- Bhatawdekar, Ramesh, Roy, Bishwajit, Changtham, Saksarid, Khandelwal, Manoj, Armaghani, Danial, Mohamad, Edy, Pathak, Pranjal, Mondal, Subhrojit, Kumar, Radhikesh, Azlan, Mohd
- Authors: Bhatawdekar, Ramesh , Roy, Bishwajit , Changtham, Saksarid , Khandelwal, Manoj , Armaghani, Danial , Mohamad, Edy , Pathak, Pranjal , Mondal, Subhrojit , Kumar, Radhikesh , Azlan, Mohd
- Date: 2022
- Type: Text , Conference paper
- Relation: International Conference on Geotechnical challenges in Mining, Tunneling and Underground structures, ICGMTU 2021, Virtual, online, 20-21 December 2021, Lecture Notes in Civil Engineering Vol. 228, p. 457-471
- Full Text: false
- Reviewed:
- Description: Physico-mechanical properties of rocks have a direct correlation with the drilling rate of percussive drill. The prediction of drilling rate is important for the deployment of drills during the planning stage. In tropical climatic regions, limestone is classified as blocky, very blocky, blocky/ seamy and disintegrated based on the degree of weathering. Weathering of limestone takes place very rapidly in tropical (wet) climatic regions. Previous researchers have correlated different individual rock mass properties with rate of drilling. However, single property of limestone is not adequate to correlate with the drilling rate. In this study, sensitivity analysis of different properties of weathered limestone was carried out with respect to drilling rate. Rock density, rock quality designation (RQD), geological strength index (GSI), point load index (PLI) and Schmidt hammer rebound number (SHRN) were identified as crucial input parameters. 113 data sets were collected with the foregoing five input parameters and the output parameter as drilling rate of percussive drills. Data was analysed with multi variable regression analysis (MVRA) which showed R2 value as 0.54. Artificial neural network (ANN) has been widely used for solving various engineering problems. On the other hand, optimization problems are solved by the Biogeography Based Optimization (BBO) model. Further this data was analysed with a hybrid intelligent model namely BBO- ANN. The R2 values for training data set and testing data set 0.638 and 0.761 respectively. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Development of architecture of autonomous hydraulic rock breaker for limestone mines
- Sinha, Aryan, Vasan, Sabari, Nandrekar, Job, Aditya, Umang, Khandelwal, Manoj, Prasad, Naresh, Bhatawdekar, Ramesh, Rathinasamy, Vynotdni
- Authors: Sinha, Aryan , Vasan, Sabari , Nandrekar, Job , Aditya, Umang , Khandelwal, Manoj , Prasad, Naresh , Bhatawdekar, Ramesh , Rathinasamy, Vynotdni
- Date: 2022
- Type: Text , Conference paper
- Relation: International Conference on Geotechnical challenges in Mining, Tunneling and Underground structures, ICGMTU 2021, Virtual, online, 20-21 December 2021, Lecture Notes in Civil Engineering Vol. 228, p. 683-695
- Full Text: false
- Reviewed:
- Description: Boulders which are generated during primary blasting are required to undergo secondary blasting prior to crusher operation. Hydraulic rock breaker is one of the techniques which is being utilized to break boulders instead of secondary blasting. This study aims to develop an architecture of AI model for rock breakers with autonomous remote operation. Firstly, several technical specifications of various rock breakers mounted on 30 T class hydraulic rock breakers were evaluated. Also, the factors affecting cost and operation were identified and discussed. Later, the autonomous rock breaker installed on the crusher hopper at a site in Australia was reviewed as global technological advancement. Based on the review, a five-stage architecture for developing autonomous hydraulic rock breaker was developed. The factors affecting the cost of hydraulic excavator and rock breaker can be classified into direct and indirect cost. The direct cost includes operational cost such as oil, replacement of chisel and bucket teeth and wages as well as maintenance cost. Meanwhile, the indirect cost is related to site issues such as locating boulder, boulders jamming crusher, waiting dozer to push boulder, etc. Also, the factors influencing operation of hydraulic hammer shall be classified into very important (i.e. oil flow, chisel diameter), important (i.e. elasticity, impact rate) and desirable (i.e. hardness, chisel length). The five stages architecture for developing autonomous hydraulic rock breaker are development, data collection, data pre-processing, model deployment and model testing. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Prediction of blast-induced ground vibration at a limestone quarry : an artificial intelligence approach
- Arthur, Clement, Bhatawdekar, Ramesh, Mohamad, Edy, Sabri, Mohanad, Bohra, Manish, Khandelwal, Manoj, Kwon, Sangki
- Authors: Arthur, Clement , Bhatawdekar, Ramesh , Mohamad, Edy , Sabri, Mohanad , Bohra, Manish , Khandelwal, Manoj , Kwon, Sangki
- Date: 2022
- Type: Text , Journal article
- Relation: Applied Sciences (Switzerland) Vol. 12, no. 18 (2022), p.
- Full Text:
- Reviewed:
- Description: Ground vibration is one of the most unfavourable environmental effects of blasting activities, which can cause serious damage to neighboring homes and structures. As a result, effective forecasting of their severity is critical to controlling and reducing their recurrence. There are several conventional vibration predictor equations available proposed by different researchers but most of them are based on only two parameters, i.e., explosive charge used per delay and distance between blast face to the monitoring point. It is a well-known fact that blasting results are influenced by a number of blast design parameters, such as burden, spacing, powder factor, etc. but these are not being considered in any of the available conventional predictors and due to that they show a high error in predicting blast vibrations. Nowadays, artificial intelligence has been widely used in blast engineering. Thus, three artificial intelligence approaches, namely Gaussian process regression (GPR), extreme learning machine (ELM) and backpropagation neural network (BPNN) were used in this study to estimate ground vibration caused by blasting in Shree Cement Ras Limestone Mine in India. To achieve that aim, 101 blasting datasets with powder factor, average depth, distance, spacing, burden, charge weight, and stemming length as input parameters were collected from the mine site. For comparison purposes, a simple multivariate regression analysis (MVRA) model as well as, a nonparametric regression-based technique known as multivariate adaptive regression splines (MARS) was also constructed using the same datasets. This study serves as a foundational study for the comparison of GPR, BPNN, ELM, MARS and MVRA to ascertain their respective predictive performances. Eighty-one (81) datasets representing 80% of the total blasting datasets were used to construct and train the various predictive models while 20 data samples (20%) were utilized for evaluating the predictive capabilities of the developed predictive models. Using the testing datasets, major indicators of performance, namely mean squared error (MSE), variance accounted for (VAF), correlation coefficient (R) and coefficient of determination (R2) were compared as statistical evaluators of model performance. This study revealed that the GPR model exhibited superior predictive capability in comparison to the MARS, BPNN, ELM and MVRA. The GPR model showed the highest VAF, R and R2 values of 99.1728%, 0.9985 and 0.9971 respectively and the lowest MSE of 0.0903. As a result, the blast engineer can employ GPR as an effective and appropriate method for forecasting blast-induced ground vibration. © 2022 by the authors.
- Authors: Arthur, Clement , Bhatawdekar, Ramesh , Mohamad, Edy , Sabri, Mohanad , Bohra, Manish , Khandelwal, Manoj , Kwon, Sangki
- Date: 2022
- Type: Text , Journal article
- Relation: Applied Sciences (Switzerland) Vol. 12, no. 18 (2022), p.
- Full Text:
- Reviewed:
- Description: Ground vibration is one of the most unfavourable environmental effects of blasting activities, which can cause serious damage to neighboring homes and structures. As a result, effective forecasting of their severity is critical to controlling and reducing their recurrence. There are several conventional vibration predictor equations available proposed by different researchers but most of them are based on only two parameters, i.e., explosive charge used per delay and distance between blast face to the monitoring point. It is a well-known fact that blasting results are influenced by a number of blast design parameters, such as burden, spacing, powder factor, etc. but these are not being considered in any of the available conventional predictors and due to that they show a high error in predicting blast vibrations. Nowadays, artificial intelligence has been widely used in blast engineering. Thus, three artificial intelligence approaches, namely Gaussian process regression (GPR), extreme learning machine (ELM) and backpropagation neural network (BPNN) were used in this study to estimate ground vibration caused by blasting in Shree Cement Ras Limestone Mine in India. To achieve that aim, 101 blasting datasets with powder factor, average depth, distance, spacing, burden, charge weight, and stemming length as input parameters were collected from the mine site. For comparison purposes, a simple multivariate regression analysis (MVRA) model as well as, a nonparametric regression-based technique known as multivariate adaptive regression splines (MARS) was also constructed using the same datasets. This study serves as a foundational study for the comparison of GPR, BPNN, ELM, MARS and MVRA to ascertain their respective predictive performances. Eighty-one (81) datasets representing 80% of the total blasting datasets were used to construct and train the various predictive models while 20 data samples (20%) were utilized for evaluating the predictive capabilities of the developed predictive models. Using the testing datasets, major indicators of performance, namely mean squared error (MSE), variance accounted for (VAF), correlation coefficient (R) and coefficient of determination (R2) were compared as statistical evaluators of model performance. This study revealed that the GPR model exhibited superior predictive capability in comparison to the MARS, BPNN, ELM and MVRA. The GPR model showed the highest VAF, R and R2 values of 99.1728%, 0.9985 and 0.9971 respectively and the lowest MSE of 0.0903. As a result, the blast engineer can employ GPR as an effective and appropriate method for forecasting blast-induced ground vibration. © 2022 by the authors.
A study on environmental issues of blasting using advanced support vector machine algorithms
- Chen, Lihua, Armaghani, Danial, Fakharian, Pouyan, Bhatawdekar, Ramesh, Samui, P., Khandelwal, Manoj, Khedher, Khaled
- Authors: Chen, Lihua , Armaghani, Danial , Fakharian, Pouyan , Bhatawdekar, Ramesh , Samui, P. , Khandelwal, Manoj , Khedher, Khaled
- Date: 2022
- Type: Text , Journal article
- Relation: International Journal of Environmental Science and Technology Vol. 19, no. 7 (2022), p. 6221-6240
- Full Text:
- Reviewed:
- Description: Air overpressure is a critical negative effect of blasting in construction or production sites and projects. So far, many attempts have been made to prevent or reduce this negative effect on the nearby construction, equipment, or people. While various experiential equations have been proposed to forecast the air overpressure value for determining the blasting area, these models are typically inaccurate and impractical. Due to the recent efforts to predict the air overpressure by employing artificial intelligence techniques, this study developed five support vector machine-based models optimized by some praised optimization techniques, including the moth flame optimization, particle swarm optimization, grey wolf optimization, cuckoo optimization algorithm, and whale optimization algorithm. These algorithms optimize the most important parameters of the support vector machine, including “C” and “gamma”, and improve the performance of this model for air overpressure prediction. The findings showed that the moth flame optimization algorithm is the best optimizer for support vector machine and is suitable for air overpressure prediction. The support vector machine–moth flame optimization model achieved the best R2 (train: 0.9939; test: 0.9941) and comprehensive score (34). On the other hand, the worst model was the support vector machine–particle swarm optimization, which achieved the lowest comprehensive score (13). In addition, all optimization techniques improved the performance of the single support vector machine model. The findings of this study imply that all optimization techniques successfully enhanced the performance of the support vector machine model; however, the moth flame optimization optimizer was the most effective one. The support vector machine–moth flame optimization technique can be employed to solve other mining-related issues. © 2022, Islamic Azad University (IAU). Correction to: A study on environmental issues of blasting using advanced support vector machine algorithms (International Journal of Environmental Science and Technology, (2022), 19, 7, (6221-6240), 10.1007/s13762-022-03999-y): The original version of this article unfortunately contains two mistakes. The spelling of the third author's name was incorrect. The correct name is Pouyan Fakharian (P. Fakharian). Another error was in the acknowledgment section. The correct Grant No. is KJQN202103415. © The Author(s) under exclusive licence to Iranian Society of Environmentalists (IRSEN) and Science and Research Branch, Islamic Azad University 2022
- Authors: Chen, Lihua , Armaghani, Danial , Fakharian, Pouyan , Bhatawdekar, Ramesh , Samui, P. , Khandelwal, Manoj , Khedher, Khaled
- Date: 2022
- Type: Text , Journal article
- Relation: International Journal of Environmental Science and Technology Vol. 19, no. 7 (2022), p. 6221-6240
- Full Text:
- Reviewed:
- Description: Air overpressure is a critical negative effect of blasting in construction or production sites and projects. So far, many attempts have been made to prevent or reduce this negative effect on the nearby construction, equipment, or people. While various experiential equations have been proposed to forecast the air overpressure value for determining the blasting area, these models are typically inaccurate and impractical. Due to the recent efforts to predict the air overpressure by employing artificial intelligence techniques, this study developed five support vector machine-based models optimized by some praised optimization techniques, including the moth flame optimization, particle swarm optimization, grey wolf optimization, cuckoo optimization algorithm, and whale optimization algorithm. These algorithms optimize the most important parameters of the support vector machine, including “C” and “gamma”, and improve the performance of this model for air overpressure prediction. The findings showed that the moth flame optimization algorithm is the best optimizer for support vector machine and is suitable for air overpressure prediction. The support vector machine–moth flame optimization model achieved the best R2 (train: 0.9939; test: 0.9941) and comprehensive score (34). On the other hand, the worst model was the support vector machine–particle swarm optimization, which achieved the lowest comprehensive score (13). In addition, all optimization techniques improved the performance of the single support vector machine model. The findings of this study imply that all optimization techniques successfully enhanced the performance of the support vector machine model; however, the moth flame optimization optimizer was the most effective one. The support vector machine–moth flame optimization technique can be employed to solve other mining-related issues. © 2022, Islamic Azad University (IAU). Correction to: A study on environmental issues of blasting using advanced support vector machine algorithms (International Journal of Environmental Science and Technology, (2022), 19, 7, (6221-6240), 10.1007/s13762-022-03999-y): The original version of this article unfortunately contains two mistakes. The spelling of the third author's name was incorrect. The correct name is Pouyan Fakharian (P. Fakharian). Another error was in the acknowledgment section. The correct Grant No. is KJQN202103415. © The Author(s) under exclusive licence to Iranian Society of Environmentalists (IRSEN) and Science and Research Branch, Islamic Azad University 2022
- «
- ‹
- 1
- ›
- »