The paper deals with a parameter identification problem for creep and
fracture model. The system of ordinary differential equations of kinetic
creep theory is applied for describing this model. As for solving the
parameter identification problem, we proposed to use the technique of neural
network modeling, as well as the multilayer approach. The procedures of
neural network modeling and multilayer approximation constructing
application is demonstrated by the example of finding parameters for
uniaxial tension model for isotropic steel 45 specimens at creep conditions.
The solution corresponding to the obtained parameters agrees well with
theoretical strain-damage characteristics, experimental data, and results
of other authors.
A detailed analysis has been performed for the prediction of long-term creep behaviour of tempered martensitic Grade 91 steel at 873 K using the microstructure-based creep damage mechanics approach. Necessary modifications have been made into the original kinetic creep law proposed by Dyson and McLean in order to account for the influence of microstructural damages arising from the coarsening of M23C6 and conversion of useful MX precipitates into deleterious Z-phase on creep behaviour of the steel. An exponential rate relationship has been introduced for the evolution of number density of MX precipitates with time. It has been shown that the developed model adequately predicts the experimental long-term creep strain–time as well as creep rate-time data. The role of Z-phase on long-term creep behaviour of Grade 91 steel has also been discussed.
Multilayer method for solving a problem of metals rupture under creep conditions