Journal
MINING METALLURGY & EXPLORATION
Volume -, Issue -, Pages -Publisher
SPRINGER HEIDELBERG
DOI: 10.1007/s42461-023-00888-x
Keywords
Advanced measurement and verification; Predictive modelling techniques; Energy forecasting; Operational management; Deep-level mines
Ask authors/readers for more resources
Advanced measurement and verification (M&V) is a real-time process to determine the impact of energy initiatives. This study proposes a method to accurately predict the energy consumption of deep-level mines, regardless of operational changes. The method is based on the Moving Average (MA) modeling technique and uses the coefficient of variation for the root mean square error (CV(RMSE)) to analyze modeling error. The developed method can predict the future energy consumption of deep-level mines with 99% accuracy, improving energy and finance management.
Advanced measurement and verification (M&V) is a process where the impact of an energy initiative is determined in real time. Data prediction models can be used to predict and compare energy consumption with a predetermined baseline. Deep-level mines can benefit from advanced M&V as the impact of operational changes can be identified in real time. Ultimately, this can ensure that informed decisions are made regarding energy management based on the impact and severity of the occurrence.Previous studies on advanced M&V do not account for operational changes to the model's baseline. These changes can significantly impact the performance of both the mine and related activities. The aim of this study is to propose a method that can accurately predict the energy consumption of a deep-level mine regardless of operational changes. To achieve this objective, nine different data predictive modelling techniques were considered.The proposed method is based on the Moving Average (MA) modelling technique due to its simplicity, flexibility, and rapid development time. The coefficient of variation for the root mean square error (CV(RMSE)) was used to statistically analyse the modelling error. If the predictions exhibit an unsatisfactory CV(RMSE), the model dynamically adjusts to reduce the prediction error.The model was developed to adapt to operational changes in scenarios where the standard model becomes irrelevant. The method developed in this study was able to predict the future energy consumption of deep-level mines with an accuracy of 99%, improving the mine's energy and finance management.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available