System adjustment for targeted performance combining symbolic regression and set inversion
For engineers and researchers dealing with black-box systems, this provides a data-driven tuning method, though it is incremental as it combines existing techniques.
This work develops a methodology combining evolutionary programming and set inversion to adjust a causal system's parameters for targeted performance using only input-output data, without prior system knowledge. The approach is validated on benchmark problems, achieving accurate performance tuning.
One presents methodology and algorithms to prepare a causal system in order to achieve desired performances if only input-output data are known and when no other informations are available. This can be done with mean of evolutionnary programming and set inversion methods, such as PSI-algorithm or SIvIA.