Why AI matters in Manufacturing

Manufacturers generate vast amounts of data every day from machines, sensors, production lines and operational systems. However, identifying emerging issues, predicting equipment failures and maintaining consistent product quality remains a significant challenge.

Artificial Intelligence (AI) and Machine Learning (ML) enable manufacturers to transform operational data into actionable insights. By detecting patterns, predicting outcomes and supporting faster decision-making, AI can help improve productivity, reduce downtime, enhance product quality and optimise manufacturing operations.

AI and Machine Learning Program

Aims:

  • Develop AI/ML models for automated diagnostics and predictive maintenance using data from various sources.

  • Design ML techniques for monitoring product quality and consistency.

  • Create data-driven optimisation solutions using reinforcement learning to enhance production planning and task scheduling.

Industry Benefits:

  • Predict equipment failures before they occur.

  • Reduce downtime and maintenance costs.

  • Optimise manufacturing processes and resource utilisation.

  • Enable real-time monitoring and decision-making.

  • Support safer, more sustainable manufacturing operations.

  • Improve product quality and consistency.

Program Leader: Prof. Helen Huang

Project 1 – Design and manufacturing of ceramic composite coatings on titanium/steel sheets for enhanced wear, corrosion, and heat resistance

Industry Challenge: Manufacturers need cost-effective ways to produce high-performance materials while using digital technologies and AI-driven process optimisation to improve quality, consistency and production efficiency.

This project will develop a cost-effective laser-based process for applying protective coatings to a novel titanium/steel hybrid plate, offering exceptional resistance to corrosion, wear, and heat at a significantly lower cost than conventional titanium alloys. A central focus is the integration of a deep learning model to enable intelligent, real-time optimisation of the deposition process, improving quality, consistency, and efficiency. The resulting high-performance hybrid plates are well suited for construction in coastal regions and marine infrastructure, where they can significantly reduce maintenance and life-cycle costs. By combining advanced materials engineering with AI-driven process control, the project advances the vision of digital manufacturing and promotes broader industrial adoption of titanium and steel products.

Personnel Name, Project Party
Project Leader Helen Huang, University of Queensland
Program Leader (Academic) Helen Huang, University of Queensland
Partner Investigator Sihai Jiao, BAOSTEEL PTY LTD
Project Personnel

Project 2 – AI/ML models for real-time diagnostics and predictive maintenance

Industry Challenge: Organisations need intelligent, data-driven systems that can continuously monitor physical assets, predict issues before failure occurs and support real-time decision-making, reducing maintenance costs and improving operational performance. Although this project focuses on road infrastructure, the AI-enabled sensing, predictive maintenance and real-time diagnostics capabilities being developed have broad applications across modern manufacturing operations.

This project aims to develop smart devices integrated with AI/ML models for real-time diagnostics and predictive maintenance to support Logan City Council in addressing community infrastructure and safety challenges. Beginning with a feasibility study of current sensing hardware and privacy considerations, the project will progress to developing a dashboard and digital model, followed by secure and scalable deployment. By leveraging multi-sensor data and advanced machine learning, the system will automate monitoring, predict issues, and optimise resource allocation, aligning with the AI/ML4DM framework for data-driven decision-making.

Personnel Name, Project Party
Project Leader Helen Huang, University of Queensland
Program Leader (Academic) Helen Huang, University of Queensland
Partner Investigator Anthony Southon, Logan City Council
Project Personnel

Project 3 – AI Powered Standard Operation Procedure Compliance Monitoring Under Steel Making Environment

Industry Challenge: Manufacturers rely on strict adherence to standard operating procedures to maintain product quality, workplace safety and operational efficiency, yet manual monitoring can be labour-intensive, inconsistent and difficult to scale across complex production environments.

This project will develop an AI-powered SOP compliance monitoring system tailored for the steelmaking industry, where complex processes demand strict procedural oversight to ensure product quality, workplace safety and operational efficiency. By leveraging advanced computer vision and vision-language models, the system will automate the monitoring of critical SOP tasks, including gasket placement and flux package loading. The project will improve monitoring precision, reduce reliance on manual inspections and enhance the consistency of operational outcomes.
Personnel Name, Project Party
Project Leader Helen Huang, University of Queensland
Program Leader (Academic) Helen Huang, University of Queensland
Partner Investigator Tiegen Peng, Baosteel
Project Personnel