Yigit, E.Hayber, Ş. E.Aydemir, Umut2023-02-152023-02-152022-06-230263-2241http://hdl.handle.net/11693/111283In this study, an artificial neural network (ANN) based model is developed for MEMS diaphragm analysis, which does not require difficult and time-consuming FEM processes. ANN-based estimator is generated for static pressure response (d) and dynamic pressure response (f) analysis of TLC (three leaf clover) diaphragms for Fabry-Perot interferometers as an example. TLC is one of the unsealed MEMS design diaphragms formed by three leaves of equal angles. The diaphragms used to train ANNs are designed with SOLIDWORKS and analyzed with ANSYS. A total of 1680 TLC diaphragms are simulated with eight diaphragm parameters (3 for SiO2 material, 4 for geometry, and 1 for pressure) to create a data pool for ANN’s training, validation, and testing processes. 80% of the data is used for training, 15% for validation, and the remaining for testing. Only four geometric parameters are used as input in the ANN estimator, and the material parameters are added to the model with an analytical multiplier. Thus, network models that estimate d and f values for all kinds of diaphragm materials are proposed, with a material-independently trained ANN structure. The performance of the ANN model is compared with the empirical equation suggested in the literature, and its superiority is demonstrated. In addition, the d and f parameters of TLC diaphragms designed with five different materials (Si, In2Se3, Ag, EPDM, Graphene) are estimated to be very close to the real ones. By using the proposed method, analyses of TLC diaphragms are quickly performed without the need for time-consuming and costly design and analysis programs.TurkishMachine learningMEMSDiaphragm designFEMFabry-perot interferometerArticle10.1016/j.measurement.2022.1115341873-412X