Rahaini Mohd Said
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Rahaini Mohd Said has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Nor Hafizah Hussin
Fakulti Teknologi dan Kejuruteraan Elektronik dan Komputer, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia
4 shared publications - Adam Samsudin
Fakulti Teknologi dan Kejuruteraan Elektrik, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia
3 shared publications - Mohamad Ridzuan Mohamad Kamal
Fakulti Teknologi dan Kejuruteraan Industri dan Pembuatan , Universiti Teknikal Malaysia Melaka, 76100, Durian Tunggal, Melaka, Malaysia
3 shared publications - Siti Haryanti Hj Hairol Anuar
Fakulti Teknologi dan Kejuruteraan Elektronik dan Komputer, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia
3 shared publications - Nur Azura Noor Azhuan
Fakulti Teknologi dan Kejuruteraan Elektrik, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, 76100 Durian Tunggal, Melaka, Malaysia
2 shared publications - Nurul Hajar Mohd Yussoff
Universiti Teknikal Malaysia Melaka, Malaysia
2 shared publications
Latest Publications
- Open Access
- 30 July 2024
- Published by Akademia Baru Publishing in Journal of Advanced Research in Applied Mechanics
- Vol. 121 (1) , 13-26
Modeling and Prediction of The Mechanical Properties of Feedstock by Cooling-Slope Casting Process using MOJaya Algorithm
Cooling-slope (CS) casting parameters optimization is very challenging due to the uncertainties of parameter values that are influenced by many factors. Therefore, a combination of estimation and optimization models that can solve multi-objective problems using limited data is proposed to reduce the real casting operational cost and time. In casting optimization, modeling and optimization of CS parameters have been considered to identify optimal CS parameters that would lead to better feedstock performance. Computational techniques have been suggested by previous researchers to solve the optimization in the manufacturing process. The study assessed the CS process to determine the feedstock's quality by evaluating its mechanical qualities, namely Tensile strength and Impact strength. Hence, computational methods namely the MOJaya algorithm are utilized to model and optimize the parameters of CS to address the CS problem and forecast the performance of the feedstock. This work conducted a thorough analysis of the impact of CS process parameters on the tensile strength and impact strength using an experimental design. The experiment was conducted using a three-level full factorial design (FFD) of the experiment (DOE), for the parameters of pouring temperature, slanting angle, and pouring distance. The modeling technique involved the development of multiple polynomial regression (MPR) as an objective function in the MOJaya Algorithm. The outcome of the optimization procedure revealed that the optimal solutions obtained from MOJaya were projected to surpass both the initial experimental data and the MOJaya algorithm in terms of the highest values of tensile strength and impact strength. The difference between the two sets of values is 10.92% and 15.76%, respectively. Subsequently, this technique may be employed by a caster to forecast the performance of the feedstock without using repeated experiments that are costly and time-consuming.
- 30 July 2024
- Published by Akademia Baru Publishing in Journal of Advanced Research in Applied Mechanics
- Vol. 121 (1) , 13-26
Open AccessModeling and Prediction of The Mechanical Properties of Feedstock by Cooling-Slope Casting Process using MOJaya Algorithm
Cooling-slope (CS) casting parameters optimization is very challenging due to the uncertainties of parameter values that are influenced by many factors. Therefore, a combination of estimation and optimization models that can solve multi-objective problems using limited data is proposed to reduce the real casting operational cost and time. In casting optimization, modeling and optimization of CS parameters have been considered to identify optimal CS parameters that would lead to better feedstock performance. Computational techniques have been suggested by previous researchers to solve the optimization in the manufacturing process. The study assessed the CS process to determine the feedstock's quality by evaluating its mechanical qualities, namely Tensile strength and Impact strength. Hence, computational methods namely the MOJaya algorithm are utilized to model and optimize the parameters of CS to address the CS problem and forecast the performance of the feedstock. This work conducted a thorough analysis of the impact of CS process parameters on the tensile strength and impact strength using an experimental design. The experiment was conducted using a three-level full factorial design (FFD) of the experiment (DOE), for the parameters of pouring temperature, slanting angle, and pouring distance. The modeling technique involved the development of multiple polynomial regression (MPR) as an objective function in the MOJaya Algorithm. The outcome of the optimization procedure revealed that the optimal solutions obtained from MOJaya were projected to surpass both the initial experimental data and the MOJaya algorithm in terms of the highest values of tensile strength and impact strength. The difference between the two sets of values is 10.92% and 15.76%, respectively. Subsequently, this technique may be employed by a caster to forecast the performance of the feedstock without using repeated experiments that are costly and time-consuming.
- Open Access
- 30 July 2024
- Published by Akademia Baru Publishing in Journal of Advanced Research in Applied Mechanics
- Vol. 121 (1) , 44-57
Handling Volatility and Nonlinearity in Wind Speed Data: A Comparative Analysis between ARIMA-GARCH and ARIMA-MLP
One of the notable features of wind speed is its volatility and nonlinearity. Thorough assessment on the presence of these features is crucial to obtain a wind speed forecasting model with higher accuracy. In this study, the conventional time series linear model; ARIMA model was applied to assess the internal structure of the wind speed daily data in two stations in Johor; Senai and Mersing. Due to the existence of some nonlinearity features in the residuals part of ARIMA modelling, two nonlinear models were introduced to capture the internal structure of the residual data. Both conventional time series models; GARCH, and machine learning model; MLP was applied to model the residuals of ARIMA model. The out-sample performance in forecasting accuracy was compared between the ARIMA-GARCH model and the ARIMA-MLP model. The findings proves that MLP model has outperformed GARCH model in capturing the dynamics in the residual data by providing the lowest error measurements. Thus, the machine learning approaches has proven its superiority against the conventional time series nonlinear model in handling the nonlinearity in the daily wind speed series for wind speed forecasting.
- 30 July 2024
- Published by Akademia Baru Publishing in Journal of Advanced Research in Applied Mechanics
- Vol. 121 (1) , 44-57
Open AccessHandling Volatility and Nonlinearity in Wind Speed Data: A Comparative Analysis between ARIMA-GARCH and ARIMA-MLP
One of the notable features of wind speed is its volatility and nonlinearity. Thorough assessment on the presence of these features is crucial to obtain a wind speed forecasting model with higher accuracy. In this study, the conventional time series linear model; ARIMA model was applied to assess the internal structure of the wind speed daily data in two stations in Johor; Senai and Mersing. Due to the existence of some nonlinearity features in the residuals part of ARIMA modelling, two nonlinear models were introduced to capture the internal structure of the residual data. Both conventional time series models; GARCH, and machine learning model; MLP was applied to model the residuals of ARIMA model. The out-sample performance in forecasting accuracy was compared between the ARIMA-GARCH model and the ARIMA-MLP model. The findings proves that MLP model has outperformed GARCH model in capturing the dynamics in the residual data by providing the lowest error measurements. Thus, the machine learning approaches has proven its superiority against the conventional time series nonlinear model in handling the nonlinearity in the daily wind speed series for wind speed forecasting.
- Open Access
- 10 July 2024
- Published by Akademia Baru Publishing in Journal of Advanced Research in Applied Mechanics
- Vol. 120 (1) , 85-98
Development Home Automation and Safety Circuit Breaker with Esp8266 Microcontroller
This study addresses common challenges in conventional home electricity usage, with a focus on safety concerns related to gas leakage. In many cases, current technology lacks immediate power usage tracking, and manual control of circuit breakers, sockets, and lamps proves challenging, especially when users are away. To overcome these issues, this project employs an ESP8266 Wi-Fi Shield Arduino as a microcontroller connected to sensors and a servo motor. In the proposed system, users can detect gas leakage, control lamp and socket activation, and manage the Residual Current Circuit Breaker (RCCB) with the servo motor by utilizing Blynk apps for monitoring. The main objective of this study is to design a centralized system that enables users to control and manage home electrical appliances via smartphone. The methodology involves developing a microcontroller program for the Cytron ESP8266 WiFi Shield, creating an auto-reclosure circuit breaker notification, and building a practical gas leakage detection prototype for household applications. Additionally, the system addresses lightning-induced overvoltage issues, analyzes nuisance tripping, and provides control over home appliance usage while effectively detecting hazardous gas leaks. The approach is based on Blynk and the ESP8266 Wi-Fi Shield Arduino by incorporating data from limit switch conditions, relay status, voltage sensors, current sensors, and power consumption. The results justify the servo's efficient performance, reliable relay operations, and precise gas sensor triggering. Despite slight variations in current and voltage values compared to the actual meter, the system offers a successful and systematic approach to enhancing home electricity management and safety.
- 10 July 2024
- Published by Akademia Baru Publishing in Journal of Advanced Research in Applied Mechanics
- Vol. 120 (1) , 85-98
Open AccessDevelopment Home Automation and Safety Circuit Breaker with Esp8266 Microcontroller
This study addresses common challenges in conventional home electricity usage, with a focus on safety concerns related to gas leakage. In many cases, current technology lacks immediate power usage tracking, and manual control of circuit breakers, sockets, and lamps proves challenging, especially when users are away. To overcome these issues, this project employs an ESP8266 Wi-Fi Shield Arduino as a microcontroller connected to sensors and a servo motor. In the proposed system, users can detect gas leakage, control lamp and socket activation, and manage the Residual Current Circuit Breaker (RCCB) with the servo motor by utilizing Blynk apps for monitoring. The main objective of this study is to design a centralized system that enables users to control and manage home electrical appliances via smartphone. The methodology involves developing a microcontroller program for the Cytron ESP8266 WiFi Shield, creating an auto-reclosure circuit breaker notification, and building a practical gas leakage detection prototype for household applications. Additionally, the system addresses lightning-induced overvoltage issues, analyzes nuisance tripping, and provides control over home appliance usage while effectively detecting hazardous gas leaks. The approach is based on Blynk and the ESP8266 Wi-Fi Shield Arduino by incorporating data from limit switch conditions, relay status, voltage sensors, current sensors, and power consumption. The results justify the servo's efficient performance, reliable relay operations, and precise gas sensor triggering. Despite slight variations in current and voltage values compared to the actual meter, the system offers a successful and systematic approach to enhancing home electricity management and safety.
- Open Access
- 14 March 2024
- Published by Universiti Putra Malaysia in Pertanika Journal of Science and Technology
- Vol. 32 (2) , 573-597
Modelling and Optimisation of Cooling-slope Parameters of Magnesium AZ91D using Improvement Multi-Objective Jaya Approach for Predicted Feedstock Performance
The cooling-slope (CS) casting technique is one of the simple semi-solid processing (SSP) processes a foundryman uses to produce the feedstock. This study attempts to develop mathematical regression models and optimise the CS parameters process for predicting optimal feedstock performance, which utilises tensile strength and impact strength to reduce the number of experimental runs and material wastage. This study considers several parameters, including pouring temperature, pouring distance, and slanting angles for producing quality feedstock. Hence, multi-objective optimisation (MOO) techniques using computational approaches utilised alongside the caster while deciding to design are applied to help produce faster and more accurate output. The experiment was performed based on the full factorial design (FFD). Then, mathematical regression models were developed from the data obtained and implemented as an objective function equation in the MOO optimisation process. In this study, MOO named multi-objective Jaya (MOJaya) was improved in terms of hybrid MOJaya and inertia weight with archive K-Nearest Neighbor (MOiJaya-aKNN) algorithm. The proposed algorithm was improved in terms of the search process and archive selection to achieve a better feedstock performance through the CS. The study’s findings showed that the values of tensile and impact strengths from MOiJaya_aKNN are close to the experiment values. The results show that the hybrid MOJaya has improved the prediction of feedstock using optimal CS parameters.
- 14 March 2024
- Published by Universiti Putra Malaysia in Pertanika Journal of Science and Technology
- Vol. 32 (2) , 573-597
Open AccessModelling and Optimisation of Cooling-slope Parameters of Magnesium AZ91D using Improvement Multi-Objective Jaya Approach for Predicted Feedstock Performance
The cooling-slope (CS) casting technique is one of the simple semi-solid processing (SSP) processes a foundryman uses to produce the feedstock. This study attempts to develop mathematical regression models and optimise the CS parameters process for predicting optimal feedstock performance, which utilises tensile strength and impact strength to reduce the number of experimental runs and material wastage. This study considers several parameters, including pouring temperature, pouring distance, and slanting angles for producing quality feedstock. Hence, multi-objective optimisation (MOO) techniques using computational approaches utilised alongside the caster while deciding to design are applied to help produce faster and more accurate output. The experiment was performed based on the full factorial design (FFD). Then, mathematical regression models were developed from the data obtained and implemented as an objective function equation in the MOO optimisation process. In this study, MOO named multi-objective Jaya (MOJaya) was improved in terms of hybrid MOJaya and inertia weight with archive K-Nearest Neighbor (MOiJaya-aKNN) algorithm. The proposed algorithm was improved in terms of the search process and archive selection to achieve a better feedstock performance through the CS. The study’s findings showed that the values of tensile and impact strengths from MOiJaya_aKNN are close to the experiment values. The results show that the hybrid MOJaya has improved the prediction of feedstock using optimal CS parameters.
- 1 January 2017
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 1842, 030023
Optimization of permeability for quality improvement by using factorial design
Sand castings are used worldwide by the manufacturing process in Metal Casting Industry, whereby the green sand are the commonly used sand mould type in the industry of sand casting. The defects on the surface of casting product is one of the problems in the industry of sand casting. The problems that relates to the defect composition of green sand are such as blowholes, pinholes shrinkage and porosity. Our objective is to optimize the best composition of green sand in order to minimize the occurrence of defects. Sand specimen of difference parameters (Bentonite, Green Sand, Cold dust and water) were design and prepared to undergo permeability test. The 24 factorial design experiment with four factors at difference composition were runs, and the total of 16 runs experiment were conducted. The developed models based on the experimental design necessary models were obtained. The model with a high coefficient of determination (R2=0.9841) and model for predicted and actual fitted well with the experimental data. Using the Analysis of Design Expert software, we identified that bentonite and water are the main interaction effect in the experiments. The optimal settings for green sand composition are 100g silica sand, 21g bentonite, 6.5 g water and 6g coal dust. This composition gives an effect of permeability number 598.3GP.
- 1 January 2017
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 1842, 030023
Optimization of permeability for quality improvement by using factorial design
Sand castings are used worldwide by the manufacturing process in Metal Casting Industry, whereby the green sand are the commonly used sand mould type in the industry of sand casting. The defects on the surface of casting product is one of the problems in the industry of sand casting. The problems that relates to the defect composition of green sand are such as blowholes, pinholes shrinkage and porosity. Our objective is to optimize the best composition of green sand in order to minimize the occurrence of defects. Sand specimen of difference parameters (Bentonite, Green Sand, Cold dust and water) were design and prepared to undergo permeability test. The 24 factorial design experiment with four factors at difference composition were runs, and the total of 16 runs experiment were conducted. The developed models based on the experimental design necessary models were obtained. The model with a high coefficient of determination (R2=0.9841) and model for predicted and actual fitted well with the experimental data. Using the Analysis of Design Expert software, we identified that bentonite and water are the main interaction effect in the experiments. The optimal settings for green sand composition are 100g silica sand, 21g bentonite, 6.5 g water and 6g coal dust. This composition gives an effect of permeability number 598.3GP.