Refine
Has Fulltext
- no (32)
Year of publication
Document Type
- Article (32) (remove)
Language
- English (32)
Is part of the Bibliography
- yes (32)
Keywords
- Genetic programming (3)
- Dynamical systems (2)
- Hydraulic models (2)
- Hydraulic networks (2)
- Maximum entropy method (2)
- Pipe networks (2)
- Probability (2)
- Synchronization control (2)
- Water distribution systems (2)
- Active flow control (1)
- Explainable AI (1)
- Extremum seeking (1)
- Machine learning (1)
- Machine learning control (1)
- Non-linear analysis (1)
- Nonlinear analysis (1)
- POD (1)
- Shear flow (1)
- Turbulence (1)
- acoustic transducers (1)
- calibration (1)
- durability (1)
- electric sensing devices (1)
- flow network (1)
- free shear layers (1)
- instability control (1)
- low-dimensional models (1)
- maximum entropy analysis (1)
- nonlinear dynamical systems (1)
- piezoelectricity (1)
- polymers (1)
- probabilistic inference (1)
- shear layers (1)
- turbulence control (1)
Machine learning control
(2020)
Recently, the term explainable AI came into discussion as an approach to produce models from artificial intelligence which allow interpretation. For a long time, symbolic regression has been used to produce explainable and mathematically tractable models. In this contribution, we extend previous work on symbolic regression methods to infer the optimal control of a dynamical system given one or several optimization criteria, or cost functions. In earlier publications, network control was achieved by automated machine learning control using genetic programming. Here, we focus on the subsequent path continuation analysis of the mathematical expressions which result from the machine learning model. In particular, we use AUTO to analyze the solution properties of the controlled oscillator system which served as our model. As a result, we show that there is a considerable advantage of explainable symbolic regression models over less accessible neural networks. In particular, the roadmap of future works may be to integrate such analyses into the optimization loop itself to filter out robust solutions by construction.