Technical Market Support

Improving the Classification of Microstructure Distribution in Coke CT Images Using Deep Learning and Lineal Path Calculations

Technical Market Support » Metallurgical Coal

Published: January 24Project Number: C34062

Get ReportAuthor: Bishnu Lamichhane, Keith Nesbitt, Stephan Chalup, Robert King and Merrick Mahoney | The University of Newcastle

This project builds on a number of earlier projects that have helped understand and characterise the 3D distribution of coke microstructure and the link to coke strength, reactivity and the formation of the microstructure in the plastic layer. This project improves the fundamental understanding of coal-to-coke conversion and coke performance, and this directly supports the technical marketing of Australian coking coals.

In a previous project C29073 a standardised approach to characterising coke from CT scans was developed and used to analyse 37 samples from 9 different cokes using Landmark Multi-Dimensional Scaling (LMDS) and clustering to classify blocks of microstructure in these 37 samples. A number of 3D statistics (K, F and G statistics) and 3D visualisation tools, developed in project C27036, were used to link known microstructure properties to the cokes derived from a range of coal rankings. The automated approach was developed for these 37 samples that classified six classes of microstructure for each coke sample. The classes were ordered and associated with microstructure that Classes 1 and 2 corresponded to low-density regions, classes 3 and 4 to mid-density locations, and Classes 5 and 6 to high-density locations. Results from project C29073 were promising, and it was recommended that the classification approach could benefit from improving the link between 3D spatial structure and classification by integrating the novel deep learning approach of Autoencoding. Autoencoding is an unsupervised learning approach based on convolutional neural nets that can be used to efficiently detect features in 3D spatial data. It was also suggested to increase the number of samples from each coke.

In summary, this project aimed to enhance the automatic characterisation of cokes, based on the distribution of microstructures with the following objectives:

  • Enhance and further evaluate an automated characterisation process that uses the distribution of structural features to characterise coke. This statistical characterisation is based on the automated identification of classes of structural microstructure. These locations will be identified in two complementary ways.
  • Further develop the 3D statistical characterisation to better quantify the linear distribution of classes of structural features. Approaches used in C29073 are applied, but also include the chord length distribution to characterise the linear arrangements of microstructure.
  • Apply and evaluate the techniques using the same broad range of cokes characterised in C29073, but to check statistical validity by including 10 samples from each coke in the analysis.

Overall, the project extended the following two techniques (1 and 2 below) developed in C29073 to a wide range of cokes and developed two novel approaches (3 and 4 below) for working with coke volumes to support better understanding of the role of coke microstructure.

  1. Landmark multi-dimensional scaling (LMDS) and clustering algorithms to identify structural features and generate points of interest from a wide range of coke samples.
  2. 3D statistical analysis to characterise the distribution of features in the coke volumes.
  3. Develop and apply the convolutional Autoencoder (CAE) technique to a wide range of coke samples and compare LMDS and CAE results.
  4. Develop and apply a chord length distribution technique to better understand the coke microstructures.

This project confirms that coke microstructures can differentiate cokes. However, it also confirms that coke is an extremely heterogeneous material, and extra care should be taken to apply a statistical technique. Applying two different machine learning approaches - LMDS and convolutional Autoencoder (CAE) to classify the coke microstructures, this study does not support the conclusions of the previous project C29073. However, the chord length distribution analysis reveals two distinct groups of cokes. The outcomes recommend that this analysis should be combined with some physical modelling to link this analysis with the coke strength.


Health and safety, productivity and environment initiatives.

Recently Completed Projects

C34019Longwall Bretby Cable Handling Monitoring With Fibre Optics

This project examined the potential of using fibre optic sensing tec...

C28028The Inclusion Of High Interest Native Plants In Mine Site Restoration Programs: Propagation, Translocation And Field Re-Introduction

This report synthesises over 10 years of ex situ and in si...

C27049Mine Machine Radar Sensor Integration

The aim of this project was to develop an integrated radar sensor an...


Open Cut

Safety, productivity and the right to operate are priorities for open cut mine research.

Recently Completed Projects

C34028Guidelines For Assessment Of Geotechnically Safe And Stable Post-Mining Landforms

The purpose of this project was to develop a guidelines document as ...

C29047Reducing Uncertainty In Long Term Void Water Quality Predictions For Final Void Management

The aim of this project was to generate new data and undertake predi...

C29048Image Based Automated Characterisation Of Waste Materials

Accurate geotechnical characterisation of mine spoils is critical to...

Open Cut

Coal Preparation

Maximising throughput and yield while minimising costs and emissions.

Recently Completed Projects

C26016Determining The Benefits Of Online Thickener Underflow Rheology Measurements

The aim of this project is to determine how useful the rheology meas...

C33056Modelling And Control Of Classifying Cyclones

Hydrocyclones are one of the key technologies for the classification...

C28056Surface Alloying Of Centrifuge Baskets And Sieve Bends Screen Surfaces To Increase The Service Lifetime

The main objective of this project was to improve the wear resistanc...

Coal Preparation

Technical Market Support

Market acceptance and emphasising the advantages of Australian coals.

Recently Completed Projects

C33066Washability And Distribution Of Sulfur And Trace Elements For Different Size And Density Fractions Of Raw Coals

Based on the hypothesis that the levels of sulfur and other toxic tr...

C34060In-Situ Investigation Of Coke Structure Formation Under Stamp Charged Coking Conditions

Stamp charged cokemaking has emerged as an effective technique to im...

C34062Improving The Classification Of Microstructure Distribution In Coke CT Images Using Deep Learning And Lineal Path Calculations

This project builds on a number of earlier projects that have helped...

Technical Market Support

Mine Site Greenhouse Gas Mitigation

Mitigating greenhouse gas emissions from the production of coal.

Recently Completed Projects

C28076Selective Absorption Of Methane By Ionic Liquids (SAMIL)

This third and final stage of this project was the culmination of a ...

C29069Low-Cost Catalyst Materials For Effective VAM Catalytic Oxidation

Application of ventilation air methane (VAM) thermal oxidiser requir...

C23052Novel Stone Dust Looping Process For Ventilation Air Methane Abatement

This multi‐phase project is concerned with the mitigation of m...

Mine Site Greenhouse Gas Mitigation

Low Emission Coal Use

Step-change technologies aimed at reducing greenhouse gas emissions.

Recently Completed Projects

C17060BGasification Of Australian Coals

Four Australian coals were trialled in the Siemens 5 MWth pilot scale ga...

C17060AOxyfuel Technology For Carbon Capture And Storage Critical Clean Coal Technology - Interim Support

The status of oxy-fuel technology for first-generation plant is indicate...

C18007Review Of Underground Coal Gasification

This report consists of a broad review of underground coal gasification,...

Low Emission Coal Use

Mining And The Community

The relationship between mines and the local community.

Recently Completed Projects

C16027Assessing Housing And Labour Market Impacts Of Mining Developments In Bowen Basin Communities

The focus of this ACARP-funded project has been to identify a number...

C22029Understanding And Managing Cumulative Impacts Of Coal Mining And Other Land Uses In Regions With Diversified Economies

The coal industry operates in the context of competing land-uses that sh...

C23016Approval And Planning Assessment Of Black Coal Mines In NSW And Qld: A Review Of Economic Assessment Techniques

This reports on issues surrounding economic assessment and analysis ...

Mining And The Community


National Energy Research,Development & Demonstration Council (NERDDC) reports - pre 1992.

Recently Completed Projects

1609-C1609Self Heating of Spoil Piles from Open Cut Coal Mines

Self Heating of Spoil Piles from Open Cut Coal Mines

1301-C1301Stress Control Methods for Optimised Development...

Stress Control Methods for Optimised Development and Extraction Operations

0033-C1356Commissioned Report: Australian Thermal Coals...

Commissioned Report: Australian Thermal Coals - An Industry Handbook