High-precision damage assessment in functionally graded composite plates

Functionally graded material (FGM) is crucial for reliable performance in production complexity increases with the desired gradient profile, making it challenging and potentially costly to produce material. Detecting, localizing, and quantifying damage in functionally graded material plate structures in an effective manner. Three different composite materials are used in FGM and composite plates: Al/ZrO_2–1, Al/Al₂O₃ and Al/ZrO_2–2. These materials are created by mixing two or more separate components to produce a new material. This manuscript proposes a hybrid method for Enhanced Damage Assessment in Functionally Graded Composite Plates. The proposed method combines Scalable Inception Graph Neural Networks (SIGNN) and Kookaburra Optimization Algorithm (KOA) and is labelled as SIGNN-KOA approach. A SIGNN is utilized to calculate the damaged elements in FGM composite plates. KOA is utilized to obtain the optimized weight parameters of SIGNN. The goal of the proposed technique is to enhance damage detection in FGM. By then, the proposed method is implemented and the execution is calculated with the existing procedure in the MATLAB working platform. The proposed method shows better efficiency methods like deep neural network (DNN), Deep Feed-forward Neural Network (DFNN) and artificial neural network (ANN). The proposed method efficiency value is 0.036 % which is lower than that of ANN, DNN and DFNN values are 0.056 %, 0.046 % and 0.066 % respectively.