TY - JOUR
TI - A method for calculating structural reliability of MEMS systems by the implicit functional function
AU - Du Juan
AU - Li Haibin
AU - He Yun
JN - Thermal Science
PY - 2026
VL - 30
IS - 2
SP - 961
EP - 971
PT - Article
AB - In this paper, a novel approach to calculate the structural reliability of  micro-electro-mechanical systems systems is proposed. This approach utilizes  the implicit functional function, which involves the acquisition of  multiple sets of inputs and responses of the structure through numerical  simulation or experimentation. Concurrently, the exponential function is  employed as the activation function of the hidden layer of the neural  network. A multi-layer neural network possesses the capacity to approximate  the properties of arbitrary non-linear functions with arbitrary precision  and construct a customized neural network structure. The training of this  customized neural network enables the visualization and expression of the  structural function. This approach has been demonstrated to enhance the  precision of functional fitting. The proposed method for modeling complex  structural systems reliability is substantiated by numerical examples.  Micro-electro-mechanical systems play a pivotal role in modern engineering,  and their integration has the potential to further enhance structural  analysis and reliability assessment.
DO - 10.2298/TSCI2602961D
ER -