#digital innovation

AI is transforming the process industry by moving from advisory tools towards AI agents, feedback loops and digitally engineered workflows. Transferring from pilot projects to operational deployment, AI has demonstrated the potential to significantly improve efficiency across the entire asset life cycle. Key applications include process modelling, digital twins and AI-driven predictive maintenance. Contributions are invited on industrial AI use cases, deployment at scale, and challenges related to robustness, data quality, explainability, and human-AI.

• AI agents and feedback-loop workflows
• AI-assisted process modelling and simulation
• AI-driven predictive maintenance
• Cross plant transfer learning
• Digital twins and AI integration
• MLOps / model lifecycle management
• Self-optimizing process control

Machine learning and AI-based methods are increasingly embedded in life science workflows, from target identification, principal component analysis (PCA), and molecular screening to bioprocess optimisation and quality control. As experimental, process and clinical data becomes more connected, AI can support actionable insights, validated decision-making and more efficient development and manufacturing workflows. Submissions addressing validated applications, domain-specific data integration, and requirements for AI/ML in regulated life science environments are particularly welcome.

• AI and machine learning in life science workflows
• AI-assisted molecular screening and target identification
• Predictive modelling in pharmaceutical and bioprocess manufacturing
• Process analytical technology (PAT) and AI-enabled quality control
• Data integration across experimental, process and clinical studies
• Regulatory requirements for AI/ML in regulated life science environments

A remotely operated plant with limited human intervention is a key vision for the future of industrial production. Seamless digitalisation and connectivity are a prerequisite for autonomous decision-making while transparency, training and validation are essential to build human trust. Autonomous robots already perform inspection tasks, and humanoid robots are an emerging field of interest. Contributions on robotics, remote operations, human-machine collaboration, safety concepts and validation of autonomous systems in regulated, batch or continuous production settings are particularly welcome.

• Autonomous operations and industrial robotics
• Remote operations, drone-based inspection and humanoid robots
• Safety and functional safety for autonomous systems
• Human-machine collaboration in plant operations
• Autonomy levels, validation and maturity models
• Trust, transparency and operator acceptance in autonomous systems

Connecting field devices, machines, and sensors through unified architecture are reshaping plant operations. The IT/OT convergence, supported by industrial communication standards and edge computing, enables real-time process visibility and reliable data exchange across production environments. Contributions are invited on connectivity architectures, field -level integration, interoperability, real-time data routing and practical implementations of connected production in industrial environments.

• Ethernet-APL / field-level connectivity
• IT/OT convergence in process plants
• Industrial IoT and edge computing
• Communication protocols and interoperability (OPC UA, MQTT, AAS)
• Real-time data routing and integration architectures
• NOA and interoperable data ecosystems

As process plants become more connected, the attack surface of industrial control and automation systems expands correspondingly. Protecting operational technology (OT) in chemical, pharmaceutical, and bioprocess environments requires targeted approaches that combine resilience, secure architecture and implementation under legacy system constraints. Contributions on OT-specific threat mitigation, secure system architecture, network segmentation, incident response, risk assessment, standards and regulatory compliance and implementation experience from industrial sites are invited.

• IT/OT cybersecurity in process and pharmaceutical plants
• Incident response & recovery in OT environments
• Legacy system security and OT risk assessment
• Evolving regulatory requirements
• Industrial security standards and regulatory compliance (e.g. IEC 62443, CRA)
• Organizational readiness and cyber resilience
• Secure OT architecture and network segmentation

Large volumes of process, sensor, and quality data generated across operations hold significant potential for product and process innovation. Turning raw operational data into actionable knowledge requires robust data architectures, high quality data management and analytical capabilities across laboratory, production, and enterprise systems. Contributions on data governance, integration and contextualising, analytical methods applied to real industrial datasets, and case studies demonstrating measurable innovation outcomes are particularly welcome.

• Data architecture, governance and quality frameworks
• Industrial data lakes, warehouses and quality frameworks
• AI-ready data: architecture, labelling and curation
• FAIR data principles / data lineage & traceability
• Analytics on real industrial datasets for innovation outcomes