The Benefit of Noise-Injection for Dynamic Gray-Box Model Creation
This addresses challenges in gray-box modeling for equipment emulation, offering a more robust alternative to black-box models, though it appears incremental as it builds on existing gray-box methods.
The paper tackled uncertainties in gray-box model creation for equipment emulators by injecting noise into the training dataset, resulting in a reduction of modeling error from 0.68 to 0.27°C and improvements of 50-60% across training, test, and validation sets.
Gray-box models offer significant benefit over black-box approaches for equipment emulator development for equipment since their integration of physics provides more confidence in the model outside of the training domain. However, challenges such as model nonlinearity, unmodeled dynamics, and local minima introduce uncertainties into grey-box creation that contemporary approaches have failed to overcome, leading to their under-performance compared with black-box models. This paper seeks to address these uncertainties by injecting noise into the training dataset. This noise injection enriches the dataset and provides a measure of robustness against such uncertainties. A dynamic model for a water-to-water heat exchanger has been used as a demonstration case for this approach and tested using a pair of real devices with live data streaming. Compared to the unprocessed signal data, the application of noise injection resulted in a significant reduction in modeling error (root mean square error), decreasing from 0.68 to 0.27°C. This improvement amounts to a 60% enhancement when assessed on the training set, and improvements of 50% and 45% when validated against the test and validation sets, respectively.