between the sedimentary rocks strength and the mineral grain size. Furthermore, the tension–shear crack propagation of rock can effectively distinguish by judging that the data set of the AF–RA density graph was nearby the AF axis or RA axis and the peak frequency data sets of below 100 kHz or more than. Alterations in the rock nature are the main key reasons for the differences between AE hit rate, AE count rate, AE energy, and cumulative energy. The plagioclase content and grain size play a decisive role in AE signal characteristics and failure mode. © 2022, The Author(s).
Novel approach to evaluate rock mass fragmentation in block caving using unascertained measurement model and information entropy with flexible credible identification criterion
- Authors: Zhou, Jian , Chen, Chao , Khandelwal, Manoj , Tao, Ming , Li, Chuanqi
- Date: 2022
- Type: Text , Journal article
- Relation: Engineering with computers Vol. 38, no. Suppl 5 (2022), p. 3789-3809
- Full Text: false
- Reviewed:
- Description: In recent years, block caving has drawn the attention of many mine enterprises due to the admired extraction rate and lower cost, which can exploit the materials via gravity inflow. At the same time, the limitation of this advanced method cannot be underestimated easily, such as surface subsidence and boulder, usually, the latter leads to the frequent secondary blast and damage of bottom structure. Thus, it is significant and crucial to evaluate the fragmentation before the implement of this method. But, traditional fragmentation assessment model suffers from the complex process of modeling and simulation. In this study, a hybrid model consists of unascertained measurement theory and information entropy was constructed to meet the requirements of this prospective mining method. Considering the influence of various parameters on rock fragmentation at the same time, twenty-three factors (i.e., uniaxial compressive strength, modulus ratio, fracture frequency, aperture, persistence, joint orientation, roughness, infilling, weathering, in situ stresses, stress orientation, stress ratio, underground water, fine ratio, hydraulic radius, undercut height, draw column height, draw points geometry, draw rate, multiple draw interaction, air gap height, broken ore density and undercut direction) were chosen to extract the main characteristics of rock mass samples from the two different mines, namely Reserve North ( Chile ), Diablo Regimiento ( Chile ) and Kemess mine ( Canada ). A new membership function (logarithm curve) was added to eliminate uncertainty results from the low level of knowledge about rock mass properties. Then, information entropy was performed to quantify the impacts of individual index. A credible degree identification criterion ( R η ) was also applied to review the sample attributes qualitatively. Ultimately, degree of fragmentation of the three samples was judged easily on the basis of a composite measurement vectors and R η . The evaluation results showed that the fragmentation grades of Reserve North , Diablo Regimiento and Kemess mine , separately, were “Good”, “Medium” and “Good”. With regard to the excellent performance of this hybrid model, it can be seen as a reliable approach to describe the fragmentation potential during the ore extraction using block caving mining method.
Performance evaluation of hybrid WOA-XGBoost, GWO-XGBoost and BO-XGBoost models to predict blast-induced ground vibration
- Authors: Qiu, Yingui , Zhou, Jian , Khandelwal, Manoj , Yang, Haitao , Yang, Peixi , Li, Chuanqi
- Date: 2022
- Type: Text , Journal article
- Relation: Engineering with Computers Vol. 38, no. (2022), p. 4145-4162
- Full Text: false
- Reviewed:
- Description: Accurate prediction of ground vibration caused by blasting has always been a significant issue in the mining industry. Ground vibration caused by blasting is a harmful phenomenon to nearby buildings and should be prevented. In this regard, a new intelligent method for predicting peak particle velocity (PPV) induced by blasting had been developed. Accordingly, 150 sets of data composed of thirteen uncontrollable and controllable indicators are selected as input dependent variables, and the measured PPV is used as the output target for characterizing blast-induced ground vibration. Also, in order to enhance its predictive accuracy, the gray wolf optimization (GWO), whale optimization algorithm (WOA) and Bayesian optimization algorithm (BO) are applied to fine-tune the hyper-parameters of the extreme gradient boosting (XGBoost) model. According to the root mean squared error (RMSE), determination coefficient (R2), the variance accounted for (VAF), and mean absolute error (MAE), the hybrid models GWO-XGBoost, WOA-XGBoost, and BO-XGBoost were verified. Additionally, XGBoost, CatBoost (CatB), Random Forest, and gradient boosting regression (GBR) were also considered and used to compare the multiple hybrid-XGBoost models that have been developed. The values of RMSE, R2, VAF, and MAE obtained from WOA-XGBoost, GWO-XGBoost, and BO-XGBoost models were equal to (3.0538, 0.9757, 97.68, 2.5032), (3.0954, 0.9751, 97.62, 2.5189), and (3.2409, 0.9727, 97.65, 2.5867), respectively. Findings reveal that compared with other machine learning models, the proposed WOA-XGBoost became the most reliable model. These three optimized hybrid models are superior to the GBR model, CatB model, Random Forest model, and the XGBoost model, confirming the ability of the meta-heuristic algorithm to enhance the performance of the PPV model, which can be helpful for mine planners and engineers using advanced supervised machine learning with metaheuristic algorithms for predicting ground vibration caused by explosions. © 2021, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.
Six novel hybrid extreme learning machine–swarm intelligence optimization (ELM–SIO) models for predicting backbreak in open-pit blasting
- Authors: Li, Chuanqi , Zhou, Jian , Khandelwal, Manoj , Zhang, Xiliang , Monjezi, Masoud , Qiu, Yingui
- Date: 2022
- Type: Text , Journal article
- Relation: Natural Resources Research Vol. 31, no. 5 (2022), p. 3017-3039
- Full Text:
- Reviewed:
- Description: Backbreak (BB) is one of the serious adverse blasting consequences in open-pit mines, because it frequently reduces economic benefits and seriously affects the safety of mines. Therefore, rapid and accurate prediction of BB is of great significance to mine blasting design and other production activities. For this purpose, six different swarm intelligence optimization (SIO) algorithms were proposed to optimize the extreme learning machine (ELM) model for BB prediction, i.e., ELM-based particle swarm optimization (ELM–PSO), ELM-based fruit fly optimization (ELM–FOA), ELM-based whale optimization algorithm (ELM–WOA), ELM-based lion swarm optimization (ELM–LOA), ELM-based seagull optimization algorithm (ELM–SOA) and ELM-based sparrow search algorithm (ELM–SSA). In total, 234 data records from blasting operations in the Sungun mine in Iran were used in this study, including six input parameters (special drilling, spacing, burden, hole length, stemming, powder factor) and one output parameter (i.e., BB). To evaluate the predictive performance of the different optimization models and initial models, six performance indicators including the root mean square error (RMSE), Pearson correlation coefficient (R), determination coefficient (R2), variance accounted for (VAF), mean absolute error (MAE) and sum of square error (SSE) were used to evaluate the models in the training and testing phases. The results show that the ELM–LSO was the best model to predict BB with RMSE of 0.1129 (R: 0.9991, R2: 0.9981, VAF: 99.8135%, MAE: 0.0706 and SSE: 2.0917) in the training phase and 0.2441 in the testing phase (R: 0.9949, R2: 0.9891, VAF: 98.9806%, MAE: 0.1669 and SSE: 4.1710). Hence, ELM techniques combined with SIO algorithms are an effective method to predict BB. © 2022, The Author(s).
Utilization methods and practice of abandoned mines and related rock mechanics under the ecological and double carbon strategy in china—a comprehensive review
- Authors: Du, Kun , Xie, Junjie , Khandelwal, Manoj , Zhou, Jian
- Date: 2022
- Type: Text , Journal article , Review
- Relation: Minerals Vol. 12, no. 9 (2022), p.
- Full Text:
- Reviewed:
- Description: Governance of abandoned mines has become a pressing issue for China. The utilization of abandoned mines is a technology that can solve the problem of governance and recreate the value of mines, which is in line with the current strategic goals of ecological protection and double carbon in China. In this paper, the various utilization models and the advances in rock mechanics of abandoned mines across the globe are summarized and reviewed. The utilization models of abandoned mines can be categorized into four aspects: Energy storage, Waste treatment, Ecological restoration, and carbon dioxide (CO2) sequestration. There are a number of applications and uses of abandoned mines, such as pumped storage, compressed air storage, salt cavern gas/oil storage construction, carbon dioxide storage and utilization, radioactive waste disposal and treatment, and tourism development. Various progress practices of abandoned mines are discussed in detail with emphasis on the national conditions of China. The basic rock mechanics problems and advances involved in the construction of the facilities related to the utilization of abandoned mines are discussed and evaluated. The establishment of relevant research and experimental platforms will contribute to the sustainable development of China’s mining industry and the improvement of clean technologies. © 2022 by the authors.
A combination of expert-based system and advanced decision-tree algorithms to predict air-overpressure resulting from quarry blasting
- Authors: He, Ziguang , Armaghani, Danial , Masoumnezhad, Mojtaba , Khandelwal, Manoj , Zhou, Jian , Murlidhar, Bhatawdekar
- Date: 2021
- Type: Text , Journal article
- Relation: Natural Resources Research Vol. 30, no. 2 (2021), p. 1889-1903
- Full Text:
- Reviewed:
- Description: This study combined a fuzzy Delphi method (FDM) and two advanced decision-tree algorithms to predict air-overpressure (AOp) caused by mine blasting. The FDM was used for input selection. Thus, the panel of experts selected four inputs, including powder factor, max charge per delay, stemming length, and distance from the blast face. Once the input selection was completed, two decision-tree algorithms, namely extreme gradient boosting tree (XGBoost-tree) and random forest (RF), were applied using the inputs selected by the experts. The models are evaluated with the following criteria: correlation coefficient, mean absolute error, gains chart, and Taylor diagram. The applied models were compared with the XGBoost-tree and RF models using the full set of data without input selection results. The results of hybridization showed that the XGBoost-tree model outperformed the RF model. Concerning the gains, the XGBoost-tree again outperformed the RF model. In comparison with the single decision-tree models, the single models had slightly better correlation coefficients; however, the hybridized models were simpler and easier to understand, analyze and implement. In addition, the Taylor diagram showed that the models applied outperformed some other conventional machine learning models, including support vector machine, k-nearest neighbors, and artificial neural network. Overall, the findings of this study suggest that combining expert opinion and advanced decision-tree algorithms can result in accurate and easy to understand predictions of AOp resulting from blasting in quarry sites. © 2020, International Association for Mathematical Geosciences.
Developing a hybrid model of Jaya algorithm-based extreme gradient boosting machine to estimate blast-induced ground vibrations
- Authors: Zhou, Jian , Qiu, Yingui , Khandelwal, Manoj , Zhu, Shuangli , Zhang, Xiliang
- Date: 2021
- Type: Text , Journal article
- Relation: International Journal of Rock Mechanics and Mining Sciences Vol. 145, no. (2021), p.
- Full Text:
- Reviewed:
- Description: Blasting is still being considered to be one the most important applicable alternatives for conventional excavations. Ground vibration generated due to blasting is an undesirable phenomenon which is harmful for the nearby structures and should be prevented. In this regard, a novel intelligent approach for predicting blast-induced PPV was developed. The distinctive Jaya algorithm and high efficient extreme gradient boosting machine (XGBoost) were applied to obtain the goal, called the Jaya-XGBoost model. Accordingly, 150 sets of data composed of 13 controllable and uncontrollable parameters are chosen as input independent variables and the measured peak particle velocity (PPV) is chosen as an output dependent variable. Also, the Jaya algorithm was used for optimization of hyper-parameters of XGBoost. Additionally, six empirical models and several machine learning models such as XGBoost, random forest, AdaBoost, artificial neural network and Bagging were also considered and applied for comparison of the proposed Jaya-XGBoost model. Accuracy criteria including determination coefficient (R2), root-mean-square error (RMSE), mean absolute error (MAE), and the variance accounted for (VAF) were used for the assessment of models. For this study, 150 blasting operations were analyzed. Also, the Shapley Additive Explanations (SHAP) method is used to interpret the importance of features and their contribution to PPV prediction. Findings reveal that the proposed Jaya-XGBoost emerged as the most reliable model in contrast to other machine learning models and traditional empirical models. This study may be helpful to mining researchers and engineers who use intelligent machine learning algorithms to predict blast-induced ground vibration. © 2021 Elsevier Ltd
Estimation of the TBM advance rate under hard rock conditions using XGBoost and Bayesian optimization
- Authors: Zhou, Jian , Qiu, Yingui , Zhu, Shuangli , Armaghani, Danial , Khandelwal, Manoj , Mohamad, Edy
- Date: 2021
- Type: Text , Journal article
- Relation: Underground Space Vol. 6, no. 5 (Oct 2021), p. 506-515
- Full Text:
- Reviewed:
- Description: The advance rate (AR) of a tunnel boring machine (TBM) under hard rock conditions is a key parameter in the successful implementation of tunneling engineering. In this study, we improved the accuracy of prediction models by employing a hybrid model of extreme gradient boosting (XGBoost) with Bayesian optimization (BO) to model the TBM AR. To develop the proposed models, 1286 sets of data were collected from the Peng Selangor Raw Water Transfer tunnel project in Malaysia. The database consists of rock mass and intact rock features, including rock mass rating, rock quality designation, weathered zone, uniaxial compressive strength, and Brazilian tensile strength. Machine specifications, including revolution per minute and thrust force, were considered to predict the TBM AR. The accuracies of the predictive models were examined using the root mean squares error (RMSE) and the coefficient of determination (R-2) between the observed and predicted yield by employing a five-fold cross-validation procedure. Results showed that the BO algorithm can capture better hyper-parameters for the XGBoost prediction model than can the default XGBoost model. The robustness and generalization of the BO-XGBoost model yielded prominent results with RMSE and R-2 values of 0.0967 and 0.9806 (for the testing phase), respectively. The results demonstrated the merits of the proposed BO-XGBoost model. In addition, variable importance through mutual information tests was applied to interpret the XGBoost model and demonstrated that machine parameters have the greatest impact as compared to rock mass and material properties.