Abdul Syukor Mohamad Jaya

Fuzzy logic-based for predicting roughness performance of TiAlN coating

In this paper a new application of fuzzy logic to predict the performance of Titanium Aluminum Nitride (TiAlN) sputtering coating process is presented. Titanium Aluminum Nitride (TiAlN) coated material is widely used as a cutting tool in machining due to its excellent properties such as hardness, roughness and wear. A fuzzy logic model was proposed to predict the coating roughness with respect to changes in input process parameters, the substrate sputtering power, bias voltage and temperature. Five membership functions are assigned to be associated with each input of the model. The predicted results obtained via fuzzy logic model were compared to the experimental result. The result indicated good agreement between the fuzzy model and experimental results with the 96.39% accuracy.

Robotic modeling and simulation of palletizer robot using Workspace5

Employment of robots in manufacturing has been a value-added entity in a manufacturing industry. Robotic simulation is used to visualize entire robotic application system, to simulate the movement of robot arm incorporated with components consist in its environment and to detect collision between the robot and components. This paper presents result of a project in implementing a computer based model to simulate Okura A1600 palletizer robot. The application uses Okura A1600 robot for palletizing bags at the end of the production line and focuses on pick-and-place application. The project objective is to generate a computer simulated model to represent the actual robot model and its environment. The project simulates the robots first four joints, namely as the waist, shoulder, elbow and waist and focuses on the position of the robots end effector, regardless its orientation. Development of the model is using Workspace5 as a simulation tool. Two types of methodology are used, which are the methodology for developing the robotic workcell simulation model and the methodology for executing the robotic simulation. The output of the project will be a three-dimensional view of robot arm movement based on series of predefined geometry points, layout checking and robots reachability by generating working envelope, collision and near miss detection, and monitoring on the cycle time upon completing a task. The project is an offline programming and no robot language is generated.

Modeling of ANFIS in predicting TiN coatings roughness

In this paper, an approach in predicting surface roughness of Titanium Aluminum Nitrite (TiN) coatings using Adaptive Network Based Fuzzy Inference System (ANFIS) is implemented. The TiN coatings were coated on tungsten carbide (WC) using Physical Vapor Deposition (PVD) magnetron sputtering process. The N2 pressure, argon pressure and turntable speed were selected as the input parameters and the surface roughness as an output of the process. Response Surface Methodology (RSM) was used to design the matrix in collecting the experimental data. In the ANFIS structure, triangular, trapezoidal, bell and Gaussian shapes were used for as input membership function (MFs). The collected experimental data was used to train the ANFIS model. Then, the ANFIS model were validated with the actual testing data and compared with regression model in terms of the residual error and model accuracy. The result indicated that the ANFIS model using three bell shapes MFs obtained better result compared to the polynomial regression model. The number of MFs showed significant influence to the ANFIS model performance. The result also indicated that the limited experimental data could be used in training the ANFIS model and resulting accurate predictive result.

Hybrid RSM-fuzzy modeling for hardness prediction of TiAlN coatings

In this paper, a new approach in predicting the hardness of Titanium Aluminum Nitrite (TiAlN) coatings using hybrid RSM-fuzzy model is implemented. TiAlN coatings are usually used in high-speed machining due to its excellent surface hardness and wear resistance. The TiAlN coatings were produced using Physical Vapor Deposition (PVD) magnetron sputtering process. A statistical design of experiment called Response Surface Methodology (RSM) was used in collecting optimized data. The fuzzy rules were constructed using actual experimental data. Meanwhile, the hardness values were generated using the RSM hardness model. Triangular shape of membership functions were used for inputs as well as output. The substrate sputtering power, bias voltage and temperature were selected as the input parameters and the coating hardness as an output of the process. The results of hybrid RSM-fuzzy model were compared against the experimental result and fuzzy single model based on the percentage error, mean square error (MSE), co-efficient determination (R2) and model accuracy. The result indicated that the hybrid RSM-fuzzy model obtained the better result compared to the fuzzy single model. The hybrid model with seven triangular membership functions gave an excellent result with respective average percentage error, MSE, R2 and model accuracy were 11.5%, 1.09, 0.989 and 88.49%. The good performance of the hybrid model showed that the RSM hardness model could be embedded in fuzzy rule-based model to assist in generating more fuzzy rules in order to obtain better prediction result.

Modeling of TiN Coating Thickness Using ANFIS

In this paper, an approach in predicting thickness of Titanium Aluminum Nitrite (TiN) coatings using Adaptive Network Based Fuzzy Inference System (ANFIS) is implemented. The TiN coatings were coated on tungsten carbide (WC) using Physical Vapor Deposition (PVD) magnetron sputtering process. The N2 pressure, argon pressure and turntable speed were selected as the input parameters and the coating thickness as an output of the process. Response Surface Methodology (RSM) was used to design the matrix in collecting the experimental data. In the ANFIS structure, three bell shapes were used as input membership function (MFs). The collected experimental data was used to train the ANFIS model. Then, the ANFIS model was validated with confirmatory test data and compared with other prediction models in terms of the root mean square error (RMSE), residual error and prediction accuracy. The result indicated that the developed ANFIS model result was the lowest RMSE7 and average residual error, besides the highest in prediction accuracy compared to the other models. The result also indicated that the limited experimental data could be used in training the ANFIS model and resulting accurate predictive result.

Modeling of TiN Coating Grain Size Using RSM Approach

Modeling of thin film coating is an important work to identify the required characteristic. In general, suitable coating process parameters are very important to find the best characteristics of coating and towards less material usage, reduced trial in experiment and less machine maintenance. In this paper, Response Surface Methodology (RSM) was implemented in modeling TiN coating grain size. N2 pressure, Argon pressure, and turntable speed were selected as process variables, while the coating grain size as an output response. Significant factors that influence the coating characteristic are determined by using Analysis of Variance (ANOVA) and to develop a polynomial quadratic model. Findings from this study suggested that turntable speed and Argon pressure quadratic term has significant effect to the TiN coating grain size. The result also showed that the actual validation data fell within the 95% prediction interval (PI) and the residual errors percentage was lower than 10%.

Modeling of TiN coating thickness using RSM approach

In this paper, modeling of Titanium Nitrite (TiN) coating thickness using Response Surface Method (RSM) is implemented. Insert cutting tools were coated with TiN using Physical Vapor Deposition (PVD) sputtering process. N2 pressure, Argon pressure and turntable speed were selected as process variables while the coating thickness as output response. The coating thickness as an important coating characteristic was measured using surface profilometer equipment. Analysis of variance (ANOVA) was used to determine the significant factors influencing TiN coating thickness. Then, a polynomial linear model represented the process variables and coating thickness was developed. The result indicated that the actual validation data fell within the 90% prediction interval (PI) and the percentage of the residual errors were low. Findings from this study suggested that Argon pressure, N2 pressure and turntable speed influenced the TiN coating thickness.

Fuzzy rule-based model to estimate surface roughness and wear in hard coatings

In this paper, a new approach in predicting the surface roughness and flank wear of hard coatings using fuzzy rule-based model is implemented. Hard coatings is important for cutting tool due to its excellent performances in 800°C temperature during high speed machining. The coating process were run using Physical Vapor Deposition (PVD) magnetron sputtering process. An experiment matrix called Response Surface Methodology (RSM) was used to collect data based on optimized data point. Sputtering power, substrate bias voltage and substrate temperature were used as the variables, and coating roughness and flank wear as the output responses of the coating process. The collected experimental data were used to develop fuzzy rules. Five triangular membership functions (MFs) for input variables and nine MFs for output responses were used in constructing the models. The results of fuzzy rule-based models were compared against the experimental result based on the percentage error, co-efficient determination (R2) and model accuracy. The rule-based model for coating roughness showed an excellent result with respective smallest percentage error, R2 and model accuracy were 0.85%, 0.953 and 89.20% respectively. Meanwhile, the fuzzy flank wear model indicated 6.38%, 0.91 and 81.79% for smallest percentage error, R2 and model accuracy. Thus, fuzzy logic can be a good alternative in predicting coating roughness and flank wear in hard coatings.

Predictive Modeling of TiN Coating Roughness

In this paper, an approach in modeling surface roughness of Titanium Nitrite (TiN) coating using Response Surface Method (RSM) is implemented. The TiN coatings were formed using Physical Vapor Deposition (PVD) sputtering process. N2 pressure, Argon pressure and turntable speed were selected as process variables. Coating surface roughness as an important coating characteristic was characterized using Atomic Force Microscopy (AFM) equipment. Analysis of variance (ANOVA) is used to determine the significant factors influencing resultant TiN coating roughness. Based on that, a quadratic polynomial model equation represented the process variables and coating roughness was developed. The result indicated that the actual coating roughness of validation runs data fell within the 90% prediction interval (PI) and the residual errors were very low. The findings from this study suggested that Argon pressure, quadratic term of N2 pressure, quadratic term of turntable speed, interaction between N2 pressure and turntable speed, and interaction between Argon pressure and turntable speed influenced the TiN coating surface roughness.

Application of Fuzzy Rule-Based Model to Predict TiAlN Coatings Roughness

In this work, an approach for predicting the roughness of Titanium Aluminum Nitride (TiAlN) coatings using fuzzy ruled-based model was discussed. TiAlN coatings were produced using magnetron sputtering process. Tungsten carbide (WC) was selected as the substrate and titanium alloy was used as the material to coat the cutting tool. The sputtering power, substrate bias voltage and substrate temperature were selected as the input variables while roughness of the TiAlN coatings was considered as the response variable. A statistical design of experiments method known as centre cubic design (CCD) was selected to collect the data for developing the fuzzy rules. The prediction performances of the fuzzy rule-based model with respect to percentage error, mean squared error (MSE), co-efficient determination (R2) and model accuracy were compared with the response surface regression model (RSM). The result shown that the fuzzy rule-based model has much better predicting capability compared to the RSM.