Applied Mechanics
Permanent URI for this collection
Browse
Recent Submissions
Item Optimizing Bottle Filling Efficiency Through a Machine Learning Approach: a Case of National Alcohol and Liquor Factory(Addis Ababa University, 2026-02) Jemera Melaku; Ameha MulugetaThe bottle filling process is an important process in beverage production since it has direct influence on the quality of the product, compliance with regulations, and the efficiency of production. Nonetheless, major deviations on the bottle filling process are noticed in the National Alcohol and Liquor Factory (NALF). Records of inspections of 35 production days in January- February 2025 found that 27,972 bottles were underfilled and 18,648 overfilled, with an average of about 1332 bottles in need of reprocessing per day. These variations raise manpower, energy use, equipment depreciation, operation expenses and lowers the total output. The factory used in the 2024 annual performance report has reached an output of 85 percent of the intended production capacity, which indicates the necessity of the better monitoring and control of the process. In this study, the aim was to maximize the efficiency of bottle filling based on a supervised machine learning approach. The study involved both quantitative and qualitative research methods using both exploratory and experimental research designs. Primary data were gathered with the help of structured interviews, structured discussions with experts of the company, and direct observations of the filling process, whereas secondary data contained records of maintenance, production records, and reports on quality inspection. A supervised machine learning approach was used in this investigation to identify filling results. A Random Forest classifier was used to distinguish filling outcomes as underfill, correct fill, or overfill. The model had a training accuracy of 99.6% and a testing accuracy of 99.3%. A macro and weighted average performance and reliability were used to validate model performance and reliability, and out-of-bag error estimation and stratified k-fold cross-validation were used to validate. To facilitate real-time monitoring and dynamic process control, the developed model was coupled with the filling process by use of a three-layer architecture. The conclusions reveal that machine learning can be used to enhance the stability of the process, minimize deviations during filling, and decrease the use of resources, as well as assist in making decisions that are supported by data. This Study adds a viable machine learning framework to enhance filling efficiency and promote intelligent manufacturing behaviors in the production of beveragesItem Hydropower Retrofitting Feasibility Study for a Comparative Engineering and Economic Analysis: A Case Study of Tendaho Dam(Addis Ababa University, 2026-05) Abiy Sileshi; Tilahun NigussieThis study assesses the technical and economic feasibility of retrofitting the Tendaho Dam in Ethiopia for hydropower generation while preserving its primary irrigation function. Three retrofit strategies are evaluated: the Dedicated Waterway Strategy (Option I), the Bifurcation Strategy (Option II), and the Channel Utilization Strategy (Option III). A sequential, quantitative, engineering-based methodology is applied, integrating hydrological analysis, engineering assessment, hydraulic modelling, and economic evaluation. Long-term hydrological data, including river discharge, reservoir levels, and irrigation releases, are analysed to determine dependable flows and available head. Structural and operational characteristics of the dam are assessed using original design documents and verified through field observations to identify physical constraints and ensure irrigation compliance. Technically feasible retrofit options are modelled using established hydropower equations to estimate installed capacity, power output, and annual energy generation. Economic and financial performance is evaluated using the RETScreen platform, employing indicators such as Net Present Value (NPV), Levelized Cost of Energy (LCOE), and payback period. The results demonstrate that retrofitting the Tendaho Dam is both technically and economically feasible. Options I and II achieve installed capacities exceeding 16 MW and annual energy generation greater than 111,000 MWh, confirming that the existing structural and hydraulic systems can support large-scale hydropower development without compromising irrigation requirements. Option III, although smaller in scale, remains technically viable and highlights the potential for incremental hydropower retrofitting. Financial analysis indicates that engineering design choices strongly influence economic outcomes. Option II yields the highest NPV, followed by Option I, while Option III generates only marginal returns. Cost-effectiveness analysis shows that Options I and II achieve LCOE values between 0.013 and 0.017 USD/kWh, well below the IRENA benchmark of 0.05 USD/kWh, whereas Option III, although feasible, is less competitive. The study concludes that optimized hydropower retrofitting of the Tendaho Dam offers a cost-effective and low-impact pathway for expanding renewable energy generationItem Barriers to Primary School Enrollment: A Study on Equitable Access to Education in Benshangul-Gumuz Regional State of Ethiopia(Addis Ababa University, 2025-06) Sosina Wondwossen; Teshome TafesseThis study examines the barriers to primary school enrollment and attendance in three woredas of Benshangul- Gumuz Regional State: Bilidigilu, Pawe, and Mandura. Although Ethiopia has achieved national progress in education, these areas remain significantly underserved, particularly in girls’ participation. The study adopts a mixed-methods design, using household-level data from UNICEF (n=399) and 30 key informant interviews (KIIs) with parents, educators, and community leaders. A Heckman two-step model was employed to account for selection bias, distinguishing factors influencing initial enrollment from those affecting continued attendance. Quantitative findings show that school costs, child labor, and child marriage significantly reduce enrollment, while lack of WASH facilities, inadequate classrooms, and language barriers negatively affect attendance. Qualitative data reinforced these patterns, revealing themes of economic vulnerability, low perceived return on education, and cultural norms restricting girls’ schooling. The study concludes that policy responses must integrate targeted household support, infrastructure improvement, and gender-sensitive community engagement. These interventions are essential to advancing inclusive education and achieving SDG 4 in marginalized and conflict-affected settings.