University of Technology Malaysia
Universiti Teknologi Malaysia Institutional RepositoryNot a member yet
70456 research outputs found
Sort by
Non-parametric induction motor rotor flux estimator based on feed-forward neural network
Get PDFThe conventional induction motor rotor flux observer based on current model and voltage model are sensitive to parameter uncertainties. In this paper, a non-parametric induction motor rotor flux estimator based on feed-forward neural network is proposed. This estimator is operating without motor parameters and therefore it is independent from parameter uncertainties. The model is trained using Levenberg-Marquardt algorithm offline. All the data collection, training and testing process are fully performed in MATLAB/Simulink environment. A forced iteration of 1,000-epochs is imposed in the training process. There are overall 603,968 datasets are used in this modeling process. This four-input two-output neural network model is capable of providing rotor flux estimation for field-oriented control systems with 3.41e-9 mse and elapsed 28 minutes 49 seconds training time consumption. This proposed model is tested with reference speed step response and parameters uncertainties. The result indicates that the proposed estimator improves voltage model and current model rotor flux observers for parameters uncertainties
Innovative research on english teaching model based on artificial intelligence and wireless communication
No full textIt is a network system for teaching English through a wireless communication (WC) premised distance teaching system. This is a process of education that is capable of encouraging students' concerns to acquire knowledge voluntarily. The paper is designed to develop and implement an online intelligent English training system using artificial intelligence (AI) that helps students improve their English learning efficiency in line with knowledge and personality. The system's numerous sensor nodes may create a variety of topologies. The gathered information is transmitted over the global system for mobile communication (GSM) network to the user interface. The operator can manage the remote sensor node via the GSM network. Nevertheless, there are certain derivative aspects such as the absence of verbal judgment, the actual evaluation and signaling system, the interactive educational platform teachers and learners need. The paper is based on the above issues. It contains a whole talk-based system where teachers, students, and English teaching can be revised together - AIWC (ET-AIWC) systems are designed to improve and advance the genetic algorithm based on an encoding technique for dynamic parameter adjustment of the iterative process based on these problems. In combination with an AI expert system, suitable learning techniques were created to enable students to double the learning effect by half the amount of work. An online teaching assistant system was designed to monitor, regulate, and engage with students throughout the learning process and a modified scoring system that provides real-time evaluation of student speakers to improve students' oral competence in English better and more efficiently, achieving 95.2%
Integrated disaster risk index model for the Malaysian local assessment
Get PDFMalaysia is considered a high-risk country on a global level due to the increasing number of natural disasters in recent years. Considering the increasing impact of natural disasters, implementing a local disaster risk assessment would improve the understanding and identification of potential disaster risks that could affect social system, the economy, and numerous institutions. Understanding and evaluating integrated disaster risk must consider multi-hazard and multidimensional vulnerability at the local level, particularly in developing nations like Malaysia. This primary gap has never been recorded in earlier research, and the purpose of this work is to close the gap. Therefore, this study developed an integrated disaster risk assessment index (IDRI) model to measure disaster risk within local administrative boundaries in Malaysia. The emphasis of this thesis is to assist decision makers in identifying high-risk areas that are exposed to natural disasters by considering local vulnerability factors. The proposed index model could enhance government disaster risk reduction measures by implementing an (IDRI) model and guiding decision maker on how to properly evaluate and analyse risk for mitigation, preparedness, and planning. The index was developed by expanding on the multi-hazard spatial overlapping and Methods for the Improvement of Vulnerability Assessment in Europe (MOVE) theoretical framework. In this study, the multi-hazard spatial overlapping combined two common hazards in Malaysia which are floods and landslides. This study used a quantitatively structured questionnaire survey to choose relevant IDRI model indicators based on expert opinion. The multidimensional vulnerability index (MDVI) model was developed using a combination of expert opinion and Principal Component Analysis (PCA). The IDRI map was created using Catastrophe Theory and Geographical Information Analysis (GIS) analysis. Based on the expert interviews, the study revealed that multidimensional vulnerability encompasses six dimensions, which in turn comprise 16 subdimensions and 54 indicators. This approach was applied in three urban districts of Selangor, Malaysia: Sepang, Kuala Langat, and Hulu Langat, which are located within the Langat River catchment and consist of 17 subdistricts. The spatial vulnerability assessment was conducted to classify vulnerability and risk in the study areas. The map produced five vulnerability categories (very low, low, medium, high and very high). The findings indicate that of the total vulnerability areas in the study, 7% were in the very high class, 12.6% were in the high class, 25.7% were in the medium class, 34.7% were in the low class and 20% were in the very low class. Overall, 32.9% of the total study area was found to be at risk, with 4.3% in the very high-risk area. Based on the Receiving Operating Characteristics (ROC) validation, the integrated disaster risk index model accuracy was 0.888, suggesting that the proposed model is good for evaluating risk. In comparison with the latest flood events in 2021, the IDRI components were highly correlated with disaster impact. In conclusion, the contribution of this study provides a novel perspective on disaster risk assessment by addressing several types of hazards and multidimensional vulnerability, as compared to the previous study focusing on a single hazard and a physical vulnerability factor. The model produced in this study will help governments at local levels to develop better strategies for disaster risk reduction practices and policies
Hybrid fractional modified skyhook controller optimized by particle swarm optimization for railway secondary lateral suspension
No full textThe suspension system is one of the mechanical systems in railway vehicles that offers greater ride quality to enhance ride comfort for passengers. However, the existing suspension system in a railway vehicle has a limitation in absorbing vibratory motion due to the lateral track irregularity. The unwanted vibratory motion reduces the ride performance of the railway vehicle system, thus leading to discomfort for railway vehicle passengers when excessive track interference occurs. Following this, it is essential to minimize unwanted vibratory motion so that the level of passenger comfort can be improved. The overall goal of the study is to enhance the railway vehicle ride performance by implementing a semi-active secondary suspension system via magneto-rheological (MR) fluid damper. Initially, a seventeen degrees of freedom (DOF) railway vehicle simulation model was developed which included the motions of lateral body acceleration (yc), yaw angle (Psi c, Psi b1, Psi b2) and roll angle of vehicle body and two bogies, (Theta c, Theta b1, Theta b2) as well as lateral acceleration (yw1, yw2, yw3, yw4) and roll angle (Theta w1, Theta w2, Theta w3, Theta w4) of four wheelsets. The effects of primary and secondary suspension elements were analysed using MATLAB/Simulink software and the result identified that the lateral damper for secondary suspension improved the railway vehicle body’s comfort level more than others by around 69.6% based on yc of the vehicle body. The study was then continued with the development of a small-scale railway vehicle test rig. The parameters for the test rig were obtained via dimensionless analysis study known as Pascal Modified method. Next, the experimental setup, calibration, modelling, and validation works on MR damper had been performed, and the force tracking control performance was assessed by using step, sinewave and saw-tooth inputs. After the small-scale railway vehicle test rig and MR damper models were validated, the performance of the proposed control strategy, specifically Body-based Modified Skyhook (BD-MS), Bogie-based Modified Skyhook (BG-MS), and Hybrid Body-based Bogie-based Modified Skyhook (HBB-MS) controllers optimized by Particle Swarm Optimization (PSO) were also examined against the passive system. The simulation results showed that the performances of BD-MS, BG-MS and HBB-MS controllers respectively improved until 13.9%, 61.6%, 85.1% reduction of yc, 17.1%, 26.4%, 69.9% reduction of Theta c, and 18.5%, 29.6%, 58% for reduction of Psi c. Lastly, the suspension system was further controlled by using a Hybrid Body-based Bogie-Based Fractional Modified Skyhook (HBB-FMS) controller to study the potential benefit of fractional gain in improving the railway vehicle body responses. The findings from the simulation work showed that the HBB-FMS controller provides better performance of about 43.5% in yc, 31% in Theta c, and 44.9% in Psi c against the HBB-MS controller. Therefore, it can be concluded that the semi-active suspension system with HBB-FMS controller was found effective in enhancing the ride performance of the railway vehicle by mitigating the unwanted vibratory motion on the railway vehicle body due to lateral track irregularities
Machining-induced surface integrity in brass alloys
Get PDFThis study presents machining process and resulting surface integrity properties of brass alloys including leaded (CW617N), low-leaded (CW511L) and lead-free (CW724R). Experimental data on cutting forces and cutting temperatures are presented to assess machining of these alloys. Surface quality, subsurface microhardness and microstructures of machined brass alloys are considered to assess surface integrity properties. Higher subsurface deformation was observed in low-leaded and lead-free brass materials compared to leaded brass materials. This present study reveals that machining process results in deformation twinning on the surface and subsurface of specimens. The role of machining parameters on performance measures and surface integrity aspects is also presented in this work. This work illustrates that machining parameters have a notable effect on measured machinability outputs. It should be noted that lead content has a strong influence on surface integrity aspects including microhardness and twinning of machined brass alloys
Performance of steel bolt connected industrialized building system subjected to hydrodynamic force with debris
Get PDFSeveral major floods have hit Malaysia within the last decades. In order to dampen the effects of the floods on communities’ different types of flood mitigation projects, mostly structural mitigation measures were carried out. While some of the measures have been successful in reducing the impact of the flooding, others were not that successful, leading to the collapse of building structures. Therefore, there is a need to concentrate on a recovery framework specially tailored towards building permanent settlements using a robust and cost-effective building system. An industrialized building system (IBS) has been proposed as one of the best solutions for rapidly building permanent settlements in flood-prone zones. However, the existing IBS is not designed to sustain the horizontal impact due to the debris carried by the flood. Thus, a new permanent settlement built in the aftermath of floods using the IBS will eventually be destroyed by the extreme impact of horizontal load in the next flood cycle. Previous studies on the behaviour and performance of the IBS subjected to horizontal impact are found to be lacking. Furthermore, the joint of an IBS is likely to be the weakest point and vulnerable to failure when subjected to the horizontal load. There is, therefore, the need to develop an improved IBS that is able to withstand the horizontal impact of the flood. Thus, this study aimed to investigate the performance and behaviour of steel bolt-connected IBS structures subjected to the sudden impact of hydrodynamic force with debris as well as the horizontal impact of the pendulum. Both dam-break tests and pendulum impact tests were simulated using Autodesk computational fluid dynamic (CFD) simulation and Autodesk simulation mechanical (nonlinear finite element analysis (NLFEA)) for optimizing the laboratory experimental work, respectively. A scale of 1:5 models (one-dimension (1D), two-dimensional (2D), and three-dimensional (3D)) were designed using Eurocode 2, developed, and constructed according to the Buckingham Pi Theorem and Similitude Theory and later tested in the laboratory. The three models which include the single column-footing, 2D IBS frame and 3D IBS platform were properly tested for the dam-break test with and without debris using 1 m, 2 m, and 3 m reservoir water height. These three models were also tested for the sudden impact of the pendulum. The result shows the percentage difference between experimental results and the CFD numerical simulation for the stress of the 3D platform is 12.87%, while the displacement difference is recorded as 0.09 cm. However, the bolt-connected IBS models resisted the highest hydrodynamic forces as compared to the estimated ones from FEMA P-646 and FEMA P-55. Hence, this assured the reliability of the bolt-connected IBS structure for real practice. Furthermore, results of the pendulum impact tests were verified with the published literatures and they showed a very good agreement. The results show that bolt-connection is more effective and contributes additional robustness to the IBS method. Moreover, bolt connection has proven to be effective in restricting damages from spreading to other structural components. The findings of this study are crucial to improving the current IBS method of construction. The study has also successfully enhanced understanding on the behaviour of debris impact on building structures and contributed new knowledge on debris impact in relation to the design code of practice
A BIM-based method for Building Energy Intensity (BEI) evaluation
No full textEnergy Usage Index (EUI) is used worldwide as a metric to evaluate and compare energy consumption of sustainable buildings. In Malaysia, EUI is referred as Building Energy Intensity (BEI) and it is adopted by different energy standards and green building rating systems. The preliminary evaluation of BEI in the Malaysian building sector is typically performed using an Excel-based tool known as Building Energy Intensity Tool (BEIT). This method has several limitations including but not limited to; (1) it supports only simplified building envelop configurations and (2) data input is manual and based on many assumptions. Due to the potential of Building Information Modelling (BIM), the opportunity for this method to adopt and benefit from BIM arises. Therefore, this research proposes a BIM-based approach for BEI assessment by integrating BEIT, BIM data and visual scripting to automatically extract the required data for BEI assessment and therefore overcome the current limitations. The applicability of the proposed system is validated in a BIM model of an office building. The proposed system provides a valuable decision support system for designers to analyze and compare the BEI of different design options
Distributed hydrological model using machine learning algorithm for assessing climate change impact
Get PDFRapid population growth, economic development, land-use modifications, and climate change are the major driving forces of growing hydrological disasters like floods and water stress. Reliable flood modelling is challenging due to the spatio-temporal changes in precipitation intensity, duration and frequency, heterogeneity in temperature rise and land-use changes. Reliable high-resolution precipitation data and distributed hydrological model can solve the problem. This study aims to develop a distributed hydrological model using Machine Learning (ML) algorithms to simulate streamflow extremes from satellite-based high-resolution climate data. An integrated statistical index coupled with a classification optimisation algorithm was used to select coupled model intercomparison project (CMIP6) global climate model (GCMs). Several bias-correction methods were evaluated to identify the best method for downscaling GCM simulations. The study also evaluated the performance of different Satellite-Based Products (SBPs) in replicating observed rainfall to select the best product. A novel two-stage bias correction method were used to correct the bias of the selected SBP. Besides, four widely used bias correction methods were compared to select the best method for downscaling GCM simulations at SBP grid locations. A novel ML-based distributed hydrological model was developed for modelling runoff from the corrected satellite rainfall data. Finally, the model was used to project future changes in runoff, and streamflow extremes from the downscaled GCM projected climate. The Johor River Basin (JRB) located at the south of Peninsular Malaysia was considered as the case study area. The results showed that three GCMs, namely EC-Earth, EC-Earth-Veg and MRI-ESM-2, were the best in replicating the precipitation climatology in mainland Southeast Asia. IMERG was the best among five SBPs with an R2 of 0.56 compared to SM2RAIN-ASCAT (0.15), GSMap (0.18), PERSIANN-CDR (0.14), PERSIANN-CSS (0.10) and CHIRPS (0.13). The two-step bias correction approach improved the performance of IMERG, which reduced the mean bias up to 140 % compared to the other conventional bias correction methods. The method also successfully simulates the historical high rainfall events that caused floods in Peninsular Malaysia. The distributed hydrological model developed using ML showed NSE values of 0.96 and 0.78 and RMSE of 4.01 and 5.64 during calibration and validation. The simulated flow analysis using the model showed that the river discharge would increase in the near future (2020 - 2059) and the far future (2060 - 2099) for different SSPs. The largest change in river discharge would be for SSP-585. The extreme rainfall indices, such as R95TOT, R99TOT, Rx1day, Rx5day and RI, were projected to increase from 5% for SSP-119 to 37% for SSP-585 in the future compared to the base period. The ML based distributed hydrological model developed using the novel two-step bias corrected SBP showed sufficient capability to simulate runoff from satellite rainfall. Application of the ML-based distributed model in JRB indicated that climate change and socio-economic development would cause an increase in the frequency streamflow extremes, causing larger flood events. The modelling framework developed in this study can be used for near-real time monitoring of flood through bias correction near-real time satellite rainfall
Phoneme duration scheme for tajweed medd rules recognition in qur’an recitation
No full textThe speech recognition techniques can be used to implement a Computer-Aided Pronunciation Learning (CAPL) System, however, the Computer-Aided Holy Qur’an Learning still needs more research because of the great difference between Qur’an recitation and normal speech. The major difference is due to the Tajweed rules that control the Qur’an recitation, especially those rules that depend on the phoneme duration like the Medd rules. Current speech recognition applications recognize the phonemes regardless of their duration and are not sufficient to recognize the Quranic recitation. There are two stages to get acquainted with the Medd rules: classification and estimation of duration. The previous studies classified phonemes in Qur’anic recitation, such as the classification of Arabic speech with no concern the Tajweed rules' impact, especially the classification of vowels governed by Medd rules. Regarding phoneme duration estimation, previous studies suggested a specific range for each long vowel calculated in milliseconds, ignoring the difference in recitation speeds from one reciter to another. Neglecting Medd rules in classification and duration estimation stages leads to a lack of proper recognition of Medd in the Qur’anic recitation. In this thesis, a new phoneme duration scheme is proposed to enhance the Medd duration recognition based on speech recognition techniques. A standard Qur’an recitation corpus has been collected to be used in training and testing of Medd duration. 21 Qur’an verses were chosen to cover all types of Medd, 100 famous Qur’an reciters' recitations have been collected from Web and 30 reciters have been asked to record their recitations four times for each verse at different speeds. This corpus was used to develop a Hidden Markov Model (HMM) model to recognize the Qur’anic recitation. A rule-based phoneme duration algorithm for Medd classification (RPDMCA) classifies all phonemes based on their duration and adds the required duration to each phoneme in triphone tree, thus determining the required duration for each phoneme according to Tajweed rules. In addition, an Artificial Neural Network-based Medd duration model was proposed to estimate the actual duration of phonemes. Moreover, a phoneme alignment algorithm based on the Qur'an acoustic model was developed, and the recitation rate was calculated to be used as input of the Artificial Neural Network (ANN) model. The results obtained demonstrated the high efficiency of the proposed scheme to recognize Medd types correctly. The accuracy of the phoneme classification algorithm was high ranging from 98% to 100% depending on the type of Medd. The proposed algorithm for phoneme alignment based on the Qur’an phoneme model gives a significant improvement in phoneme segmentation compared to the existing HMM Toolkit (HTK) forced alignment algorithm, where 30% of phonemes have time-error less than 30 milliseconds with manual segmentation reference. Likewise, for the Medd estimation model, it achieved results that significantly outperform the previous techniques, as its accuracy reached 86% when using manual segmentation and 70% when using automatic segmentation
Water quality modeling using artificial neural networks incorporating land use and sewage treatment plant factors
No full textSkudai River has undergone a general decline in water quality in recent years due to agricultural practices, urbanisation, industrial and other human activities in the river catchment. It is classified as “slightly contaminated” by the Department of Environment (DOE), and as such, immediate actions are needed to prevent further deterioration and improve the water quality. Majority of existing research on water quality modelling focuses on water quality data and the impact of land use on water quality, while those on the effects of sewage treatment plants (STP) discharge on river water quality have also been conducted to a certain extent. However, limited research on water quality prediction is based on land use input, existing STP, and rainfall. This is due to the complicated relationships between these three factors and water quality parameters. River systems are highly complex, hierarchical and patchy. Accurate predictions of the time series concerning the changing water quality could support early warnings on water pollution and help with management decisions. Currently, artificial intelligence (AI) technologies can simulate this behaviour and complement the inherent deficiencies. Among the latest research in integrating AI into water quality modelling, artificial neural networks (ANNs) are the most popular techniques used. This study aimed to identify and determine key water quality parameters using principal component analysis (PCA) based on land use and pollution sources, to correlate and predict water quality index (WQI) based on in-situ parameters using ANNs, and to determine and predict the relationships between land use patterns, precipitation, STP, and WQI, also using ANNs. ANNs were employed in a total of 839 physical and chemical pollution data sets from the Skudai River from 2001 to 2019 as training (70%), test (15%) and validation data (15%) for the analysis in this study. River water sampling was also carried out to evaluate the modelling results (36 data sets). ArcMap 10.4 was used to prepare the map for the changes occurring in land use, observed from 2000 to 2019 The PCAs results indicated that the parameters causing water quality variations were mainly related to physical parameters (natural) and organic pollutants (anthropogenic). The study also showed that the cascade-forward net was the optimal ANNs-water quality index-1 (ANNWQI-1) model for WQI prediction with seven parameters: DO, pH, conductivity, temperature, TDS, salinity, and turbidity with an RSME of 7.15, and a coefficient of correlation (R) of 0.92. The analysis with Spearman correlation could explain that in-situ parameters correlated with the parameters used to calculate WQI values. The best ANNWQI-2 model was a feed-forward net with land use, STP service coverage, and precipitatin data as input data, resulting in RMSE of 6.98 and R of 0.80. An input data analysis with Spearman correlation could explain that land use data, STP and rainfall data correlated with the parameters used to calculate WQI values. The integrated model of ANNWQI-3 had RMSE and R of 6.01 and 0.92, respectively. ANNWQI-1 demonstrated that accurate WQI predictions could be made, with only seven in-situ water quality parameters, while ANNWQI-3 required more comprehensive input data to get almost the same R. More importantly, the input data was in-situ water quality parameters, and no laboratory analysis was needed. The study determined the effective input parameters using PCA for successful ANN modelling while illustrating the usefulness of ANNs for WQI prediction. Ultimately, the results will give decision-makers valuable information to identify the causes of water pollution and the critical source areas that are useful for protecting the environment in terms of sustainable water resources