Faster calibration, with less data
Secondmind for Calibration helps calibration engineers design high-value control strategies and optimize the performance of complex systems to produce high-precision calibration maps in less time using fewer costly prototypes.
- Reduce manual calibration overhead with easily customizable intelligent, automated DoE and accurate modelling.
- Automated control parameter optimization by considering user-configurable constraints.
Key features
- Flexible modeling for noisy systems, such as ICE, and low noise systems, such as e-motor.
- Modeling of datasets of any scale or complexity, including multimodal data.
- Multi-fidelity modeling for combined virtual-physical calibration.
- Optimization of critical parameters considering unlimited user-defined constraints.
- Intelligent temperature control for e-motor calibration.
- Data collection recommendations for slow-response and partially-controllable variables.
- Output confidence indicator to manage risk.
- Calibration profile smoothing.
- Intuitive user interface, with explainable, transparent results and coverage indicators of experiments.
- Downloadable models for additional analysis and visualization.
Impact
80%
less data needed to create high-precision models that learn
50%
less time to achieve calibration profile optimum
40%
fewer costly prototypes needed for design and development
“Secondmind’s unique Active Learning technology will enable us to automate the engine calibration process and we expect to more than double efficiency in this area”
Eiji Nakai
Executive officer Powertrain Development and Integrated Control System Development at Mazda
Applications
Secondmind for Calibration supports a wide range of system calibration applications, including:
- E-motor and inverter
- Gasoline engine
- Diesel engine
- Fuel cell
- Battery management system
- ADAS
- Steering
- Drivability
- Chassis
