Research Output
Prediction of the material consumption of PLA plus fused deposition models using artificial neural network technique
Failure envelope modelling of glass/epoxy composite pipes using system identification method
1 - 2 of 2
Publication
Fused Deposition Modelling (FDM) is a complex additive manufacturing (AM) process involving multiple process parameters incapable of being modelled with conventional methods such as regression and mathematical modelling. The goal of the study is to develop an Artificial Neural Network (ANN) model that can accurately predict the material consumption of FDM printed parts considering the effect of process parameters such as layer height, infill density, printing temperature, and printing speed to create an ideal model that can optimize the use of resources and reduce material. The experiment was designed using face centered central composite design (FCCCD) yielding 78 specimens that were weighed using a densimeter to identify material consumption. Then, three networks with a different number of hidden layers and neurons were trained to identify the best-performing ANN structure with the lowest mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE) and highest coefficient of determination (R2). The fittest models were modelled and compared to identify the best-performing structure. Results indicated that the ANN model with double hidden layers with 19 and 14 neurons each showed the most precise prediction in modelling material consumption with the lowest MSE of 0.00096.
Publication
The paper aims to model the performance of the Glass Fibre Reinforced Epoxy (GRE) composite pipe under multiaxial loading via system identification approach. System identification modelling depends on the input and output data of the experimental result. In this study, the experimental data used are obtained from a pressurised test rig. The model is based on pure hydrostatic (2H: 1A) loading using GRE pipes with three different winding angles (±45°, ±55°, ±63°). Several models based on different model structures are derived for comparison to obtain the best modelling accuracy. The result shows that the transfer function method could model and has the highest efficiency compared with the experimental result. The ±45°pipe model have achieved 92.41% and 85.13% for both its hoop and axial model. The ±55°pipe model has achieved 96.64% and 86.1%. Follow by the ±63°which the best fit is 92.41% and 94.26%. At the last part of this research, the ±55°pipe model and experimental data has been use to identified when the damage occur and found that the axial strain of 78 bar can damage the experimental pipe in this research.