In modern process plants, overall control performance depends not only on how individual controllers are tuned but on how they are structured and interconnected across the plant. Designing this plantwide control architecture - defining control loops, interactions, and coordination strategies - remains a knowledge-intensive task that relies heavily on experienced control engineers.

This thesis explores how artificial intelligence and machine learning can be leveraged to support plantwide control architecture design. The goal is to develop a proof-of-concept tool that interprets process information and engineering documentation to recommend suitable control configurations and structures. By assisting engineers in the early design phase, the tool aims to improve consistency, accelerate project execution, and enhance knowledge reuse in process automation.

Details:

• Start: January/February 2026 , duration of 5 months
• 30 ECTS per student
• 1-2 students
• Location: On-site at ABB Corporate Research in Västerås (ABB may cover the accommodation)

Your role and responsibilities

Research questions:

• AI-Assisted Selection of Control Structures in Plantwide Automation
• Ontology and Knowledge Graph Development for Process Automation
• AI/ML for Control Strategy Classification and Recommendation

Goals:

• Develop an AI-Based Framework for Control Architecture Recommendation
• Demonstrate and Evaluate the Framework in an Industrial Context

Approach - the work will address the following points:

• Literature review on control structures and AI applications in process control
• Develop a prototype tool using existing LLM APIs (ABB AI)
• Implement basic P&ID interpretation (text extraction and pattern recognition)
• Create prompt engineering strategies for control structure recommendation
• Validate the tool with real test cases

• Drive and interest in working with real-world use cases
• A background in control engineering or computer science/AI is suitable. We will provide support to help you build the required skills and knowledge during the project, especially in the areas of Machine learning, Large Language Models, Process control
• Programming environment: Python and MATLAB
• Self-driven and solution-oriented
• Good spoken and written English
• Ability to analyze results and draw conclusions
• Good soft skills and collaborative spirit

More about us

Supervisor Soroush Rastegarpour, [email protected], will answer all your questions about the thesis topic and expectations. Recruiting Manager Linus Thrybom, +46 730 809 906, will answer your questions regarding the hiring.

Positions are filled continuously. Please apply with your CV, academic transcripts, and a cover letter in English. We look forward to receiving your application!

Join us. Be part of the team where progress happens, industries transform, and your work shapes the world. Run What Runs the World.