Comminution is one of the most energy-intensive and critical operations in mineral processing, and the efficiency of grinding circuits has a profound impact on overall plant performance. Within these circuits, hydrocyclones play a pivotal role in particle classification, directly influencing both throughput and product size distribution. As such, their performance strongly affects grinding efficiency, energy consumption and downstream processing.
Despite their importance, the reliable monitoring of hydrocyclones remains a challenging and, to some extent, unresolved problem in industrial practice. While significant research effort over the past decade has explored sensor-based monitoring approaches\u2014particularly using vibration, acoustic and image-based measurements\u2014these methods are not yet firmly established in routine plant operations.
This project will investigate hybrid approaches that combine computational fluid flow modelling, empirical or mechanistic modelling, and modern machine learning to advance the monitoring of hydrocyclones. The aim is to develop models capable of detecting abnormal operating states (e.g. roping or no-flow conditions) and providing soft estimates of key performance indicators such as cut size or separation efficiency.
A particular focus will be on theory-informed machine learning, where physical knowledge derived from fluid dynamics, empirical correlations, or simplified process models is embedded within data-driven approaches. This has the potential to improve robustness, interpretability and generalisability, especially in situations where experimental data are limited. Advances in both machine learning and computational modelling offer new opportunities to develop such hybrid models and, ultimately, to support improved monitoring and control of grinding circuits.
Depending on the final scope, the project may involve laboratory-scale experiments, the generation of simulated data, or a combination of both<\/p>\n\n\n\n
Aim <\/p>\n\n\n\n
Objectives <\/p>\n\n\n\n
Significance <\/p>\n\n\n\n
Comminution circuits are among the most energy-intensive operations in mineral processing, and their efficiency has a major impact on overall plant performance. Hydrocyclones play a central role in these circuits by controlling particle size distribution, thereby influencing grinding efficiency, circulating loads and downstream recovery. Sub-optimal hydrocyclone performance can lead to reduced efficiency and increased energy consumption, highlighting the need for reliable monitoring.
While substantial research has been conducted on hydrocyclone monitoring, these approaches are not yet firmly established in industrial practice. Recent advances in machine learning and computational modelling provide an opportunity to develop improved monitoring solutions. In particular, theory-informed machine learning offers a promising pathway to integrate physical insight with data-driven models, enabling more robust and interpretable soft sensors. This project aims to contribute to this emerging area, with potential benefits for process monitoring, control and optimisation of comminution circuits.<\/p>\n\n\n\n
Ideal Candidate <\/p>\n\n\n\n
We are seeking a highly motivated PhD candidate with strong analytical and problem-solving skills, and the ability to work independently and as part of a team. Candidates should have a solid background in chemical, metallurgical or process engineering, applied mathematics, or a related field. Strong quantitative skills are desirable, including experience with machine learning, data analysis, or computational modelling (e.g. CFD or empirical modelling). Familiarity with programming environments such as MATLAB or Python would be advantageous. The candidate must meet the eligibility requirements for enrolment in a PhD program at Curtin University. <\/p>\n\n\n\n
This project is open to International and Domestic applicants. <\/p>\n\n\n\n
Internship \u00a0<\/p>\n\n\n\n
Through this project you will also have an internship opportunity. Further details will be provided at a later date.\u00a0\u00a0<\/p>\n\n\n\n
Scholarship <\/p>\n\n\n\n
If you are identified as the preferred candidate for this project, you may be considered for an RTP scholarship<\/a>. <\/p>\n\n\n\n Enquires and How to Apply <\/p>\n\n\n\n For enquires about this opportunity contact Professor Chris Aldrich at\u00a0Chris.Aldrich@curtin.edu.au<\/a><\/p>\n\n\n\n