AI and machine learning: Using Machine Learning to Control Single-Pass Tangential Flow Filtration in Biopharmaceutical Processing
Bastian Oetomo, University of Melbourne, Australia

Bastian will explore the use of machine learning and AI to optimise single-pass tangential flow filtration (SPTFF) in ultrafiltration/diafiltration, aiming to meet stringent quality standards and support the shift towards continuous bioprocessing through greater automation and intelligence.

AI and machine learning: A Hybrid Machine Learning Assisted Modelling Framework Across the Scales for Heat Transfer Systems 
Nima Nazemzadeh, Hexxcell, UK

This study demonstrates hybrid modelling frameworks that combine data-driven methods with first-principles to improve prediction accuracy and reliability for complex heat transfer challenges, specifically condensation in microfin tubes and fouling in industrial-scale heat exchangers.​

Digital twin technology: Hybrid Modelling and Optimisation Framework for Plant-Wide Real-Time Applications
Patrick Thorpe, Spiro, UK

Patrick will introduce a hybrid modelling and optimisation framework combining simplified physical and AI-based unit models for real-time plant-wide optimisation in complex facilities, illustrated through a refinery case study and practical deployment insights.

Digital twin technology: Bioprocessing 4.0: Minimising Cost of mRNA Vaccine Manufacturing
Kesler Isoko, University College London / University of Sheffield, UK

Kesla will showcase the first end-to-end Bioprocessing 4.0 solution for mRNA vaccine production, featuring a physics-informed soft sensor and dynamic model integrated into an IIoT platform, achieving significant reagent and cost reductions while maintaining product quality.

Advanced process automation: Showcase of Advanced Regulatory Control in British Sugar
James Caws, British Sugar, UK

Discover how British Sugar is solving complex process challenges by enhancing its existing DCS with advanced regulatory control strategies. James presents compelling case studies showing how these traditional approaches continue to drive significant industrial value – even amid growing interest in AI technologies.

Advanced process automation: Introducing ORTO – A Novel Approach Real-time Optimisation
Paul Oram, Ortomation, UK

Hear from Paul as he outlines Ortomation Ltd’s novel agent-based real-time optimisation (RTO) approach, designed to overcome the cost, complexity, and resource challenges of traditional RTO methods and enable widespread industrial adoption.

Digital twin technology: Achieving Heat Transfer Equipment Reliability in the Process Industry Through Digital Transformation with HTRIconnect and SmartPM 
Edward Ishiyama, HTRI, UK

Hear how HTRI’s digital platforms – HTRIconnect™ and SmartPM™ – leverage validated digital twins and machine learning to provide real-time monitoring, predictive analytics, and optimisation of heat exchanger performance, enhancing productivity, safety, and sustainability across diverse industries.

Digital twin technology: Digital Twin for Bio-Process Based on Open-Source Technologies
Trung Trinh, SINTEF, Norway

Trung will present a cloud-based digital twin system that applies open-source solutions for real-time data streaming, big data analytics, and optimisation, integrated with machine learning models of the process.

Advanced process automation: Replacing Missing Instrumentation with Data Science: Calculating Virtual Flow Rates for Chemical Injection
Murray Callander, Eigen, UK

Murray introduces an innovative digital twin solution that estimates chemical flow and dosage in real time using existing tank level and fluid rate data. Ideal for mature plants without flow meters, it enhances dosing accuracy, minimises chemical waste, and reduces risk – all without adding new instrumentation.

Advanced process automation: Digital Twins and Process Control with Software-defined Process Automation
Raghav Tripathi, Siemens, UK

Discover how Siemens is revolutionising process control through software-defined automation, blending real and digital worlds to achieve IT and OT convergence, with a focus on their web-based distributed control system delivering high availability, flexible deployment, and enhanced connectivity to optimise operations and drive sustainable growth.

Digital twin technology: A Roadmap for Model-based Bioprocess Development
Khadija Mu’azzam, DPS Engineering & Construction Limited, Ireland

Khadija will present on the shift in the bioprocessing industry from Quality by Testing (QbT) to Quality by Design (QbD), and how Industry 4.0/5.0 technologies—particularly Digital Twins—are driving real-time optimization, quality, and compliance while facing integration and security challenges.

AI and machine learning: Machine Learning and Hybrid Modelling of Particle Breakage in a Jet Mill
Carl Jackson, Johnson Matthey, UK

Showcasing a novel hybrid modelling strategy, Carl will explore how combining machine learning with population balance modelling enhances particle size reduction processes in jet mills – driving performance in demanding pharmaceutical and fine chemical applications.

Data management and integration: The Process Industry Neurology Project
Chris Hamlin, HancockHamlin, UK

Despite significant investments and efforts, digital transformation in the process industries remains elusive, with many AI initiatives failing to deliver. This presentation examines these challenges through Stafford Beer’s Viable Systems Model, providing valuable insights into organisational dynamics and proposing more effective approaches.

Data management and integration: Bringing Consequence Modelling to the Cloud: Unlocking Real-Time Risk Insights with Phast APIs
James Pickles, DNV, UK

Hear from James as he outlines how cloud-based access to DNV’s Phast consequence models via secure APIs enables seamless integration with digital twins and IoT platforms, supporting real-time, risk-based decision-making and advancing digital risk management throughout the asset lifecycle.

Data management and integration: Digitalisation Practice Applied to Tablet Packing
Anthony Margetts, Factorytalk, UK

Find out how the Manufacturing Technology Centre in Liverpool has developed an automatic tablet packing line, showcasing the use of digitalisation to address practical challenges in medicines packaging.

Advanced process automation: Monitoring and Evaluation of the In-situ Consolidation of Prepreg Layers During Manufacturing Stage to Improve Interlaminar Bond Strength by Optimisation of Parameters
Obinna Okolie, Robert Gordon University, UK

Introducing a sensor-integrated in-situ consolidation technique, this study employs real-time data and optimisation to enhance bond quality and reduce defects in thermoplastic composites – paving the way for intelligent, data-driven manufacturing.

Advanced process automation: Automation of Polymer Solubility Studies Using Robotics and AI: An iDMT Case Study
Danill Bash, University of Cambridge, UK

Danill will present an automated workflow for polymer solubility screening that integrates liquid-handling robotics, robotic arm, advanced image processing, and active-learning models to map solvent–polymer compatibility efficiently. The pipeline reduces hands-on time, generates thousands of datapoints in a high-throughput fashion, and quantifies the solubility with rich metadata and context. The session will also introduce iDMT’s broader mission and capabilities in digital, AI-assisted molecular R&D and industry collaboration.

Advanced process automation: Optimising PID Control with Proven Tuning and Monitoring Solutions
Damien Munroe, Control Station, Ireland

Explore Control Station’s cutting-edge PID optimisation and analytics solutions – PlantESP™ for advanced process monitoring and Loop-Pro™ for precise controller tuning – that drive enhanced performance, efficiency, and sustainability in process manufacturing.

Digital risk management strategies: Towards an Agentic AI Assistant for Safety Barrier Risk Management
Joel Chacon, Eigen, UK

Discover an AI chatbot built with Retrieval Augmented Generation and a graph-based Safety Critical Elements model, delivering real-time, conversational insights into process safety barrier status. This presentation highlights how Large Language Models enable smarter, safer decisions in hazardous environments.

How to make the most out of your heat exchangers with Hybrid-AI Digital Twins
Delivered by Hexxcell

Hexxcell will lead a workshop on unlocking the full potential of heat exchangers with Hybrid-AI Digital Twins. Drawing on decades of experience in developing and deploying digital technology for industrial thermal systems, the session will provide practical technical and organisational recommendations that participants can take back to their plants to successfully implement digital projects that boost performance, cut costs, reduce emissions, and extend equipment life.

AI and machine learning: AI, Ethics and Workforce Transformation: Preparing Engineers for Digital Manufacturing Challenges
Mo Zandi, University of Sheffield, UK

Join Mo as he explores the ethical and workforce implications of AI adoption in the chemical process industry, highlighting challenges such as job displacement and training gaps. Drawing on insights from global experts, he proposes a framework to guide fair and transparent AI deployment and informs the redesign of engineering education to prepare professionals for ethical decision-making in digital manufacturing.

Digital twin technologies: Toward Transparent Decision Support: Building Fully Integrated Digital Twin for Refinery Operations
Balazs Palotai, MOL Group, Hungary

This work presents the development and deployment of a model-based digital twin for refinery operations, highlighting real-time optimisation, hybrid modeling, and explainability as key enablers for operational efficiency, safety, and end-user trust.

Digital twin technologies: Evaluating the Impact of Local Policy and Techno-Economic Drivers on Decision Making Using Digital Twins
Monica Tirapelle, Hexxcell, UK

This work demonstrates how Hybrid-AI Digital Twins can improve refinery decision-making by integrating technical, economic, and policy data to optimise preheat train cleaning strategies. Through regional comparisons, it shows how local factors like fuel cost, CO₂ policy, and profit margins influence maintenance planning, enabling more informed, cost-effective, and sustainable operations.