4.7 Article

Six Novel Hybrid Extreme Learning Machine-Swarm Intelligence Optimization (ELM-SIO) Models for Predicting Backbreak in Open-Pit Blasting

Journal

NATURAL RESOURCES RESEARCH
Volume 31, Issue 5, Pages 3017-3039

Publisher

SPRINGER
DOI: 10.1007/s11053-022-10082-3

Keywords

Backbreak; blasting; extreme learning machine; swarm intelligence optimization

Funding

  1. National Natural Science Foundation Project of China [42177164]
  2. Innovation-Driven Project of Central South University [2020CX040]
  3. China Scholarship Council [202106370038]

Ask authors/readers for more resources

Backbreak is a serious issue in open-pit mines, impacting the economic benefits and safety. This study proposes six different swarm intelligence optimization algorithms to predict backbreak, and the results show that combining swarm intelligence optimization algorithms with extreme learning machine techniques is effective for backbreak prediction.
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 (R-2), 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, R-2: 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, R-2: 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.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available