College of Engineering

Permanent URI for this communityhttp://itsupport.cu.edu.ng:4000/handle/123456789/28755

Welcome to the page of the College of Engineering.

Browse

Author: search.filters.author.Covenant University Dissertation

Search Results

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    QUALITY CONTROL ASSESSMENT OF BODY-MAKING PROCESS IN ALUMINIUM BEVERAGE CAN PRODUCTION
    (Covenant University Ota, 2025-01) AKEREKAN OPEYEMI ERNEST; Covenant University Dissertation
    This study focused on the analyses of the quality control process of aluminium beverage can production (sleek size – 330 ml) monitored over a period of time, by deploying six key parameters: Bright Can Axial Load, Finished Can Height, Flange Width, Groove Diameter after Reformer, Dome Depth with Reformer, and Finished Can Buckle. These parameters revolve around the standardization and specification of the beverage can for a sustainable food packaging process. The study employed Statgraphics Centurion (version VII) as a statistical tool for analyzing process stability and capability through Statistical Process Control (SPC) techniques. This software generated control charts (X-bar charts) and process capability indices (Cp and Cpk) to evaluate process performance and identify areas requiring improvement. Descriptive statistical measures such as process mean and standard deviation were calculated to support the analysis. The methodology also included thoroughly evaluating production line data, with variations in each quality parameter assessed against defined specification limits. Results indicate that the Bright Can Axial Load has a moderate capability (Cp = 0.82, Cpk = 0.75) with a slightly off-center mean. Also, the Finished Can Height show low capability (Cp = 0.30, Cpk = 0.25), indicating significant variability. Flange Width has moderate capability (Cp = 0.43, Cpk = 0.43), while Groove Diameter after Reformer presents a Cp of 0.60 but a very low Cpk of 0.06, reflecting a misaligned process mean. In addition to this, Dome Depth with Reformer shows moderate capability (Cp = 0.53, Cpk = 0.23), needing better centering. Finished Can Buckle demonstrates the highest capability (Cp = 1.63, Cpk = 0.74) with a slightly off-center mean. The findings imply that aligning process means with specification limits and reducing variability will ensure consistent, high-quality aluminium production. Thus improving the operation process and subsequent improvement in the overall productivity of aluminium beverage cans.
  • No Thumbnail Available
    Item
    ASSESSMENT OF THE UTILISATION OF SUSTAINABLE ENERGY AND ENVIRONMENTAL PROTECTION IN SOUTHERN NIGERIA
    (Covenant University Ota, 2025-01) OBANOR ENOCH IWINOSA; Covenant University Dissertation
    This study evaluates renewable energy adoption across Ogun, Lagos, Edo, and Delta states using a mixed-methods approach. A bibliometric analysis of 424 research publications (2014–2024) revealed that solar energy was the most studied topic (35%), followed by hydropower (25%) and bioenergy (20%). The analysis identified a 32% increase in renewable energy publications since 2019, with 62% of highly cited papers focusing on policy and deployment strategies. Citation mapping indicated that the top 10 research institutions contributed 47% of all renewable energy studies, highlighting the concentration of expertise in specific regions. Survey data from 387 respondents indicated that 68% lacked reliable electricity access, while 78% relied on traditional biomass or fossil fuels. Among respondents, 62% expressed willingness to adopt solar energy if installation costs were reduced by at least 40%. However, only 23% were aware of existing renewable energy policies, and 54% rated government efforts as inadequate. In terms of energy satisfaction, only 9% of respondents rated their current energy sources as highly adequate, while 36% described them as moderate, and 21% rated them as low. The study further analysed energy availability across Nigerian states. Lagos, Ogun, Edo, and Delta states experience an average of 12–18 hours of electricity outages per day, forcing 74% of households to rely on generators as backup power sources despite Nigeria’s solar radiation potential of 3.5–7.0 kWh/m². Alignment with Sustainable Development Goals (SDGs) 7 and 13 was assessed, revealing that only 19% of publications explicitly addressed energy access and climate change mitigation, while survey results showed that 69% of respondents were unaware of Nigeria’s commitment to SDGs. Projections based on current adoption rates estimate that, if key policy recommendations, energy access in Southern Nigeria could rise from 32% to over 70% by 2035 and fossil fuel dependency could decline by 55%. This research shows that achieving an efficient renewable energy transition requires urgent policy interventions, enhanced financial incentives, and strengthened institutional frameworks.
  • No Thumbnail Available
    Item
    ENHANCEMENT OF FINGERPRINT TEMPLATE PROTECTION AND PRIVACY PRESERVATION USING FULLY HOMOMORPHIC ENCRYPTION
    (Covenant University Ota, 2025-03) ITUH NICOL IGNATIUS; Covenant University Dissertation
    The transition from conventional or token-based passwords to biometric technologies because of the advantageous characteristics of biometrics traits is increasing daily. Nowadays, biometric technologies are utilised in applications such as border control, e-banking, e-health, etc. Biometric traits comprise biological traits (iris, face, fingerprint, etc) and behavioural traits (keystroke, signature, voice, etc). In contrast to other biometric traits, the fingerprint is the most utilised in most applications. Despite the advantages, biometric technologies have their drawbacks. The biometric data of an individual is unique since no two people have the same biometrics, and compromising this biometric data could have devastating results. This issue was addressed using the implementation of the Paillier cryptosystem, a partial homomorphic encryption scheme which only involves addition operations. This implementation suffers drawbacks when faced with complex computations such as the multiplication of two ciphertexts and faces ciphertext noise growth due to these complex computations. Thus, a need for fully homomorphic encryption which handles complex computation and manages noise growth through several techniques. This research work is aimed at enhancing fingerprint template protection and privacy preservation using fully homomorphic encryption. The proposed system was developed utilising the Brakerski/Fan-Vercauteren fully homomorphic encryption scheme implemented using the OpenFHE-Python library. The system was evaluated using the Neurotechnology CrossMatch dataset according to performance metrics including Accuracy, Genuine Acceptance Rate (GAR) and Equal Error Rate (EER). Results indicated that the Neurotechnology CrossMatch dataset achieved an accuracy of 84%, GAR of 84%, and EER of 16%. Therefore, the implementation of fully homomorphic encryption in biometrics achieves adequate accuracy despite both the encryption and decryption processes, thereby safeguarding the template, and preserving the user’s privacy.
  • No Thumbnail Available
    Item
    DEVELOPMENT OF AN AUTONOMOU AGENT FOR A NUMBER STRATEGY GAME USING DEEP Q-NETWORK
    (Covenant University Ota, 2025-03) NKWOR, JANE CHINELO; Covenant University Dissertation
    Deep Q-Networks (DQNs) have emerged as a pivotal reinforcement learning algorithm for training autonomous agents in complex decision-making tasks. This study investigates the application of Deep Q-Networks in Numero, a number strategy game that requires logical reasoning and iterative feedback processing. Numero is a number strategy game where players predict an opponent's secret four-digit number in the fewest steps possible by analysing feedback and refining strategies. The study explores Numero's unique challenges, such as sparse reward structures, high-dimensional state-action spaces, and non-deterministic feedback mechanisms. To address these challenges, a Deep Q-Network algorithm augmented with Prioritised Experience Replay(PER) was designed and developed to enhance sample efficiency by prioritising critical experiences during training. The autonomous agent interacts with the custom environment, sampling mini-batches from the replay buffer, performing backpropagation, and updating Q-values to improve decision-making. Hyperparameters, such as learning rate, discount factor, replay buffer and exploration rate, were tuned to optimise the agent's learning efficiency. Comparative analysis was conducted using Reservoir Sampling without Replacement and the Minimax algorithm as a baseline approach. Experimental results show that the algorithm achieved a higher success rate (correctly predicted numbers) and faster convergence than Minimax, reducing the average number of steps required to guess the secret number by more than 100%. Additionally, this algorithm demonstrated superior adaptability in handling dynamic feedback, outperforming Reservoir sampling in long-term decision-making. These findings reveal the effectiveness of Deep Q-Networks in structured feedback-driven environments, suggesting their potential application in logical reasoning and decision-making tasks and that the autonomous agent learns effective decision-making strategies through iterative training and fine-tuning, demonstrating improved performance in predicting the opponent's secret number. Further research directions include extending this approach to multi-agent settings where multiple autonomous agents can compete or collaborate to refine their strategic reasoning and explore its application in real-world scenarios requiring structured feedback processing.