A digital twin framework for predictive slurry pump diagnostics in mining operations
1 Department of Industrial and Manufacturing Engineering, National University of Science and Technology, Bulawayo, Zimbabwe.
2 Department of Agricultural Engineering, National University of Science and Technology, Bulawayo, Zimbabwe.
3 Department of Chemical Engineering, National University of Science and Technology, Bulawayo, Zimbabwe.
4 Department of Electronics Engineering, National University of Science and Technology, Bulawayo, Zimbabwe.
2 Department of Agricultural Engineering, National University of Science and Technology, Bulawayo, Zimbabwe.
3 Department of Chemical Engineering, National University of Science and Technology, Bulawayo, Zimbabwe.
4 Department of Electronics Engineering, National University of Science and Technology, Bulawayo, Zimbabwe.
Research Article
Open Access Research Journal of Science and Technology, 2026, 17(02), 044–056.
Article DOI: 10.53022/oarjst.2026.17.2.0072
Publication history:
Received on 16 June 2026; revised on 22 July 2026; accepted on 25 July 2026
Abstract:
A digital twin is a virtual representation of a physical component, part, or system created by collecting and analysing data from sensors and other connected devices. The development of a digital twin for slurry pumps in a mineral processing plant can improve pump reliability and efficiency, leading to reduced downtime, cost savings, and increased plant productivity. Recent advances in sensors, the Internet of Things, and Artificial Intelligence have made it possible to monitor machinery continuously and analyse large quantities of operating data in real time. This paper presents the design and prototype development of a digital twin for a centrifugal slurry pump. The digital twin is hosted locally on a web page developed in Microsoft Visual Studio Code using JavaScript, while sensor data are transmitted to a microcontroller and communicated to the web application through the Message Queuing Telemetry Transport protocol. A machine learning model developed in Google Colab using a Python Jupyter notebook monitors the incoming data and provides insights into pump health. The system supports real-time performance monitoring, anomaly detection, failure prediction, alert logging, and maintenance scheduling. By linking a 3D virtual model to live operating conditions, the proposed digital twin enables remote monitoring of slurry pump behaviour and provides a practical foundation for predictive maintenance in mining processing plants.
Keywords:
Digital twin; Slurry pump; Fault diagnosis; Machine learning; Artificial intelligence; Predictive maintenance
Full text article in PDF:
Copyright information:
Copyright © 2026 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0