1887

n South African Journal of Industrial Engineering - Estimating the continuous risk of accidents occurring in the mining industry in South Africa

Volume 26, Issue 3
  • ISSN : 1012-277X
USD

 

Abstract

This study contributes to the on-going efforts to improve occupational safety in the mining industry by creating a model capable of predicting the continuous risk of occupational accidents occurring. Contributing factors were identified and their sensitivity quantified. The approach included using an Artificial Neural Network (ANN) to identify patterns between the input attributes and to predict the continuous risk of accidents occurring. The predictive Artificial Neural Network (ANN) model used in this research was created, trained, and validated in the form of a case study with data from a platinum mine near Rustenburg in South Africa. This resulted in meaningful correlation between the predicted continuous risk and actual accidents.

Hierdie studie probeer 'n bydrae lewer om beroepsveiligheid in die mynbedryf te verbeter deur 'n model te skep wat in staat is daartoe om die voortdurende risiko's van moontlike werksongelukke te voorspel. Bydraende faktore is geïdentifiseer en hulle sensitiwiteit is gekwantifiseer. Die benadering sluit in die gebruik van 'n Kunsmatige Neurale Netwerk (ANN) wat patrone identifiseer tussen die bydraende kenmerke en om die aanhoudende risiko van ongelukke te voorspel. Hierdie model was geskep, opgelei en gevalideer tydens 'n gevallestudie waar die data verkry is van 'n platinum-myn naby Rustenburg in Suid-Afrika. Die gevolgtrekking was dat 'n betekenisvolle korrelasie tussen die voorspelbare voortdurende risiko's en werklike ongelukke bestaan.

Loading full text...

Full text loading...

Loading

Article metrics loading...

/content/indeng/26/3/EJC181210
2015-11-01
2016-12-09

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error