Wyniki wyszukiwania - BazTech

1

A MLMVN with arbitrary complex-valued inputs and a hybrid testability approach for the extraction of lumped models using FRA

Aizenberg Igor, Luchetta Antonio, Manetti Stefano, Piccirilli Maria Cristina

Journal of Artificial Intelligence and Soft Computing Research

|

2019

|

Vol. 9, No. 1

5--19

EN

A procedure for the identification of lumped models of distributed parameter electromagnetic systems is presented in this paper. A Frequency Response Analysis (FRA) of the device to be modeled is performed, executing repeated measurements or intensive simulations. The method can be used to extract the values of the components. The fundamental brick of this architecture is a multi-valued neuron (MVN), used in a multilayer neural network (MLMVN); the neuron is modified in order to use arbitrary complex-valued inputs, which represent the frequency response of the device. It is shown that this modification requires just a slight change in the MLMVN learning algorithm. The method is tested over three completely different examples to clearly explain its generality.

2

Improvement of lumped models in multiple infows rivers by principal component analysis and reliability analysis

Pashazadeh Arash, Javan Mitra

Acta Geophysica

|

2019

|

Vol. 67, no. 4

1149--1161

EN

Flood routing as an important part of food management is a technique for predicting the fow in downstream of a river channel or reservoir. Lumped, semi-distributed and distributed models have been devised in this regard. The convex and Att-Kin models are capable of simulating foods in single branches, while in reality, rivers and channels are multiple infows. The convex and modifed Att-Kin models as the simplest lumped models in terms of the storage equation were developed based on an equivalent infow for routing the multiple infows rivers in the present study. The genetic algorithm, a quite robust algorithm, was used for parameter estimation of the extended models. The ability of the extended models in simulating the outfow hydrograph of multiple infows systems was tested on two multiple infows case studies. The results of extended models were compared with the equivalent Muskingum infow model. Comparison of the extended models with the Muskingum model showed that the extended models with one parameter less than the Muskingum model could be suitable for use in food routing of multiple infows systems. The efect of infow hydrographs at diferent time steps was investigated by the principal component analysis (PCA) and reliability analysis. The results showed that the outfow hydrograph of the case study was precisely simulated and predicted by the gene expression programming (GEP) and multilayer perceptron (MLP) models. The PCA and reliability analysis results were adopted for the lumped, GEP and MLP models. The outfow hydrograph was precisely simulated and predicted by the GEP and MLP models, while the precision of lumped models (extended convex, extended modifed Att-Kin and Muskingum models) was not increased.

3

Lumped models of the cardiovascular system of various complexity

Ježek F., Kulhánek T., Kalecký K., Kofránek J.

Biocybernetics and Biomedical Engineering

|

2017

|

Vol. 37, no. 4

666--678

EN

Purpose: The main objective is to accelerate the mathematical modeling of complex systems and offer the researchers an accessible and standardized platform for model sharing and reusing. Methods: We describe a methodology for creating mathematical lumped models, decomposing a system into basic components represented by elementary physical laws and relationships expressed as equations. Our approach is based on Modelica, an object-oriented, equation-based, visual, non-proprietary modeling language, together with Physiolibrary, an open-source library for the domain of physiology. Results: We demonstrate this methodology on an open implementation of a range of simple to complex cardiovascular models, with great complexity variance (simulation time from several seconds to hours). The parts of different complexity could be combined together. Conclusions: Thanks to the equation-based nature of Modelica, a hierarchy of subsystems can be built with an appropriate connecting component. Such a structural model follows the concept of the system rather than the computational order. Such a model representation retains structural knowledge, which is important for e.g., model maintainability and reusability of the components and multidisciplinary cooperation with domain experts not familiar with modeling methods.