• Refine Query
  • Source
  • Publication year
  • to
  • Language
  • 1
  • 1
  • Tagged with
  • 2
  • 2
  • 2
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • 1
  • About
  • The Global ETD Search service is a free service for researchers to find electronic theses and dissertations. This service is provided by the Networked Digital Library of Theses and Dissertations.
    Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
1

Modeliranje funkcija obradivosti pri procesu obrade glodanjem / Modeling of machinability functions in the milling process

Savković Borislav 23 November 2015 (has links)
<p>U radu je izvršeno eksperimentalno istraživanje procesa obrade<br />glodanjem u cilju saznanja o obradivosti legure aluminijuma dobijene<br />sa dva različita tipa livenja. Izvršeno je modeliranje funkcija<br />obradivosti preko izmerenih karakteristika stanja procesa: sila<br />rezanja, hrapavosti obrađene površine, temperature u procesu rezanja<br />i faktora sabijanja strugotine. Modeliranje funkcija obradivosti je<br />izvršeno pomoću faktornog plana eksperimenta, kao i primenom<br />veštačkih neuronskih mreža i fazi logike. Optimizacija ulaznih<br />parametara procesa obrade glodanjem sprovedena je pomoću Taguči<br />metode. Proces glodanja simuliran je pomoću metoda konačnih<br />elemenata.</p> / <p>In this work an experimental research of the milling process were performed<br />in order to find out the machinability of aluminum alloys which are obtained<br />with two different types of casting procedure. Modeling of machinability<br />functions is performed through the measured process state characteristics:<br />cutting force, surface roughness, temperature in the cutting zone and chip<br />compression ratio. Modeling of the machinability functions was performed<br />using a full factorial experiment and through the model of artificial neural<br />networks and fuzzy logic. Optimization of process input values in defined<br />models is performed through Taguchi methods. The process of milling is<br />simulated with finite element method.</p>
2

Identification de paramètre basée sur l'optimisation de l'intelligence artificielle et le contrôle de suivi distribué des systèmes multi-agents d'ordre fractionnaire / Parameter identification based on artificial intelligence optimization and distributed tracking control of fractional-order multi-agent systems

Hu, Wei 10 July 2019 (has links)
Cette thèse traite de l'identification des paramètres du point de vue de l'optimisation et du contrôle de suivi distribué des systèmes multi-agents d'ordre fractionnaire (FOMASs) en tenant compte des retards, des perturbations externes, de la non-linéarité inhérente, des incertitudes des paramètres et de l'hétérogénéité dans le cadre d'une topologie de communication fixe non dirigée / dirigée. Plusieurs contrôleurs efficaces sont conçus pour réaliser avec succès le contrôle de suivi distribué des FOMASs dans différentes conditions. Plusieurs types d'algorithmes d'optimisation de l'intelligence artificielle et leurs versions modifiées sont appliquées pour identifier les paramètres inconnus des FOMASs avec une grande précision, une convergence rapide et une grande robustesse. Il est à noter que cette thèse fournit un lien prometteur entre la technique d'intelligence artificielle et le contrôle distribué. / This thesis deals with the parameter identification from the viewpoint of optimization and distributed tracking control of fractional-order multi-agent systems (FOMASs) considering time delays, external disturbances, inherent nonlinearity, parameters uncertainties, and heterogeneity under fixed undirected/directed communication topology. Several efficient controllers are designed to achieve the distributed tracking control of FOMASs successfully under different conditions. Several kinds of artificial intelligence optimization algorithms andtheir modified versions are applied to identify the unknown parameters of the FOMASs with high accuracy, fast convergence and strong robustness. It should be noted that this thesis provides a promising link between the artificial intelligence technique and distributed control.

Page generated in 0.1683 seconds