Mohd Sazli Saad
Thumbnail Image
Preferred name
Mohd Sazli Saad
Official Name
Mohd Sazli , Saad
Alternative Name
Saad, Mohd Sazli
Saad, M. Sazli
Saad, Mohd S.
Saad, M. Sazli
Main Affiliation
Scopus Author ID
57219520932
Researcher ID
Y-4444-2019

Research Output

Filters

5
3 1
Reset filters

Settings
Now showing 1 - 5 of 5
  • Publication
    Optimizing Fused Deposition Modeling with ANN: Material Consumption and Tensile Strength Predictions
    ( 2023-01-01)
    Nasuha H.
    ;
    Mohd Sazli Saad
    ;
    Mohamad Ezral Baharudin
    ;
    Nor A.M.
    ;
    Mohd Zakimi Zakaria
    Conventional modelling was once favored for process modelling for its straightforward nature and simplicity. However, conventional modelling is incapable of modelling complex processes such as fused deposition modelling (FDM). This study aims to model an accurate FDM process using an artificial neural network (ANN) to predict material consumption and tensile strength based on layer height, infill density, printing temperature and printing speed. The design of the experiment (DOE) was constructed using face-centered central composite design (FCCCD) yielding a total of 78 specimens. The material consumption was measured by weighting the specimen using a densimeter while the tensile strength of the specimen was tested using a universal testing machine (UTM). Best ANN structures were first identified in a trained network before being modelled for comparison. Models were compared using 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 best predictive model structure for material consumption is 4-19-14-1 with the lowest MSE of 0.00096 while the best predictive model structure for tensile strength is 4-16-15-12-1 with the lowest MSE of 0.005274145.
  • Publication
    Prediction of the material consumption of PLA plus fused deposition models using artificial neural network technique
    ( 2024-04-22)
    Nasuha H.
    ;
    Mohd Sazli Saad
    ;
    Mohamad Ezral Baharudin
    ;
    Nor A.M.
    ;
    Mohd Zakimi Zakaria
    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
    ANN-Based Predictive Modelling for Fused Deposition Modelling: Material Consumption, Tensile Strength & Dimensional Accuracy
    ( 2023-01-01)
    Irazman H.N.H.
    ;
    Mohd Sazli Saad
    ;
    Mohamad Ezral Baharudin
    ;
    Mohd Zakimi Zakaria
    ;
    Nor A.M.
    ;
    Rahim Y.A.
    Conventional modelling approaches fall short of accurately capturing the complexities of Fused Deposition Modelling (FDM). This research proposes an Artificial Neural Network (ANN) model to predict the FDM process's material consumption, tensile strength, and dimensional accuracy. Inputs such as layer height, infill density, printing temperature, and printing speed are considered. A Face-Centered Central Composite Design (FCCCD) with 78 specimens is employed to design experiments (DOE). Material consumption is measured using a densimeter, while tensile strength is determined using a Universal Testing Machine (UTM). The performance of the ANN models is evaluated based on metrics like Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and coefficient of determination (R2). The optimal ANN structure for material consumption prediction is found to be 4-19-14-1, achieving a low MSE of 0.00096. For tensile strength prediction, the best ANN structure is determined as 4-16-15-12-1 with an MSE of 0.005274145. Furthermore, dimensional accuracy is successfully captured using a 4-12-12-11-1 network configuration, which attains the lowest overall MSE of 0.002898. The proposed ANN model provides accurate predictions for material consumption, tensile strength, and dimensional accuracy in the FDM process. This study contributes to the optimization and understanding of FDM manufacturing processes through the utilization of optimized network architectures. The findings demonstrate the efficacy of the ANN model in improving FDM process control and performance.
  • Publication
    Optimizing Surface Roughness of PLA Printed Parts using Particle Swarm Optimization (PSO)
    ( 2023-01-01)
    Hadi Irazman H.N.
    ;
    Mohd Sazli Saad
    ;
    Mohamad Ezral Baharudin
    ;
    Mohd Zakimi Zakaria
    ;
    Nor A.M.
    ;
    As'arry A.
    Fused Deposition Modelling (FDM) is an additive manufacturing-based rapid prototyping technology that has gained widespread attention due to its ability to produce complex geometries with relatively low cost and fast production time. However, the surface finish of the FDM printed parts can be adversely affected by the selection of input parameters, such as layer height, infill density, print temperature, etc. This study aims to investigate the impact of these parameters on surface roughness and optimize the FDM process to improve surface finish. Two optimization approaches were employed in the study to address this problem, namely the Response Surface Methodology (RSM) and the particle swarm optimization (PSO) method. The impacts of four factors, layer height, printing speed, infill density, and print temperature, on the surface roughness of Polylactic Acid (PLA) printed parts were evaluated. A Face-centred Central Composite Design (FCCD) was used to reduce the number of experiments and to optimize the process. Both RSM and PSO methods were employed to find the best combination of process parameters for minimum surface roughness. The results of the experiment indicated that the optimal settings for minimum surface roughness were a layer height of 0.10 mm, printing speed of 30.36 m/s, infill density of 77.10 %, and print temperature of 195.12 °C, resulting in a surface roughness value of 1.31 µm. From these findings, the PSO optimization method was found to be more effective than the RSM method, showing a significant improvement in surface roughness with a reduction of 13.5 %.
  • Publication
    Modeling coupled electric drives systems using a modified narmax model
    ( 2021-05-03)
    Mohd Zakimi Zakaria
    ;
    Mansor Z.
    ;
    Nor A.M.
    ;
    Mohamad Ezral Baharudin
    ;
    Mohd Sazli Saad
    The nonlinear auto-regressive moving average with exogeneous input (NARMAX) model known as one of superior type of models to represent a wide class of dynamic systems. In this paper, a modified NARMAX is proposed in modeling dynamic system. The aim is to investigate the performance of the modified NARMAX model and compared to the conventional NARMAX model for modeling CE8 coupled electric drives system. Multi-objective optimization differential evolution (MOODE) algorithm is used as a model structure selection algorithm to obtain the final model from both approached models. Model predicted output (MPO) test is applied in order to reveal the performance of each model. Through the MPO test, it is concluded that the modified NARMAX model offers a better predicted output than conventional NARMAX model.