Ethiopian International Journal of Engineering and Technology

Modelling for Multiport Converter-based Hybrid Power supply for Renewable Energy Source Application

Yalisho Girma, Dr.Ing.Getachew Biru, Chandar Reddy — Sat, 30 Dec 2023 00:00:00 +0300

This research work deals with the design, modeling and technical evaluation of multiport modular converter based hybrid Power supply using solar PV for small village. The village’s maximum power demand is 50kvA, consisting of demands of twenty (20) households. The first converter in the proposed multiport system is a high frequency isolated DC-DC converter fed with HVDC link yielding an output voltage of 700vDC. The isolated DC-DC converter uses a medium frequency transformer with primary and secondary side converters in input-series output-parallel (ISOP) configuration. Also, the output of first converter is connected to a solar PV and battery system through a buck-boost converter. The second converter in the system is solar PV fed three phase modular inverter designed to have output AC line voltage of 0.415 kV. The three phase inverter is based on modular multilevel converter (MMC) with interleaved modulation techniques. A silicon carbide power MOSFETs, with model numbers CPM3-10000-0270(CREE) and SD11703 (Solitron) are used as a building blocks for isolated DC-DC converter. On the other hand, SiC -MOSFET with part number SCT3017AL (RHOM) is used as basic building block for modular inverter. A solar PV module with open circuit voltage of 85V and maximum power rating of 415W is used to feed the inverter. Different scenarios such as changes in load and changes in solar irradiance are used for critically evaluating the performances of the system under question. The output voltage THD, current distortions, changes in the converter output voltage, current magnitude and converter efficiency are used for performance evaluation of the system under consideration. Simulink/ PLECS (Piecewise Linear Electrical Circuit Simulation) combo simulation platform is used to model and simulate the system in question. Simulation results showed that the proposed multiport converter system can be a viable alternative to low frequency distribution transformer.

Keywords: Multiport converter, MMC, DC-DC converter, Hybrid power Supply, Solar PV.

Cattle Pinkeye Disease Classification using Machine Learning

Serkalem Mekonnen, Mohammed Abebe — Sat, 30 Dec 2023 00:00:00 +0300

Pinkeye (infectious bovine keratoconjunctivitis, or IBK) is a bacterial infection of the cattle eye that causes inflammation and, in severe cases, temporary or permanent blindness. It is a painful, debilitating condition that can severely affect animal productivity. Due to lower weight gain, lower milk production, and higher medical costs, the cattle industry could experience large losses. Previous studies tried to classify livestock diseases using machine learning, but there has been a lack of studies conducted on pinkeye disease classification. The proposed study aims to design a classification model to classify whether the infected cattle have pinkeye or not at an early stage by analyzing a set of attributes. The study collected data from the Wolaita Sodo Kenido Koyisha Wereda Livestock and Fishery Office. The significance of this study is to prevent the expansion of disease among the cattle with an early detection for taking precautionary measures. The researchers used the percentage splits 80/20, 70/30, 60/40, and 90/10 to build classification models. Based on the results of the experiments, the researcher chose the 70/30 split due to the better performance obtained. The study trained four different models, including Random Forest, AdaBoost, Artificial Neural Network, and Extreme Gradient Boost algorithms. These models are selected based on an exhaustive study conducted. To assess the algorithm's performance, confusion matrix, accuracy, precision, recall, and f1-score have all been utilized. By a 99.15% accuracy, the Artificial Neural Network outperforms the other algorithms by all the metrics except recall.

Keywords: Machine learning, Infectious bovine keratoconjunctivitis, IBK, Cattle pinkeye, Pinkeye disease classification

Biomimetic Architecture: An Innovative Approach to Attain Sustain-ability in Built Environment

Zeeshan Haider, Mohammad Salman, Alemea Girma — Sat, 30 Dec 2023 00:00:00 +0300

Architecture has always inserted itself into and interacted with the nature Environment. Biomimetics is an applied science that infers motivation for answer for human issues through the investigation of common plan from nature. Biomimetic is used in design for many years. It is the fastest Growing Research in the Area of Architecture. This is because of the innovative and problem-solving approach to Achieve Sustainability in Design. However, Application of Biomimetic Design to achieve Sustainability requires a proper understanding of relation between Biology and environmental science. The Review of Achievement by the use of biomimetic Architecture could make easier for understanding relation between biomimetic ecosystem and the built environment and therefore contribute to environmental sustainability. This Paper elaborates the Different Approach to Attain Sustainability through different literature Study and Case Study. These Varied Approaches have different outcomes in terms of sustainability.

Keywords: Sustainable Architecture, Biomimetic Architecture, Built Environment, Ecosystem.

Pulmonary Disease Identification and Classification Using Deep Learning Approach

Minalu Chalie, Zewdie Mossie — Sat, 30 Dec 2023 00:00:00 +0300

Deep Learning (DL) based model has shown great performance in the medical field for the detection of diseases. We examine the difficulty of classifying pulmonary disease (PD) classification in X-ray images in order to address medical-related issues. PD is a disease that prevents the lungs from functioning properly. Various researches have been done to automate the detection of pulmonary diseases. However, most studies concentrate only on identifying the presence or absence of the disease. As well, almost all studies ignore the automatic classification of tuberculosis in the lungs with other diseases. This research work focuses on the major occurrence of respiratory diseases, which are pneumonia, pulmonary tuberculosis, and pleural effusion. We proposed a novel framework for the detection and classification of PD from Chest X-Ray (CXR) images. Noise reduction, image quality enhancement, data augmentation, segmentation, feature extraction, and classification are all the part of the proposed framework. During image preparation, we used a Gaussian filter to eliminate noise from X-ray images and an advanced histogram equalization technique to improve image quality. The Region of Interest (ROI) has been extracted through the segmentation technique. We proposed Otsu's threshold segmentation approach to extract the ROI of the lung. In the feature extraction technique, we utilized the Gabor filter to apply the raw image to extract texture features. For classification, we employed a Deep Convolutional Neural Network (DCNN). To classify into a given class (normal, pneumonia, pulmonary tuberculosis, and pleural effusion), a four-way SoftMax classification is utilized. We developed four DCNN models (VGG16, VGG19, ResNet50V2, and DenseNet201) and compared their performance. In our models, DenseNet201 model had a training accuracy of 97.80% and a testing accuracy of 95.73% in PD detection and classification. When compared to the state-of-the-art models, the DenseNet201 model has great accuracy and is better at detecting and classifying diseases.

Keywords: Feature Learning, Gabor filter, Pulmonary Disease, Segmentation, X-ray.

Numerical Investigation of Reinforced Concrete Beam Contain-ing Iron Ore Tailings as Partial Replacement of Sand

Mahmud Abubakar — Sat, 30 Dec 2023 00:00:00 +0300

The production of industrial and agricultural residual byproducts can generate significant environmental impact. In response, researchers have begun incorporating supplementary materials made from agro-industrial wastes to create more sustainable concrete. However, testing the performance of these waste-based concrete mixtures can be time-consuming and expensive. To address this issue, this study utilized three-dimensional non-linear Finite Element simulation using the ABAQUS/CAE software to predict the behaviour of a reinforced concrete beam that incorporated 20% IOT as partial sand replacement. The simulation successfully predicted the damage behaviour of the 20% IOT concrete, indicating the potential of this modelling approach to accurately predict the performance of waste-based concrete mixtures in various designs.

Keywords: ABAQUS; Iron Ore Tailings; Numerical Analysis; Reinforced Concrete Beam.

Designing an Exploratory Indigenous Knowledge Management Framework for Soil Conservation Mechanism in the Konso Community

Amin Tuni, Addisu Mulugeta, Eyasu Tafere — Sat, 30 Dec 2023 00:00:00 +0300

Today, Indigenous knowledge (IK) has a lot of contribution all over the world which it is the traditional knowledge that didn’t codified and not supported by technology. Furthermore, in Ethiopia there are different Indigenous knowledge Management (IKM) in different regions and ethnicities. In addition, Konso people also have different indigenous knowledge that used for various purposes like for forecasting weather, traditional medicine, soil conservation for protecting their environment and productivity. The main goal of this research study is to explore and design the Indigenous knowledge management framework for soil conservation mechanism in Konso People. As far as the knowledge of the researchers, this very power full knowledge is not explored and also
not supported by emerging technology for making easy knowledge management processes like sharing, transferring, utilization and preservation. Therefore, it is very import to explore and design the IKM framework and develop the prototype to make enabled knowledge management process easy. The exploratory research method and design science research design were used to explore the knowledge from sources. Hence, both qualitative and quantitative research approach used data were collected from the sources using data collection tool like interview (questions), survey (questionnaires), technical observation (check list) and existing documents analysis. From the collected data new knowledge was revealed and the newly proposed IKM framework for soil conservation were design and developed using SWI Prolog tool for implementation. In addition, the designed and developed IKM framework for soil conservation were evaluated and validated by using ISO-1826 I standards. As per this study revealed, this study is significantly very import for sharing, transferring utilization and preserving
Knowledge and for police development that used to protect the soil erosion and land degradation in Ethiopia and in Konso people specifically. Accordingly, this research, user and expert evaluation was assessed and its result as 70% respondents were responded that knowledge deliverability, 87.5% respondents were assented with attractively, 75% of respondents were agreed with accessibility and 62.5% of respondents were responded with suitability of proposed IKM framework and prototype. Furthermore, the obtained result significantly shows that, the proposed IKM framework for Soil conservation in Konso People have the ability to share, transfer and preserve Indigenous knowledge for the next generation.

Keywords: Indigenous Knowledge, Soil conservation, Knowledge Management, Knowledge Preservation.