Via this project we will optimize control parameter tuning, specifically inverter controllers and low-level drivetrain controllers. Existing solutions rely on expert intuition, rule-of-thumb guidelines, linear auto-tuners, and standardized inverter-motor combinations with pre-tuned parameters.
However, these approaches face significant challenges due to the variability in application load and environmental conditions, the complexity of interdependent controller loops, and safety limitations. Additionally, the lack of modularity in configuration and the proliferation of variants, given the diversity of inverters and motors, result in inefficiencies.
Therefore, the industry demands innovative solutions that can adapt to changing conditions, enhance control parameter tuning efficiency, and ensure safety while accommodating a wide range of configurations.
Project goals
Shorten time to market: Streamline the commissioning process by reducing the time required for control engineers to fine-tune inverter and drivetrain control parameters.
Enhance tuning efficiency: Develop tools that capture and transfer tuning knowledge, facilitating more efficient tuning procedures. This will minimize the need for expert intervention and allow for the tuning of a class of similar problems.
Improve robustness of autotuning: Ensure autotuners and tuning rules can handle systems with significant variability, converging on different applications, even in diverse environmental conditions.
Enhance system performance: Find better tuning approaches to improve system performance, particularly under conditions of temporary overloading. This involves developing superior configuration tools and more accurate estimations of short start times while constraints are active.
The project will employ a range of approaches, including (but not limited to) formalized application knowledge, AI methods, physics-inspired models, and the integration of offline and online data for efficient tuning. The focus is on developing robust, adaptable, and efficient solutions for the industrial sector.
Interested?
EIDETIC_IRVA is an industrial research project. We are looking for companies that want to be part of the user group and work with us to valorise the project.
Interested? Fill in the form below and we will contact you as soon as possible.
