DIKUL - logo
VSE knjižnice (vzajemna bibliografsko-kataložna baza podatkov COBIB.SI)
  • Comparison between genetic algorithm and genetic programming approach to predict stress distribution in cold-formed material
    Brezočnik, Miran ; Gusel, Leo, 1968- ; Balič, Jože
    In this paper a comparison is made between gene tie algorithm (GA) and genetic programming (GP) approach to predict radial stress distribution in cold-formed material. Cylindrical specimens of copper ... alloy were forward extruded and analyzed by visioplasticity method. After each extrusion the values of three independent variables (i.e., radial position of measured stress node. axial position of measured stress node, and coeficient of friction) were collected. These variables influence the value of dependent variable. i.e.. radial stress. Two types of data were chosen randomly from the pool of measurements: training and testing data. On the basis of training data, diffirent prediction models for radial stress distribution were developed independently by the GA and the GP. In modeling by the GA, only the coefficients of the prespecified models were optimized. In modeling by the GP, the form, size, and the complexity of the models were left to the simulate devolution. The obtained models were tested with the testing data. The research showed that both methods give relatively precise prediction models; however, if the relations between input and output variables are complex, the models developed by the GP approach are much more accurate.
    Vir: Proceedings of the 13th International conference on flexible automation and intelligent manufacturing, June 9th - 11th, Tampa, Florida, USA (Vol. 1, str. 106-116)
    Vrsta gradiva - prispevek na konferenci
    Leto - 2003
    Jezik - angleški
    COBISS.SI-ID - 8047382

Vnos na polico