Coal mines are prone to fatal vulnerabilities due to improper airflow, a susceptible threat that leads to vitiating safety and human resources. Hence, continuous monitoring of the underground mine’s airflow is essential for detecting any calamities. Various artificial intelligent methods estimate the underground mines’ airflow (non-linear parameter). However, these methods fall into local minima and low convergence rates. This article proposed a novel algorithm that integrates an Adaptive Neural Fuzzy Interface System (ANFIS) and genetic algorithm (GA) to predict the energy consumption and airflow of the ventilation system for underground mines. A GA is studied to automatically search and configure network architecture to reduce the manual tuning effort required for optimal network architecture. Two predictive reference models (i.e., particle swarm optimisation (PSO) and Bayesian optimisation (BO)) are introduced for comparison to demonstrate the capability of GA in identifying the best hyper-parameters of ANFIS and ANN. To validate the proposed model, extensive experiment analysis and comparison with several baseline approaches in terms of the statistical parameters that include root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). In terms of the performance metric employed, the experiment findings indicate that the proposed model gives superior results over the baseline models. Thus, the proposed work advances the mine ventilation and monitoring system technologies to enhance performance and reliability, improve health and safety, reduce energy and operational cost, and enhance mine productivity.
Read full abstract7-days of FREE Audio papers, translation & more with Prime
7-days of FREE Prime access