Self-Organizing Polynomial Networks for Time-Constrained Applications

A metamodeling of complex calculation procedures (static systems) is investigated with the aim to create low-complexity surrogate models that are applicable in low-computing-power real-time (RT) measurement systems. Unlike the single-parameter error criteria and minimum description length measure, the proposed compound-squared-relative-error measure forces the group method of data handling (GMDH) algorithm to prefer the models having the smallest compound deviation of accuracy and execution time from the given thresholds and thus generally leads to more favorable models with respect to both conditions. Approximation errors, execution speed, and the applicability of the derived GMDH models in RT flow-rate measurements of natural gas are discussed and compared with the corresponding models derived by artificial neural network and support vector regression.