Improved active output selection strategy for noisy environments
This work offers an incremental improvement for engineers performing model-based calibration, potentially reducing the number of measurements needed.
This paper introduces an improved active output selection strategy for model-based calibration, which aims to reduce test bench time. By incorporating noise estimates from Gaussian processes, the new strategy achieves performance equal to or better than existing methods on three toy examples, potentially reducing required measurements by at least 10% in the best case.
The test bench time needed for model-based calibration can be reduced with active learning methods for test design. This paper presents an improved strategy for active output selection. This is the task of learning multiple models in the same input dimensions and suits the needs of calibration tasks. Compared to an existing strategy, we take into account the noise estimate, which is inherent to Gaussian processes. The method is validated on three different toy examples. The performance compared to the existing best strategy is the same or better in each example. In a best case scenario, the new strategy needs at least 10% less measurements compared to all other active or passive strategies. Further efforts will evaluate the strategy on a real-world application. Moreover, the implementation of more sophisticated active-learning strategies for the query placement will be realized.