Research leadership in process-control engineering.
Bryan Onyango leads NURU's research agenda in process-control engineering, with an emphasis on dynamic systems, simulation and the rigorous evaluation of learning-based control.
Bryan Onyango
NURU Process Control Engineering Research Lab · Kenya
Focus: process modelling · control theory · reinforcement learning · industrial digital twins
Research profile
Bryan leads the lab's technical direction and research programme. The work is centred on applying and evaluating control methods for dynamic engineering systems where operating constraints, disturbances and performance trade-offs matter.
The research approach combines process understanding and simulation with control baselines and learning-based methods. Studies are structured around explicit hypotheses, documented model assumptions, repeatable test conditions and clear reporting of limitations.
Research responsibilities
- Define research questions and evaluation criteria for process-control studies.
- Direct the development of simulation environments and control experiments.
- Evaluate learning-based approaches against conventional control baselines.
- Maintain reproducible records of modelling assumptions, configurations, results and limitations.
- Guide the lab's longer-term research agenda in digital twins and intelligent industrial automation.
Current technical focus
The first priority is a simulation-based study of learning-assisted chemical process control, with candidate comparisons to PID and model-predictive control. Research outputs and claims will be published when the methods and results are ready for independent inspection.
Public work
Code and public development activity are available through the NuruLabs254 GitHub profile. For evidence of a specific technical contribution, refer to the relevant repository, commit history, release or research report rather than relying on a profile summary alone.