Ensemble learning model on Artificial Neural Network - Backpropagation (ANN-BP) architecture for coal pillar stability classification

Abstract

Pillars are important structural units used to ensure mining safety in underground hard rock mines. Unstable pillars can significantly increase worker safety hazards and sudden roof collapse. Therefore, precise predictions regarding the stability of underground pillars are required. One common index that is often used to assess pillar stability is the Safety Factor (SF). Unfortunately, such crisp boundaries in pillar stability assessment using SF are unreliable. This paper presents a novel application of Artificial Neural Network-Backpropagation (ANN-BP) and Deep Ensemble Learning for pillar stability classification. There are three types of ANN-BP used for the classification of pillar stability distinguished by their activation functions: ANN-BP ReLU, ANN-BP ELU, and ANN-BP GELU. These three activation functions were chosen because they can solve the vanishing gradient problem in ANN-BP. In addition, a Deep Ensemble Learning process was carried out on these three types of ANN-BP to reduce the prediction variance and improve the classification results. This study also presents two labeling alternatives for pillar stability by considering its suitability with the SF. Thus, pillar stability is expanded into four categories: failed with a suitable safety factor, intact with a suitable safety factor, failed without a suitable safety factor, and intact without a suitable safety factor. There are five features used for each model: pillar width, mining height, bord width, depth to floor, and ratio. In constructing the model, the initial dataset is divided into training data, validation data, and testing data. In this case, four type of proportions are used. For training-testing division the proportions are: 80 % : 20 %, 70 % : 30 %, for training-validation-testing division the proportions are: 80 % : 10 % : 10 %, 70 % : 15 % : 15 %. Average accuracy, F1-score, and F2-score from 10 trials were used as performance indicators for each model. The results showed that the ANN-BP model with Ensemble Learning could improve ANN-BP performance with an average accuracy 86.48 % and an F2-score 96.35 % for the category of failed with a suitable safety factor.