What question did this study set out to answer?

The research aims to create a GA-ANN framework for predicting and optimizing the impacts of blasting in mining operations.

March 26, 2026Discover Applied Sciences1 citationsOpen Access

Simultaneous prediction and design optimisation of blast impacts at Jwaneng mine using a GA ANN framework

OSOnalethata Saubi RJ Rodrigo S. Jamisola RSRaymond S. Suglo

Key Points

The research aims to create a GA-ANN framework for predicting and optimizing the impacts of blasting in mining operations.
Developed a multi-output GA-ANN framework for prediction and design optimization.
Utilized ten input parameters from 120 production blasts.
Compared GA-ANN with PSO-ANN, ABC-ANN, and ICA-ANN for model selection based on accuracy.
Constructed a solution surface using Monte Carlo methods and applied gradient-descent for inverse design.
GA-ANN achieved accuracies of R2 = 0.910 for fragmentation, 0.925 for ground vibration, and 0.967 for airblast.
Inverse design produced input settings yielding approximately 84% fragmentation, 0.10 mm/s vibration, and 41 dB airblast.
The framework enables rapid, constraint-aware 'what-if' queries to improve blast design efficiency.

Abstract

We present a design-ready, multi-output GA-ANN framework for simultaneous prediction and design optimisation of blast impacts, rock fragmentation, ground vibration, and airblast at Debswana’s Jwaneng Mine. Using ten input parameters from 120 production blasts, the model both predicts these impacts and supports rapid, constraint-aware blast design that meets regulatory limits while improving productivity. We compare genetic algorithm-artificial neural network (GA-ANN) with particle swarm optimisation (PSO-ANN), artificial bee colony (ABC-ANN), and imperialist competitive algorithm (ICA-ANN), select GA-ANN on held-out accuracy, construct a multi-output solution surface (10-70-25-3 architecture via Monte Carlo), and apply gradient-descent inverse design. On the test set, GA-ANN attains R2 = 0. 910 (fragmentation), 0. 925 (ground vibration), and 0. 967 (airblast) ; inverse design returns input settings that maximise fragmentation (84%) while minimising vibration (0. 10 mm/s) and airblast (41 dB). The learned solution surface reveals operational trade-offs, enables fast constraint-aware “what-if” queries, and provides a retrainable path to safer, more efficient, compliance-oriented blast design at scale.

AI से पूछें

Bookmark

View Full Paper