Application of Artificial Neural Network for Blast Performance Evaluation

Trivedi, Ratnesh

doi:10.15623/ijret.2014.0305104

Cited by 10 publications

(2 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Backpropagation, short for backward propagation of errors, is used to adjust the weights and biases of the ANN by minimizing the error at the output. Bacpropagation is widely used in engineering and science because it is the most versatile and robust technique to find the global minima on an error surface [77]. Backpropagation consists of two steps: the propagation phase and the updating of the weight [75].…”

Section: Artificial Neural Networkmentioning

confidence: 99%

An Overview of Opportunities for Machine Learning Methods in Underground Rock Engineering Design

2019

View full text Add to dashboard Cite

Machine learning methods for data processing are gaining momentum in many geoscience industries. This includes the mining industry, where machine learning is primarily being applied to autonomously driven vehicles such as haul trucks, and ore body and resource delineation. However, the development of machine learning applications in rock engineering literature is relatively recent, despite being widely used and generally accepted for decades in other risk assessment-type design areas, such as flood forecasting. Operating mines and underground infrastructure projects collect more instrumentation data than ever before, however, only a small fraction of the useful information is typically extracted for rock engineering design, and there is often insufficient time to investigate complex rock mass phenomena in detail. This paper presents a summary of current practice in rock engineering design, as well as a review of literature and methods at the intersection of machine learning and rock engineering. It identifies gaps, such as standards for architecture, input selection and performance metrics, and areas for future work. These gaps present an opportunity to define a framework for integrating machine learning into conventional rock engineering design methodologies to make them more rigorous and reliable in predicting probable underlying physical mechanics and phenomenon.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

An Overview of Opportunities for Machine Learning Methods in Underground Rock Engineering Design

2019

View full text Add to dashboard Cite

show abstract

“…Algorithms can analyze various factors, such as material properties, environmental conditions, and explosive characteristics, to optimize blast designs (Monjezi et al, 2011). Modelling blast operation enhances safety, efficiency, and precision, reducing the risk of undesired consequences and improving overall blast performance in mining, construction, or military applications (Trivedi et al, 2014). According to Ganaie et al (2022) ensemble learning is a machine learning technique that combines predictions from multiple models to improve overall performance and accuracy.…”

Section: Introductionmentioning

confidence: 99%

Blast Toes Volume Estimation for Post-Blast Efficiency: A Comparative Analysis of hybrid ensemble learning, voting, and base AI-algorithms

Kahraman,

Taiwo,

Hosseini

et al. 2024

Preprint

View full text Add to dashboard Cite

This study compares base, hybrid, and voting modeling techniques to predict blast toe volume size. The investigation integrates independent models, explores synergies in hybrid approaches, and optimizes accuracy through ensemble voting to offer comprehensive knowledge and more reliable forecasts for blast toe volume estimation in various design. 457 blasting was investigated and data was collected at Anguran lead and zinc mine in Iran. Nine model accuracy indices were used to compare the algorithm's prediction accuracy. The study indicates a significant relationship between toe volume size and explosive charge per delay, as demonstrated by multicollinearity, Spearman, and Kendall correlation analyses. The analysis of the model showed that Light Gradient Boosting Machine (LightGBM) achieved the highest accuracy compared to the other 8 conventional models, with correlation coefficients (R2) of 0.9004 and 0.8625 for the training and testing datasets, respectively. The Hybrid 6 model, which combines LightGBM and CART algorithms, achieved the highest R2 scores of 0.9473 in the training phase and 0.9467 in the testing phase. The Voting 8 model, consisting of LightGBM, GBM, DT, ET, RF, CatBoost, CART, AdaBoost, and XGBoost, had the greatest R2 scores of 0.9876 and 0.97265 in both the training and testing stages. The voting models can reliably forecast toe volume resulting from a blast design pattern, thereby providing a novel tool for simulation.

show abstract