Adaptive Network-Based Fuzzy Inference for Damage Detection in Rectangular Laminated Composite Plates Using Vibrational Data

A novel model is developed to identify damages severities in rectangular laminated composite plates (RLCPs) based on the finite element method (FEM) and adaptive neuro-fuzzy inference system (ANFIS). Empirical data are generated via FEM, and then the ANFIS algorithm is applied to identify damages’ severities of single damage scenarios. In this study, the networks’ inputs and outputs are the first five natural frequencies and damages’ severities. Also, a multilayer perceptron neural network (MLP) is developed to compare results obtained from ANFIS. Results show that the MLP model can identify the severity of every single damage scenario in RLCPs with a high precision (R > 0.9). Also, results obtained indicate that ANFIS can identify and predict the severity of every single damage scenario in RLCPs better than MLP with perfect precision (R = 0.99999)