Now showing 1 - 10 of 13
  • Publication
    Prediction of the material consumption of PLA plus fused deposition models using artificial neural network technique
    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.
      2
  • Publication
    Addressing labour ergonomics through automation in oil palm plantation activities a necessity for sustainable agriculture
    A key element of the potential of robotics is understanding how effective automation can improve labour‐intensive jobs while also considering worker ergonomics. These sectors often depend on manual labour, which exposes employees to considerable ergonomic stress, especially musculoskeletal disorders (MSDs) that can result from repetitive and physically demanding activities like harvesting, pruning, and lifting heavy items. By coordinating automation tools such as harvesters, unloaders, and driverless carts with the various manual tasks that workers perform, we can significantly lower safety risks. The main objective of introducing automation is to reduce the physical strain on workers, which not only aims to alleviate MSD‐related health problems but also helps to lessen worker fatigue. Effectively integrating artificial intelligence (AI) and big data analytics will improve workforce efficiency, making the Brightfield industry stronger. Transitioning from manual tasks to automated solutions is just the initial step toward enhancing production in this field. By tackling these ergonomic issues through automation, this paper highlights the dual advantages of promoting worker health and increasing productivity in the industry.
      1  24
  • Publication
    Application of Differential Evolution (DE) Optimization Method in CNC Turning Process for Surface Roughness
    This paper presents the optimization of cutting speed, feed rate and depth of cut during CNC turning process of ASTM A36 Mild steel in order to minimize the surface roughness. The default parameters setting in some cases of machining process using conventional optimization technique does not guarantee the best surface roughness quality of the machined part. Therefore, in this study, a non-conventional method, Differential Evolution (DE) optimization, has been developed to address this problem. At first, a regression model using Response Surface Method (RSM) was developed using experimental data. The experiment was designed by using DOE method. Central composite design was applied in Design Expert software for building a second order (quadratic) model for minimum surface roughness. Then, DE algorithm was implemented using Matlab programming. The performances of both conventional and non-conventional techniques were compared through experimental validation tests. The results showed that optimal parameters setting values provided by DE obtained better results than RSM. Thus, in this study, DE can be considered as an efficient and effective technique to achieve a better surface roughness.
      1  13
  • Publication
    ARx modeling of flexible beam system using bat algorithm
    This paper describes the development of dynamic model of flexible beam system using system identification method based on nature inspired algorithm i.e. bat algorithm. At first, input-output data from the experimental rig of flexible beam were collected such that input signal is taken from piezo actuator and output signal from the laser displacement sensor. Then, linear parametric model structure is accomplished using auto regressive with exogenous inputs (ARX). The optimal parameters of the ARX model are identified using bat algorithm. The best parameter setting estimation is selected based on the best fit criterion i.e mean square error (MSE). The identified model is compared with the model from conventional estimation approach. Simulation results show that bat algorithm can outperform the least square algorithm in parametric modelling of the flexible beam.
      4  2
  • Publication
    Optimizing Fused Deposition Modeling with ANN: Material Consumption and Tensile Strength Predictions
    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.
      4
  • Publication
    ANN-Based Predictive Modelling for Fused Deposition Modelling: Material Consumption, Tensile Strength & Dimensional Accuracy
    ( 2023-01-01)
    Irazman H.N.H.
    ;
    ; ; ;
    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.
      2  12
  • Publication
    FDM Parameters Optimization for Improving Tensile Strength using Response Surface Methodology and Particle Swarm Optimization
    Fused deposition modelling (FDM) is a popular 3D printing technique that uses a thermoplastic filament as the build material. In FDM 3D printing, tensile strength can be an issue because the layers of the object are built on top of each other, and if the layers do not adhere properly, the object can be weak and prone to breaking. Typically, this problem is caused by incorrect parameter settings. Hence, this study was then carried out to analyse and improve the printing quality in term of tensile strength of the printed part using the response surface methodology (RSM) and the particle swarm optimization (PSO) method. The effect of four input parameters such as layer height, printing speed, infill density, and print temperature was examined on the tensile strength of polylactic acid (PLA) standard samples ASTM D638-IV. The experimental design was performed using face-centred central composite designs (FCCD). The experimental data were statistically analysed to form a regression model of the tensile strength. This model was used to approximate the actual process. The optimization was performed using desirability analysis from RSM and PSO to search for the optimal parameter for maximum tensile strength. Experimental results showed that PSO outperformed RSM with a 1.52 % reduction in tensile strength. The maximum tensile strength obtained from PSO was about 39.069 MPa with the optimal process parameters of layer height of 0.30 mm, printing speed of 30.17 m/s, infill density of 79.72 %, and print temperature of 205.92 °C.
      3  21
  • Publication
    System identification of flexible structure using firefly algorithm
    This paper originally concentrates on application of firefly algorithm on modeling of flexible beam. An attempt of obtaining a linear parametric model is accomplished by acquiring the input-output data from the vibration of beam and followed by the selection the auto regressive with exogenous inputs (ARX) model structure as a benchmark for mathematical model of beam. The parameters of the model structure are identified using firefly algorithm. A few sets of parameter settings are tested to find the most optimal value. The best parameter setting estimation is selected based on performance of model. The model is compared with the model from conventional estimation approach and validated using validity test. It is found that firefly algorithm produces the best ARX model with the lowest MSE compared to the least square algorithm.
      1  20
  • Publication
    Optimizing Surface Roughness of PLA Printed Parts using Particle Swarm Optimization (PSO)
    ( 2023-01-01)
    Hadi Irazman H.N.
    ;
    ; ; ;
    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 %.
      3
  • Publication
    Critical heat flux and Leidenfrost temperature on Electrical Discharge Machining (EDM) - constructed hemispherical surface
    ( 2021-10-01) ; ;
    Rosman N.A.
    ;
    ;
    Shaiful A.I.M.
    ;
    Ismail K.A.
    ;
    Ani M.H.
    This paper reports a Leidenfrost temperature on hemispherical surface constructed by Electrical discharge machining or known as EDM. We focus our study on the droplet evaporation lifetime to investigate and identify the Leidenfrost temperature. Three (3) different types of materials were selected i. e such as Brass (Br), Aluminum (Al) and Copper (Cu). Meanwhile, ethanol liquid has been chosen as the test liquid. Ethanol liquid was elected due to its low boiling point of approximately 78 °C. The droplet impact velocity and droplet diameter was approximately 1.129 m/s and 3.476 mm, respectively. As a result, we finally succeeded in determining the Leidenfrost temperature for all materials mentioned above. On top of that, all the Leidenfrost temperature results, TL were close to the superheat limit temperature of ethanol liquid, TSL which is about 197.8 °C.
      2