Nowe zasoby w kolekcji Bibliografia Publikacji Pracowników PK http://suw.biblos.pk.edu.pl/ Biblioteka Politechniki Krakowskiej lipinska@biblos.pk.edu.pl 60 <![CDATA[Neural networks for the simulation and identification analysis of buildings subjected to paraseismic excitations]]> Thu, 22 Feb 2024 07:43:10 +0100 Kuźniar, Krystyna; Waszczyszyn, Zenon
rodzaj: rozdział/fragment książki
Abstrakt: The chapter deals with an application of neural networks to the analysis of vibrations of medium-height prefabricated buildings with load-bearing walls subjected to paraseismic excitations. Neural network technique was used for identification of dynamic properties of actual buildings, simulation of building responses to paraseismic excitations as well as for the analysis of response spectra. Mining tremors in strip mines and in the most seismically active mining regions in Poland with underground exploitation were the sources of these vibrations. On the basis of the experimental data obtained from the measurements of kinematic excitations and dynamic building responses of actual structures the training and testing patterns were formulated. It was stated that the application of neural networks enables us to predict the results with accuracy quite satisfactory for engineering practice. The results presented in this chapter lead to a conclusion that the neural technique gives new prospects of efficient analysis of structural dynamics problems related to paraseismic excitations.]]>
<![CDATA[Fuzzy weight neural network in the analysis of concrete specimens and R/C column buckling tests]]> Wed, 21 Feb 2024 17:07:02 +0100 Jakubek, Magdalena
rodzaj: materiały konferencyjne w czasopiśmie
Abstrakt: The paper describes the applications of back propagation neural networks with the ability to process input and output variables expressed as fuzzy numbers. The presentation of an algorithm for finding fuzzy neural network weights is followed by three examples of applications of this technique to the problems of implicit modelling of material and structure behaviour. The following problems are considered: prediction of concrete fatigue failure, high performance concrete strength prediction, and prediction of critical axial load for eccentrically loaded reinforced concrete columns.]]>
<![CDATA[Identification of an equivalent model for granular soils by FEM/NMM/p-EMP hybrid system]]> Wed, 21 Feb 2024 15:27:15 +0100 Pabisek, Ewa
rodzaj: materiały konferencyjne w czasopiśmie
Abstrakt: The application of FEM/NMM/p-EMP computational hybrid system in formulation of the Neural Material Model (NMM) for granular soils is presented. NMM is a Multi Layer Preceptron formulated 'on-line'. The cumulative algorithm of the autoprogressive method was implemented into the FEM program. The patterns for NMM training were generated in the rigid strip footing analysis. Pseudo-empirical equilibrium paths p-EMP for verification of the NMM were computed by a FEM program for the elastic-plastic Drucker-Prage material model. The discussed inverse problem of NMM identification is illustrated by two study cases of footing: 1) rigid strip footing on plane semispace, 2) inclined slope analysis. It was numerically proved that the NMM identified in the first study case can be successfully applied to the analysis of the latter one.]]>
<![CDATA[Bayesian neural networks and Gaussian processes in identification of concrete properties]]> Wed, 21 Feb 2024 15:03:18 +0100 Słoński, Marek
rodzaj: materiały konferencyjne w czasopiśmie
Abstrakt: This paper gives a concise overview of concrete properties prediction using advanced nonlinear regression approach and Bayesian inference. Feed-forward layered neural network (FLNN) with Markov chain Monte Carlo stochastic sampling and Gaussian process (GP) with maximum likelihood hyperparameters estimation are introduced and compared. An empirical assessment of these two models using two benchmark problems are presented. Results on these benchmark datasets show that Bayesian neural networks and Gaussian processes have rather similar prediction accuracy and are superior in comparison to linear regression model.]]>
<![CDATA[Analysis of concrete fatigue failure by the neuro-fuzzy network FWNN]]> Wed, 21 Feb 2024 10:57:12 +0100 Jakubek, M.; Waszczyszyn, Z.
rodzaj: artykuł w czasopiśmie
Abstrakt: The paper is related to where the standard BPNNs (Back-Propagation Neural Networks) were applied to the analysis of concrete fatigue durability. Failure is related to the number N of compressive load cycles causing fatigue damage of laboratory specimens. About 450 results on laboratory concrete specimen tests were taken from. The main goals of the paper are to improve the neural approximation performed by the standard BPNN and to extend neural simulation also for data given in intervals of concrete strength and cycle frequencies. That is why a neuro-fuzzy NN called for short FWNN (Fuzzy Weght NN) was applied. This approach enables us to be closer to the experimental reality.]]>
<![CDATA[Analityczno-numeryczne metody modelowania rurowych krzyżowo-prądowych wymienników ciepła o złożonym systemie przepływowym : rozprawa doktorska]]> Tue, 20 Feb 2024 17:33:19 +0100 Węglarz, Katarzyna
rodzaj: rozprawa doktorska
Abstrakt: W rozprawie przedstawiono dwie metody analityczno-numeryczne wyznaczania rozkładu temperatury pary, ścianek rur i spalin w przegrzewaczach pary. Pierwsza metoda bazuje na rozwiązaniu ścisłym dla jednorzędowego wymiennika krzyżowo-prądowego. Przegrzewacz dzielony jest na objętości skończone, wewnątrz których temperatura pary i spalin określona jest analitycznymi wzorami ścisłymi. Temperatura pary, ścianek rur i spalin może być obliczona w dowolnym punkcie przegrzewacza. Liczba objętości skończonych na długości jednego biegu może być niewielka, aby uzyskać bardzo dobrą dokładność wyznaczania temperatur pary i spalin oraz ścianek rur. W metodzie drugiej, podobnie jak w metodzie pierwszej, przegrzewacz dzielony jest na objętości skończone. Temperaturę pary i spalin wyznacza się jednak tylko na wylocie z objętości kontrolnej, a temperaturę ścianki w środku objętości kontrolnej. Z modelu matematycznego przegrzewacza, bazującego na metodzie drugiej, wyznaczane są temperatury pary, spalin i rur w węzłach objętości skończonych. Przy niewielkiej liczbie objętości skończonych na długości rur, mniejszej od czterech, dokładność wyznaczania temperatur czynników i rury jest nieco mniejsza niż w metodzie pierwszej. Dokładność obydwu opracowanych metod zweryfikowano poprzez ich porównanie z metodami analitycznymi ścisłymi.]]>
<![CDATA[Selected problems of artificial neural networks development]]> Tue, 20 Feb 2024 14:22:34 +0100 Waszczyszyn, Zenon; Słoński, Marek
rodzaj: rozdział/fragment książki
Abstrakt: The chapter discusses selected problems of applications of Standard (deterministic) Neural Networks (SNN) but the main attention is focused on Bayesian Neural Networks (BNNs). In Sections 2 and 3 the problems of regression analysis, over-fitting and regularization are discussed basing on two types of network, i.e. Feed-forward Layered Neural Network (FLNN) and Radial Basis Function NN (RBFN). Application of Principal Component Analysis (PCA) is discussed as a method for reduction of input space dimensionality. In Section 4 the application of Kalman filtering tolearning of SNNs is presented. Section 5 is devoted to discussion of some basics related to Bayesian inference. Then Maximum Likelihood (ML) and Maximum APosterior (MAP) methods are presented as a basis for formulation of networks SNN-ML and SNN-MAP. A more general Bayesian framework corresponding to formulation of simple, semi-probabilistic network-BNN, true probabilistic T-BNN and Gaussian Process GP-BNN is discussed. Section 6 is devoted to the analysis of four study cases, related mostly to the analysis of structural engineering and material mechanics problems.]]>