Search results for "Model quality"
showing 2 items of 2 documents
Testing selected optimal descriptors with artificial neural networks
2013
Eleven properties have been modeled with the objective of checking the importance for model purposes of mixed descriptors made of empirical parameters, molecular connectivity indices and random numbers. The mixed descriptors with random indices have a descriptive character which is satisfactorily confirmed by the leave-one-out method of statistical analysis. The introduction of a partition of the set of compounds into training and evaluation sets decreases drastically the probability to find a mixed descriptor with random indices with good model quality. Two properties, the magnetic susceptibility and the elutropic values, insist on having optimal descriptors with random indices. The overal…
Magnetic Levitation – Modelling, Identification and Open Loop Verification
2020
<p>The paper describes a procedure using the first principle modelling and experimental identification of the Magnetic Levitation Model CE 152. It is a modified version of the paper [1]. The difference is that the identification and verification is done in open loop and constraints logic is added in the current paper. The author optimized and simplified dynamic model to a minimum to what is needed to characterize given system for the simulation and control design purposes. Only few open-loop experiments are needed to estimate the unknown parameters. Model quality is verified in open loop where the real and simulated data are compared. The model can serve as a simulation model for some…