Search for Articles:

MECS Press Menu

Hermanus M. Scholtz

Work place: The Engineering Institute of Technology Pty Ltd (EIT), Perth, WA6005, Australia

E-mail: 449971@student.eit.edu.au

Website:

Research Interests: Artificial Intelligence

Biography

Scholtz M. Hermanus was born in Rehoboth, Namibia in 1981. He received his Trade Diploma in Instrumentation in 2005. He later earned an Advanced Diploma in industrial automation from the Engineering Institute of Technology (EIT), Australia, in 2019, followed by a Bachelor of Science in industrial automation from EIT in 2022. In 2024, he completed his Master of Engineering in industrial automation from the same institution in (2024). His major field of study is industrial automation.
He began his career in 2006 at a Uranium Mine, where he gained experience in mining automation and instrumentation. In 2010, he transitioned to a Desalination Plant, working in process control and system optimization. By 2014, he was a Process Control Engineer in the brewing industry, focusing on automation solutions for large-scale production. He later joined Ohorongo Cement as a Senior Automation Technician, overseeing advanced automation in cement manufacturing.
In September 2023, he returned to same Uranium Mine as the Supervisor of System Integration and Instrumentation, and a few months later, he was promoted to Superintendent of the same section. He currently leads automation and instrumentation initiatives, integrating cutting-edge technologies into mining operations. His research interests include artificial intelligence in production environments, particularly in optimizing automation and improving process efficiency.

Author Articles
Improving Boiler Performance Using Machine Learning: A Predictive Approach to Steam Demand Optimization

By Hermanus M. Scholtz Hadi Harb

DOI: https://doi.org/10.5815/ijisa.2025.06.01, Pub. Date: 8 Dec. 2025

This paper explores the application of machine learning to enhance boiler efficiency and cost management at a Uranium Mine in Africa. The current steam control system relies on a feedforward loop, which adjusts based on slurry flow into the leach tank, and a feedback loop, which regulates steam to a setpoint. However, this method is inefficient, as it does not account for slurry temperature variations, leading to unstable control and suboptimal steam usage. To address these limitations, this study applies the Extra Trees algorithm to predict steam demand more accurately. The data-driven approach achieves a 6.6% reduction in steam consumption and a 2% decrease in heavy fuel oil (HFO) usage, resulting in cost savings and improved sustainability. Based on multiple evaluation metrics, the Extra Trees model proved to be the most accurate and consistent algorithm, achieving a 96.67% R-squared score and a Root Mean Square Error (RMSE) of 1131.37 kg, indicating minimal deviation between actual and predicted values. The findings highlight the shortcomings of traditional control strategies under fluctuating conditions and demonstrate how advanced feature engineering enhances predictive accuracy. By integrating machine learning into operational workflows, this research provides actionable insights to improve boiler performance, process stability, and overall efficiency.

[...] Read more.
Other Articles

Subscribe to receive issue release notifications and newsletters from MECS Press journals