University of Technology Malaysia
Universiti Teknologi Malaysia Institutional RepositoryNot a member yet
70456 research outputs found
Sort by
Photovoltaic system DC series arc fault: A case study
Get PDFPhotovoltaic (PV) systems are becoming increasingly popular, however, arc faults on the direct current (DC) side are becoming more widespread as a result of the effects of aging as well as the trend toward higher DC voltage levels, posing severe risk to human safety and system stability. The parallel arc faults present higher level of current as compared with the series arc faults, making it more difficult to spot the series arc. In this paper and For the aim of condition monitoring, the features of a DC series arc fault are Analyzed by analysing the arc features, performing model's simulation in PSCAD, and carrying out experimental studies. Various arc models are simulated and investigated, for low current arcs, the heuristic model is used where a set of parameters established. Moreover, the heuristic model's simulated arc has been shown to be compatible with the experimental data. The features of arc noise in the electrode separation region and steady-arcing states with varied gap widths are investigated. It has been discovered that after an arc fault occurs, arc noise increases, notably in the frequency range below 50 kHz, where this property is useful for detecting DC series arc faults. Besides that, variations in air gap width are more sensitive to frequencies under 5 kHz
IoT based real-time monitoring system of rainfall and water level for flood prediction using LSTM network
Get PDFThis project outlines the design of a flood monitoring system to obtain accurate data on river overflows. Additionally, it provides the machine learning technique, to predict the arrival of floods, by considering the rainfall data and water level from previously available data to predict the rainfall and water level for the next hours. The problem is the shortage of flood information in areas that are constantly flooded leads to malfunction in analysing the flood reasons. In addition, the fuzzy and unpredicted situation of the flood. Moreover, there is no flood data analysis so action can be taken based. Finally, data is not visualized in a Dashboard, so they can have a deeper look at the situation. The object of this study is to design an IoT flood monitoring system based on two water level sensors and a rain gauge sensor. In addition, to forecast the flood based on Long Short-Term Memory (LSTM) networks for historical data and the data collected from the monitoring system. The monitoring system utilizes a submersible water level sensor that measures the water level. Additionally, the tipping bucket rainfall sensor measures the rain gauge and tests the rainfall in the natural environment. The system is based on IoT to provide real-time data. The recorded data is transmitted to the cloud via a GSM network and displayed on an online platform. The flood forecasting model used Long Short-Term Memory (LSTM) networks to predict future floods. The aim of this case study is to contribute to the reduction of casualties and flood damage in streams, as well as to the development of more accurate flood forecasting in typical urban flood risk locations. The result was experimented with using historical data since the current data is insufficient yet to make an accurate prediction. The main findings of the research are the predicted values of streamflow and rainfall for historical data, also water level and rain gauge for new data. The forecasting method that applied LSTM showed high accuracy of the result reaching more than 90% with evaluation errors for historical data MAE, RMSE and MSE are 0.93, 1.7 and 3.025 respectively. Also, 0.0055, 0.3325 and 0.1175 for new data respectively. The developed monitoring system and flood forecasting can be used efficiently as a non-structural solution to alleviate the damage caused by urban floods
Automated visual detection of external welding defect using embedded machine learning
Get PDFThis project is designed to perform a quality check on a welded material's surface. Welding is the most useful process for joining materials in the manufacturing, automotive, and construction industries. As a result, in order to meet a client requirements, all welding works must be inspected, with the most basic method is nondestructive visual inspection testing. Surface inspection can be performed using nondestructive methods such as dye-penetration testing and magnetic particle inspection. However, those methods are expensive, take a long time to complete inspections, and require a complex procedure to operate. This project proposed an automated visual inspection system that relies on embedded machine learning. This system is made up of a camera, a microcontroller, and web server. The camera-based system will detect any defects on the welded material, which will then be processed by the microcontroller before being displayed on the web server through Wi-Fi connection. As a result, this system was split into two parts: software and hardware. The Arduino IDE was used to programme the system, and Edge Impulse was used to develop the embedding machine learning model. This system's hardware consists only ESP32- CAM module. As a result, it is possible to create an automated system that is user friendly and has simple operation procedure. Furthermore, a low-cost system with a short inspection time have been developed. A sharp and clear image with single type of defect appear on the workpiece help to provide best performance of defect classification. However, most likely same image captured, e.g. good welding and overlap defect, decrease the effectiveness of detection. The detection accuracy of this system can reach up to 95% with more training data provided, as for this project each defects detection accuracy are falls between 75 - 94 percent. In conclusion, the use of embedded machine learning in non-destructive testing is successful for the visual inspection method
Comparison of 1D VS 2D convolutional neural networks for bird sound detection
Get PDFAutomatic acoustic detection system is useful to assist the bird naturalists on bird species monitoring and overall ecosystem health. Many birds are most easily discovered by their sounds, therefore passive acoustic monitoring is most appropriate. However, acoustic monitoring encounters practical limitations such as manual configuration requirement, highly dependent on sounds libraries, less accurate and less robust. In recent years, various machines learning techniques are proposed and detailed performance evaluation are conducted to determine how feasible the automatic acoustic detection system can be achieved. In this paper, we propose a 1D convolutional neural network (CNN) architecture for bird sound detection and compare it with Bulbul 2D CNN architecture which is the winner of Bird Audio Detection (BAD) challenge. The proposed 1D CNNs managed to learn a representation directly from the raw audio recordings. The preprocessing phase divides the audio signal into overlapping frames using a sliding window, thus it can handle audio streams of any duration. The sizes of each frame are compatible to the input layer of the 1D CNNs. On the other hand, the preprocessing phase of Bulbul 2D CNN architecture adopted two type of feature extraction methods, STFT spectrogram and Mel-scaled spectrogram to capture the amplitude of a signal as it changes over time and at various frequencies. The performance o f the proposed 1D CNN model in detecting the bird sound was assessed on the warblrb10k dataset and the experimental results have shown that it achieves an accuracy lower than the Bulbul 2D CNN model. It was proven in a few previous 1D CNN state-of-the-art approaches outperform most of the other approaches that uses handcrafted features or 2D representations as input. Due to time constraint, several significant steps of promising high accuracy on 1D CNN model could not be done, such as aggregating the prediction result for all the audio frames belonging to the same audio recording with a majority rule or sum rule to determine the final prediction for presence of bird for the whole individual audio recording, thus lead to achieving low accuracy of 1D CNN model in this paper
The effect of different specifications of passive spaces on residents’ satisfaction in adjoining spaces within a hot dry climate
Get PDFPassive spaces are a passive design strategy that aims to reduce energy consumption and increase user satisfaction in buildings. One example of passive space is the air shaft. The air shaft is a vertical void within the building from the ground level to the roof level, and it provides the building with natural ventilation and daylight, especially in deep-plan buildings. However, the function of the air shaft is questioned due to its impacts on residents’ needs. This study assesses the effects of air shaft specifications on residents’ satisfaction with the indoor environment quality of air shafts and adjoining spaces. Survey questionnaires were distributed to residents of apartment buildings. The results proved that air shafts have a significant negative impact on residents’ satisfaction. The findings of cross-tabulation analysis illustrate a significant relationship between the air shafts’ specifications and the residents’ answers. The analysis also showed that the air shafts that are closed from the bottom and include A\C outdoor units have a more negative impact on the thermal environment and air quality. Regarding the air shaft areas, the small areas have a high negative response regarding bad smell, the view, visual and acoustic privacy, and thermal environment. From the indoor environment quality perspective, this study emphasizes the need to consider the impact of air shaft design on a building’s performance and residents’ satisfaction. The results of this study are expected to contribute to the development of future passive spaces design
Water footprint assessment of paddy cultivation: Quantifying direct and indirect water consumption
Get PDFWater footprint quantification across product’s life cycle has become increasingly prominent. Thus, this study was conducted focusing on developing a quantification approach for water consumption of paddy cultivation at each growth phase using ISO 14046 as a guideline. A case study applying the proposed methodological framework at Muda Rice Granary, Malaysia from the year 2012 to 2015 is presented in this paper. The total irrigation water of paddy planted on Muda Rice Granary ranges from 1800-2600 litres/kg gross paddy. The study was conducted on three phases of paddy growth cycle, which were vegetative phase, reproductive phase and mature phase. Vegetative phase was identified as the hotspot during paddy cultivation as it has the highest water consumption. The demand for rice in the year 2030 is expected to increase to 533 million tonnes to meet the public demand globally. Therefore, it is imperative to identify ways to increase paddy yield while reducing water irrigation to accommodate such a challenge. The outcomes from this research can provide guidelines to the agricultural development authorities, rice farm owners, government as well as farmers to develop a sustainable paddy cultivation at all levels of rice farming
Construction 4.0 readiness and challenges for construction skills training institutions in Malaysia
No full textRapid changes in technology application due to increment of market requirements have been a pushing factor to radical industry adoption and adaptation upon new technologies. The integration of emerging technologies associated with Industry 4.0 with construction delivery processes had founded the Construction 4.0 term which been emerging in the recent research corpus. The adoption of Construction 4.0, major changes in the construction process delivery stages, project structures and organization and ultimately integrate the known highly fragmented construction industry atmosphere including its work force. These changes will require another level of skill set for the construction personnel who involve in the construction project life cycle and its value chain. The current level of awareness on Construction 4.0, key challenges faced and technologies adoption readiness amongst construction skill training institutes in Malaysia upon changes associated with Construction 4.0 technologies need to be assessed and well understood. This will be the basis for construction lead body in Malaysia to mitigate the way forward for the construction skills training institutions of the nation. As there are still limited research and study conducted in understanding Construction 4.0 adoption clarity by the construction skills training institutions in Malaysia, this research will contribute to the enrichment of academic studies documentation related to the Construction 4.0 in specific and the Industry 4.0 generally for Malaysia context
Evaluation of monotonic tensile properties of Napier single fibre
No full textNatural fibres are derived from plants and animals, and they are the most efficient replacement for synthetic fibre. However, these fibres differ widely in physicochemical characteristics, hollow of lumen, uniformity, and degree of crystallinity, resulting in inconsistent mechanical property values. In this study, the tensile properties of a single Napier fibre were investigated according to ASTMD 3822-07. The test was performed using universal testing machines at a crosshead displacement rate of 1 mm/min. It revealed that the average tensile strength and modulus of a single Napier fibre were 23.47 MPa and 0.18 GPa, respectively. The Weibull modulus was determined to be 1.4261 with a Weibull parameter estimation error of 48%
Field measurement test to estimate level of accuracy between actual and simulated air-temperature: Case study of mosque buildings
No full textOne of the main drawbacks of current simulation tools is inaccuracy and each simulation software has a set of different calculation algorithms, which is also prone to limitations and errors. Although the results can be achieved from running the simulation analysis, these results may not reflect the actual performance of a building in in real world scenarios. Additionally, when using simulation software for decision-making tools or to build a numerical model, validation tests are required to ensure the quality of the obtained results. This paper conducted a field measurement test to record the interior air temperature for specific period of time and compare it with EnergyPlus™ simulation results at the same time. A digital recorder of Temperature Humidity Tester Thermometer Clock Hygrometer KT-908 was applied and the results showed that the difference between the measured and simulated air temperatures did not exceed 0.55°C. As there was no significant difference between the measured and simulated air-temperatures, which gives credibility and attests to the quality of the EnergyPlus™ simulation results
Environmental impact hotspots of an integrated wet anaerobic digestion through life cycle assessment for food waste management
Get PDFWet anaerobic digestion (AD) is one of the most widely implemented systems that valorize food waste (FW) for biogas production. Despite the undeniable AD benefits, the environmental impact of AD could differ depending on the biogas systems used. This article examines the hotspots on environmental impact of FW management such as global warming and ozone depletion based on integrated wet AD by utilizing a life cycle assessment approach. The integrated wet AD scenario in this study is a technology that combines wet AD, aerobic windrow composting and a landfill. The scenario modelling was accomplished by applying GaBi v6.0 software with 1 ton of pre-treated FW as a functional unit, and the analysis was based on the ReCiPe (H) v1.07 characterization technique. At the midpoint level, it was observed that the integrated wet AD presented the most significant environmental impact in terms of ionizing radiation (1.4×100 kg U235-eq), followed by water depletion (1.11×103 m3-eq), global warming (6.27×102 kg CO2-eq), fossil depletion (2.18×102 kg oil-eq) and human toxicity (2.89×101 kg 1,4-DB-eq). The disadvantages of the integrated wet AD in global warming were associated with CO2, CH4, and N2O emissions from the energy used for process treatment and fossil fuels during transportation, primarily in landfill activities, followed by wet AD and aerobic windrow composting stages. Regarding single-score indicators, integrated wet AD presented the most resource damaging impact (3.50×103 Pt), mainly due to fossil depletion. This study emphasizes the necessity of reducing the life cycle consequences related to CH4, N2O and NH3 emissions throughout the decomposition process in integrated wet AD, particularly landfill activities